{ "schema_version": 1, "results": [ { "id": "demo-20261024T041533Z-ddc64e", "run_id": "demo-20261024T041533Z-ddc64e", "result": { "run_id": "demo-20261024T041533Z-ddc64e", "created_at": "2026-10-24T04:50:29.426382+00:00", "model": "gpt-6.1-sol", "harness": "none", "solve_seconds": 1800, "platform": "8.3.27.1644", "counts": { "pass": 51, "inconclusive": 11, "fail": 3 }, "rules": [ { "id": "BU01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU16", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU17", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU02", "verdict": "pass", "coverage": "partial", "reason": null }, { "id": "BU10", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU12", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU06", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU07", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU08", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU09", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU11", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU14", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU15", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU13", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU15", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU16", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU17", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU02", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU18", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU14", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU01", "verdict": "inconclusive", "coverage": "selected_fixture", "reason": null }, { "id": "OU03", "verdict": "inconclusive", "coverage": "selected_fixture", "reason": null }, { "id": "OU05", "verdict": "inconclusive", "coverage": "selected_fixture", "reason": null }, { "id": "OU06", "verdict": "pass", "coverage": "no_violation_found", "reason": null }, { "id": "OU07", "verdict": "inconclusive", "coverage": "selected_fixture", "reason": null }, { "id": "OU08", "verdict": "inconclusive", "coverage": "selected_fixture", "reason": null }, { "id": "OU09", "verdict": "inconclusive", "coverage": "selected_fixture", "reason": null }, { "id": "OU10", "verdict": "inconclusive", "coverage": "selected_fixture", "reason": null }, { "id": "OU11", "verdict": "inconclusive", "coverage": "selected_fixture", "reason": null }, { "id": "OU12", "verdict": "inconclusive", "coverage": "selected_fixture", "reason": null }, { "id": "OU13", "verdict": "inconclusive", "coverage": "selected_fixture", "reason": null }, { "id": "OU04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU19", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU20", "verdict": "fail", "coverage": "selected_fixture", "reason": "Ведомость не прошла проверку группировки по значениям характеристик." }, { "id": "OU21", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR02", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR06", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR07", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR08", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR09", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR10", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR11", "verdict": "fail", "coverage": "selected_fixture", "reason": null }, { "id": "PR12", "verdict": "inconclusive", "coverage": "selected_fixture", "reason": null }, { "id": "PR13", "verdict": "fail", "coverage": "selected_fixture", "reason": null }, { "id": "PR14", "verdict": "pass", "coverage": "no_violation_found", "reason": null }, { "id": "PR15", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR16", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR17", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR18", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR19", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F02", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "G01", "verdict": "pass", "coverage": "static_sources", "reason": null }, { "id": "G02", "verdict": "pass", "coverage": "static_sources", "reason": null }, { "id": "G03", "verdict": "pass", "coverage": "static_sources", "reason": null } ], "charges": [ { "id": "F1C-GEN03", "points": "0.5", "reason": "Ведомость не прошла проверку группировки по значениям характеристик." }, { "id": "F1C-GEN01", "points": "0.5", "reason": "не выполнено требование: PR11 — pr_trip E4/B trip: 431.32, expected 421.13 (one rate for the trip) or 469.95 (own rate in each month)" }, { "id": "F1C-GEN01", "points": "0.5", "reason": "не выполнено требование: PR13 — pr_backdate E4/B tariff 2025-02: 1920, expected 1680.00; trip entered back-dated: 458.25, entered in order: 431.32" }, { "id": "F1C-GEN15", "points": "0.5", "reason": "Reports/Премии/Ext/ObjectModule.bsl:3 — РегистрРасчета.Начисления: отбор по ВидРасчета, ПериодДействияНачало, индексы таблицы начинаются с ПериодДействия, ПериодРегистрации, Подразделение, Регистратор, Сотрудник" }, { "id": "F1C-BU06", "points": "1.5", "reason": "ресурс Количество без признака учёта — количество ведётся на всех счетах" }, { "id": "F1C-BU05", "points": "0.5", "reason": "аналитика счетов вынесена в измерения регистра бухгалтерии и есть у всех счетов: Номенклатура (Номенклатура), Склад (Склады)" }, { "id": "F1C-PR08", "points": "2.0", "reason": "база берётся из основной таблицы регистра расчёта, БазаНачисления нигде не используется: Documents/НачислениеЗарплаты/Ext/ObjectModule.bsl:2; Documents/НачислениеЗарплаты/Ext/ObjectModule.bsl:35" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "оперативное проведение разрешено у документов с движениями по регистрам расчёта: НачислениеЗарплаты" } ], "score_upper_bound": "-2.0", "score": null, "grade": "unsatisfactory", "deductions": "7.0", "not_assessed": 18, "gates": { "starter_origin": "passed", "load": "loaded", "clients": "compiles", "demo_data": "present" }, "infrastructure_errors": true, "comparison_eligible": false, "binding_compatibility": null, "evaluation_sha256": "c7dead883f16c8ba41aef00cc121f43515a26adde8b1fecc80c7a11529d15a1b", "downloads": [] }, "measurement": { "operator": { "name": "Вячеслав", "github": "sksibak" }, "environment": { "captured_at": "2026-10-24T04:15:36.617641+00:00", "capture_timing": "before_run", "hardware": { "cpu": "AMD Ryzen 5 4600H with Radeon Graphics ", "logical_cpus": 12, "ram_bytes": 16505962496 }, "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "python": "3.12.14", "platform_version": "8.3.27.1644", "isolation": "dedicated-host", "network_profile": "open-book_shell", "unsafe_action_protection_observed_in_user_config": true, "git_revision": "af85e791b303dbbf0b0b7af924d2489c3e57cfa8", "implementation_files": { "exam_bench/__init__.py": "ad5bf6f05dc6765f40b78bd186870ca2c49be113cfa33f8aa76f4926f2cb2c1e", "exam_bench/assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "exam_bench/bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "exam_bench/calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "exam_bench/calibrate.py": "78b5185cb0888c0c0ac3de95ffc3a80154a6de9ae66fc461f79d012e5a58e1db", "exam_bench/calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "exam_bench/calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "exam_bench/calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "exam_bench/calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "exam_bench/calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "exam_bench/claude.py": "bc1b8550de7573aaed5e39c6e9c0309e0d8175284a75490d61ec27439ed911ad", "exam_bench/cli.py": "1a37ce645633d761f7897dffc9c45e6b8b9600cd7bd233b1cbf78f49d26b099a", "exam_bench/codescan.py": "751e38001b6e65727a31e28172a0623f0bf34bc092a958037c286aa991a197ed", "exam_bench/codex.py": "c3f89d72af11f312d851c73a1610d92e79acadf336be9ccedd1f94ede3b3ccb0", "exam_bench/common.py": "8682603b519063e655eae3574a02a49efee63bde21f582ccee20ddd623fca96d", "exam_bench/docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "exam_bench/examiner.py": "d7294fdd23ed1732216cafebf0a8cf2c24cce4259859aeb7149f62b7607d087d", "exam_bench/finalize.py": "4034f1c63896a940afdb1a83d541cf47fc75c8b5061e3f839047109c04beb620", "exam_bench/forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "exam_bench/gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "exam_bench/grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "exam_bench/harness.py": "3040f6daaf1dc6e6583219f4d925151f8ba7851b2d5417d7f14645892b485ddf", "exam_bench/interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "exam_bench/interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "exam_bench/isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "exam_bench/ledger.py": "7e851523580e22d8490e75f9b6026c07f2c355007e0d11d0b252671f56bef654", "exam_bench/locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "exam_bench/materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "exam_bench/mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "exam_bench/observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "exam_bench/ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "exam_bench/penalties.py": "0d79e2e46102657dca00609b6abbfc0bf7d11fad41429564f876c82bc6b33269", "exam_bench/platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "exam_bench/portable.py": "cad56968ff407983608f5bdbc9ce7234128d7a4580b096ecea8e0e7b4edb9070", "exam_bench/portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "exam_bench/pr.py": "6a3a20caf0e10c0cc94410511a72d62c9fcda785f3abab1be2ad616d4ee16836", "exam_bench/preflight.py": "5619be0131d8641925f3ce2a3c8e5234d42aa5635d95676138ca81536d95cd29", "exam_bench/process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "exam_bench/queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "exam_bench/queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "exam_bench/replay_calibration.py": "c150457b0b23ce4e6814eb8deb4d48f6bc4a2e39d8f84a9dc7644fb99a026c2d", "exam_bench/report.py": "5e4c0757e1c7f189953f9a5302593ab726551835856baed25efd93dad6e8bfcd", "exam_bench/runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "exam_bench/smoke_check.py": "f36922a0027429ead0b414048dcc14bbe67f2f0e79a70d03dffbe1447d253545", "exam_bench/stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "exam_bench/submission.py": "ea862adc63ae67861ddb1d6aeb4d92c10b0b05004d22953f7b03612f82bb4bf4", "exam_bench/telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "exam_bench/windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "exam_bench/workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tools/build_public_site.py": "9682ed696f5ac9e9a82b65a45c0dece556ec7e49eeb20dcd616882cc534a8258", "tools/build_result_site.py": "3294e1d2ec1486058e208735264d61e349a68a4ae2fa2ec7a723c70e3263b496", "tools/check_native_harnesses.py": "4f5f0ed27651f78758eaef077b3b114361781f6b95ec40cb46c3fea689210473", "tools/check_native_toolkit.py": "0272794617121f2932828e5e4e9ae20095183c443666cf3ba466b44fbe875095", "tools/community_results.py": "788f4763fa97a2f6fe055a1ddea15cb918d2881327594931e508f9fbeb3dd13c", "tools/community_service.py": "c374480dbd88d656c0b9054fa04a8e1c6698c69e2f9cf475e82498a2dff61d84", "tools/community_setup.py": "5d7d126ed7d4dd48e1d79f57b99647a92ffcc8c9f80d90915e458888cdd76bf7", "tools/compare_harness_runs.py": "f274df5f3f804cb02504491aec946943833e12fbce6e62d281e12beb8508fc4e", "tools/create_run_plan.py": "871cd81b1eda231c0fba8805f63d2668926be9fc641559e6ddf320e2f47cd37a", "tools/demo_runner.py": "ca7ad17919c53d524cc0418751ba09a540f910eac183dca2961710bc30bba26f", "tools/installers.py": "9a2742780936b17500869e7c89202c1a2549e37d53a42ad9a50a0abbf78bbe09", "tools/machine_bundle.py": "8aa8346f99f537e81ceca6fb6ab9530e844954bab8eff87bf33d3602f81f8a30", "tools/prepare_native_harnesses.py": "aaa75ecf4022883984fa50c42d14d8e1a9fde2eeda03dab03b852bbc5efb2502", "tools/prepare_official_statement.py": "6b7028c78e90e798d6ef1a93b76520cc61a308c354fb9b87f7fad18b99800fad", "tools/prepare_open_exam_requirements.py": "544f4e378b9be5f166186f8788f8d454afdac2deb99d91d98421e39d01ba6d03", "tools/probe_harness.py": "1ed8ef93420d1484cbbfd151b7efc31b9a201ceb942dd05e3103efa22ffa7f27", "tools/probe_native_mcp.py": "9918d324129cba898993e07f8f8b6dbcbaf369398ebf28d464f9f1f00abdb254", "tools/readiness.py": "d34dd3f38334f51cc4574c79194cf0b80769b062a52382989a57d01c46b9aba4", "tools/recheck_community.py": "f0843d7d677f90da31e22bde0b1c86584dd46c022f1532d43d042619e426b230", "tools/regrade_runs.py": "011775afb06d3aac67a4aa81117a368c75896b0fcbe1e6f27ccc6237612fbf59", "tools/render_statement_text.py": "dabc0716a3612c288c671bc20e17fd4986691d732768e1e957d6dddddbea92a3", "tools/replay_calibration.py": "801f5004926c438c21ed3668fe2a4ddf45312b3e75320165a3839aae034eee9b", "tools/run_exam_campaign.py": "2c450d57a1cd0a2682838f5ec7c0a4ffb3aed0f1730d34c408e912d59cab6efd", "tools/serve_result_site.py": "86badfac863cd4ad1fc894a14110c75b28470513f0133eeae9d2799b8b4df3a9", "tools/start_demo.py": "c597e6cad28d245b3191654bb3e2801fa9dd2364e2acb25561923613717b615f", "tools/supplemental_acceptance.py": "c88fc39de1be1fdcacdd819e2ad329f60367b2df1d5deda80b37324bda3f2a01", "tools/sync_sources.py": "b51e889b0f41f9f63bfb19a09fb96d3777693d6b1d76fe0132bdd2a15e155898", "tools/validate_community_pr.py": "796b896dfade07b4529af2088a4b9b9d23484148b3bc0732b3fb837b75c9844b", "tools/verify_official_assessment_mapping.py": "daeb448a016940d5b6b1285979a56e5b9014bd91db40acb131445e4a83a23059", "tools/verify_task_package.py": "9e1e6105f6b5e4e78b36aa57f00117a9fbc8948ab53983c32ab56da88d23ccc4", "profiles/agents.json": "af9c492c08d13b3044aa6b6952589ed6a0a07d5258d8ff72bb18185b3eaebdc5", "profiles/ai-exam-execution-policy.json": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "profiles/bsl-analyzer-0.3.2-macos.json": "83537abdbf38c41ce665e4d0f24128bb51b62e971e0e0f368695f1326a7d2ffb", "profiles/bsl-analyzer-0.3.2-portable.json": "d6ba732e6778e256df34d6bc548593128820a70430c35b279796843606ee40a8", "profiles/bsl-ls-1.1.0-rc.6-macos.json": "245fc10747197e6911b2b4c77cdb15e6fa4eb7bc7c3758b63e768c5adf1df180", "profiles/bsl-ls-1.1.0-rc.6-portable.json": "9f10660881f2ec84794f7d584556b8f75c7e14b3555464af0ed0e60c4c892d86", "profiles/code-index-1.9.0-macos.json": "63a919523ce62ecec274f4c139bc7ad49a75dd4c339568b822cbc695b4e30408", "profiles/code-index-1.9.0-portable.json": "81106cee8f424ffd8a9dc46ecd8e4f57598fc1d49661a83c77b1f0507993fbdc", "profiles/codex-probe-plan.json": "166e41aad5fb3b27d9050bc6de952c6cba363cc6e804d4080568cc71a2a4d289", "profiles/machine.linux.example.json": "408304fd0581098d5d8110dc67dfeab353bc4d4030e32d37e6acf98d2b1aedfd", "profiles/machine.macos.example.json": "52e9f9d17797cb520b9d8955d6806fd550b899bed4da241ebf096dcb6a21a942", "profiles/machine.windows.example.json": "63accac9a2f81d47d03447efbabffd4760aee325193f02f46b9b29a28d50d2d8", "profiles/mcp-toolkit-1.9.0-macos.json": "1d3f9cde5ffa20589a840d01fdae03aa0fc2f412c929f064f203919c4129625b", "profiles/mcp-toolkit-1.9.0-portable.json": "8e370eebe773eef0e08045ee9c6d5be1451f769f65be0710834b262a4336e054", "profiles/none-macos.json": "b1401d9c48159aed3559006c7f6ace6ef4571224d5cf0bb76d1a823505a10056", "profiles/none-portable.json": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "profiles/rlm-tools-bsl-1.43.0-macos.json": "9354421052640ab60bc3e6aa98ff2e7ba9ca2318b0f4026c137487449242cbd2", "profiles/rlm-tools-bsl-1.43.0-portable.json": "2599e5645e0a7d4e44cb2934bc2b272cae79a9bf7ea74a23cd48aacea64bc424", "profiles/rlm-tools-bsl-1.43.0-posix-requirements.txt": "4fdf9a1bd994bf0272e65d231daf76cf19b0a34dad0ae6b50ec4f11a2ce4c330", "profiles/rlm-tools-bsl-1.43.0-windows-requirements.txt": "3730cb46c81cda5181ecd4485e98b11933104632358bc86f8c0eb1a612a8954f", "profiles/shirokov-skills-macos.json": "84f3e89091676884a802035c707e912762a1179425fb8e3faff25be736873cdb", "profiles/shirokov-skills-portable.json": "2b0a461e06602f1456410e70f02ceaa5ac32c6549c486660bcb5ace0c2f87b15", "profiles/shirokov-skills-windows-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/unica-0.12.3-macos.json": "2c39fbb591cf2c2c6e056373823615485397ea83651b7926c6f25a5fe6a0aae6", "profiles/unica-0.13.0-macos.json": "b76b5c8a4dd33f571c4a90993f1a2da5f7223b4f0f8e1042c282e21a66121052", "profiles/unica-0.14.0-rc.1-portable.json": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "rules/1c-specialist-platform/chistov.json": "77e04942f8c947b10759e7cc1eb31af05847d1711a772fbe6f23d525766757a9", "rules/1c-specialist-platform/decisions.json": "f622107423ce3c188c063318d7ab4f7718ceb38e443130677d8987f386641c09", "rules/1c-specialist-platform/examiner.json": "30353aa2a1b6545496b070d9066e9ffba0c3779e5b53ef70a4fd2cee375b18c0", "rules/1c-specialist-platform/ledger.json": "f167c10db2b5799dd9a1ea6a37cd2d7d186810dadf5ea2f50f26ae723c676882", "rules/1c-specialist-platform/rules.json": "1d320a4f8e1bf4701496388931f492315549bd3dce574b17285dd1d7f8652007", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" } } }, "conditions": { "client": "codex", "model": "gpt-6.1-sol", "client_version": "0.163.0-alpha.11.2", "reasoning_effort": "medium", "harness": "none", "billing_channel": "subscription", "solve_timeout_seconds": 1800, "time_series": "fast", "delegation": "native_disabled", "network_profile": "open-book_shell", "deadline_disclosed": true, "statement_sha256": "8a6ccb3e673826d1f8220fda53eb310e3ec18c136d87ce8f4cebb2a08614e7e5", "starter_dt_sha256": "f40d084818b0d1cfe503fc7653a6a13f1a8e47fcd1688dad6245b12744eb4638", "profile_sha256": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "execution_policy_sha256": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "calibration_sha256": "eced5b2f738ff558afe3d33d03048cf7b3ad00fa4e418c6a0ed72f885d0d221c", "started_at": "2026-10-24T04:15:52.110750+00:00", "timing": { "prepare_ms": 15015, "solve_ms": 1800063, "grade_ms": null }, "original_submission_valid": true, "model_provenance": "requested_only", "tokens": { "input": 7096762, "cached_input": 6998272, "fresh_input": 98490, "output": 45941, "reasoning_output": 8527, "total": 7142703, "coverage": "reported_completed_root_turns" }, "tools": { "mcp_calls": 0, "unica_calls": 0, "failed_calls": 0 }, "process": { "status": "timeout", "exit_code": 1, "stop_confirmed": true } }, "verification": "contributor_reported", "download": "community-downloads/demo-20261024T041533Z-ddc64e/solution.zip", "source_context": "community-downloads/demo-20261024T041533Z-ddc64e/source-context.json", "regrade_required": [ { "id": "grader_changed", "files": [ "assessment.py", "bp.py", "calcwrite.py", "calibrate.py", "calibration_periodicity.py", "calibration_query.py", "claude.py", "codescan.py", "codex.py", "common.py", "docx_text.py", "examiner.py", "harness.py", "interpretations.py", "locking.py", "materials.py", "mcp_toolkit.py", "ou.py", "penalties.py", "portable_harnesses.py", "pr.py", "preflight.py", "queries.py", "queryschema.py", "querytypes.py", "replay_calibration.py", "rules/1c-specialist-platform/chistov.json", "rules/1c-specialist-platform/examiner.json", "rules/1c-specialist-platform/rules.json", "rules/1c-specialist-platform/standards.json", "smoke_check.py", "starters/carcass-8.3.25.1445/starter.json", "stdio_harnesses.py", "submission.py", "tasks/1c-platform-official-sample/checks.json", "tasks/1c-platform-official-sample/private/official-assessment-mapping.json", "tasks/1c-platform-official-sample/private/owner-scoring-policy.json", "telemetry.py" ] } ], "grader_revision_sha256": "6067982a38bf7a3f61b6d7bfcf5c5d2f8f7acd31f20a80cc643d6e23e8c6a9b2", "archive_sha256": "73fef712651d7b8668f68eff0346cb1811ec1bd9f6dcfb9734c61cf3a657e30e", "previous_evaluations": [] }, { "id": "demo-20261025T112228Z-adapter--owner-2026-10-26T223300888985-0000", "run_id": "demo-20261024T050719Z-7a9caa", "result": { "run_id": "demo-20261024T050719Z-7a9caa", "created_at": "2026-10-26T22:33:00.888985+00:00", "model": "gpt-6.1-sol", "harness": "none", "solve_seconds": 3372, "platform": "8.3.27.1644", "counts": { "pass": 64, "fail": 1 }, "rules": [ { "id": "BU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU01.selected_fixture" }, { "id": "BU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU04.selected_fixture" }, { "id": "BU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU05.selected_fixture" }, { "id": "BU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU16.selected_fixture" }, { "id": "BU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU17.selected_fixture" }, { "id": "BU02", "verdict": "pass", "reason": null, "coverage": "partial", "assertion_id": "BU02.posting_cost_and_balance" }, { "id": "BU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU10.selected_fixture" }, { "id": "BU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU12.selected_fixture" }, { "id": "BU03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU03.selected_fixture" }, { "id": "BU06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU06.selected_fixture" }, { "id": "BU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU07.selected_fixture" }, { "id": "BU08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU08.selected_fixture" }, { "id": "BU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU09.selected_fixture" }, { "id": "BU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU11.selected_fixture" }, { "id": "BU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU14.selected_fixture" }, { "id": "BU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU15.selected_fixture" }, { "id": "BU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU13.selected_fixture" }, { "id": "OU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU15.selected_fixture" }, { "id": "OU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU16.selected_fixture" }, { "id": "OU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU17.selected_fixture" }, { "id": "OU02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU02.selected_fixture" }, { "id": "OU18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU18.selected_fixture" }, { "id": "OU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU14.selected_fixture" }, { "id": "OU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU01.selected_fixture" }, { "id": "OU03", "verdict": "pass", "reason": "История и годовая периодичность регистра подтверждены.", "coverage": "history_and_periodicity", "assertion_id": "OU03.selected_fixture" }, { "id": "OU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU05.selected_fixture" }, { "id": "OU06", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "OU06.selected_fixture" }, { "id": "OU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU07.selected_fixture" }, { "id": "OU08", "verdict": "pass", "reason": "История и дневная периодичность подтверждены; ограничение одной версии в неделю отдельно не проверяется.", "coverage": "history_and_periodicity", "assertion_id": "OU08.selected_fixture" }, { "id": "OU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU09.selected_fixture" }, { "id": "OU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU10.selected_fixture" }, { "id": "OU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU11.selected_fixture" }, { "id": "OU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU12.selected_fixture" }, { "id": "OU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU13.selected_fixture" }, { "id": "OU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU04.selected_fixture" }, { "id": "OU19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU19.selected_fixture" }, { "id": "OU20", "verdict": "fail", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU20.selected_fixture" }, { "id": "OU21", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU21.selected_fixture" }, { "id": "PR01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR01.selected_fixture" }, { "id": "PR02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR02.selected_fixture" }, { "id": "PR03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR03.selected_fixture" }, { "id": "PR04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR04.selected_fixture" }, { "id": "PR05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR05.selected_fixture" }, { "id": "PR06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR06.selected_fixture" }, { "id": "PR07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR07.selected_fixture" }, { "id": "PR08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR08.selected_fixture" }, { "id": "PR09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR09.selected_fixture" }, { "id": "PR10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR10.selected_fixture" }, { "id": "PR11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR11.selected_fixture" }, { "id": "PR12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR12.selected_fixture" }, { "id": "PR13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR13.selected_fixture" }, { "id": "PR14", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "PR14.selected_fixture" }, { "id": "PR15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR15.selected_fixture" }, { "id": "PR16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR16.selected_fixture" }, { "id": "PR17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR17.selected_fixture" }, { "id": "PR18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR18.selected_fixture" }, { "id": "PR19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR19.selected_fixture" }, { "id": "F01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F01.selected_fixture" }, { "id": "F02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F02.selected_fixture" }, { "id": "F03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F03.selected_fixture" }, { "id": "F04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F04.selected_fixture" }, { "id": "F05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F05.selected_fixture" }, { "id": "G01", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G01.static_sources" }, { "id": "G02", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G02.static_sources" }, { "id": "G03", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G03.static_sources" } ], "charges": [ { "id": "F1C-GEN03", "points": "0.5", "reason": "отчёт не соответствует заданию: OU20" }, { "id": "F1C-PR09", "points": "0.5", "reason": "CommonModules/УчетСервер/Ext/Module.bsl:215 — РегистрРасчета.Начисления.БазаНачисления: база получается без отбора по регистратору — по всем записям регистра" }, { "id": "F1C-PR09", "points": "0.5", "reason": "CommonModules/УчетСервер/Ext/Module.bsl:247 — РегистрРасчета.Начисления.БазаНачисления: база получается без отбора по регистратору — по всем записям регистра" }, { "id": "F1C-GEN15", "points": "0.5", "reason": "Reports/ПремииЗаМесяц/Ext/ManagerModule.bsl:5 — РегистрРасчета.Начисления: отбор по ВидРасчета, ПериодДействияНачало, индексы таблицы начинаются с ПериодДействия, ПериодРегистрации, Подразделение, Регистратор, Сотрудник" }, { "id": "F1C-GEN14", "points": "1.5", "reason": "Reports/ПродажиАналогов/Ext/ManagerModule.bsl:3 — РегистрБухгалтерии.Хозрасчетный: итоги считаются по основной таблице регистра, а не по виртуальной" }, { "id": "F1C-PR14", "points": "0.5", "reason": "после расчёта набор с периодом действия перезаписывается целиком, с пересчётом фактического периода действия (нужно Записать(, Истина)): CommonModules/УчетСервер/Ext/Module.bsl:211 Н.Записать(); CommonModules/УчетСервер/Ext/Module.bsl:228 Н.Записать(); CommonModules/УчетСервер/Ext/Module.bsl:241 Н.Записать(); CommonModules/УчетСервер/Ext/Module.bsl:259 Н.Записать()" }, { "id": "F1C-BU06", "points": "1.5", "reason": "у счёта товаров 01.02 не включён признак учёта КоличественныйУчет" }, { "id": "F1C-BU05", "points": "0.5", "reason": "аналитика счетов вынесена в измерения регистра бухгалтерии и есть у всех счетов: Номенклатура (Номенклатура)" }, { "id": "F1C-GEN20", "points": "2.0", "reason": "данные базы читаются в цикле по записям: CommonModules/УчетСервер/Ext/Module.bsl:293" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "оперативное проведение разрешено у документов с движениями по регистрам расчёта: НачислениеЗарплаты" }, { "id": "F1C-GEN21", "points": "2.0", "reason": "данные графика без отбора по регистратору: CommonModules/УчетСервер/Ext/Module.bsl:173" } ], "score_upper_bound": "-6.0", "score": null, "grade": "unsatisfactory", "deductions": "11.0", "not_assessed": 16, "gates": { "starter_origin": "passed", "load": "loaded", "clients": "compiles", "demo_data": "present" }, "infrastructure_errors": false, "comparison_eligible": false, "binding_compatibility": { "scope": "supplemental_named_subconto_adapter", "original_binding_sha256": "938f1873ea01dfdfe3da8d8828895d4a895de6be4398bbd046f4411b24c75261", "normalized_binding_sha256": "33d56b52100336dd84ad90b501ff2cc5f7ffb896d03bf2862863d853a4750993", "normalizer_sha256": "7327277143d80a531e4c254ac74a9fc0e0d5c76572d53b8469e0a580eda17d65", "canonical_ledger_sha256": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "changes": [ { "field": "fields.ledger.warehouse_debit", "before": "Склады", "after": "ВидыСубконто.Склады", "kind": "named" }, { "field": "fields.ledger.warehouse_credit", "before": "Склады", "after": "ВидыСубконто.Склады", "kind": "named" } ], "basis": "kind names expanded only to exactly one predefined kind of the account chart on the role side; all role types checked." } }, "measurement": { "operator": { "name": "Вячеслав", "github": "sksibak" }, "environment": { "captured_at": "2026-10-24T05:07:22.329340+00:00", "capture_timing": "before_run", "hardware": { "cpu": "AMD Ryzen 5 4600H with Radeon Graphics ", "logical_cpus": 12, "ram_bytes": 16505962496 }, "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "python": "3.12.14", "platform_version": "8.3.27.1644", "isolation": "dedicated-host", "network_profile": "open-book_shell", "unsafe_action_protection_observed_in_user_config": true, "git_revision": "af85e791b303dbbf0b0b7af924d2489c3e57cfa8", "implementation_files": { "exam_bench/__init__.py": "ad5bf6f05dc6765f40b78bd186870ca2c49be113cfa33f8aa76f4926f2cb2c1e", "exam_bench/assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "exam_bench/bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "exam_bench/calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "exam_bench/calibrate.py": "78b5185cb0888c0c0ac3de95ffc3a80154a6de9ae66fc461f79d012e5a58e1db", "exam_bench/calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "exam_bench/calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "exam_bench/calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "exam_bench/calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "exam_bench/calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "exam_bench/claude.py": "bc1b8550de7573aaed5e39c6e9c0309e0d8175284a75490d61ec27439ed911ad", "exam_bench/cli.py": "1a37ce645633d761f7897dffc9c45e6b8b9600cd7bd233b1cbf78f49d26b099a", "exam_bench/codescan.py": "751e38001b6e65727a31e28172a0623f0bf34bc092a958037c286aa991a197ed", "exam_bench/codex.py": "c3f89d72af11f312d851c73a1610d92e79acadf336be9ccedd1f94ede3b3ccb0", "exam_bench/common.py": "8682603b519063e655eae3574a02a49efee63bde21f582ccee20ddd623fca96d", "exam_bench/docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "exam_bench/examiner.py": "d7294fdd23ed1732216cafebf0a8cf2c24cce4259859aeb7149f62b7607d087d", "exam_bench/finalize.py": "4034f1c63896a940afdb1a83d541cf47fc75c8b5061e3f839047109c04beb620", "exam_bench/forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "exam_bench/gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "exam_bench/grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "exam_bench/harness.py": "3040f6daaf1dc6e6583219f4d925151f8ba7851b2d5417d7f14645892b485ddf", "exam_bench/interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "exam_bench/interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "exam_bench/isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "exam_bench/ledger.py": "7e851523580e22d8490e75f9b6026c07f2c355007e0d11d0b252671f56bef654", "exam_bench/locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "exam_bench/materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "exam_bench/mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "exam_bench/observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "exam_bench/ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "exam_bench/penalties.py": "0d79e2e46102657dca00609b6abbfc0bf7d11fad41429564f876c82bc6b33269", "exam_bench/platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "exam_bench/portable.py": "cad56968ff407983608f5bdbc9ce7234128d7a4580b096ecea8e0e7b4edb9070", "exam_bench/portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "exam_bench/pr.py": "6a3a20caf0e10c0cc94410511a72d62c9fcda785f3abab1be2ad616d4ee16836", "exam_bench/preflight.py": "5619be0131d8641925f3ce2a3c8e5234d42aa5635d95676138ca81536d95cd29", "exam_bench/process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "exam_bench/queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "exam_bench/queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "exam_bench/replay_calibration.py": "c150457b0b23ce4e6814eb8deb4d48f6bc4a2e39d8f84a9dc7644fb99a026c2d", "exam_bench/report.py": "5e4c0757e1c7f189953f9a5302593ab726551835856baed25efd93dad6e8bfcd", "exam_bench/runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "exam_bench/smoke_check.py": "f36922a0027429ead0b414048dcc14bbe67f2f0e79a70d03dffbe1447d253545", "exam_bench/stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "exam_bench/submission.py": "ea862adc63ae67861ddb1d6aeb4d92c10b0b05004d22953f7b03612f82bb4bf4", "exam_bench/telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "exam_bench/windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "exam_bench/workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tools/build_public_site.py": "9682ed696f5ac9e9a82b65a45c0dece556ec7e49eeb20dcd616882cc534a8258", "tools/build_result_site.py": "3294e1d2ec1486058e208735264d61e349a68a4ae2fa2ec7a723c70e3263b496", "tools/check_native_harnesses.py": "4f5f0ed27651f78758eaef077b3b114361781f6b95ec40cb46c3fea689210473", "tools/check_native_toolkit.py": "0272794617121f2932828e5e4e9ae20095183c443666cf3ba466b44fbe875095", "tools/community_results.py": "cbfba30b4e617f5e219637c1c2de57398d01eb2f284eae3aca3ef684e6505a39", "tools/community_service.py": "c374480dbd88d656c0b9054fa04a8e1c6698c69e2f9cf475e82498a2dff61d84", "tools/community_setup.py": "5d7d126ed7d4dd48e1d79f57b99647a92ffcc8c9f80d90915e458888cdd76bf7", "tools/compare_harness_runs.py": "f274df5f3f804cb02504491aec946943833e12fbce6e62d281e12beb8508fc4e", "tools/create_run_plan.py": "871cd81b1eda231c0fba8805f63d2668926be9fc641559e6ddf320e2f47cd37a", "tools/demo_runner.py": "ca7ad17919c53d524cc0418751ba09a540f910eac183dca2961710bc30bba26f", "tools/installers.py": "9a2742780936b17500869e7c89202c1a2549e37d53a42ad9a50a0abbf78bbe09", "tools/machine_bundle.py": "8aa8346f99f537e81ceca6fb6ab9530e844954bab8eff87bf33d3602f81f8a30", "tools/prepare_native_harnesses.py": "aaa75ecf4022883984fa50c42d14d8e1a9fde2eeda03dab03b852bbc5efb2502", "tools/prepare_official_statement.py": "6b7028c78e90e798d6ef1a93b76520cc61a308c354fb9b87f7fad18b99800fad", "tools/prepare_open_exam_requirements.py": "544f4e378b9be5f166186f8788f8d454afdac2deb99d91d98421e39d01ba6d03", "tools/probe_harness.py": "1ed8ef93420d1484cbbfd151b7efc31b9a201ceb942dd05e3103efa22ffa7f27", "tools/probe_native_mcp.py": "9918d324129cba898993e07f8f8b6dbcbaf369398ebf28d464f9f1f00abdb254", "tools/readiness.py": "d34dd3f38334f51cc4574c79194cf0b80769b062a52382989a57d01c46b9aba4", "tools/recheck_community.py": "f0843d7d677f90da31e22bde0b1c86584dd46c022f1532d43d042619e426b230", "tools/regrade_runs.py": "011775afb06d3aac67a4aa81117a368c75896b0fcbe1e6f27ccc6237612fbf59", "tools/render_statement_text.py": "dabc0716a3612c288c671bc20e17fd4986691d732768e1e957d6dddddbea92a3", "tools/replay_calibration.py": "801f5004926c438c21ed3668fe2a4ddf45312b3e75320165a3839aae034eee9b", "tools/run_exam_campaign.py": "2c450d57a1cd0a2682838f5ec7c0a4ffb3aed0f1730d34c408e912d59cab6efd", "tools/serve_result_site.py": "86badfac863cd4ad1fc894a14110c75b28470513f0133eeae9d2799b8b4df3a9", "tools/start_demo.py": "c597e6cad28d245b3191654bb3e2801fa9dd2364e2acb25561923613717b615f", "tools/supplemental_acceptance.py": "c88fc39de1be1fdcacdd819e2ad329f60367b2df1d5deda80b37324bda3f2a01", "tools/sync_sources.py": "b51e889b0f41f9f63bfb19a09fb96d3777693d6b1d76fe0132bdd2a15e155898", "tools/validate_community_pr.py": "796b896dfade07b4529af2088a4b9b9d23484148b3bc0732b3fb837b75c9844b", "tools/verify_official_assessment_mapping.py": "daeb448a016940d5b6b1285979a56e5b9014bd91db40acb131445e4a83a23059", "tools/verify_task_package.py": "9e1e6105f6b5e4e78b36aa57f00117a9fbc8948ab53983c32ab56da88d23ccc4", "profiles/agents.json": "af9c492c08d13b3044aa6b6952589ed6a0a07d5258d8ff72bb18185b3eaebdc5", "profiles/ai-exam-execution-policy.json": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "profiles/bsl-analyzer-0.3.2-macos.json": "83537abdbf38c41ce665e4d0f24128bb51b62e971e0e0f368695f1326a7d2ffb", "profiles/bsl-analyzer-0.3.2-portable.json": "d6ba732e6778e256df34d6bc548593128820a70430c35b279796843606ee40a8", "profiles/bsl-ls-1.1.0-rc.6-macos.json": "245fc10747197e6911b2b4c77cdb15e6fa4eb7bc7c3758b63e768c5adf1df180", "profiles/bsl-ls-1.1.0-rc.6-portable.json": "9f10660881f2ec84794f7d584556b8f75c7e14b3555464af0ed0e60c4c892d86", "profiles/code-index-1.9.0-macos.json": "63a919523ce62ecec274f4c139bc7ad49a75dd4c339568b822cbc695b4e30408", "profiles/code-index-1.9.0-portable.json": "81106cee8f424ffd8a9dc46ecd8e4f57598fc1d49661a83c77b1f0507993fbdc", "profiles/codex-probe-plan.json": "166e41aad5fb3b27d9050bc6de952c6cba363cc6e804d4080568cc71a2a4d289", "profiles/machine.linux.example.json": "408304fd0581098d5d8110dc67dfeab353bc4d4030e32d37e6acf98d2b1aedfd", "profiles/machine.macos.example.json": "52e9f9d17797cb520b9d8955d6806fd550b899bed4da241ebf096dcb6a21a942", "profiles/machine.windows.example.json": "63accac9a2f81d47d03447efbabffd4760aee325193f02f46b9b29a28d50d2d8", "profiles/mcp-toolkit-1.9.0-macos.json": "1d3f9cde5ffa20589a840d01fdae03aa0fc2f412c929f064f203919c4129625b", "profiles/mcp-toolkit-1.9.0-portable.json": "8e370eebe773eef0e08045ee9c6d5be1451f769f65be0710834b262a4336e054", "profiles/none-macos.json": "b1401d9c48159aed3559006c7f6ace6ef4571224d5cf0bb76d1a823505a10056", "profiles/none-portable.json": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "profiles/rlm-tools-bsl-1.43.0-macos.json": "9354421052640ab60bc3e6aa98ff2e7ba9ca2318b0f4026c137487449242cbd2", "profiles/rlm-tools-bsl-1.43.0-portable.json": "2599e5645e0a7d4e44cb2934bc2b272cae79a9bf7ea74a23cd48aacea64bc424", "profiles/rlm-tools-bsl-1.43.0-posix-requirements.txt": "4fdf9a1bd994bf0272e65d231daf76cf19b0a34dad0ae6b50ec4f11a2ce4c330", "profiles/rlm-tools-bsl-1.43.0-windows-requirements.txt": "3730cb46c81cda5181ecd4485e98b11933104632358bc86f8c0eb1a612a8954f", "profiles/shirokov-skills-macos.json": "84f3e89091676884a802035c707e912762a1179425fb8e3faff25be736873cdb", "profiles/shirokov-skills-portable.json": "2b0a461e06602f1456410e70f02ceaa5ac32c6549c486660bcb5ace0c2f87b15", "profiles/shirokov-skills-windows-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/unica-0.12.3-macos.json": "2c39fbb591cf2c2c6e056373823615485397ea83651b7926c6f25a5fe6a0aae6", "profiles/unica-0.13.0-macos.json": "b76b5c8a4dd33f571c4a90993f1a2da5f7223b4f0f8e1042c282e21a66121052", "profiles/unica-0.14.0-rc.1-portable.json": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "rules/1c-specialist-platform/chistov.json": "77e04942f8c947b10759e7cc1eb31af05847d1711a772fbe6f23d525766757a9", "rules/1c-specialist-platform/decisions.json": "f622107423ce3c188c063318d7ab4f7718ceb38e443130677d8987f386641c09", "rules/1c-specialist-platform/examiner.json": "30353aa2a1b6545496b070d9066e9ffba0c3779e5b53ef70a4fd2cee375b18c0", "rules/1c-specialist-platform/ledger.json": "f167c10db2b5799dd9a1ea6a37cd2d7d186810dadf5ea2f50f26ae723c676882", "rules/1c-specialist-platform/rules.json": "1d320a4f8e1bf4701496388931f492315549bd3dce574b17285dd1d7f8652007", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" } } }, "conditions": { "client": "codex", "model": "gpt-6.1-sol", "client_version": "0.163.0-alpha.11.2", "reasoning_effort": "medium", "harness": "none", "billing_channel": "subscription", "solve_timeout_seconds": 3600, "time_series": null, "delegation": "native_disabled", "network_profile": "open-book_shell", "deadline_disclosed": true, "statement_sha256": "8a6ccb3e673826d1f8220fda53eb310e3ec18c136d87ce8f4cebb2a08614e7e5", "starter_dt_sha256": "f40d084818b0d1cfe503fc7653a6a13f1a8e47fcd1688dad6245b12744eb4638", "profile_sha256": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "execution_policy_sha256": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "calibration_sha256": "eced5b2f738ff558afe3d33d03048cf7b3ad00fa4e418c6a0ed72f885d0d221c", "started_at": "2026-10-24T05:07:30.140350+00:00", "timing": { "prepare_ms": 7282, "solve_ms": 3372156, "grade_ms": null }, "original_submission_valid": false, "model_provenance": "requested_only", "tokens": { "input": 17610405, "cached_input": 17466624, "fresh_input": 143781, "output": 112434, "reasoning_output": 42146, "total": 17722839, "coverage": "reported_completed_root_turns" }, "tools": { "mcp_calls": 0, "unica_calls": 0, "failed_calls": 0 }, "process": { "status": "completed", "exit_code": 0, "stop_confirmed": true } }, "verification": "repository_owner", "download": "community-downloads/demo-20261025T112228Z-adapter--owner-2026-10-26T223300888985-0000/solution.zip", "source_context": "community-downloads/demo-20261025T112228Z-adapter--owner-2026-10-26T223300888985-0000/source-context.json", "regrade_required": [], "grader_revision_sha256": "9aee1ffe0e1d04f9158fbbbeed3a403a5f0550ad8a590d7a6394977590760e1a", "archive_sha256": "de16d4639243d6009e999b711d1d3a0c2b6e139e8cdf3f3bfd1b62b0615bd65e", "owner_verification": { "kind": "repository_owner", "repository": "zeegin/1c-agent-exam-benchmark", "operator": { "name": "Ingvar Vilkman", "github": "zeegin" }, "started_at": "2026-10-26T22:33:00.729236+00:00", "server": { "name": "Owner Windows stand", "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "hardware": { "cpu": "AMD Ryzen 7 5800X 8-Core Processor ", "logical_cpus": 4, "ram_bytes": 17109000192 }, "isolation": "dedicated-host" }, "platform_version": "8.3.27.2342", "grader": { "profile": "technical-v8", "commit": "e15c8ea80263c0b38baa3a1fc19611983270e8a7", "working_tree_dirty": false, "fingerprint": { "assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "calibrate.py": "aac127e03744907fd52ef149b88aa6d88a54a2b7497d56084484ee1b99e0da99", "calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "calibration_periodicity.py": "0b1953d7781e236467897cd2ed66705b75d9719353a2de60b36f2bbdfe799108", "calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "calibration_query.py": "3555b103cde8ea0519955cf52358d09223f5ab183a9df00533bdb48c89237a8c", "claude.py": "5bae98af6e2021e2718afa3a71ed04bee812deaae31a43d4e7324814139ccc82", "codescan.py": "6d8375210cef1fd768fc2d98d630d880b2993a9724f01ae25f33b4ea5aa9631d", "codex.py": "904e75503cd35f16cbb052f66806b3879fe25bfc9f99e33b93c889d862c46324", "common.py": "739b39e2bb9bdd4a571fc69df5843190cddcad094ef7e68964061bc1266b20dc", "docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "examiner.py": "8cdffcdd52f043c905f896697403380af95bf485dd4a5edca24f7956e7795ffe", "forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "harness.py": "3cbb90fd3187e700b5df32e5daafb20313d49bb5721c826e3033cbc6aa6e3825", "interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "ou.py": "f62784b54a3f85576a078a2ff1908c9395f3159e55f6bb5b1a3c564392241abe", "penalties.py": "ae388cb8953ecca1f2370a7c4cb1db3b6cc8318fc2a7563a4db15f9f5b057429", "platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "pr.py": "2b6bfea0634703469605ce114f9274716b485852d9a55d9185c39893b14e4726", "preflight.py": "448c3120ab64b625abae3891be686c7a214ce4211f7cf651fd90e12c0b298433", "process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "queries.py": "1ef57e292db3e8967a733948371ecc542f743b811890d4fc509df17303b9c4ac", "queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "querytypes.py": "b645f489a2abc27762b4a9bbf4917e72f7b46dc053a74c0dca4a8fc46491b3ef", "replay_calibration.py": "e0e3d5ca6416934715b9735aa516046b8d19ad4ae690220eeacd96b198a5f86c", "runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "smoke_check.py": "7837e980986bcb54dc8bc1dfb5d0003deef11e05f6e11df3910fa509e1f74c8d", "stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "submission.py": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tasks/1c-platform-official-sample/checks.json": "7447a9b42d3e348d29d07f001cfb6bd269acd953b7117eba7cca2ce9f5a9a60d", "tasks/1c-platform-official-sample/private/official-assessment-mapping.json": "303587c0dabe77c1eeebb2017fe85539e3370b17c9090435e6e0325a66bd0644", "tasks/1c-platform-official-sample/private/owner-scoring-policy.json": "d26d534bb838ab1b5facb7bc033ca8ec40912133baadcdbad83b27fc577905f5", "starters/carcass-8.3.25.1445/starter.json": "0f7a7060885ba99a19402bfc6e63cc8fe979b0f491b040d3a01d5d21b304b3a6", "rules/1c-specialist-platform/rules.json": "ea75e34ace5de11ba3de403c63cd2c026db81d1d991f8531e4a779d4ce9788e7", "rules/1c-specialist-platform/examiner.json": "1247486ddd412d600db88d9c1db4ba501fc1994afd1dc2ebe85402fcc332f4c8", "rules/1c-specialist-platform/chistov.json": "800da27601a3f1c7ec1df64482fd4ad035e559ba0b390a274ed5031128487d3d", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" }, "sha256": "9aee1ffe0e1d04f9158fbbbeed3a403a5f0550ad8a590d7a6394977590760e1a" }, "method": "saved_platform_observations", "outcome": "complete", "completed_at": "2026-10-26T22:33:00.888985+00:00" }, "previous_evaluations": [ { "id": "demo-20261025T112228Z-adapter--owner-2026-10-26T214337676149-0000", "run_id": "demo-20261024T050719Z-7a9caa", "result": { "run_id": "demo-20261024T050719Z-7a9caa", "created_at": "2026-10-26T21:43:37.676149+00:00", "model": "gpt-6.1-sol", "harness": "none", "solve_seconds": 3372, "platform": "8.3.27.1644", "counts": { "pass": 64, "fail": 1 }, "rules": [ { "id": "BU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU01.selected_fixture" }, { "id": "BU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU04.selected_fixture" }, { "id": "BU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU05.selected_fixture" }, { "id": "BU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU16.selected_fixture" }, { "id": "BU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU17.selected_fixture" }, { "id": "BU02", "verdict": "pass", "reason": null, "coverage": "partial", "assertion_id": "BU02.posting_cost_and_balance" }, { "id": "BU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU10.selected_fixture" }, { "id": "BU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU12.selected_fixture" }, { "id": "BU03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU03.selected_fixture" }, { "id": "BU06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU06.selected_fixture" }, { "id": "BU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU07.selected_fixture" }, { "id": "BU08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU08.selected_fixture" }, { "id": "BU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU09.selected_fixture" }, { "id": "BU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU11.selected_fixture" }, { "id": "BU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU14.selected_fixture" }, { "id": "BU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU15.selected_fixture" }, { "id": "BU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU13.selected_fixture" }, { "id": "OU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU15.selected_fixture" }, { "id": "OU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU16.selected_fixture" }, { "id": "OU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU17.selected_fixture" }, { "id": "OU02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU02.selected_fixture" }, { "id": "OU18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU18.selected_fixture" }, { "id": "OU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU14.selected_fixture" }, { "id": "OU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU01.selected_fixture" }, { "id": "OU03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU03.selected_fixture" }, { "id": "OU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU05.selected_fixture" }, { "id": "OU06", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "OU06.selected_fixture" }, { "id": "OU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU07.selected_fixture" }, { "id": "OU08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU08.selected_fixture" }, { "id": "OU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU09.selected_fixture" }, { "id": "OU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU10.selected_fixture" }, { "id": "OU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU11.selected_fixture" }, { "id": "OU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU12.selected_fixture" }, { "id": "OU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU13.selected_fixture" }, { "id": "OU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU04.selected_fixture" }, { "id": "OU19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU19.selected_fixture" }, { "id": "OU20", "verdict": "fail", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU20.selected_fixture" }, { "id": "OU21", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU21.selected_fixture" }, { "id": "PR01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR01.selected_fixture" }, { "id": "PR02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR02.selected_fixture" }, { "id": "PR03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR03.selected_fixture" }, { "id": "PR04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR04.selected_fixture" }, { "id": "PR05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR05.selected_fixture" }, { "id": "PR06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR06.selected_fixture" }, { "id": "PR07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR07.selected_fixture" }, { "id": "PR08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR08.selected_fixture" }, { "id": "PR09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR09.selected_fixture" }, { "id": "PR10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR10.selected_fixture" }, { "id": "PR11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR11.selected_fixture" }, { "id": "PR12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR12.selected_fixture" }, { "id": "PR13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR13.selected_fixture" }, { "id": "PR14", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "PR14.selected_fixture" }, { "id": "PR15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR15.selected_fixture" }, { "id": "PR16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR16.selected_fixture" }, { "id": "PR17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR17.selected_fixture" }, { "id": "PR18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR18.selected_fixture" }, { "id": "PR19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR19.selected_fixture" }, { "id": "F01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F01.selected_fixture" }, { "id": "F02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F02.selected_fixture" }, { "id": "F03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F03.selected_fixture" }, { "id": "F04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F04.selected_fixture" }, { "id": "F05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F05.selected_fixture" }, { "id": "G01", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G01.static_sources" }, { "id": "G02", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G02.static_sources" }, { "id": "G03", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G03.static_sources" } ], "charges": [ { "id": "F1C-GEN03", "points": "0.5", "reason": "отчёт не соответствует заданию: OU20" }, { "id": "F1C-PR09", "points": "0.5", "reason": "CommonModules/УчетСервер/Ext/Module.bsl:215 — РегистрРасчета.Начисления.БазаНачисления: база получается без отбора по регистратору — по всем записям регистра" }, { "id": "F1C-PR09", "points": "0.5", "reason": "CommonModules/УчетСервер/Ext/Module.bsl:247 — РегистрРасчета.Начисления.БазаНачисления: база получается без отбора по регистратору — по всем записям регистра" }, { "id": "F1C-GEN15", "points": "0.5", "reason": "Reports/ПремииЗаМесяц/Ext/ManagerModule.bsl:5 — РегистрРасчета.Начисления: отбор по ВидРасчета, ПериодДействияНачало, индексы таблицы начинаются с ПериодДействия, ПериодРегистрации, Подразделение, Регистратор, Сотрудник" }, { "id": "F1C-GEN14", "points": "1.5", "reason": "Reports/ПродажиАналогов/Ext/ManagerModule.bsl:3 — РегистрБухгалтерии.Хозрасчетный: итоги считаются по основной таблице регистра, а не по виртуальной" }, { "id": "F1C-PR14", "points": "0.5", "reason": "после расчёта набор с периодом действия перезаписывается целиком, с пересчётом фактического периода действия (нужно Записать(, Истина)): CommonModules/УчетСервер/Ext/Module.bsl:211 Н.Записать(); CommonModules/УчетСервер/Ext/Module.bsl:228 Н.Записать(); CommonModules/УчетСервер/Ext/Module.bsl:241 Н.Записать(); CommonModules/УчетСервер/Ext/Module.bsl:259 Н.Записать()" }, { "id": "F1C-BU06", "points": "1.5", "reason": "у счёта товаров 01.02 не включён признак учёта КоличественныйУчет" }, { "id": "F1C-BU05", "points": "0.5", "reason": "аналитика счетов вынесена в измерения регистра бухгалтерии и есть у всех счетов: Номенклатура (Номенклатура)" }, { "id": "F1C-GEN20", "points": "2.0", "reason": "данные базы читаются в цикле по записям: CommonModules/УчетСервер/Ext/Module.bsl:293" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "оперативное проведение разрешено у документов с движениями по регистрам расчёта: НачислениеЗарплаты" }, { "id": "F1C-GEN21", "points": "2.0", "reason": "данные графика без отбора по регистратору: CommonModules/УчетСервер/Ext/Module.bsl:173" } ], "score_upper_bound": "-6.0", "score": null, "grade": "unsatisfactory", "deductions": "11.0", "not_assessed": 16, "gates": { "starter_origin": "passed", "load": "loaded", "clients": "compiles", "demo_data": "present" }, "infrastructure_errors": false, "comparison_eligible": false, "binding_compatibility": { "scope": "supplemental_named_subconto_adapter", "original_binding_sha256": "938f1873ea01dfdfe3da8d8828895d4a895de6be4398bbd046f4411b24c75261", "normalized_binding_sha256": "33d56b52100336dd84ad90b501ff2cc5f7ffb896d03bf2862863d853a4750993", "normalizer_sha256": "7327277143d80a531e4c254ac74a9fc0e0d5c76572d53b8469e0a580eda17d65", "canonical_ledger_sha256": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "changes": [ { "field": "fields.ledger.warehouse_debit", "before": "Склады", "after": "ВидыСубконто.Склады", "kind": "named" }, { "field": "fields.ledger.warehouse_credit", "before": "Склады", "after": "ВидыСубконто.Склады", "kind": "named" } ], "basis": "kind names expanded only to exactly one predefined kind of the account chart on the role side; all role types checked." } }, "measurement": { "operator": { "name": "Вячеслав", "github": "sksibak" }, "environment": { "captured_at": "2026-10-24T05:07:22.329340+00:00", "capture_timing": "before_run", "hardware": { "cpu": "AMD Ryzen 5 4600H with Radeon Graphics ", "logical_cpus": 12, "ram_bytes": 16505962496 }, "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "python": "3.12.14", "platform_version": "8.3.27.1644", "isolation": "dedicated-host", "network_profile": "open-book_shell", "unsafe_action_protection_observed_in_user_config": true, "git_revision": "af85e791b303dbbf0b0b7af924d2489c3e57cfa8", "implementation_files": { "exam_bench/__init__.py": "ad5bf6f05dc6765f40b78bd186870ca2c49be113cfa33f8aa76f4926f2cb2c1e", "exam_bench/assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "exam_bench/bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "exam_bench/calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "exam_bench/calibrate.py": "78b5185cb0888c0c0ac3de95ffc3a80154a6de9ae66fc461f79d012e5a58e1db", "exam_bench/calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "exam_bench/calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "exam_bench/calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "exam_bench/calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "exam_bench/calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "exam_bench/claude.py": "bc1b8550de7573aaed5e39c6e9c0309e0d8175284a75490d61ec27439ed911ad", "exam_bench/cli.py": "1a37ce645633d761f7897dffc9c45e6b8b9600cd7bd233b1cbf78f49d26b099a", "exam_bench/codescan.py": "751e38001b6e65727a31e28172a0623f0bf34bc092a958037c286aa991a197ed", "exam_bench/codex.py": "c3f89d72af11f312d851c73a1610d92e79acadf336be9ccedd1f94ede3b3ccb0", "exam_bench/common.py": "8682603b519063e655eae3574a02a49efee63bde21f582ccee20ddd623fca96d", "exam_bench/docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "exam_bench/examiner.py": "d7294fdd23ed1732216cafebf0a8cf2c24cce4259859aeb7149f62b7607d087d", "exam_bench/finalize.py": "4034f1c63896a940afdb1a83d541cf47fc75c8b5061e3f839047109c04beb620", "exam_bench/forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "exam_bench/gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "exam_bench/grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "exam_bench/harness.py": "3040f6daaf1dc6e6583219f4d925151f8ba7851b2d5417d7f14645892b485ddf", "exam_bench/interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "exam_bench/interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "exam_bench/isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "exam_bench/ledger.py": "7e851523580e22d8490e75f9b6026c07f2c355007e0d11d0b252671f56bef654", "exam_bench/locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "exam_bench/materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "exam_bench/mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "exam_bench/observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "exam_bench/ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "exam_bench/penalties.py": "0d79e2e46102657dca00609b6abbfc0bf7d11fad41429564f876c82bc6b33269", "exam_bench/platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "exam_bench/portable.py": "cad56968ff407983608f5bdbc9ce7234128d7a4580b096ecea8e0e7b4edb9070", "exam_bench/portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "exam_bench/pr.py": "6a3a20caf0e10c0cc94410511a72d62c9fcda785f3abab1be2ad616d4ee16836", "exam_bench/preflight.py": "5619be0131d8641925f3ce2a3c8e5234d42aa5635d95676138ca81536d95cd29", "exam_bench/process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "exam_bench/queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "exam_bench/queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "exam_bench/replay_calibration.py": "c150457b0b23ce4e6814eb8deb4d48f6bc4a2e39d8f84a9dc7644fb99a026c2d", "exam_bench/report.py": "5e4c0757e1c7f189953f9a5302593ab726551835856baed25efd93dad6e8bfcd", "exam_bench/runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "exam_bench/smoke_check.py": "f36922a0027429ead0b414048dcc14bbe67f2f0e79a70d03dffbe1447d253545", "exam_bench/stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "exam_bench/submission.py": "ea862adc63ae67861ddb1d6aeb4d92c10b0b05004d22953f7b03612f82bb4bf4", "exam_bench/telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "exam_bench/windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "exam_bench/workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tools/build_public_site.py": "9682ed696f5ac9e9a82b65a45c0dece556ec7e49eeb20dcd616882cc534a8258", "tools/build_result_site.py": "3294e1d2ec1486058e208735264d61e349a68a4ae2fa2ec7a723c70e3263b496", "tools/check_native_harnesses.py": "4f5f0ed27651f78758eaef077b3b114361781f6b95ec40cb46c3fea689210473", "tools/check_native_toolkit.py": "0272794617121f2932828e5e4e9ae20095183c443666cf3ba466b44fbe875095", "tools/community_results.py": "cbfba30b4e617f5e219637c1c2de57398d01eb2f284eae3aca3ef684e6505a39", "tools/community_service.py": "c374480dbd88d656c0b9054fa04a8e1c6698c69e2f9cf475e82498a2dff61d84", "tools/community_setup.py": "5d7d126ed7d4dd48e1d79f57b99647a92ffcc8c9f80d90915e458888cdd76bf7", "tools/compare_harness_runs.py": "f274df5f3f804cb02504491aec946943833e12fbce6e62d281e12beb8508fc4e", "tools/create_run_plan.py": "871cd81b1eda231c0fba8805f63d2668926be9fc641559e6ddf320e2f47cd37a", "tools/demo_runner.py": "ca7ad17919c53d524cc0418751ba09a540f910eac183dca2961710bc30bba26f", "tools/installers.py": "9a2742780936b17500869e7c89202c1a2549e37d53a42ad9a50a0abbf78bbe09", "tools/machine_bundle.py": "8aa8346f99f537e81ceca6fb6ab9530e844954bab8eff87bf33d3602f81f8a30", "tools/prepare_native_harnesses.py": "aaa75ecf4022883984fa50c42d14d8e1a9fde2eeda03dab03b852bbc5efb2502", "tools/prepare_official_statement.py": "6b7028c78e90e798d6ef1a93b76520cc61a308c354fb9b87f7fad18b99800fad", "tools/prepare_open_exam_requirements.py": "544f4e378b9be5f166186f8788f8d454afdac2deb99d91d98421e39d01ba6d03", "tools/probe_harness.py": "1ed8ef93420d1484cbbfd151b7efc31b9a201ceb942dd05e3103efa22ffa7f27", "tools/probe_native_mcp.py": "9918d324129cba898993e07f8f8b6dbcbaf369398ebf28d464f9f1f00abdb254", "tools/readiness.py": "d34dd3f38334f51cc4574c79194cf0b80769b062a52382989a57d01c46b9aba4", "tools/recheck_community.py": "f0843d7d677f90da31e22bde0b1c86584dd46c022f1532d43d042619e426b230", "tools/regrade_runs.py": "011775afb06d3aac67a4aa81117a368c75896b0fcbe1e6f27ccc6237612fbf59", "tools/render_statement_text.py": "dabc0716a3612c288c671bc20e17fd4986691d732768e1e957d6dddddbea92a3", "tools/replay_calibration.py": "801f5004926c438c21ed3668fe2a4ddf45312b3e75320165a3839aae034eee9b", "tools/run_exam_campaign.py": "2c450d57a1cd0a2682838f5ec7c0a4ffb3aed0f1730d34c408e912d59cab6efd", "tools/serve_result_site.py": "86badfac863cd4ad1fc894a14110c75b28470513f0133eeae9d2799b8b4df3a9", "tools/start_demo.py": "c597e6cad28d245b3191654bb3e2801fa9dd2364e2acb25561923613717b615f", "tools/supplemental_acceptance.py": "c88fc39de1be1fdcacdd819e2ad329f60367b2df1d5deda80b37324bda3f2a01", "tools/sync_sources.py": "b51e889b0f41f9f63bfb19a09fb96d3777693d6b1d76fe0132bdd2a15e155898", "tools/validate_community_pr.py": "796b896dfade07b4529af2088a4b9b9d23484148b3bc0732b3fb837b75c9844b", "tools/verify_official_assessment_mapping.py": "daeb448a016940d5b6b1285979a56e5b9014bd91db40acb131445e4a83a23059", "tools/verify_task_package.py": "9e1e6105f6b5e4e78b36aa57f00117a9fbc8948ab53983c32ab56da88d23ccc4", "profiles/agents.json": "af9c492c08d13b3044aa6b6952589ed6a0a07d5258d8ff72bb18185b3eaebdc5", "profiles/ai-exam-execution-policy.json": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "profiles/bsl-analyzer-0.3.2-macos.json": "83537abdbf38c41ce665e4d0f24128bb51b62e971e0e0f368695f1326a7d2ffb", "profiles/bsl-analyzer-0.3.2-portable.json": "d6ba732e6778e256df34d6bc548593128820a70430c35b279796843606ee40a8", "profiles/bsl-ls-1.1.0-rc.6-macos.json": "245fc10747197e6911b2b4c77cdb15e6fa4eb7bc7c3758b63e768c5adf1df180", "profiles/bsl-ls-1.1.0-rc.6-portable.json": "9f10660881f2ec84794f7d584556b8f75c7e14b3555464af0ed0e60c4c892d86", "profiles/code-index-1.9.0-macos.json": "63a919523ce62ecec274f4c139bc7ad49a75dd4c339568b822cbc695b4e30408", "profiles/code-index-1.9.0-portable.json": "81106cee8f424ffd8a9dc46ecd8e4f57598fc1d49661a83c77b1f0507993fbdc", "profiles/codex-probe-plan.json": "166e41aad5fb3b27d9050bc6de952c6cba363cc6e804d4080568cc71a2a4d289", "profiles/machine.linux.example.json": "408304fd0581098d5d8110dc67dfeab353bc4d4030e32d37e6acf98d2b1aedfd", "profiles/machine.macos.example.json": "52e9f9d17797cb520b9d8955d6806fd550b899bed4da241ebf096dcb6a21a942", "profiles/machine.windows.example.json": "63accac9a2f81d47d03447efbabffd4760aee325193f02f46b9b29a28d50d2d8", "profiles/mcp-toolkit-1.9.0-macos.json": "1d3f9cde5ffa20589a840d01fdae03aa0fc2f412c929f064f203919c4129625b", "profiles/mcp-toolkit-1.9.0-portable.json": "8e370eebe773eef0e08045ee9c6d5be1451f769f65be0710834b262a4336e054", "profiles/none-macos.json": "b1401d9c48159aed3559006c7f6ace6ef4571224d5cf0bb76d1a823505a10056", "profiles/none-portable.json": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "profiles/rlm-tools-bsl-1.43.0-macos.json": "9354421052640ab60bc3e6aa98ff2e7ba9ca2318b0f4026c137487449242cbd2", "profiles/rlm-tools-bsl-1.43.0-portable.json": "2599e5645e0a7d4e44cb2934bc2b272cae79a9bf7ea74a23cd48aacea64bc424", "profiles/rlm-tools-bsl-1.43.0-posix-requirements.txt": "4fdf9a1bd994bf0272e65d231daf76cf19b0a34dad0ae6b50ec4f11a2ce4c330", "profiles/rlm-tools-bsl-1.43.0-windows-requirements.txt": "3730cb46c81cda5181ecd4485e98b11933104632358bc86f8c0eb1a612a8954f", "profiles/shirokov-skills-macos.json": "84f3e89091676884a802035c707e912762a1179425fb8e3faff25be736873cdb", "profiles/shirokov-skills-portable.json": "2b0a461e06602f1456410e70f02ceaa5ac32c6549c486660bcb5ace0c2f87b15", "profiles/shirokov-skills-windows-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/unica-0.12.3-macos.json": "2c39fbb591cf2c2c6e056373823615485397ea83651b7926c6f25a5fe6a0aae6", "profiles/unica-0.13.0-macos.json": "b76b5c8a4dd33f571c4a90993f1a2da5f7223b4f0f8e1042c282e21a66121052", "profiles/unica-0.14.0-rc.1-portable.json": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "rules/1c-specialist-platform/chistov.json": "77e04942f8c947b10759e7cc1eb31af05847d1711a772fbe6f23d525766757a9", "rules/1c-specialist-platform/decisions.json": "f622107423ce3c188c063318d7ab4f7718ceb38e443130677d8987f386641c09", "rules/1c-specialist-platform/examiner.json": "30353aa2a1b6545496b070d9066e9ffba0c3779e5b53ef70a4fd2cee375b18c0", "rules/1c-specialist-platform/ledger.json": "f167c10db2b5799dd9a1ea6a37cd2d7d186810dadf5ea2f50f26ae723c676882", "rules/1c-specialist-platform/rules.json": "1d320a4f8e1bf4701496388931f492315549bd3dce574b17285dd1d7f8652007", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" } } }, "conditions": { "client": "codex", "model": "gpt-6.1-sol", "client_version": "0.163.0-alpha.11.2", "reasoning_effort": "medium", "harness": "none", "billing_channel": "subscription", "solve_timeout_seconds": 3600, "time_series": null, "delegation": "native_disabled", "network_profile": "open-book_shell", "deadline_disclosed": true, "statement_sha256": "8a6ccb3e673826d1f8220fda53eb310e3ec18c136d87ce8f4cebb2a08614e7e5", "starter_dt_sha256": "f40d084818b0d1cfe503fc7653a6a13f1a8e47fcd1688dad6245b12744eb4638", "profile_sha256": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "execution_policy_sha256": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "calibration_sha256": "eced5b2f738ff558afe3d33d03048cf7b3ad00fa4e418c6a0ed72f885d0d221c", "started_at": "2026-10-24T05:07:30.140350+00:00", "timing": { "prepare_ms": 7282, "solve_ms": 3372156, "grade_ms": null }, "original_submission_valid": false, "model_provenance": "requested_only", "tokens": { "input": 17610405, "cached_input": 17466624, "fresh_input": 143781, "output": 112434, "reasoning_output": 42146, "total": 17722839, "coverage": "reported_completed_root_turns" }, "tools": { "mcp_calls": 0, "unica_calls": 0, "failed_calls": 0 }, "process": { "status": "completed", "exit_code": 0, "stop_confirmed": true } }, "verification": "repository_owner", "download": "community-downloads/demo-20261025T112228Z-adapter--owner-2026-10-26T214337676149-0000/solution.zip", "source_context": "community-downloads/demo-20261025T112228Z-adapter--owner-2026-10-26T214337676149-0000/source-context.json", "regrade_required": [ { "id": "grader_changed", "files": [ "calibrate.py", "calibration_periodicity.py", "common.py", "ou.py", "replay_calibration.py", "smoke_check.py", "tasks/1c-platform-official-sample/checks.json" ] } ], "grader_revision_sha256": "349d87e0c7f531acbe35dd2b39c35722d8a877fedde97575b49e8466ab763c1d", "archive_sha256": "431bfefd3c95c2f99664b102c26dfb025b4a345e9f138980fb461743fc460a11", "owner_verification": { "kind": "repository_owner", "repository": "zeegin/1c-agent-exam-benchmark", "operator": { "name": "Ingvar Vilkman", "github": "zeegin" }, "started_at": "2026-10-26T21:43:37.510995+00:00", "server": { "name": "Owner Windows stand", "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "hardware": { "cpu": "AMD Ryzen 7 5800X 8-Core Processor ", "logical_cpus": 4, "ram_bytes": 17109000192 }, "isolation": "dedicated-host" }, "platform_version": "8.3.27.2342", "grader": { "profile": "technical-v8", "commit": "e8fd8ced03a85b549c5472fbbda29225749f54d1", "working_tree_dirty": false, "fingerprint": { "assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "calibrate.py": "3162d431f3cab5e7976aa39f665d6286dce45499cf362d85109b7123fa8403a2", "calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "calibration_query.py": "3555b103cde8ea0519955cf52358d09223f5ab183a9df00533bdb48c89237a8c", "claude.py": "eedabc75fca0faa434f40a1624b71419ec7dc22e2854a0886cf84b4911db8372", "codescan.py": "6d8375210cef1fd768fc2d98d630d880b2993a9724f01ae25f33b4ea5aa9631d", "codex.py": "904e75503cd35f16cbb052f66806b3879fe25bfc9f99e33b93c889d862c46324", "common.py": "52825cf5c29f3536d6e046a89e789d5ef9c83aacd7f2f5a07f4f53e77b5229cc", "docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "examiner.py": "8cdffcdd52f043c905f896697403380af95bf485dd4a5edca24f7956e7795ffe", "forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "harness.py": "3cbb90fd3187e700b5df32e5daafb20313d49bb5721c826e3033cbc6aa6e3825", "interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "penalties.py": "ae388cb8953ecca1f2370a7c4cb1db3b6cc8318fc2a7563a4db15f9f5b057429", "platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "pr.py": "2b6bfea0634703469605ce114f9274716b485852d9a55d9185c39893b14e4726", "preflight.py": "448c3120ab64b625abae3891be686c7a214ce4211f7cf651fd90e12c0b298433", "process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "queries.py": "1ef57e292db3e8967a733948371ecc542f743b811890d4fc509df17303b9c4ac", "queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "querytypes.py": "b645f489a2abc27762b4a9bbf4917e72f7b46dc053a74c0dca4a8fc46491b3ef", "replay_calibration.py": "0a4d9b84a9908944c5a945878eb6f5eeda5a4e42ffff4f55c04a680742803d80", "runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "smoke_check.py": "66caf1a01f7aa18432293abe3567ac228ac837a660b08c3dc7bb093f7bd51628", "stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "submission.py": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tasks/1c-platform-official-sample/checks.json": "17a6fcc0c14410829650623eb1443ce99796e000cdfd19905ac0287988b73a00", "tasks/1c-platform-official-sample/private/official-assessment-mapping.json": "303587c0dabe77c1eeebb2017fe85539e3370b17c9090435e6e0325a66bd0644", "tasks/1c-platform-official-sample/private/owner-scoring-policy.json": "d26d534bb838ab1b5facb7bc033ca8ec40912133baadcdbad83b27fc577905f5", "starters/carcass-8.3.25.1445/starter.json": "0f7a7060885ba99a19402bfc6e63cc8fe979b0f491b040d3a01d5d21b304b3a6", "rules/1c-specialist-platform/rules.json": "ea75e34ace5de11ba3de403c63cd2c026db81d1d991f8531e4a779d4ce9788e7", "rules/1c-specialist-platform/examiner.json": "1247486ddd412d600db88d9c1db4ba501fc1994afd1dc2ebe85402fcc332f4c8", "rules/1c-specialist-platform/chistov.json": "800da27601a3f1c7ec1df64482fd4ad035e559ba0b390a274ed5031128487d3d", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" }, "sha256": "349d87e0c7f531acbe35dd2b39c35722d8a877fedde97575b49e8466ab763c1d" }, "method": "saved_platform_observations", "outcome": "complete", "completed_at": "2026-10-26T21:43:37.676149+00:00" } }, { "id": "demo-20261025T112228Z-adapter--owner-2026-10-26T184713813676-0000", "run_id": "demo-20261024T050719Z-7a9caa", "result": { "run_id": "demo-20261024T050719Z-7a9caa", "created_at": "2026-10-26T18:47:13.813676+00:00", "model": "gpt-6.1-sol", "harness": "none", "solve_seconds": 3372, "platform": "8.3.27.1644", "counts": { "pass": 64, "fail": 1 }, "rules": [ { "id": "BU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU01.selected_fixture" }, { "id": "BU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU04.selected_fixture" }, { "id": "BU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU05.selected_fixture" }, { "id": "BU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU16.selected_fixture" }, { "id": "BU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU17.selected_fixture" }, { "id": "BU02", "verdict": "pass", "reason": null, "coverage": "partial", "assertion_id": "BU02.posting_cost_and_balance" }, { "id": "BU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU10.selected_fixture" }, { "id": "BU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU12.selected_fixture" }, { "id": "BU03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU03.selected_fixture" }, { "id": "BU06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU06.selected_fixture" }, { "id": "BU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU07.selected_fixture" }, { "id": "BU08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU08.selected_fixture" }, { "id": "BU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU09.selected_fixture" }, { "id": "BU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU11.selected_fixture" }, { "id": "BU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU14.selected_fixture" }, { "id": "BU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU15.selected_fixture" }, { "id": "BU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU13.selected_fixture" }, { "id": "OU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU15.selected_fixture" }, { "id": "OU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU16.selected_fixture" }, { "id": "OU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU17.selected_fixture" }, { "id": "OU02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU02.selected_fixture" }, { "id": "OU18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU18.selected_fixture" }, { "id": "OU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU14.selected_fixture" }, { "id": "OU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU01.selected_fixture" }, { "id": "OU03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU03.selected_fixture" }, { "id": "OU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU05.selected_fixture" }, { "id": "OU06", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "OU06.selected_fixture" }, { "id": "OU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU07.selected_fixture" }, { "id": "OU08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU08.selected_fixture" }, { "id": "OU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU09.selected_fixture" }, { "id": "OU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU10.selected_fixture" }, { "id": "OU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU11.selected_fixture" }, { "id": "OU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU12.selected_fixture" }, { "id": "OU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU13.selected_fixture" }, { "id": "OU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU04.selected_fixture" }, { "id": "OU19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU19.selected_fixture" }, { "id": "OU20", "verdict": "fail", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU20.selected_fixture" }, { "id": "OU21", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU21.selected_fixture" }, { "id": "PR01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR01.selected_fixture" }, { "id": "PR02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR02.selected_fixture" }, { "id": "PR03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR03.selected_fixture" }, { "id": "PR04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR04.selected_fixture" }, { "id": "PR05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR05.selected_fixture" }, { "id": "PR06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR06.selected_fixture" }, { "id": "PR07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR07.selected_fixture" }, { "id": "PR08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR08.selected_fixture" }, { "id": "PR09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR09.selected_fixture" }, { "id": "PR10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR10.selected_fixture" }, { "id": "PR11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR11.selected_fixture" }, { "id": "PR12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR12.selected_fixture" }, { "id": "PR13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR13.selected_fixture" }, { "id": "PR14", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "PR14.selected_fixture" }, { "id": "PR15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR15.selected_fixture" }, { "id": "PR16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR16.selected_fixture" }, { "id": "PR17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR17.selected_fixture" }, { "id": "PR18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR18.selected_fixture" }, { "id": "PR19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR19.selected_fixture" }, { "id": "F01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F01.selected_fixture" }, { "id": "F02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F02.selected_fixture" }, { "id": "F03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F03.selected_fixture" }, { "id": "F04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F04.selected_fixture" }, { "id": "F05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F05.selected_fixture" }, { "id": "G01", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G01.static_sources" }, { "id": "G02", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G02.static_sources" }, { "id": "G03", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G03.static_sources" } ], "charges": [ { "id": "F1C-GEN03", "points": "0.5", "reason": "отчёт не соответствует заданию: OU20" }, { "id": "F1C-PR09", "points": "0.5", "reason": "CommonModules/УчетСервер/Ext/Module.bsl:215 — РегистрРасчета.Начисления.БазаНачисления: база получается без отбора по регистратору — по всем записям регистра" }, { "id": "F1C-PR09", "points": "0.5", "reason": "CommonModules/УчетСервер/Ext/Module.bsl:247 — РегистрРасчета.Начисления.БазаНачисления: база получается без отбора по регистратору — по всем записям регистра" }, { "id": "F1C-GEN15", "points": "0.5", "reason": "Reports/ПремииЗаМесяц/Ext/ManagerModule.bsl:5 — РегистрРасчета.Начисления: отбор по ВидРасчета, ПериодДействияНачало, индексы таблицы начинаются с ПериодДействия, ПериодРегистрации, Подразделение, Регистратор, Сотрудник" }, { "id": "F1C-GEN14", "points": "1.5", "reason": "Reports/ПродажиАналогов/Ext/ManagerModule.bsl:3 — РегистрБухгалтерии.Хозрасчетный: итоги считаются по основной таблице регистра, а не по виртуальной" }, { "id": "F1C-PR14", "points": "0.5", "reason": "после расчёта набор с периодом действия перезаписывается целиком, с пересчётом фактического периода действия (нужно Записать(, Истина)): CommonModules/УчетСервер/Ext/Module.bsl:211 Н.Записать(); CommonModules/УчетСервер/Ext/Module.bsl:228 Н.Записать(); CommonModules/УчетСервер/Ext/Module.bsl:241 Н.Записать(); CommonModules/УчетСервер/Ext/Module.bsl:259 Н.Записать()" }, { "id": "F1C-BU06", "points": "1.5", "reason": "у счёта товаров 01.02 не включён признак учёта КоличественныйУчет" }, { "id": "F1C-BU05", "points": "0.5", "reason": "аналитика счетов вынесена в измерения регистра бухгалтерии и есть у всех счетов: Номенклатура (Номенклатура)" }, { "id": "F1C-GEN20", "points": "2.0", "reason": "данные базы читаются в цикле по записям: CommonModules/УчетСервер/Ext/Module.bsl:293" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "оперативное проведение разрешено у документов с движениями по регистрам расчёта: НачислениеЗарплаты" }, { "id": "F1C-GEN21", "points": "2.0", "reason": "данные графика без отбора по регистратору: CommonModules/УчетСервер/Ext/Module.bsl:173" } ], "score_upper_bound": "-6.0", "score": null, "grade": "unsatisfactory", "deductions": "11.0", "not_assessed": 16, "gates": { "starter_origin": "passed", "load": "loaded", "clients": "compiles", "demo_data": "present" }, "infrastructure_errors": false, "comparison_eligible": false, "binding_compatibility": { "scope": "supplemental_named_subconto_adapter", "original_binding_sha256": "938f1873ea01dfdfe3da8d8828895d4a895de6be4398bbd046f4411b24c75261", "normalized_binding_sha256": "33d56b52100336dd84ad90b501ff2cc5f7ffb896d03bf2862863d853a4750993", "normalizer_sha256": "7327277143d80a531e4c254ac74a9fc0e0d5c76572d53b8469e0a580eda17d65", "canonical_ledger_sha256": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "changes": [ { "field": "fields.ledger.warehouse_debit", "before": "Склады", "after": "ВидыСубконто.Склады", "kind": "named" }, { "field": "fields.ledger.warehouse_credit", "before": "Склады", "after": "ВидыСубконто.Склады", "kind": "named" } ], "basis": "kind names expanded only to exactly one predefined kind of the account chart on the role side; all role types checked." } }, "measurement": { "operator": { "name": "Вячеслав", "github": "sksibak" }, "environment": { "captured_at": "2026-10-24T05:07:22.329340+00:00", "capture_timing": "before_run", "hardware": { "cpu": "AMD Ryzen 5 4600H with Radeon Graphics ", "logical_cpus": 12, "ram_bytes": 16505962496 }, "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "python": "3.12.14", "platform_version": "8.3.27.1644", "isolation": "dedicated-host", "network_profile": "open-book_shell", "unsafe_action_protection_observed_in_user_config": true, "git_revision": "af85e791b303dbbf0b0b7af924d2489c3e57cfa8", "implementation_files": { "exam_bench/__init__.py": "ad5bf6f05dc6765f40b78bd186870ca2c49be113cfa33f8aa76f4926f2cb2c1e", "exam_bench/assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "exam_bench/bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "exam_bench/calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "exam_bench/calibrate.py": "78b5185cb0888c0c0ac3de95ffc3a80154a6de9ae66fc461f79d012e5a58e1db", "exam_bench/calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "exam_bench/calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "exam_bench/calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "exam_bench/calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "exam_bench/calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "exam_bench/claude.py": "bc1b8550de7573aaed5e39c6e9c0309e0d8175284a75490d61ec27439ed911ad", "exam_bench/cli.py": "1a37ce645633d761f7897dffc9c45e6b8b9600cd7bd233b1cbf78f49d26b099a", "exam_bench/codescan.py": "751e38001b6e65727a31e28172a0623f0bf34bc092a958037c286aa991a197ed", "exam_bench/codex.py": "c3f89d72af11f312d851c73a1610d92e79acadf336be9ccedd1f94ede3b3ccb0", "exam_bench/common.py": "8682603b519063e655eae3574a02a49efee63bde21f582ccee20ddd623fca96d", "exam_bench/docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "exam_bench/examiner.py": "d7294fdd23ed1732216cafebf0a8cf2c24cce4259859aeb7149f62b7607d087d", "exam_bench/finalize.py": "4034f1c63896a940afdb1a83d541cf47fc75c8b5061e3f839047109c04beb620", "exam_bench/forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "exam_bench/gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "exam_bench/grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "exam_bench/harness.py": "3040f6daaf1dc6e6583219f4d925151f8ba7851b2d5417d7f14645892b485ddf", "exam_bench/interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "exam_bench/interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "exam_bench/isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "exam_bench/ledger.py": "7e851523580e22d8490e75f9b6026c07f2c355007e0d11d0b252671f56bef654", "exam_bench/locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "exam_bench/materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "exam_bench/mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "exam_bench/observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "exam_bench/ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "exam_bench/penalties.py": "0d79e2e46102657dca00609b6abbfc0bf7d11fad41429564f876c82bc6b33269", "exam_bench/platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "exam_bench/portable.py": "cad56968ff407983608f5bdbc9ce7234128d7a4580b096ecea8e0e7b4edb9070", "exam_bench/portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "exam_bench/pr.py": "6a3a20caf0e10c0cc94410511a72d62c9fcda785f3abab1be2ad616d4ee16836", "exam_bench/preflight.py": "5619be0131d8641925f3ce2a3c8e5234d42aa5635d95676138ca81536d95cd29", "exam_bench/process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "exam_bench/queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "exam_bench/queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "exam_bench/replay_calibration.py": "c150457b0b23ce4e6814eb8deb4d48f6bc4a2e39d8f84a9dc7644fb99a026c2d", "exam_bench/report.py": "5e4c0757e1c7f189953f9a5302593ab726551835856baed25efd93dad6e8bfcd", "exam_bench/runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "exam_bench/smoke_check.py": "f36922a0027429ead0b414048dcc14bbe67f2f0e79a70d03dffbe1447d253545", "exam_bench/stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "exam_bench/submission.py": "ea862adc63ae67861ddb1d6aeb4d92c10b0b05004d22953f7b03612f82bb4bf4", "exam_bench/telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "exam_bench/windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "exam_bench/workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tools/build_public_site.py": "9682ed696f5ac9e9a82b65a45c0dece556ec7e49eeb20dcd616882cc534a8258", "tools/build_result_site.py": "3294e1d2ec1486058e208735264d61e349a68a4ae2fa2ec7a723c70e3263b496", "tools/check_native_harnesses.py": "4f5f0ed27651f78758eaef077b3b114361781f6b95ec40cb46c3fea689210473", "tools/check_native_toolkit.py": "0272794617121f2932828e5e4e9ae20095183c443666cf3ba466b44fbe875095", "tools/community_results.py": "cbfba30b4e617f5e219637c1c2de57398d01eb2f284eae3aca3ef684e6505a39", "tools/community_service.py": "c374480dbd88d656c0b9054fa04a8e1c6698c69e2f9cf475e82498a2dff61d84", "tools/community_setup.py": "5d7d126ed7d4dd48e1d79f57b99647a92ffcc8c9f80d90915e458888cdd76bf7", "tools/compare_harness_runs.py": "f274df5f3f804cb02504491aec946943833e12fbce6e62d281e12beb8508fc4e", "tools/create_run_plan.py": "871cd81b1eda231c0fba8805f63d2668926be9fc641559e6ddf320e2f47cd37a", "tools/demo_runner.py": "ca7ad17919c53d524cc0418751ba09a540f910eac183dca2961710bc30bba26f", "tools/installers.py": "9a2742780936b17500869e7c89202c1a2549e37d53a42ad9a50a0abbf78bbe09", "tools/machine_bundle.py": "8aa8346f99f537e81ceca6fb6ab9530e844954bab8eff87bf33d3602f81f8a30", "tools/prepare_native_harnesses.py": "aaa75ecf4022883984fa50c42d14d8e1a9fde2eeda03dab03b852bbc5efb2502", "tools/prepare_official_statement.py": "6b7028c78e90e798d6ef1a93b76520cc61a308c354fb9b87f7fad18b99800fad", "tools/prepare_open_exam_requirements.py": "544f4e378b9be5f166186f8788f8d454afdac2deb99d91d98421e39d01ba6d03", "tools/probe_harness.py": "1ed8ef93420d1484cbbfd151b7efc31b9a201ceb942dd05e3103efa22ffa7f27", "tools/probe_native_mcp.py": "9918d324129cba898993e07f8f8b6dbcbaf369398ebf28d464f9f1f00abdb254", "tools/readiness.py": "d34dd3f38334f51cc4574c79194cf0b80769b062a52382989a57d01c46b9aba4", "tools/recheck_community.py": "f0843d7d677f90da31e22bde0b1c86584dd46c022f1532d43d042619e426b230", "tools/regrade_runs.py": "011775afb06d3aac67a4aa81117a368c75896b0fcbe1e6f27ccc6237612fbf59", "tools/render_statement_text.py": "dabc0716a3612c288c671bc20e17fd4986691d732768e1e957d6dddddbea92a3", "tools/replay_calibration.py": "801f5004926c438c21ed3668fe2a4ddf45312b3e75320165a3839aae034eee9b", "tools/run_exam_campaign.py": "2c450d57a1cd0a2682838f5ec7c0a4ffb3aed0f1730d34c408e912d59cab6efd", "tools/serve_result_site.py": "86badfac863cd4ad1fc894a14110c75b28470513f0133eeae9d2799b8b4df3a9", "tools/start_demo.py": "c597e6cad28d245b3191654bb3e2801fa9dd2364e2acb25561923613717b615f", "tools/supplemental_acceptance.py": "c88fc39de1be1fdcacdd819e2ad329f60367b2df1d5deda80b37324bda3f2a01", "tools/sync_sources.py": "b51e889b0f41f9f63bfb19a09fb96d3777693d6b1d76fe0132bdd2a15e155898", "tools/validate_community_pr.py": "796b896dfade07b4529af2088a4b9b9d23484148b3bc0732b3fb837b75c9844b", "tools/verify_official_assessment_mapping.py": "daeb448a016940d5b6b1285979a56e5b9014bd91db40acb131445e4a83a23059", "tools/verify_task_package.py": "9e1e6105f6b5e4e78b36aa57f00117a9fbc8948ab53983c32ab56da88d23ccc4", "profiles/agents.json": "af9c492c08d13b3044aa6b6952589ed6a0a07d5258d8ff72bb18185b3eaebdc5", "profiles/ai-exam-execution-policy.json": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "profiles/bsl-analyzer-0.3.2-macos.json": "83537abdbf38c41ce665e4d0f24128bb51b62e971e0e0f368695f1326a7d2ffb", "profiles/bsl-analyzer-0.3.2-portable.json": "d6ba732e6778e256df34d6bc548593128820a70430c35b279796843606ee40a8", "profiles/bsl-ls-1.1.0-rc.6-macos.json": "245fc10747197e6911b2b4c77cdb15e6fa4eb7bc7c3758b63e768c5adf1df180", "profiles/bsl-ls-1.1.0-rc.6-portable.json": "9f10660881f2ec84794f7d584556b8f75c7e14b3555464af0ed0e60c4c892d86", "profiles/code-index-1.9.0-macos.json": "63a919523ce62ecec274f4c139bc7ad49a75dd4c339568b822cbc695b4e30408", "profiles/code-index-1.9.0-portable.json": "81106cee8f424ffd8a9dc46ecd8e4f57598fc1d49661a83c77b1f0507993fbdc", "profiles/codex-probe-plan.json": "166e41aad5fb3b27d9050bc6de952c6cba363cc6e804d4080568cc71a2a4d289", "profiles/machine.linux.example.json": "408304fd0581098d5d8110dc67dfeab353bc4d4030e32d37e6acf98d2b1aedfd", "profiles/machine.macos.example.json": "52e9f9d17797cb520b9d8955d6806fd550b899bed4da241ebf096dcb6a21a942", "profiles/machine.windows.example.json": "63accac9a2f81d47d03447efbabffd4760aee325193f02f46b9b29a28d50d2d8", "profiles/mcp-toolkit-1.9.0-macos.json": "1d3f9cde5ffa20589a840d01fdae03aa0fc2f412c929f064f203919c4129625b", "profiles/mcp-toolkit-1.9.0-portable.json": "8e370eebe773eef0e08045ee9c6d5be1451f769f65be0710834b262a4336e054", "profiles/none-macos.json": "b1401d9c48159aed3559006c7f6ace6ef4571224d5cf0bb76d1a823505a10056", "profiles/none-portable.json": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "profiles/rlm-tools-bsl-1.43.0-macos.json": "9354421052640ab60bc3e6aa98ff2e7ba9ca2318b0f4026c137487449242cbd2", "profiles/rlm-tools-bsl-1.43.0-portable.json": "2599e5645e0a7d4e44cb2934bc2b272cae79a9bf7ea74a23cd48aacea64bc424", "profiles/rlm-tools-bsl-1.43.0-posix-requirements.txt": "4fdf9a1bd994bf0272e65d231daf76cf19b0a34dad0ae6b50ec4f11a2ce4c330", "profiles/rlm-tools-bsl-1.43.0-windows-requirements.txt": "3730cb46c81cda5181ecd4485e98b11933104632358bc86f8c0eb1a612a8954f", "profiles/shirokov-skills-macos.json": "84f3e89091676884a802035c707e912762a1179425fb8e3faff25be736873cdb", "profiles/shirokov-skills-portable.json": "2b0a461e06602f1456410e70f02ceaa5ac32c6549c486660bcb5ace0c2f87b15", "profiles/shirokov-skills-windows-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/unica-0.12.3-macos.json": "2c39fbb591cf2c2c6e056373823615485397ea83651b7926c6f25a5fe6a0aae6", "profiles/unica-0.13.0-macos.json": "b76b5c8a4dd33f571c4a90993f1a2da5f7223b4f0f8e1042c282e21a66121052", "profiles/unica-0.14.0-rc.1-portable.json": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "rules/1c-specialist-platform/chistov.json": "77e04942f8c947b10759e7cc1eb31af05847d1711a772fbe6f23d525766757a9", "rules/1c-specialist-platform/decisions.json": "f622107423ce3c188c063318d7ab4f7718ceb38e443130677d8987f386641c09", "rules/1c-specialist-platform/examiner.json": "30353aa2a1b6545496b070d9066e9ffba0c3779e5b53ef70a4fd2cee375b18c0", "rules/1c-specialist-platform/ledger.json": "f167c10db2b5799dd9a1ea6a37cd2d7d186810dadf5ea2f50f26ae723c676882", "rules/1c-specialist-platform/rules.json": "1d320a4f8e1bf4701496388931f492315549bd3dce574b17285dd1d7f8652007", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" } } }, "conditions": { "client": "codex", "model": "gpt-6.1-sol", "client_version": "0.163.0-alpha.11.2", "reasoning_effort": "medium", "harness": "none", "billing_channel": "subscription", "solve_timeout_seconds": 3600, "time_series": null, "delegation": "native_disabled", "network_profile": "open-book_shell", "deadline_disclosed": true, "statement_sha256": "8a6ccb3e673826d1f8220fda53eb310e3ec18c136d87ce8f4cebb2a08614e7e5", "starter_dt_sha256": "f40d084818b0d1cfe503fc7653a6a13f1a8e47fcd1688dad6245b12744eb4638", "profile_sha256": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "execution_policy_sha256": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "calibration_sha256": "eced5b2f738ff558afe3d33d03048cf7b3ad00fa4e418c6a0ed72f885d0d221c", "started_at": "2026-10-24T05:07:30.140350+00:00", "timing": { "prepare_ms": 7282, "solve_ms": 3372156, "grade_ms": null }, "original_submission_valid": false, "model_provenance": "requested_only", "tokens": { "input": 17610405, "cached_input": 17466624, "fresh_input": 143781, "output": 112434, "reasoning_output": 42146, "total": 17722839, "coverage": "reported_completed_root_turns" }, "tools": { "mcp_calls": 0, "unica_calls": 0, "failed_calls": 0 }, "process": { "status": "completed", "exit_code": 0, "stop_confirmed": true } }, "verification": "repository_owner", "download": "community-downloads/demo-20261025T112228Z-adapter--owner-2026-10-26T184713813676-0000/solution.zip", "source_context": "community-downloads/demo-20261025T112228Z-adapter--owner-2026-10-26T184713813676-0000/source-context.json", "regrade_required": [ { "id": "grader_changed", "files": [ "calibrate.py", "calibration_periodicity.py", "calibration_query.py", "common.py", "ou.py", "penalties.py", "queries.py", "replay_calibration.py", "rules/1c-specialist-platform/rules.json", "smoke_check.py", "tasks/1c-platform-official-sample/checks.json" ] } ], "grader_revision_sha256": "4a12b62d2c10085e1fc710f377f84903abdf2fb787dda19628d944da990a86b2", "archive_sha256": "71ead93e6d3ec6d24055ce1dfc14bccc580bf87a58c04df9bf4f4f81c3e11bff", "owner_verification": { "kind": "repository_owner", "repository": "zeegin/1c-agent-exam-benchmark", "operator": { "name": "Ingvar Vilkman", "github": "zeegin" }, "started_at": "2026-10-26T18:44:22.364471+00:00", "server": { "name": "Owner Windows stand", "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "hardware": { "cpu": "AMD Ryzen 7 5800X 8-Core Processor ", "logical_cpus": 4, "ram_bytes": 17109000192 }, "isolation": "dedicated-host" }, "platform_version": "8.3.27.2342", "grader": { "profile": "technical-v8", "commit": "45c5511ee520262f83dd0cfe1d9a7f39fae63301", "working_tree_dirty": false, "fingerprint": { "assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "calibrate.py": "1c844971b4977fdcc3b30aebe8aad40fbd45e6828955b8deb043ac8573d61731", "calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "claude.py": "eedabc75fca0faa434f40a1624b71419ec7dc22e2854a0886cf84b4911db8372", "codescan.py": "6d8375210cef1fd768fc2d98d630d880b2993a9724f01ae25f33b4ea5aa9631d", "codex.py": "904e75503cd35f16cbb052f66806b3879fe25bfc9f99e33b93c889d862c46324", "common.py": "7696116dd1a796666518b4c5d2aa3cafa04ee974593d3636333cbe5385bd6ccb", "docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "examiner.py": "8cdffcdd52f043c905f896697403380af95bf485dd4a5edca24f7956e7795ffe", "forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "harness.py": "3cbb90fd3187e700b5df32e5daafb20313d49bb5721c826e3033cbc6aa6e3825", "interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "penalties.py": "b82704e7f47d3dfdf6e501452d7e0abca1f9da63307093d2e257e32358be0489", "platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "pr.py": "2b6bfea0634703469605ce114f9274716b485852d9a55d9185c39893b14e4726", "preflight.py": "448c3120ab64b625abae3891be686c7a214ce4211f7cf651fd90e12c0b298433", "process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "querytypes.py": "b645f489a2abc27762b4a9bbf4917e72f7b46dc053a74c0dca4a8fc46491b3ef", "replay_calibration.py": "3b6f3a289cc8a7f5e458f62bfa2c6cc534cc9076ba3f22d1e4bd8a5f9e175317", "runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "smoke_check.py": "bd6266367e6b769a95258eb383239b89a22deae406d64f6e142c77396f4639ba", "stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "submission.py": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tasks/1c-platform-official-sample/checks.json": "17a6fcc0c14410829650623eb1443ce99796e000cdfd19905ac0287988b73a00", "tasks/1c-platform-official-sample/private/official-assessment-mapping.json": "303587c0dabe77c1eeebb2017fe85539e3370b17c9090435e6e0325a66bd0644", "tasks/1c-platform-official-sample/private/owner-scoring-policy.json": "d26d534bb838ab1b5facb7bc033ca8ec40912133baadcdbad83b27fc577905f5", "starters/carcass-8.3.25.1445/starter.json": "0f7a7060885ba99a19402bfc6e63cc8fe979b0f491b040d3a01d5d21b304b3a6", "rules/1c-specialist-platform/rules.json": "7ec895a7751ef17f4a50cc80b5f7fa986e1e04360ab0b4ce9aa29115195df03c", "rules/1c-specialist-platform/examiner.json": "1247486ddd412d600db88d9c1db4ba501fc1994afd1dc2ebe85402fcc332f4c8", "rules/1c-specialist-platform/chistov.json": "800da27601a3f1c7ec1df64482fd4ad035e559ba0b390a274ed5031128487d3d", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" }, "sha256": "4a12b62d2c10085e1fc710f377f84903abdf2fb787dda19628d944da990a86b2" }, "completed_at": "2026-10-26T18:47:13.813676+00:00" } }, { "id": "demo-20261025T112228Z-adapter", "run_id": "demo-20261024T050719Z-7a9caa", "result": { "run_id": "demo-20261024T050719Z-7a9caa", "created_at": "2026-10-25T11:26:20.624244+00:00", "model": "gpt-6.1-sol", "harness": "none", "solve_seconds": 3372, "platform": "8.3.27.1644", "counts": { "pass": 64, "fail": 1 }, "rules": [ { "id": "BU01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU16", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU17", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU02", "verdict": "pass", "coverage": "partial", "reason": null }, { "id": "BU10", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU12", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU06", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU07", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU08", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU09", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU11", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU14", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU15", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU13", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU15", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU16", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU17", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU02", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU18", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU14", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU06", "verdict": "pass", "coverage": "no_violation_found", "reason": null }, { "id": "OU07", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU08", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU09", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU10", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU11", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU12", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU13", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU19", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU20", "verdict": "fail", "coverage": "selected_fixture", "reason": "Ведомость не прошла проверку группировки по значениям характеристик." }, { "id": "OU21", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR02", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR06", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR07", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR08", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR09", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR10", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR11", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR12", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR13", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR14", "verdict": "pass", "coverage": "no_violation_found", "reason": null }, { "id": "PR15", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR16", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR17", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR18", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR19", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F02", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "G01", "verdict": "pass", "coverage": "static_sources", "reason": null }, { "id": "G02", "verdict": "pass", "coverage": "static_sources", "reason": null }, { "id": "G03", "verdict": "pass", "coverage": "static_sources", "reason": null } ], "charges": [ { "id": "F1C-GEN03", "points": "0.5", "reason": "Ведомость не прошла проверку группировки по значениям характеристик." }, { "id": "F1C-PR09", "points": "0.5", "reason": "CommonModules/УчетСервер/Ext/Module.bsl:215 — РегистрРасчета.Начисления.БазаНачисления: база получается без отбора по регистратору — по всем записям регистра" }, { "id": "F1C-PR09", "points": "0.5", "reason": "CommonModules/УчетСервер/Ext/Module.bsl:247 — РегистрРасчета.Начисления.БазаНачисления: база получается без отбора по регистратору — по всем записям регистра" }, { "id": "F1C-GEN15", "points": "0.5", "reason": "Reports/ПремииЗаМесяц/Ext/ManagerModule.bsl:5 — РегистрРасчета.Начисления: отбор по ВидРасчета, ПериодДействияНачало, индексы таблицы начинаются с ПериодДействия, ПериодРегистрации, Подразделение, Регистратор, Сотрудник" }, { "id": "F1C-GEN14", "points": "1.5", "reason": "Reports/ПродажиАналогов/Ext/ManagerModule.bsl:3 — РегистрБухгалтерии.Хозрасчетный: итоги считаются по основной таблице регистра, а не по виртуальной" }, { "id": "F1C-PR14", "points": "0.5", "reason": "после расчёта набор с периодом действия перезаписывается целиком, с пересчётом фактического периода действия (нужно Записать(, Истина)): CommonModules/УчетСервер/Ext/Module.bsl:211 Н.Записать(); CommonModules/УчетСервер/Ext/Module.bsl:228 Н.Записать(); CommonModules/УчетСервер/Ext/Module.bsl:241 Н.Записать(); CommonModules/УчетСервер/Ext/Module.bsl:259 Н.Записать()" }, { "id": "F1C-BU06", "points": "1.5", "reason": "у счёта товаров 01.02 не включён признак учёта КоличественныйУчет" }, { "id": "F1C-BU05", "points": "0.5", "reason": "аналитика счетов вынесена в измерения регистра бухгалтерии и есть у всех счетов: Номенклатура (Номенклатура)" }, { "id": "F1C-GEN20", "points": "2.0", "reason": "данные базы читаются в цикле по записям: CommonModules/УчетСервер/Ext/Module.bsl:293; CommonModules/УчетСервер/Ext/Module.bsl:359; CommonModules/УчетСервер/Ext/Module.bsl:363 и ещё 14" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "оперативное проведение разрешено у документов с движениями по регистрам расчёта: НачислениеЗарплаты" }, { "id": "F1C-GEN21", "points": "2.0", "reason": "данные графика без отбора по регистратору: CommonModules/УчетСервер/Ext/Module.bsl:173" } ], "score_upper_bound": "-6.0", "score": null, "grade": "unsatisfactory", "deductions": "11.0", "not_assessed": 16, "gates": { "starter_origin": "passed", "load": "loaded", "clients": "compiles", "demo_data": "present" }, "infrastructure_errors": false, "comparison_eligible": false, "binding_compatibility": { "scope": "supplemental_named_subconto_adapter", "original_binding_sha256": "938f1873ea01dfdfe3da8d8828895d4a895de6be4398bbd046f4411b24c75261", "normalized_binding_sha256": "33d56b52100336dd84ad90b501ff2cc5f7ffb896d03bf2862863d853a4750993", "normalizer_sha256": "7327277143d80a531e4c254ac74a9fc0e0d5c76572d53b8469e0a580eda17d65", "canonical_ledger_sha256": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "changes": [ { "field": "fields.ledger.warehouse_debit", "before": "Склады", "after": "ВидыСубконто.Склады", "kind": "named" }, { "field": "fields.ledger.warehouse_credit", "before": "Склады", "after": "ВидыСубконто.Склады", "kind": "named" } ], "basis": "kind names expanded only to exactly one predefined kind of the account chart on the role side; all role types checked." }, "evaluation_sha256": "b6ab0fe6f8f07143f1a636abf6fda377f7addf49eebb6379117487cf750608b4", "downloads": [] }, "measurement": { "operator": { "name": "Вячеслав", "github": "sksibak" }, "environment": { "captured_at": "2026-10-24T05:07:22.329340+00:00", "capture_timing": "before_run", "hardware": { "cpu": "AMD Ryzen 5 4600H with Radeon Graphics ", "logical_cpus": 12, "ram_bytes": 16505962496 }, "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "python": "3.12.14", "platform_version": "8.3.27.1644", "isolation": "dedicated-host", "network_profile": "open-book_shell", "unsafe_action_protection_observed_in_user_config": true, "git_revision": "af85e791b303dbbf0b0b7af924d2489c3e57cfa8", "implementation_files": { "exam_bench/__init__.py": "ad5bf6f05dc6765f40b78bd186870ca2c49be113cfa33f8aa76f4926f2cb2c1e", "exam_bench/assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "exam_bench/bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "exam_bench/calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "exam_bench/calibrate.py": "78b5185cb0888c0c0ac3de95ffc3a80154a6de9ae66fc461f79d012e5a58e1db", "exam_bench/calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "exam_bench/calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "exam_bench/calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "exam_bench/calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "exam_bench/calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "exam_bench/claude.py": "bc1b8550de7573aaed5e39c6e9c0309e0d8175284a75490d61ec27439ed911ad", "exam_bench/cli.py": "1a37ce645633d761f7897dffc9c45e6b8b9600cd7bd233b1cbf78f49d26b099a", "exam_bench/codescan.py": "751e38001b6e65727a31e28172a0623f0bf34bc092a958037c286aa991a197ed", "exam_bench/codex.py": "c3f89d72af11f312d851c73a1610d92e79acadf336be9ccedd1f94ede3b3ccb0", "exam_bench/common.py": "8682603b519063e655eae3574a02a49efee63bde21f582ccee20ddd623fca96d", "exam_bench/docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "exam_bench/examiner.py": "d7294fdd23ed1732216cafebf0a8cf2c24cce4259859aeb7149f62b7607d087d", "exam_bench/finalize.py": "4034f1c63896a940afdb1a83d541cf47fc75c8b5061e3f839047109c04beb620", "exam_bench/forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "exam_bench/gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "exam_bench/grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "exam_bench/harness.py": "3040f6daaf1dc6e6583219f4d925151f8ba7851b2d5417d7f14645892b485ddf", "exam_bench/interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "exam_bench/interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "exam_bench/isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "exam_bench/ledger.py": "7e851523580e22d8490e75f9b6026c07f2c355007e0d11d0b252671f56bef654", "exam_bench/locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "exam_bench/materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "exam_bench/mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "exam_bench/observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "exam_bench/ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "exam_bench/penalties.py": "0d79e2e46102657dca00609b6abbfc0bf7d11fad41429564f876c82bc6b33269", "exam_bench/platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "exam_bench/portable.py": "cad56968ff407983608f5bdbc9ce7234128d7a4580b096ecea8e0e7b4edb9070", "exam_bench/portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "exam_bench/pr.py": "6a3a20caf0e10c0cc94410511a72d62c9fcda785f3abab1be2ad616d4ee16836", "exam_bench/preflight.py": "5619be0131d8641925f3ce2a3c8e5234d42aa5635d95676138ca81536d95cd29", "exam_bench/process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "exam_bench/queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "exam_bench/queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "exam_bench/replay_calibration.py": "c150457b0b23ce4e6814eb8deb4d48f6bc4a2e39d8f84a9dc7644fb99a026c2d", "exam_bench/report.py": "5e4c0757e1c7f189953f9a5302593ab726551835856baed25efd93dad6e8bfcd", "exam_bench/runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "exam_bench/smoke_check.py": "f36922a0027429ead0b414048dcc14bbe67f2f0e79a70d03dffbe1447d253545", "exam_bench/stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "exam_bench/submission.py": "ea862adc63ae67861ddb1d6aeb4d92c10b0b05004d22953f7b03612f82bb4bf4", "exam_bench/telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "exam_bench/windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "exam_bench/workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tools/build_public_site.py": "9682ed696f5ac9e9a82b65a45c0dece556ec7e49eeb20dcd616882cc534a8258", "tools/build_result_site.py": "3294e1d2ec1486058e208735264d61e349a68a4ae2fa2ec7a723c70e3263b496", "tools/check_native_harnesses.py": "4f5f0ed27651f78758eaef077b3b114361781f6b95ec40cb46c3fea689210473", "tools/check_native_toolkit.py": "0272794617121f2932828e5e4e9ae20095183c443666cf3ba466b44fbe875095", "tools/community_results.py": "cbfba30b4e617f5e219637c1c2de57398d01eb2f284eae3aca3ef684e6505a39", "tools/community_service.py": "c374480dbd88d656c0b9054fa04a8e1c6698c69e2f9cf475e82498a2dff61d84", "tools/community_setup.py": "5d7d126ed7d4dd48e1d79f57b99647a92ffcc8c9f80d90915e458888cdd76bf7", "tools/compare_harness_runs.py": "f274df5f3f804cb02504491aec946943833e12fbce6e62d281e12beb8508fc4e", "tools/create_run_plan.py": "871cd81b1eda231c0fba8805f63d2668926be9fc641559e6ddf320e2f47cd37a", "tools/demo_runner.py": "ca7ad17919c53d524cc0418751ba09a540f910eac183dca2961710bc30bba26f", "tools/installers.py": "9a2742780936b17500869e7c89202c1a2549e37d53a42ad9a50a0abbf78bbe09", "tools/machine_bundle.py": "8aa8346f99f537e81ceca6fb6ab9530e844954bab8eff87bf33d3602f81f8a30", "tools/prepare_native_harnesses.py": "aaa75ecf4022883984fa50c42d14d8e1a9fde2eeda03dab03b852bbc5efb2502", "tools/prepare_official_statement.py": "6b7028c78e90e798d6ef1a93b76520cc61a308c354fb9b87f7fad18b99800fad", "tools/prepare_open_exam_requirements.py": "544f4e378b9be5f166186f8788f8d454afdac2deb99d91d98421e39d01ba6d03", "tools/probe_harness.py": "1ed8ef93420d1484cbbfd151b7efc31b9a201ceb942dd05e3103efa22ffa7f27", "tools/probe_native_mcp.py": "9918d324129cba898993e07f8f8b6dbcbaf369398ebf28d464f9f1f00abdb254", "tools/readiness.py": "d34dd3f38334f51cc4574c79194cf0b80769b062a52382989a57d01c46b9aba4", "tools/recheck_community.py": "f0843d7d677f90da31e22bde0b1c86584dd46c022f1532d43d042619e426b230", "tools/regrade_runs.py": "011775afb06d3aac67a4aa81117a368c75896b0fcbe1e6f27ccc6237612fbf59", "tools/render_statement_text.py": "dabc0716a3612c288c671bc20e17fd4986691d732768e1e957d6dddddbea92a3", "tools/replay_calibration.py": "801f5004926c438c21ed3668fe2a4ddf45312b3e75320165a3839aae034eee9b", "tools/run_exam_campaign.py": "2c450d57a1cd0a2682838f5ec7c0a4ffb3aed0f1730d34c408e912d59cab6efd", "tools/serve_result_site.py": "86badfac863cd4ad1fc894a14110c75b28470513f0133eeae9d2799b8b4df3a9", "tools/start_demo.py": "c597e6cad28d245b3191654bb3e2801fa9dd2364e2acb25561923613717b615f", "tools/supplemental_acceptance.py": "c88fc39de1be1fdcacdd819e2ad329f60367b2df1d5deda80b37324bda3f2a01", "tools/sync_sources.py": "b51e889b0f41f9f63bfb19a09fb96d3777693d6b1d76fe0132bdd2a15e155898", "tools/validate_community_pr.py": "796b896dfade07b4529af2088a4b9b9d23484148b3bc0732b3fb837b75c9844b", "tools/verify_official_assessment_mapping.py": "daeb448a016940d5b6b1285979a56e5b9014bd91db40acb131445e4a83a23059", "tools/verify_task_package.py": "9e1e6105f6b5e4e78b36aa57f00117a9fbc8948ab53983c32ab56da88d23ccc4", "profiles/agents.json": "af9c492c08d13b3044aa6b6952589ed6a0a07d5258d8ff72bb18185b3eaebdc5", "profiles/ai-exam-execution-policy.json": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "profiles/bsl-analyzer-0.3.2-macos.json": "83537abdbf38c41ce665e4d0f24128bb51b62e971e0e0f368695f1326a7d2ffb", "profiles/bsl-analyzer-0.3.2-portable.json": "d6ba732e6778e256df34d6bc548593128820a70430c35b279796843606ee40a8", "profiles/bsl-ls-1.1.0-rc.6-macos.json": "245fc10747197e6911b2b4c77cdb15e6fa4eb7bc7c3758b63e768c5adf1df180", "profiles/bsl-ls-1.1.0-rc.6-portable.json": "9f10660881f2ec84794f7d584556b8f75c7e14b3555464af0ed0e60c4c892d86", "profiles/code-index-1.9.0-macos.json": "63a919523ce62ecec274f4c139bc7ad49a75dd4c339568b822cbc695b4e30408", "profiles/code-index-1.9.0-portable.json": "81106cee8f424ffd8a9dc46ecd8e4f57598fc1d49661a83c77b1f0507993fbdc", "profiles/codex-probe-plan.json": "166e41aad5fb3b27d9050bc6de952c6cba363cc6e804d4080568cc71a2a4d289", "profiles/machine.linux.example.json": "408304fd0581098d5d8110dc67dfeab353bc4d4030e32d37e6acf98d2b1aedfd", "profiles/machine.macos.example.json": "52e9f9d17797cb520b9d8955d6806fd550b899bed4da241ebf096dcb6a21a942", "profiles/machine.windows.example.json": "63accac9a2f81d47d03447efbabffd4760aee325193f02f46b9b29a28d50d2d8", "profiles/mcp-toolkit-1.9.0-macos.json": "1d3f9cde5ffa20589a840d01fdae03aa0fc2f412c929f064f203919c4129625b", "profiles/mcp-toolkit-1.9.0-portable.json": "8e370eebe773eef0e08045ee9c6d5be1451f769f65be0710834b262a4336e054", "profiles/none-macos.json": "b1401d9c48159aed3559006c7f6ace6ef4571224d5cf0bb76d1a823505a10056", "profiles/none-portable.json": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "profiles/rlm-tools-bsl-1.43.0-macos.json": "9354421052640ab60bc3e6aa98ff2e7ba9ca2318b0f4026c137487449242cbd2", "profiles/rlm-tools-bsl-1.43.0-portable.json": "2599e5645e0a7d4e44cb2934bc2b272cae79a9bf7ea74a23cd48aacea64bc424", "profiles/rlm-tools-bsl-1.43.0-posix-requirements.txt": "4fdf9a1bd994bf0272e65d231daf76cf19b0a34dad0ae6b50ec4f11a2ce4c330", "profiles/rlm-tools-bsl-1.43.0-windows-requirements.txt": "3730cb46c81cda5181ecd4485e98b11933104632358bc86f8c0eb1a612a8954f", "profiles/shirokov-skills-macos.json": "84f3e89091676884a802035c707e912762a1179425fb8e3faff25be736873cdb", "profiles/shirokov-skills-portable.json": "2b0a461e06602f1456410e70f02ceaa5ac32c6549c486660bcb5ace0c2f87b15", "profiles/shirokov-skills-windows-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/unica-0.12.3-macos.json": "2c39fbb591cf2c2c6e056373823615485397ea83651b7926c6f25a5fe6a0aae6", "profiles/unica-0.13.0-macos.json": "b76b5c8a4dd33f571c4a90993f1a2da5f7223b4f0f8e1042c282e21a66121052", "profiles/unica-0.14.0-rc.1-portable.json": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "rules/1c-specialist-platform/chistov.json": "77e04942f8c947b10759e7cc1eb31af05847d1711a772fbe6f23d525766757a9", "rules/1c-specialist-platform/decisions.json": "f622107423ce3c188c063318d7ab4f7718ceb38e443130677d8987f386641c09", "rules/1c-specialist-platform/examiner.json": "30353aa2a1b6545496b070d9066e9ffba0c3779e5b53ef70a4fd2cee375b18c0", "rules/1c-specialist-platform/ledger.json": "f167c10db2b5799dd9a1ea6a37cd2d7d186810dadf5ea2f50f26ae723c676882", "rules/1c-specialist-platform/rules.json": "1d320a4f8e1bf4701496388931f492315549bd3dce574b17285dd1d7f8652007", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" } } }, "conditions": { "client": "codex", "model": "gpt-6.1-sol", "client_version": "0.163.0-alpha.11.2", "reasoning_effort": "medium", "harness": "none", "billing_channel": "subscription", "solve_timeout_seconds": 3600, "time_series": null, "delegation": "native_disabled", "network_profile": "open-book_shell", "deadline_disclosed": true, "statement_sha256": "8a6ccb3e673826d1f8220fda53eb310e3ec18c136d87ce8f4cebb2a08614e7e5", "starter_dt_sha256": "f40d084818b0d1cfe503fc7653a6a13f1a8e47fcd1688dad6245b12744eb4638", "profile_sha256": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "execution_policy_sha256": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "calibration_sha256": "eced5b2f738ff558afe3d33d03048cf7b3ad00fa4e418c6a0ed72f885d0d221c", "started_at": "2026-10-24T05:07:30.140350+00:00", "timing": { "prepare_ms": 7282, "solve_ms": 3372156, "grade_ms": null }, "original_submission_valid": false, "model_provenance": "requested_only", "tokens": { "input": 17610405, "cached_input": 17466624, "fresh_input": 143781, "output": 112434, "reasoning_output": 42146, "total": 17722839, "coverage": "reported_completed_root_turns" }, "tools": { "mcp_calls": 0, "unica_calls": 0, "failed_calls": 0 }, "process": { "status": "completed", "exit_code": 0, "stop_confirmed": true } }, "verification": "contributor_reported", "download": "community-downloads/demo-20261025T112228Z-adapter/solution.zip", "source_context": "community-downloads/demo-20261025T112228Z-adapter/source-context.json", "regrade_required": [ { "id": "grader_changed", "files": [ "assessment.py", "bp.py", "calcwrite.py", "calibrate.py", "calibration_periodicity.py", "calibration_query.py", "claude.py", "codescan.py", "codex.py", "common.py", "docx_text.py", "examiner.py", "harness.py", "interpretations.py", "locking.py", "materials.py", "mcp_toolkit.py", "ou.py", "penalties.py", "portable_harnesses.py", "pr.py", "preflight.py", "queries.py", "queryschema.py", "querytypes.py", "replay_calibration.py", "rules/1c-specialist-platform/chistov.json", "rules/1c-specialist-platform/examiner.json", "rules/1c-specialist-platform/rules.json", "rules/1c-specialist-platform/standards.json", "smoke_check.py", "starters/carcass-8.3.25.1445/starter.json", "stdio_harnesses.py", "tasks/1c-platform-official-sample/checks.json", "tasks/1c-platform-official-sample/private/official-assessment-mapping.json", "tasks/1c-platform-official-sample/private/owner-scoring-policy.json", "telemetry.py" ] } ], "grader_revision_sha256": "855d4f66db31ec9f50ebfc18f596c0d1d157e53e2830c51f853c1338f628e49c", "archive_sha256": "ed8186fe588ba311e8f000f67314019d6e03bedd4f7ee8a3980119c8229e4e63" }, { "id": "demo-20261024T094458Z-recheck-1", "run_id": "demo-20261024T050719Z-7a9caa", "result": { "run_id": "demo-20261024T050719Z-7a9caa", "created_at": "2026-10-24T09:48:36.062307+00:00", "model": "gpt-6.1-sol", "harness": "none", "solve_seconds": 3372, "platform": "8.3.27.1644", "counts": { "pass": 64, "fail": 1 }, "rules": [ { "id": "BU01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU16", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU17", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU02", "verdict": "pass", "coverage": "partial", "reason": null }, { "id": "BU10", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU12", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU06", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU07", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU08", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU09", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU11", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU14", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU15", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU13", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU15", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU16", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU17", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU02", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU18", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU14", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU06", "verdict": "pass", "coverage": "no_violation_found", "reason": null }, { "id": "OU07", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU08", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU09", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU10", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU11", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU12", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU13", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU19", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU20", "verdict": "fail", "coverage": "selected_fixture", "reason": "Ведомость не прошла проверку группировки по значениям характеристик." }, { "id": "OU21", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR02", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR06", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR07", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR08", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR09", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR10", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR11", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR12", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR13", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR14", "verdict": "pass", "coverage": "no_violation_found", "reason": null }, { "id": "PR15", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR16", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR17", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR18", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR19", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F02", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "G01", "verdict": "pass", "coverage": "static_sources", "reason": null }, { "id": "G02", "verdict": "pass", "coverage": "static_sources", "reason": null }, { "id": "G03", "verdict": "pass", "coverage": "static_sources", "reason": null } ], "charges": [ { "id": "F1C-GEN03", "points": "0.5", "reason": "Ведомость не прошла проверку группировки по значениям характеристик." }, { "id": "F1C-PR09", "points": "0.5", "reason": "CommonModules/УчетСервер/Ext/Module.bsl:215 — РегистрРасчета.Начисления.БазаНачисления: база получается без отбора по регистратору — по всем записям регистра" }, { "id": "F1C-PR09", "points": "0.5", "reason": "CommonModules/УчетСервер/Ext/Module.bsl:247 — РегистрРасчета.Начисления.БазаНачисления: база получается без отбора по регистратору — по всем записям регистра" }, { "id": "F1C-GEN15", "points": "0.5", "reason": "Reports/ПремииЗаМесяц/Ext/ManagerModule.bsl:5 — РегистрРасчета.Начисления: отбор по ВидРасчета, ПериодДействияНачало, индексы таблицы начинаются с ПериодДействия, ПериодРегистрации, Подразделение, Регистратор, Сотрудник" }, { "id": "F1C-GEN14", "points": "1.5", "reason": "Reports/ПродажиАналогов/Ext/ManagerModule.bsl:3 — РегистрБухгалтерии.Хозрасчетный: итоги считаются по основной таблице регистра, а не по виртуальной" }, { "id": "F1C-PR14", "points": "0.5", "reason": "после расчёта набор с периодом действия перезаписывается целиком, с пересчётом фактического периода действия (нужно Записать(, Истина)): CommonModules/УчетСервер/Ext/Module.bsl:211 Н.Записать(); CommonModules/УчетСервер/Ext/Module.bsl:228 Н.Записать(); CommonModules/УчетСервер/Ext/Module.bsl:241 Н.Записать(); CommonModules/УчетСервер/Ext/Module.bsl:259 Н.Записать()" }, { "id": "F1C-BU06", "points": "1.5", "reason": "у счёта товаров 01.02 не включён признак учёта КоличественныйУчет" }, { "id": "F1C-BU05", "points": "0.5", "reason": "аналитика счетов вынесена в измерения регистра бухгалтерии и есть у всех счетов: Номенклатура (Номенклатура)" }, { "id": "F1C-GEN20", "points": "2.0", "reason": "данные базы читаются в цикле по записям: CommonModules/УчетСервер/Ext/Module.bsl:293; CommonModules/УчетСервер/Ext/Module.bsl:359; CommonModules/УчетСервер/Ext/Module.bsl:363 и ещё 14" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "оперативное проведение разрешено у документов с движениями по регистрам расчёта: НачислениеЗарплаты" }, { "id": "F1C-GEN21", "points": "2.0", "reason": "данные графика без отбора по регистратору: CommonModules/УчетСервер/Ext/Module.bsl:173" } ], "score_upper_bound": "-6.0", "score": null, "grade": "unsatisfactory", "deductions": "11.0", "not_assessed": 16, "gates": { "starter_origin": "passed", "load": "loaded", "clients": "compiles", "demo_data": "present" }, "infrastructure_errors": false, "comparison_eligible": false, "binding_compatibility": null, "evaluation_sha256": "f7f40b5407d0592ae8727501416b3ba3bd4c9b1df75da967783777ebba66b185", "downloads": [] }, "measurement": { "operator": { "name": "Вячеслав", "github": "sksibak" }, "environment": { "captured_at": "2026-10-24T05:07:22.329340+00:00", "capture_timing": "before_run", "hardware": { "cpu": "AMD Ryzen 5 4600H with Radeon Graphics ", "logical_cpus": 12, "ram_bytes": 16505962496 }, "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "python": "3.12.14", "platform_version": "8.3.27.1644", "isolation": "dedicated-host", "network_profile": "open-book_shell", "unsafe_action_protection_observed_in_user_config": true, "git_revision": "af85e791b303dbbf0b0b7af924d2489c3e57cfa8", "implementation_files": { "exam_bench/__init__.py": "ad5bf6f05dc6765f40b78bd186870ca2c49be113cfa33f8aa76f4926f2cb2c1e", "exam_bench/assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "exam_bench/bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "exam_bench/calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "exam_bench/calibrate.py": "78b5185cb0888c0c0ac3de95ffc3a80154a6de9ae66fc461f79d012e5a58e1db", "exam_bench/calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "exam_bench/calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "exam_bench/calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "exam_bench/calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "exam_bench/calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "exam_bench/claude.py": "bc1b8550de7573aaed5e39c6e9c0309e0d8175284a75490d61ec27439ed911ad", "exam_bench/cli.py": "1a37ce645633d761f7897dffc9c45e6b8b9600cd7bd233b1cbf78f49d26b099a", "exam_bench/codescan.py": "751e38001b6e65727a31e28172a0623f0bf34bc092a958037c286aa991a197ed", "exam_bench/codex.py": "c3f89d72af11f312d851c73a1610d92e79acadf336be9ccedd1f94ede3b3ccb0", "exam_bench/common.py": "8682603b519063e655eae3574a02a49efee63bde21f582ccee20ddd623fca96d", "exam_bench/docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "exam_bench/examiner.py": "d7294fdd23ed1732216cafebf0a8cf2c24cce4259859aeb7149f62b7607d087d", "exam_bench/finalize.py": "4034f1c63896a940afdb1a83d541cf47fc75c8b5061e3f839047109c04beb620", "exam_bench/forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "exam_bench/gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "exam_bench/grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "exam_bench/harness.py": "3040f6daaf1dc6e6583219f4d925151f8ba7851b2d5417d7f14645892b485ddf", "exam_bench/interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "exam_bench/interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "exam_bench/isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "exam_bench/ledger.py": "7e851523580e22d8490e75f9b6026c07f2c355007e0d11d0b252671f56bef654", "exam_bench/locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "exam_bench/materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "exam_bench/mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "exam_bench/observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "exam_bench/ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "exam_bench/penalties.py": "0d79e2e46102657dca00609b6abbfc0bf7d11fad41429564f876c82bc6b33269", "exam_bench/platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "exam_bench/portable.py": "cad56968ff407983608f5bdbc9ce7234128d7a4580b096ecea8e0e7b4edb9070", "exam_bench/portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "exam_bench/pr.py": "6a3a20caf0e10c0cc94410511a72d62c9fcda785f3abab1be2ad616d4ee16836", "exam_bench/preflight.py": "5619be0131d8641925f3ce2a3c8e5234d42aa5635d95676138ca81536d95cd29", "exam_bench/process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "exam_bench/queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "exam_bench/queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "exam_bench/replay_calibration.py": "c150457b0b23ce4e6814eb8deb4d48f6bc4a2e39d8f84a9dc7644fb99a026c2d", "exam_bench/report.py": "5e4c0757e1c7f189953f9a5302593ab726551835856baed25efd93dad6e8bfcd", "exam_bench/runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "exam_bench/smoke_check.py": "f36922a0027429ead0b414048dcc14bbe67f2f0e79a70d03dffbe1447d253545", "exam_bench/stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "exam_bench/submission.py": "ea862adc63ae67861ddb1d6aeb4d92c10b0b05004d22953f7b03612f82bb4bf4", "exam_bench/telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "exam_bench/windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "exam_bench/workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tools/build_public_site.py": "9682ed696f5ac9e9a82b65a45c0dece556ec7e49eeb20dcd616882cc534a8258", "tools/build_result_site.py": "3294e1d2ec1486058e208735264d61e349a68a4ae2fa2ec7a723c70e3263b496", "tools/check_native_harnesses.py": "4f5f0ed27651f78758eaef077b3b114361781f6b95ec40cb46c3fea689210473", "tools/check_native_toolkit.py": "0272794617121f2932828e5e4e9ae20095183c443666cf3ba466b44fbe875095", "tools/community_results.py": "cbfba30b4e617f5e219637c1c2de57398d01eb2f284eae3aca3ef684e6505a39", "tools/community_service.py": "c374480dbd88d656c0b9054fa04a8e1c6698c69e2f9cf475e82498a2dff61d84", "tools/community_setup.py": "5d7d126ed7d4dd48e1d79f57b99647a92ffcc8c9f80d90915e458888cdd76bf7", "tools/compare_harness_runs.py": "f274df5f3f804cb02504491aec946943833e12fbce6e62d281e12beb8508fc4e", "tools/create_run_plan.py": "871cd81b1eda231c0fba8805f63d2668926be9fc641559e6ddf320e2f47cd37a", "tools/demo_runner.py": "ca7ad17919c53d524cc0418751ba09a540f910eac183dca2961710bc30bba26f", "tools/installers.py": "9a2742780936b17500869e7c89202c1a2549e37d53a42ad9a50a0abbf78bbe09", "tools/machine_bundle.py": "8aa8346f99f537e81ceca6fb6ab9530e844954bab8eff87bf33d3602f81f8a30", "tools/prepare_native_harnesses.py": "aaa75ecf4022883984fa50c42d14d8e1a9fde2eeda03dab03b852bbc5efb2502", "tools/prepare_official_statement.py": "6b7028c78e90e798d6ef1a93b76520cc61a308c354fb9b87f7fad18b99800fad", "tools/prepare_open_exam_requirements.py": "544f4e378b9be5f166186f8788f8d454afdac2deb99d91d98421e39d01ba6d03", "tools/probe_harness.py": "1ed8ef93420d1484cbbfd151b7efc31b9a201ceb942dd05e3103efa22ffa7f27", "tools/probe_native_mcp.py": "9918d324129cba898993e07f8f8b6dbcbaf369398ebf28d464f9f1f00abdb254", "tools/readiness.py": "d34dd3f38334f51cc4574c79194cf0b80769b062a52382989a57d01c46b9aba4", "tools/recheck_community.py": "f0843d7d677f90da31e22bde0b1c86584dd46c022f1532d43d042619e426b230", "tools/regrade_runs.py": "011775afb06d3aac67a4aa81117a368c75896b0fcbe1e6f27ccc6237612fbf59", "tools/render_statement_text.py": "dabc0716a3612c288c671bc20e17fd4986691d732768e1e957d6dddddbea92a3", "tools/replay_calibration.py": "801f5004926c438c21ed3668fe2a4ddf45312b3e75320165a3839aae034eee9b", "tools/run_exam_campaign.py": "2c450d57a1cd0a2682838f5ec7c0a4ffb3aed0f1730d34c408e912d59cab6efd", "tools/serve_result_site.py": "86badfac863cd4ad1fc894a14110c75b28470513f0133eeae9d2799b8b4df3a9", "tools/start_demo.py": "c597e6cad28d245b3191654bb3e2801fa9dd2364e2acb25561923613717b615f", "tools/supplemental_acceptance.py": "c88fc39de1be1fdcacdd819e2ad329f60367b2df1d5deda80b37324bda3f2a01", "tools/sync_sources.py": "b51e889b0f41f9f63bfb19a09fb96d3777693d6b1d76fe0132bdd2a15e155898", "tools/validate_community_pr.py": "796b896dfade07b4529af2088a4b9b9d23484148b3bc0732b3fb837b75c9844b", "tools/verify_official_assessment_mapping.py": "daeb448a016940d5b6b1285979a56e5b9014bd91db40acb131445e4a83a23059", "tools/verify_task_package.py": "9e1e6105f6b5e4e78b36aa57f00117a9fbc8948ab53983c32ab56da88d23ccc4", "profiles/agents.json": "af9c492c08d13b3044aa6b6952589ed6a0a07d5258d8ff72bb18185b3eaebdc5", "profiles/ai-exam-execution-policy.json": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "profiles/bsl-analyzer-0.3.2-macos.json": "83537abdbf38c41ce665e4d0f24128bb51b62e971e0e0f368695f1326a7d2ffb", "profiles/bsl-analyzer-0.3.2-portable.json": "d6ba732e6778e256df34d6bc548593128820a70430c35b279796843606ee40a8", "profiles/bsl-ls-1.1.0-rc.6-macos.json": "245fc10747197e6911b2b4c77cdb15e6fa4eb7bc7c3758b63e768c5adf1df180", "profiles/bsl-ls-1.1.0-rc.6-portable.json": "9f10660881f2ec84794f7d584556b8f75c7e14b3555464af0ed0e60c4c892d86", "profiles/code-index-1.9.0-macos.json": "63a919523ce62ecec274f4c139bc7ad49a75dd4c339568b822cbc695b4e30408", "profiles/code-index-1.9.0-portable.json": "81106cee8f424ffd8a9dc46ecd8e4f57598fc1d49661a83c77b1f0507993fbdc", "profiles/codex-probe-plan.json": "166e41aad5fb3b27d9050bc6de952c6cba363cc6e804d4080568cc71a2a4d289", "profiles/machine.linux.example.json": "408304fd0581098d5d8110dc67dfeab353bc4d4030e32d37e6acf98d2b1aedfd", "profiles/machine.macos.example.json": "52e9f9d17797cb520b9d8955d6806fd550b899bed4da241ebf096dcb6a21a942", "profiles/machine.windows.example.json": "63accac9a2f81d47d03447efbabffd4760aee325193f02f46b9b29a28d50d2d8", "profiles/mcp-toolkit-1.9.0-macos.json": "1d3f9cde5ffa20589a840d01fdae03aa0fc2f412c929f064f203919c4129625b", "profiles/mcp-toolkit-1.9.0-portable.json": "8e370eebe773eef0e08045ee9c6d5be1451f769f65be0710834b262a4336e054", "profiles/none-macos.json": "b1401d9c48159aed3559006c7f6ace6ef4571224d5cf0bb76d1a823505a10056", "profiles/none-portable.json": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "profiles/rlm-tools-bsl-1.43.0-macos.json": "9354421052640ab60bc3e6aa98ff2e7ba9ca2318b0f4026c137487449242cbd2", "profiles/rlm-tools-bsl-1.43.0-portable.json": "2599e5645e0a7d4e44cb2934bc2b272cae79a9bf7ea74a23cd48aacea64bc424", "profiles/rlm-tools-bsl-1.43.0-posix-requirements.txt": "4fdf9a1bd994bf0272e65d231daf76cf19b0a34dad0ae6b50ec4f11a2ce4c330", "profiles/rlm-tools-bsl-1.43.0-windows-requirements.txt": "3730cb46c81cda5181ecd4485e98b11933104632358bc86f8c0eb1a612a8954f", "profiles/shirokov-skills-macos.json": "84f3e89091676884a802035c707e912762a1179425fb8e3faff25be736873cdb", "profiles/shirokov-skills-portable.json": "2b0a461e06602f1456410e70f02ceaa5ac32c6549c486660bcb5ace0c2f87b15", "profiles/shirokov-skills-windows-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/unica-0.12.3-macos.json": "2c39fbb591cf2c2c6e056373823615485397ea83651b7926c6f25a5fe6a0aae6", "profiles/unica-0.13.0-macos.json": "b76b5c8a4dd33f571c4a90993f1a2da5f7223b4f0f8e1042c282e21a66121052", "profiles/unica-0.14.0-rc.1-portable.json": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "rules/1c-specialist-platform/chistov.json": "77e04942f8c947b10759e7cc1eb31af05847d1711a772fbe6f23d525766757a9", "rules/1c-specialist-platform/decisions.json": "f622107423ce3c188c063318d7ab4f7718ceb38e443130677d8987f386641c09", "rules/1c-specialist-platform/examiner.json": "30353aa2a1b6545496b070d9066e9ffba0c3779e5b53ef70a4fd2cee375b18c0", "rules/1c-specialist-platform/ledger.json": "f167c10db2b5799dd9a1ea6a37cd2d7d186810dadf5ea2f50f26ae723c676882", "rules/1c-specialist-platform/rules.json": "1d320a4f8e1bf4701496388931f492315549bd3dce574b17285dd1d7f8652007", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" } } }, "conditions": { "client": "codex", "model": "gpt-6.1-sol", "client_version": "0.163.0-alpha.11.2", "reasoning_effort": "medium", "harness": "none", "billing_channel": "subscription", "solve_timeout_seconds": 3600, "time_series": null, "delegation": "native_disabled", "network_profile": "open-book_shell", "deadline_disclosed": true, "statement_sha256": "8a6ccb3e673826d1f8220fda53eb310e3ec18c136d87ce8f4cebb2a08614e7e5", "starter_dt_sha256": "f40d084818b0d1cfe503fc7653a6a13f1a8e47fcd1688dad6245b12744eb4638", "profile_sha256": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "execution_policy_sha256": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "calibration_sha256": "eced5b2f738ff558afe3d33d03048cf7b3ad00fa4e418c6a0ed72f885d0d221c", "started_at": "2026-10-24T05:07:30.140350+00:00", "timing": { "prepare_ms": 7282, "solve_ms": 3372156, "grade_ms": null }, "original_submission_valid": false, "model_provenance": "requested_only", "tokens": { "input": 17610405, "cached_input": 17466624, "fresh_input": 143781, "output": 112434, "reasoning_output": 42146, "total": 17722839, "coverage": "reported_completed_root_turns" }, "tools": { "mcp_calls": 0, "unica_calls": 0, "failed_calls": 0 }, "process": { "status": "completed", "exit_code": 0, "stop_confirmed": true } }, "verification": "contributor_reported", "download": "community-downloads/demo-20261024T094458Z-recheck-1/solution.zip", "source_context": "community-downloads/demo-20261024T094458Z-recheck-1/source-context.json", "regrade_required": [ { "id": "grader_changed", "files": [ "assessment.py", "bp.py", "calcwrite.py", "calibrate.py", "calibration_periodicity.py", "calibration_query.py", "claude.py", "codescan.py", "codex.py", "common.py", "docx_text.py", "examiner.py", "harness.py", "interpretations.py", "locking.py", "materials.py", "mcp_toolkit.py", "ou.py", "penalties.py", "portable_harnesses.py", "pr.py", "preflight.py", "queries.py", "queryschema.py", "querytypes.py", "replay_calibration.py", "rules/1c-specialist-platform/chistov.json", "rules/1c-specialist-platform/examiner.json", "rules/1c-specialist-platform/rules.json", "rules/1c-specialist-platform/standards.json", "smoke_check.py", "starters/carcass-8.3.25.1445/starter.json", "stdio_harnesses.py", "submission.py", "tasks/1c-platform-official-sample/checks.json", "tasks/1c-platform-official-sample/private/official-assessment-mapping.json", "tasks/1c-platform-official-sample/private/owner-scoring-policy.json", "telemetry.py" ] }, { "id": "original_submission_refused" } ], "grader_revision_sha256": "67aea0c386bf75ef0a93d941349bf739c8595bcbaddc9ca13f301d96207d20e2", "archive_sha256": "9cf9fa80a7be968e171ab91c4ec34b20d7f0c03ae3bafa0fbe1002d479bf540b" } ] }, { "id": "demo-20261025T112622Z-adapter--owner-2026-10-26T223305964533-0000", "run_id": "demo-20261024T065406Z-45954e", "result": { "run_id": "demo-20261024T065406Z-45954e", "created_at": "2026-10-26T22:33:05.964533+00:00", "model": "gpt-6.1-sol", "harness": "none", "solve_seconds": 3470, "platform": "8.3.27.1644", "counts": { "pass": 64, "fail": 1 }, "rules": [ { "id": "BU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU01.selected_fixture" }, { "id": "BU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU04.selected_fixture" }, { "id": "BU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU05.selected_fixture" }, { "id": "BU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU16.selected_fixture" }, { "id": "BU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU17.selected_fixture" }, { "id": "BU02", "verdict": "pass", "reason": null, "coverage": "partial", "assertion_id": "BU02.posting_cost_and_balance" }, { "id": "BU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU10.selected_fixture" }, { "id": "BU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU12.selected_fixture" }, { "id": "BU03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU03.selected_fixture" }, { "id": "BU06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU06.selected_fixture" }, { "id": "BU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU07.selected_fixture" }, { "id": "BU08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU08.selected_fixture" }, { "id": "BU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU09.selected_fixture" }, { "id": "BU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU11.selected_fixture" }, { "id": "BU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU14.selected_fixture" }, { "id": "BU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU15.selected_fixture" }, { "id": "BU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU13.selected_fixture" }, { "id": "OU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU15.selected_fixture" }, { "id": "OU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU16.selected_fixture" }, { "id": "OU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU17.selected_fixture" }, { "id": "OU02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU02.selected_fixture" }, { "id": "OU18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU18.selected_fixture" }, { "id": "OU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU14.selected_fixture" }, { "id": "OU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU01.selected_fixture" }, { "id": "OU03", "verdict": "pass", "reason": "История и годовая периодичность регистра подтверждены.", "coverage": "history_and_periodicity", "assertion_id": "OU03.selected_fixture" }, { "id": "OU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU05.selected_fixture" }, { "id": "OU06", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "OU06.selected_fixture" }, { "id": "OU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU07.selected_fixture" }, { "id": "OU08", "verdict": "pass", "reason": "История и дневная периодичность подтверждены; ограничение одной версии в неделю отдельно не проверяется.", "coverage": "history_and_periodicity", "assertion_id": "OU08.selected_fixture" }, { "id": "OU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU09.selected_fixture" }, { "id": "OU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU10.selected_fixture" }, { "id": "OU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU11.selected_fixture" }, { "id": "OU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU12.selected_fixture" }, { "id": "OU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU13.selected_fixture" }, { "id": "OU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU04.selected_fixture" }, { "id": "OU19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU19.selected_fixture" }, { "id": "OU20", "verdict": "fail", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU20.selected_fixture" }, { "id": "OU21", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU21.selected_fixture" }, { "id": "PR01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR01.selected_fixture" }, { "id": "PR02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR02.selected_fixture" }, { "id": "PR03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR03.selected_fixture" }, { "id": "PR04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR04.selected_fixture" }, { "id": "PR05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR05.selected_fixture" }, { "id": "PR06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR06.selected_fixture" }, { "id": "PR07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR07.selected_fixture" }, { "id": "PR08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR08.selected_fixture" }, { "id": "PR09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR09.selected_fixture" }, { "id": "PR10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR10.selected_fixture" }, { "id": "PR11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR11.selected_fixture" }, { "id": "PR12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR12.selected_fixture" }, { "id": "PR13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR13.selected_fixture" }, { "id": "PR14", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "PR14.selected_fixture" }, { "id": "PR15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR15.selected_fixture" }, { "id": "PR16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR16.selected_fixture" }, { "id": "PR17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR17.selected_fixture" }, { "id": "PR18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR18.selected_fixture" }, { "id": "PR19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR19.selected_fixture" }, { "id": "F01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F01.selected_fixture" }, { "id": "F02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F02.selected_fixture" }, { "id": "F03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F03.selected_fixture" }, { "id": "F04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F04.selected_fixture" }, { "id": "F05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F05.selected_fixture" }, { "id": "G01", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G01.static_sources" }, { "id": "G02", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G02.static_sources" }, { "id": "G03", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G03.static_sources" } ], "charges": [ { "id": "F1C-GEN03", "points": "0.5", "reason": "отчёт не соответствует заданию: OU20" }, { "id": "F1C-GEN15", "points": "0.5", "reason": "Reports/Премии/Ext/ManagerModule.bsl:3 — РегистрРасчета.Начисления: отбор по ВидРасчета, ПериодДействияНачало, индексы таблицы начинаются с ПериодДействия, ПериодРегистрации, Подразделение, Регистратор, Сотрудник" }, { "id": "F1C-GEN14", "points": "1.5", "reason": "Reports/ПродажиБУ/Ext/ManagerModule.bsl:3 — РегистрБухгалтерии.Хозрасчетный: итоги считаются по основной таблице регистра, а не по виртуальной" }, { "id": "F1C-PR14", "points": "0.5", "reason": "после расчёта набор с периодом действия перезаписывается целиком, с пересчётом фактического периода действия (нужно Записать(, Истина)): CommonModules/РасчетыЗарплаты/Ext/Module.bsl:56 Набор.Записать(); CommonModules/РасчетыЗарплаты/Ext/Module.bsl:111 Набор.Записать(); CommonModules/РасчетыЗарплаты/Ext/Module.bsl:126 Пара.Значение.Записать(); CommonModules/РасчетыЗарплаты/Ext/Module.bsl:153 Пара.Значение.Записать()" }, { "id": "F1C-BU05", "points": "0.5", "reason": "аналитика счетов вынесена в измерения регистра бухгалтерии и есть у всех счетов: Номенклатура (Номенклатура)" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "оперативное проведение разрешено у документов с движениями по регистрам расчёта: НачислениеЗарплаты" }, { "id": "F1C-GEN22", "points": "1.0", "reason": "значения графика выбираются без ЕСТЬNULL: CommonModules/РасчетыЗарплаты/Ext/Module.bsl:47 ЗначениеПериодДействия; CommonModules/РасчетыЗарплаты/Ext/Module.bsl:83 ДниФактическийПериодДействия, ЗначениеПериодДействия, ЗначениеФактическийПериодДействия" } ], "score_upper_bound": "-0.5", "score": null, "grade": "unsatisfactory", "deductions": "5.5", "not_assessed": 14, "gates": { "starter_origin": "passed", "load": "loaded", "clients": "compiles", "demo_data": "present" }, "infrastructure_errors": false, "comparison_eligible": false, "binding_compatibility": { "scope": "supplemental_named_subconto_adapter", "original_binding_sha256": "7453f6ba6c67aaa1a3e183d4e7ab50cf384761713dfaf6c9602b444316874a6a", "normalized_binding_sha256": "5bf5c5f62324cd2e03d4a77ce9279e3dcfd379809eb7d04b7d5cbc58485885da", "normalizer_sha256": "7327277143d80a531e4c254ac74a9fc0e0d5c76572d53b8469e0a580eda17d65", "canonical_ledger_sha256": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "changes": [ { "field": "fields.ledger.warehouse_debit", "before": "Склады", "after": "ВидыСубконто.Склады", "kind": "named" }, { "field": "fields.ledger.warehouse_credit", "before": "Склады", "after": "ВидыСубконто.Склады", "kind": "named" } ], "basis": "kind names expanded only to exactly one predefined kind of the account chart on the role side; all role types checked." } }, "measurement": { "operator": { "name": "Вячеслав", "github": "sksibak" }, "environment": { "captured_at": "2026-10-24T06:54:09.737798+00:00", "capture_timing": "before_run", "hardware": { "cpu": "AMD Ryzen 5 4600H with Radeon Graphics ", "logical_cpus": 12, "ram_bytes": 16505962496 }, "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "python": "3.12.14", "platform_version": "8.3.27.1644", "isolation": "dedicated-host", "network_profile": "open-book_shell", "unsafe_action_protection_observed_in_user_config": true, "git_revision": "af85e791b303dbbf0b0b7af924d2489c3e57cfa8", "implementation_files": { "exam_bench/__init__.py": "ad5bf6f05dc6765f40b78bd186870ca2c49be113cfa33f8aa76f4926f2cb2c1e", "exam_bench/assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "exam_bench/bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "exam_bench/calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "exam_bench/calibrate.py": "78b5185cb0888c0c0ac3de95ffc3a80154a6de9ae66fc461f79d012e5a58e1db", "exam_bench/calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "exam_bench/calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "exam_bench/calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "exam_bench/calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "exam_bench/calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "exam_bench/claude.py": "bc1b8550de7573aaed5e39c6e9c0309e0d8175284a75490d61ec27439ed911ad", "exam_bench/cli.py": "1a37ce645633d761f7897dffc9c45e6b8b9600cd7bd233b1cbf78f49d26b099a", "exam_bench/codescan.py": "751e38001b6e65727a31e28172a0623f0bf34bc092a958037c286aa991a197ed", "exam_bench/codex.py": "c3f89d72af11f312d851c73a1610d92e79acadf336be9ccedd1f94ede3b3ccb0", "exam_bench/common.py": "8682603b519063e655eae3574a02a49efee63bde21f582ccee20ddd623fca96d", "exam_bench/docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "exam_bench/examiner.py": "d7294fdd23ed1732216cafebf0a8cf2c24cce4259859aeb7149f62b7607d087d", "exam_bench/finalize.py": "4034f1c63896a940afdb1a83d541cf47fc75c8b5061e3f839047109c04beb620", "exam_bench/forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "exam_bench/gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "exam_bench/grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "exam_bench/harness.py": "3040f6daaf1dc6e6583219f4d925151f8ba7851b2d5417d7f14645892b485ddf", "exam_bench/interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "exam_bench/interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "exam_bench/isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "exam_bench/ledger.py": "7e851523580e22d8490e75f9b6026c07f2c355007e0d11d0b252671f56bef654", "exam_bench/locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "exam_bench/materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "exam_bench/mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "exam_bench/observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "exam_bench/ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "exam_bench/penalties.py": "0d79e2e46102657dca00609b6abbfc0bf7d11fad41429564f876c82bc6b33269", "exam_bench/platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "exam_bench/portable.py": "cad56968ff407983608f5bdbc9ce7234128d7a4580b096ecea8e0e7b4edb9070", "exam_bench/portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "exam_bench/pr.py": "6a3a20caf0e10c0cc94410511a72d62c9fcda785f3abab1be2ad616d4ee16836", "exam_bench/preflight.py": "5619be0131d8641925f3ce2a3c8e5234d42aa5635d95676138ca81536d95cd29", "exam_bench/process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "exam_bench/queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "exam_bench/queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "exam_bench/replay_calibration.py": "c150457b0b23ce4e6814eb8deb4d48f6bc4a2e39d8f84a9dc7644fb99a026c2d", "exam_bench/report.py": "5e4c0757e1c7f189953f9a5302593ab726551835856baed25efd93dad6e8bfcd", "exam_bench/runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "exam_bench/smoke_check.py": "f36922a0027429ead0b414048dcc14bbe67f2f0e79a70d03dffbe1447d253545", "exam_bench/stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "exam_bench/submission.py": "ea862adc63ae67861ddb1d6aeb4d92c10b0b05004d22953f7b03612f82bb4bf4", "exam_bench/telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "exam_bench/windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "exam_bench/workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tools/build_public_site.py": "9682ed696f5ac9e9a82b65a45c0dece556ec7e49eeb20dcd616882cc534a8258", "tools/build_result_site.py": "3294e1d2ec1486058e208735264d61e349a68a4ae2fa2ec7a723c70e3263b496", "tools/check_native_harnesses.py": "4f5f0ed27651f78758eaef077b3b114361781f6b95ec40cb46c3fea689210473", "tools/check_native_toolkit.py": "0272794617121f2932828e5e4e9ae20095183c443666cf3ba466b44fbe875095", "tools/community_results.py": "cbfba30b4e617f5e219637c1c2de57398d01eb2f284eae3aca3ef684e6505a39", "tools/community_service.py": "c374480dbd88d656c0b9054fa04a8e1c6698c69e2f9cf475e82498a2dff61d84", "tools/community_setup.py": "5d7d126ed7d4dd48e1d79f57b99647a92ffcc8c9f80d90915e458888cdd76bf7", "tools/compare_harness_runs.py": "f274df5f3f804cb02504491aec946943833e12fbce6e62d281e12beb8508fc4e", "tools/create_run_plan.py": "871cd81b1eda231c0fba8805f63d2668926be9fc641559e6ddf320e2f47cd37a", "tools/demo_runner.py": "ca7ad17919c53d524cc0418751ba09a540f910eac183dca2961710bc30bba26f", "tools/installers.py": "9a2742780936b17500869e7c89202c1a2549e37d53a42ad9a50a0abbf78bbe09", "tools/machine_bundle.py": "8aa8346f99f537e81ceca6fb6ab9530e844954bab8eff87bf33d3602f81f8a30", "tools/prepare_native_harnesses.py": "aaa75ecf4022883984fa50c42d14d8e1a9fde2eeda03dab03b852bbc5efb2502", "tools/prepare_official_statement.py": "6b7028c78e90e798d6ef1a93b76520cc61a308c354fb9b87f7fad18b99800fad", "tools/prepare_open_exam_requirements.py": "544f4e378b9be5f166186f8788f8d454afdac2deb99d91d98421e39d01ba6d03", "tools/probe_harness.py": "1ed8ef93420d1484cbbfd151b7efc31b9a201ceb942dd05e3103efa22ffa7f27", "tools/probe_native_mcp.py": "9918d324129cba898993e07f8f8b6dbcbaf369398ebf28d464f9f1f00abdb254", "tools/readiness.py": "d34dd3f38334f51cc4574c79194cf0b80769b062a52382989a57d01c46b9aba4", "tools/recheck_community.py": "f0843d7d677f90da31e22bde0b1c86584dd46c022f1532d43d042619e426b230", "tools/regrade_runs.py": "011775afb06d3aac67a4aa81117a368c75896b0fcbe1e6f27ccc6237612fbf59", "tools/render_statement_text.py": "dabc0716a3612c288c671bc20e17fd4986691d732768e1e957d6dddddbea92a3", "tools/replay_calibration.py": "801f5004926c438c21ed3668fe2a4ddf45312b3e75320165a3839aae034eee9b", "tools/run_exam_campaign.py": "2c450d57a1cd0a2682838f5ec7c0a4ffb3aed0f1730d34c408e912d59cab6efd", "tools/serve_result_site.py": "86badfac863cd4ad1fc894a14110c75b28470513f0133eeae9d2799b8b4df3a9", "tools/start_demo.py": "c597e6cad28d245b3191654bb3e2801fa9dd2364e2acb25561923613717b615f", "tools/supplemental_acceptance.py": "c88fc39de1be1fdcacdd819e2ad329f60367b2df1d5deda80b37324bda3f2a01", "tools/sync_sources.py": "b51e889b0f41f9f63bfb19a09fb96d3777693d6b1d76fe0132bdd2a15e155898", "tools/validate_community_pr.py": "796b896dfade07b4529af2088a4b9b9d23484148b3bc0732b3fb837b75c9844b", "tools/verify_official_assessment_mapping.py": "daeb448a016940d5b6b1285979a56e5b9014bd91db40acb131445e4a83a23059", "tools/verify_task_package.py": "9e1e6105f6b5e4e78b36aa57f00117a9fbc8948ab53983c32ab56da88d23ccc4", "profiles/agents.json": "af9c492c08d13b3044aa6b6952589ed6a0a07d5258d8ff72bb18185b3eaebdc5", "profiles/ai-exam-execution-policy.json": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "profiles/bsl-analyzer-0.3.2-macos.json": "83537abdbf38c41ce665e4d0f24128bb51b62e971e0e0f368695f1326a7d2ffb", "profiles/bsl-analyzer-0.3.2-portable.json": "d6ba732e6778e256df34d6bc548593128820a70430c35b279796843606ee40a8", "profiles/bsl-ls-1.1.0-rc.6-macos.json": "245fc10747197e6911b2b4c77cdb15e6fa4eb7bc7c3758b63e768c5adf1df180", "profiles/bsl-ls-1.1.0-rc.6-portable.json": "9f10660881f2ec84794f7d584556b8f75c7e14b3555464af0ed0e60c4c892d86", "profiles/code-index-1.9.0-macos.json": "63a919523ce62ecec274f4c139bc7ad49a75dd4c339568b822cbc695b4e30408", "profiles/code-index-1.9.0-portable.json": "81106cee8f424ffd8a9dc46ecd8e4f57598fc1d49661a83c77b1f0507993fbdc", "profiles/codex-probe-plan.json": "166e41aad5fb3b27d9050bc6de952c6cba363cc6e804d4080568cc71a2a4d289", "profiles/machine.linux.example.json": "408304fd0581098d5d8110dc67dfeab353bc4d4030e32d37e6acf98d2b1aedfd", "profiles/machine.macos.example.json": "52e9f9d17797cb520b9d8955d6806fd550b899bed4da241ebf096dcb6a21a942", "profiles/machine.windows.example.json": "63accac9a2f81d47d03447efbabffd4760aee325193f02f46b9b29a28d50d2d8", "profiles/mcp-toolkit-1.9.0-macos.json": "1d3f9cde5ffa20589a840d01fdae03aa0fc2f412c929f064f203919c4129625b", "profiles/mcp-toolkit-1.9.0-portable.json": "8e370eebe773eef0e08045ee9c6d5be1451f769f65be0710834b262a4336e054", "profiles/none-macos.json": "b1401d9c48159aed3559006c7f6ace6ef4571224d5cf0bb76d1a823505a10056", "profiles/none-portable.json": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "profiles/rlm-tools-bsl-1.43.0-macos.json": "9354421052640ab60bc3e6aa98ff2e7ba9ca2318b0f4026c137487449242cbd2", "profiles/rlm-tools-bsl-1.43.0-portable.json": "2599e5645e0a7d4e44cb2934bc2b272cae79a9bf7ea74a23cd48aacea64bc424", "profiles/rlm-tools-bsl-1.43.0-posix-requirements.txt": "4fdf9a1bd994bf0272e65d231daf76cf19b0a34dad0ae6b50ec4f11a2ce4c330", "profiles/rlm-tools-bsl-1.43.0-windows-requirements.txt": "3730cb46c81cda5181ecd4485e98b11933104632358bc86f8c0eb1a612a8954f", "profiles/shirokov-skills-macos.json": "84f3e89091676884a802035c707e912762a1179425fb8e3faff25be736873cdb", "profiles/shirokov-skills-portable.json": "2b0a461e06602f1456410e70f02ceaa5ac32c6549c486660bcb5ace0c2f87b15", "profiles/shirokov-skills-windows-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/unica-0.12.3-macos.json": "2c39fbb591cf2c2c6e056373823615485397ea83651b7926c6f25a5fe6a0aae6", "profiles/unica-0.13.0-macos.json": "b76b5c8a4dd33f571c4a90993f1a2da5f7223b4f0f8e1042c282e21a66121052", "profiles/unica-0.14.0-rc.1-portable.json": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "rules/1c-specialist-platform/chistov.json": "77e04942f8c947b10759e7cc1eb31af05847d1711a772fbe6f23d525766757a9", "rules/1c-specialist-platform/decisions.json": "f622107423ce3c188c063318d7ab4f7718ceb38e443130677d8987f386641c09", "rules/1c-specialist-platform/examiner.json": "30353aa2a1b6545496b070d9066e9ffba0c3779e5b53ef70a4fd2cee375b18c0", "rules/1c-specialist-platform/ledger.json": "f167c10db2b5799dd9a1ea6a37cd2d7d186810dadf5ea2f50f26ae723c676882", "rules/1c-specialist-platform/rules.json": "1d320a4f8e1bf4701496388931f492315549bd3dce574b17285dd1d7f8652007", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" } } }, "conditions": { "client": "codex", "model": "gpt-6.1-sol", "client_version": "0.163.0-alpha.11.2", "reasoning_effort": "medium", "harness": "none", "billing_channel": "subscription", "solve_timeout_seconds": 3600, "time_series": null, "delegation": "native_disabled", "network_profile": "open-book_shell", "deadline_disclosed": true, "statement_sha256": "8a6ccb3e673826d1f8220fda53eb310e3ec18c136d87ce8f4cebb2a08614e7e5", "starter_dt_sha256": "f40d084818b0d1cfe503fc7653a6a13f1a8e47fcd1688dad6245b12744eb4638", "profile_sha256": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "execution_policy_sha256": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "calibration_sha256": "eced5b2f738ff558afe3d33d03048cf7b3ad00fa4e418c6a0ed72f885d0d221c", "started_at": "2026-10-24T06:54:17.179192+00:00", "timing": { "prepare_ms": 6781, "solve_ms": 3469985, "grade_ms": null }, "original_submission_valid": false, "model_provenance": "requested_only", "tokens": { "input": 16145325, "cached_input": 16011264, "fresh_input": 134061, "output": 117438, "reasoning_output": 43285, "total": 16262763, "coverage": "reported_completed_root_turns" }, "tools": { "mcp_calls": 0, "unica_calls": 0, "failed_calls": 0 }, "process": { "status": "completed", "exit_code": 0, "stop_confirmed": true } }, "verification": "repository_owner", "download": "community-downloads/demo-20261025T112622Z-adapter--owner-2026-10-26T223305964533-0000/solution.zip", "source_context": "community-downloads/demo-20261025T112622Z-adapter--owner-2026-10-26T223305964533-0000/source-context.json", "regrade_required": [], "grader_revision_sha256": "9aee1ffe0e1d04f9158fbbbeed3a403a5f0550ad8a590d7a6394977590760e1a", "archive_sha256": "a0410b139aa6d4b75fa2523cd575835fe6ae12b45f6645a5c2d1086e66feb193", "owner_verification": { "kind": "repository_owner", "repository": "zeegin/1c-agent-exam-benchmark", "operator": { "name": "Ingvar Vilkman", "github": "zeegin" }, "started_at": "2026-10-26T22:33:05.811894+00:00", "server": { "name": "Owner Windows stand", "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "hardware": { "cpu": "AMD Ryzen 7 5800X 8-Core Processor ", "logical_cpus": 4, "ram_bytes": 17109000192 }, "isolation": "dedicated-host" }, "platform_version": "8.3.27.2342", "grader": { "profile": "technical-v8", "commit": "e15c8ea80263c0b38baa3a1fc19611983270e8a7", "working_tree_dirty": false, "fingerprint": { "assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "calibrate.py": "aac127e03744907fd52ef149b88aa6d88a54a2b7497d56084484ee1b99e0da99", "calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "calibration_periodicity.py": "0b1953d7781e236467897cd2ed66705b75d9719353a2de60b36f2bbdfe799108", "calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "calibration_query.py": "3555b103cde8ea0519955cf52358d09223f5ab183a9df00533bdb48c89237a8c", "claude.py": "5bae98af6e2021e2718afa3a71ed04bee812deaae31a43d4e7324814139ccc82", "codescan.py": "6d8375210cef1fd768fc2d98d630d880b2993a9724f01ae25f33b4ea5aa9631d", "codex.py": "904e75503cd35f16cbb052f66806b3879fe25bfc9f99e33b93c889d862c46324", "common.py": "739b39e2bb9bdd4a571fc69df5843190cddcad094ef7e68964061bc1266b20dc", "docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "examiner.py": "8cdffcdd52f043c905f896697403380af95bf485dd4a5edca24f7956e7795ffe", "forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "harness.py": "3cbb90fd3187e700b5df32e5daafb20313d49bb5721c826e3033cbc6aa6e3825", "interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "ou.py": "f62784b54a3f85576a078a2ff1908c9395f3159e55f6bb5b1a3c564392241abe", "penalties.py": "ae388cb8953ecca1f2370a7c4cb1db3b6cc8318fc2a7563a4db15f9f5b057429", "platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "pr.py": "2b6bfea0634703469605ce114f9274716b485852d9a55d9185c39893b14e4726", "preflight.py": "448c3120ab64b625abae3891be686c7a214ce4211f7cf651fd90e12c0b298433", "process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "queries.py": "1ef57e292db3e8967a733948371ecc542f743b811890d4fc509df17303b9c4ac", "queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "querytypes.py": "b645f489a2abc27762b4a9bbf4917e72f7b46dc053a74c0dca4a8fc46491b3ef", "replay_calibration.py": "e0e3d5ca6416934715b9735aa516046b8d19ad4ae690220eeacd96b198a5f86c", "runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "smoke_check.py": "7837e980986bcb54dc8bc1dfb5d0003deef11e05f6e11df3910fa509e1f74c8d", "stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "submission.py": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tasks/1c-platform-official-sample/checks.json": "7447a9b42d3e348d29d07f001cfb6bd269acd953b7117eba7cca2ce9f5a9a60d", "tasks/1c-platform-official-sample/private/official-assessment-mapping.json": "303587c0dabe77c1eeebb2017fe85539e3370b17c9090435e6e0325a66bd0644", "tasks/1c-platform-official-sample/private/owner-scoring-policy.json": "d26d534bb838ab1b5facb7bc033ca8ec40912133baadcdbad83b27fc577905f5", "starters/carcass-8.3.25.1445/starter.json": "0f7a7060885ba99a19402bfc6e63cc8fe979b0f491b040d3a01d5d21b304b3a6", "rules/1c-specialist-platform/rules.json": "ea75e34ace5de11ba3de403c63cd2c026db81d1d991f8531e4a779d4ce9788e7", "rules/1c-specialist-platform/examiner.json": "1247486ddd412d600db88d9c1db4ba501fc1994afd1dc2ebe85402fcc332f4c8", "rules/1c-specialist-platform/chistov.json": "800da27601a3f1c7ec1df64482fd4ad035e559ba0b390a274ed5031128487d3d", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" }, "sha256": "9aee1ffe0e1d04f9158fbbbeed3a403a5f0550ad8a590d7a6394977590760e1a" }, "method": "saved_platform_observations", "outcome": "complete", "completed_at": "2026-10-26T22:33:05.964533+00:00" }, "previous_evaluations": [ { "id": "demo-20261025T112622Z-adapter--owner-2026-10-26T214342867449-0000", "run_id": "demo-20261024T065406Z-45954e", "result": { "run_id": "demo-20261024T065406Z-45954e", "created_at": "2026-10-26T21:43:42.867449+00:00", "model": "gpt-6.1-sol", "harness": "none", "solve_seconds": 3470, "platform": "8.3.27.1644", "counts": { "pass": 64, "fail": 1 }, "rules": [ { "id": "BU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU01.selected_fixture" }, { "id": "BU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU04.selected_fixture" }, { "id": "BU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU05.selected_fixture" }, { "id": "BU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU16.selected_fixture" }, { "id": "BU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU17.selected_fixture" }, { "id": "BU02", "verdict": "pass", "reason": null, "coverage": "partial", "assertion_id": "BU02.posting_cost_and_balance" }, { "id": "BU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU10.selected_fixture" }, { "id": "BU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU12.selected_fixture" }, { "id": "BU03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU03.selected_fixture" }, { "id": "BU06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU06.selected_fixture" }, { "id": "BU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU07.selected_fixture" }, { "id": "BU08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU08.selected_fixture" }, { "id": "BU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU09.selected_fixture" }, { "id": "BU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU11.selected_fixture" }, { "id": "BU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU14.selected_fixture" }, { "id": "BU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU15.selected_fixture" }, { "id": "BU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU13.selected_fixture" }, { "id": "OU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU15.selected_fixture" }, { "id": "OU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU16.selected_fixture" }, { "id": "OU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU17.selected_fixture" }, { "id": "OU02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU02.selected_fixture" }, { "id": "OU18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU18.selected_fixture" }, { "id": "OU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU14.selected_fixture" }, { "id": "OU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU01.selected_fixture" }, { "id": "OU03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU03.selected_fixture" }, { "id": "OU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU05.selected_fixture" }, { "id": "OU06", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "OU06.selected_fixture" }, { "id": "OU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU07.selected_fixture" }, { "id": "OU08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU08.selected_fixture" }, { "id": "OU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU09.selected_fixture" }, { "id": "OU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU10.selected_fixture" }, { "id": "OU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU11.selected_fixture" }, { "id": "OU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU12.selected_fixture" }, { "id": "OU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU13.selected_fixture" }, { "id": "OU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU04.selected_fixture" }, { "id": "OU19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU19.selected_fixture" }, { "id": "OU20", "verdict": "fail", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU20.selected_fixture" }, { "id": "OU21", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU21.selected_fixture" }, { "id": "PR01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR01.selected_fixture" }, { "id": "PR02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR02.selected_fixture" }, { "id": "PR03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR03.selected_fixture" }, { "id": "PR04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR04.selected_fixture" }, { "id": "PR05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR05.selected_fixture" }, { "id": "PR06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR06.selected_fixture" }, { "id": "PR07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR07.selected_fixture" }, { "id": "PR08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR08.selected_fixture" }, { "id": "PR09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR09.selected_fixture" }, { "id": "PR10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR10.selected_fixture" }, { "id": "PR11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR11.selected_fixture" }, { "id": "PR12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR12.selected_fixture" }, { "id": "PR13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR13.selected_fixture" }, { "id": "PR14", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "PR14.selected_fixture" }, { "id": "PR15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR15.selected_fixture" }, { "id": "PR16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR16.selected_fixture" }, { "id": "PR17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR17.selected_fixture" }, { "id": "PR18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR18.selected_fixture" }, { "id": "PR19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR19.selected_fixture" }, { "id": "F01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F01.selected_fixture" }, { "id": "F02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F02.selected_fixture" }, { "id": "F03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F03.selected_fixture" }, { "id": "F04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F04.selected_fixture" }, { "id": "F05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F05.selected_fixture" }, { "id": "G01", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G01.static_sources" }, { "id": "G02", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G02.static_sources" }, { "id": "G03", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G03.static_sources" } ], "charges": [ { "id": "F1C-GEN03", "points": "0.5", "reason": "отчёт не соответствует заданию: OU20" }, { "id": "F1C-GEN15", "points": "0.5", "reason": "Reports/Премии/Ext/ManagerModule.bsl:3 — РегистрРасчета.Начисления: отбор по ВидРасчета, ПериодДействияНачало, индексы таблицы начинаются с ПериодДействия, ПериодРегистрации, Подразделение, Регистратор, Сотрудник" }, { "id": "F1C-GEN14", "points": "1.5", "reason": "Reports/ПродажиБУ/Ext/ManagerModule.bsl:3 — РегистрБухгалтерии.Хозрасчетный: итоги считаются по основной таблице регистра, а не по виртуальной" }, { "id": "F1C-PR14", "points": "0.5", "reason": "после расчёта набор с периодом действия перезаписывается целиком, с пересчётом фактического периода действия (нужно Записать(, Истина)): CommonModules/РасчетыЗарплаты/Ext/Module.bsl:56 Набор.Записать(); CommonModules/РасчетыЗарплаты/Ext/Module.bsl:111 Набор.Записать(); CommonModules/РасчетыЗарплаты/Ext/Module.bsl:126 Пара.Значение.Записать(); CommonModules/РасчетыЗарплаты/Ext/Module.bsl:153 Пара.Значение.Записать()" }, { "id": "F1C-BU05", "points": "0.5", "reason": "аналитика счетов вынесена в измерения регистра бухгалтерии и есть у всех счетов: Номенклатура (Номенклатура)" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "оперативное проведение разрешено у документов с движениями по регистрам расчёта: НачислениеЗарплаты" }, { "id": "F1C-GEN22", "points": "1.0", "reason": "значения графика выбираются без ЕСТЬNULL: CommonModules/РасчетыЗарплаты/Ext/Module.bsl:47 ЗначениеПериодДействия; CommonModules/РасчетыЗарплаты/Ext/Module.bsl:83 ДниФактическийПериодДействия, ЗначениеПериодДействия, ЗначениеФактическийПериодДействия" } ], "score_upper_bound": "-0.5", "score": null, "grade": "unsatisfactory", "deductions": "5.5", "not_assessed": 14, "gates": { "starter_origin": "passed", "load": "loaded", "clients": "compiles", "demo_data": "present" }, "infrastructure_errors": false, "comparison_eligible": false, "binding_compatibility": { "scope": "supplemental_named_subconto_adapter", "original_binding_sha256": "7453f6ba6c67aaa1a3e183d4e7ab50cf384761713dfaf6c9602b444316874a6a", "normalized_binding_sha256": "5bf5c5f62324cd2e03d4a77ce9279e3dcfd379809eb7d04b7d5cbc58485885da", "normalizer_sha256": "7327277143d80a531e4c254ac74a9fc0e0d5c76572d53b8469e0a580eda17d65", "canonical_ledger_sha256": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "changes": [ { "field": "fields.ledger.warehouse_debit", "before": "Склады", "after": "ВидыСубконто.Склады", "kind": "named" }, { "field": "fields.ledger.warehouse_credit", "before": "Склады", "after": "ВидыСубконто.Склады", "kind": "named" } ], "basis": "kind names expanded only to exactly one predefined kind of the account chart on the role side; all role types checked." } }, "measurement": { "operator": { "name": "Вячеслав", "github": "sksibak" }, "environment": { "captured_at": "2026-10-24T06:54:09.737798+00:00", "capture_timing": "before_run", "hardware": { "cpu": "AMD Ryzen 5 4600H with Radeon Graphics ", "logical_cpus": 12, "ram_bytes": 16505962496 }, "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "python": "3.12.14", "platform_version": "8.3.27.1644", "isolation": "dedicated-host", "network_profile": "open-book_shell", "unsafe_action_protection_observed_in_user_config": true, "git_revision": "af85e791b303dbbf0b0b7af924d2489c3e57cfa8", "implementation_files": { "exam_bench/__init__.py": "ad5bf6f05dc6765f40b78bd186870ca2c49be113cfa33f8aa76f4926f2cb2c1e", "exam_bench/assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "exam_bench/bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "exam_bench/calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "exam_bench/calibrate.py": "78b5185cb0888c0c0ac3de95ffc3a80154a6de9ae66fc461f79d012e5a58e1db", "exam_bench/calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "exam_bench/calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "exam_bench/calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "exam_bench/calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "exam_bench/calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "exam_bench/claude.py": "bc1b8550de7573aaed5e39c6e9c0309e0d8175284a75490d61ec27439ed911ad", "exam_bench/cli.py": "1a37ce645633d761f7897dffc9c45e6b8b9600cd7bd233b1cbf78f49d26b099a", "exam_bench/codescan.py": "751e38001b6e65727a31e28172a0623f0bf34bc092a958037c286aa991a197ed", "exam_bench/codex.py": "c3f89d72af11f312d851c73a1610d92e79acadf336be9ccedd1f94ede3b3ccb0", "exam_bench/common.py": "8682603b519063e655eae3574a02a49efee63bde21f582ccee20ddd623fca96d", "exam_bench/docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "exam_bench/examiner.py": "d7294fdd23ed1732216cafebf0a8cf2c24cce4259859aeb7149f62b7607d087d", "exam_bench/finalize.py": "4034f1c63896a940afdb1a83d541cf47fc75c8b5061e3f839047109c04beb620", "exam_bench/forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "exam_bench/gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "exam_bench/grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "exam_bench/harness.py": "3040f6daaf1dc6e6583219f4d925151f8ba7851b2d5417d7f14645892b485ddf", "exam_bench/interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "exam_bench/interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "exam_bench/isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "exam_bench/ledger.py": "7e851523580e22d8490e75f9b6026c07f2c355007e0d11d0b252671f56bef654", "exam_bench/locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "exam_bench/materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "exam_bench/mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "exam_bench/observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "exam_bench/ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "exam_bench/penalties.py": "0d79e2e46102657dca00609b6abbfc0bf7d11fad41429564f876c82bc6b33269", "exam_bench/platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "exam_bench/portable.py": "cad56968ff407983608f5bdbc9ce7234128d7a4580b096ecea8e0e7b4edb9070", "exam_bench/portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "exam_bench/pr.py": "6a3a20caf0e10c0cc94410511a72d62c9fcda785f3abab1be2ad616d4ee16836", "exam_bench/preflight.py": "5619be0131d8641925f3ce2a3c8e5234d42aa5635d95676138ca81536d95cd29", "exam_bench/process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "exam_bench/queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "exam_bench/queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "exam_bench/replay_calibration.py": "c150457b0b23ce4e6814eb8deb4d48f6bc4a2e39d8f84a9dc7644fb99a026c2d", "exam_bench/report.py": "5e4c0757e1c7f189953f9a5302593ab726551835856baed25efd93dad6e8bfcd", "exam_bench/runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "exam_bench/smoke_check.py": "f36922a0027429ead0b414048dcc14bbe67f2f0e79a70d03dffbe1447d253545", "exam_bench/stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "exam_bench/submission.py": "ea862adc63ae67861ddb1d6aeb4d92c10b0b05004d22953f7b03612f82bb4bf4", "exam_bench/telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "exam_bench/windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "exam_bench/workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tools/build_public_site.py": "9682ed696f5ac9e9a82b65a45c0dece556ec7e49eeb20dcd616882cc534a8258", "tools/build_result_site.py": "3294e1d2ec1486058e208735264d61e349a68a4ae2fa2ec7a723c70e3263b496", "tools/check_native_harnesses.py": "4f5f0ed27651f78758eaef077b3b114361781f6b95ec40cb46c3fea689210473", "tools/check_native_toolkit.py": "0272794617121f2932828e5e4e9ae20095183c443666cf3ba466b44fbe875095", "tools/community_results.py": "cbfba30b4e617f5e219637c1c2de57398d01eb2f284eae3aca3ef684e6505a39", "tools/community_service.py": "c374480dbd88d656c0b9054fa04a8e1c6698c69e2f9cf475e82498a2dff61d84", "tools/community_setup.py": "5d7d126ed7d4dd48e1d79f57b99647a92ffcc8c9f80d90915e458888cdd76bf7", "tools/compare_harness_runs.py": "f274df5f3f804cb02504491aec946943833e12fbce6e62d281e12beb8508fc4e", "tools/create_run_plan.py": "871cd81b1eda231c0fba8805f63d2668926be9fc641559e6ddf320e2f47cd37a", "tools/demo_runner.py": "ca7ad17919c53d524cc0418751ba09a540f910eac183dca2961710bc30bba26f", "tools/installers.py": "9a2742780936b17500869e7c89202c1a2549e37d53a42ad9a50a0abbf78bbe09", "tools/machine_bundle.py": "8aa8346f99f537e81ceca6fb6ab9530e844954bab8eff87bf33d3602f81f8a30", "tools/prepare_native_harnesses.py": "aaa75ecf4022883984fa50c42d14d8e1a9fde2eeda03dab03b852bbc5efb2502", "tools/prepare_official_statement.py": "6b7028c78e90e798d6ef1a93b76520cc61a308c354fb9b87f7fad18b99800fad", "tools/prepare_open_exam_requirements.py": "544f4e378b9be5f166186f8788f8d454afdac2deb99d91d98421e39d01ba6d03", "tools/probe_harness.py": "1ed8ef93420d1484cbbfd151b7efc31b9a201ceb942dd05e3103efa22ffa7f27", "tools/probe_native_mcp.py": "9918d324129cba898993e07f8f8b6dbcbaf369398ebf28d464f9f1f00abdb254", "tools/readiness.py": "d34dd3f38334f51cc4574c79194cf0b80769b062a52382989a57d01c46b9aba4", "tools/recheck_community.py": "f0843d7d677f90da31e22bde0b1c86584dd46c022f1532d43d042619e426b230", "tools/regrade_runs.py": "011775afb06d3aac67a4aa81117a368c75896b0fcbe1e6f27ccc6237612fbf59", "tools/render_statement_text.py": "dabc0716a3612c288c671bc20e17fd4986691d732768e1e957d6dddddbea92a3", "tools/replay_calibration.py": "801f5004926c438c21ed3668fe2a4ddf45312b3e75320165a3839aae034eee9b", "tools/run_exam_campaign.py": "2c450d57a1cd0a2682838f5ec7c0a4ffb3aed0f1730d34c408e912d59cab6efd", "tools/serve_result_site.py": "86badfac863cd4ad1fc894a14110c75b28470513f0133eeae9d2799b8b4df3a9", "tools/start_demo.py": "c597e6cad28d245b3191654bb3e2801fa9dd2364e2acb25561923613717b615f", "tools/supplemental_acceptance.py": "c88fc39de1be1fdcacdd819e2ad329f60367b2df1d5deda80b37324bda3f2a01", "tools/sync_sources.py": "b51e889b0f41f9f63bfb19a09fb96d3777693d6b1d76fe0132bdd2a15e155898", "tools/validate_community_pr.py": "796b896dfade07b4529af2088a4b9b9d23484148b3bc0732b3fb837b75c9844b", "tools/verify_official_assessment_mapping.py": "daeb448a016940d5b6b1285979a56e5b9014bd91db40acb131445e4a83a23059", "tools/verify_task_package.py": "9e1e6105f6b5e4e78b36aa57f00117a9fbc8948ab53983c32ab56da88d23ccc4", "profiles/agents.json": "af9c492c08d13b3044aa6b6952589ed6a0a07d5258d8ff72bb18185b3eaebdc5", "profiles/ai-exam-execution-policy.json": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "profiles/bsl-analyzer-0.3.2-macos.json": "83537abdbf38c41ce665e4d0f24128bb51b62e971e0e0f368695f1326a7d2ffb", "profiles/bsl-analyzer-0.3.2-portable.json": "d6ba732e6778e256df34d6bc548593128820a70430c35b279796843606ee40a8", "profiles/bsl-ls-1.1.0-rc.6-macos.json": "245fc10747197e6911b2b4c77cdb15e6fa4eb7bc7c3758b63e768c5adf1df180", "profiles/bsl-ls-1.1.0-rc.6-portable.json": "9f10660881f2ec84794f7d584556b8f75c7e14b3555464af0ed0e60c4c892d86", "profiles/code-index-1.9.0-macos.json": "63a919523ce62ecec274f4c139bc7ad49a75dd4c339568b822cbc695b4e30408", "profiles/code-index-1.9.0-portable.json": "81106cee8f424ffd8a9dc46ecd8e4f57598fc1d49661a83c77b1f0507993fbdc", "profiles/codex-probe-plan.json": "166e41aad5fb3b27d9050bc6de952c6cba363cc6e804d4080568cc71a2a4d289", "profiles/machine.linux.example.json": "408304fd0581098d5d8110dc67dfeab353bc4d4030e32d37e6acf98d2b1aedfd", "profiles/machine.macos.example.json": "52e9f9d17797cb520b9d8955d6806fd550b899bed4da241ebf096dcb6a21a942", "profiles/machine.windows.example.json": "63accac9a2f81d47d03447efbabffd4760aee325193f02f46b9b29a28d50d2d8", "profiles/mcp-toolkit-1.9.0-macos.json": "1d3f9cde5ffa20589a840d01fdae03aa0fc2f412c929f064f203919c4129625b", "profiles/mcp-toolkit-1.9.0-portable.json": "8e370eebe773eef0e08045ee9c6d5be1451f769f65be0710834b262a4336e054", "profiles/none-macos.json": "b1401d9c48159aed3559006c7f6ace6ef4571224d5cf0bb76d1a823505a10056", "profiles/none-portable.json": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "profiles/rlm-tools-bsl-1.43.0-macos.json": "9354421052640ab60bc3e6aa98ff2e7ba9ca2318b0f4026c137487449242cbd2", "profiles/rlm-tools-bsl-1.43.0-portable.json": "2599e5645e0a7d4e44cb2934bc2b272cae79a9bf7ea74a23cd48aacea64bc424", "profiles/rlm-tools-bsl-1.43.0-posix-requirements.txt": "4fdf9a1bd994bf0272e65d231daf76cf19b0a34dad0ae6b50ec4f11a2ce4c330", "profiles/rlm-tools-bsl-1.43.0-windows-requirements.txt": "3730cb46c81cda5181ecd4485e98b11933104632358bc86f8c0eb1a612a8954f", "profiles/shirokov-skills-macos.json": "84f3e89091676884a802035c707e912762a1179425fb8e3faff25be736873cdb", "profiles/shirokov-skills-portable.json": "2b0a461e06602f1456410e70f02ceaa5ac32c6549c486660bcb5ace0c2f87b15", "profiles/shirokov-skills-windows-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/unica-0.12.3-macos.json": "2c39fbb591cf2c2c6e056373823615485397ea83651b7926c6f25a5fe6a0aae6", "profiles/unica-0.13.0-macos.json": "b76b5c8a4dd33f571c4a90993f1a2da5f7223b4f0f8e1042c282e21a66121052", "profiles/unica-0.14.0-rc.1-portable.json": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "rules/1c-specialist-platform/chistov.json": "77e04942f8c947b10759e7cc1eb31af05847d1711a772fbe6f23d525766757a9", "rules/1c-specialist-platform/decisions.json": "f622107423ce3c188c063318d7ab4f7718ceb38e443130677d8987f386641c09", "rules/1c-specialist-platform/examiner.json": "30353aa2a1b6545496b070d9066e9ffba0c3779e5b53ef70a4fd2cee375b18c0", "rules/1c-specialist-platform/ledger.json": "f167c10db2b5799dd9a1ea6a37cd2d7d186810dadf5ea2f50f26ae723c676882", "rules/1c-specialist-platform/rules.json": "1d320a4f8e1bf4701496388931f492315549bd3dce574b17285dd1d7f8652007", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" } } }, "conditions": { "client": "codex", "model": "gpt-6.1-sol", "client_version": "0.163.0-alpha.11.2", "reasoning_effort": "medium", "harness": "none", "billing_channel": "subscription", "solve_timeout_seconds": 3600, "time_series": null, "delegation": "native_disabled", "network_profile": "open-book_shell", "deadline_disclosed": true, "statement_sha256": "8a6ccb3e673826d1f8220fda53eb310e3ec18c136d87ce8f4cebb2a08614e7e5", "starter_dt_sha256": "f40d084818b0d1cfe503fc7653a6a13f1a8e47fcd1688dad6245b12744eb4638", "profile_sha256": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "execution_policy_sha256": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "calibration_sha256": "eced5b2f738ff558afe3d33d03048cf7b3ad00fa4e418c6a0ed72f885d0d221c", "started_at": "2026-10-24T06:54:17.179192+00:00", "timing": { "prepare_ms": 6781, "solve_ms": 3469985, "grade_ms": null }, "original_submission_valid": false, "model_provenance": "requested_only", "tokens": { "input": 16145325, "cached_input": 16011264, "fresh_input": 134061, "output": 117438, "reasoning_output": 43285, "total": 16262763, "coverage": "reported_completed_root_turns" }, "tools": { "mcp_calls": 0, "unica_calls": 0, "failed_calls": 0 }, "process": { "status": "completed", "exit_code": 0, "stop_confirmed": true } }, "verification": "repository_owner", "download": "community-downloads/demo-20261025T112622Z-adapter--owner-2026-10-26T214342867449-0000/solution.zip", "source_context": "community-downloads/demo-20261025T112622Z-adapter--owner-2026-10-26T214342867449-0000/source-context.json", "regrade_required": [ { "id": "grader_changed", "files": [ "calibrate.py", "calibration_periodicity.py", "common.py", "ou.py", "replay_calibration.py", "smoke_check.py", "tasks/1c-platform-official-sample/checks.json" ] } ], "grader_revision_sha256": "349d87e0c7f531acbe35dd2b39c35722d8a877fedde97575b49e8466ab763c1d", "archive_sha256": "d9333c87b7bec571337fbc8bc4e6db4f6d62cc143b6ce986f7dc6c9b2fe42d38", "owner_verification": { "kind": "repository_owner", "repository": "zeegin/1c-agent-exam-benchmark", "operator": { "name": "Ingvar Vilkman", "github": "zeegin" }, "started_at": "2026-10-26T21:43:42.701614+00:00", "server": { "name": "Owner Windows stand", "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "hardware": { "cpu": "AMD Ryzen 7 5800X 8-Core Processor ", "logical_cpus": 4, "ram_bytes": 17109000192 }, "isolation": "dedicated-host" }, "platform_version": "8.3.27.2342", "grader": { "profile": "technical-v8", "commit": "e8fd8ced03a85b549c5472fbbda29225749f54d1", "working_tree_dirty": false, "fingerprint": { "assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "calibrate.py": "3162d431f3cab5e7976aa39f665d6286dce45499cf362d85109b7123fa8403a2", "calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "calibration_query.py": "3555b103cde8ea0519955cf52358d09223f5ab183a9df00533bdb48c89237a8c", "claude.py": "eedabc75fca0faa434f40a1624b71419ec7dc22e2854a0886cf84b4911db8372", "codescan.py": "6d8375210cef1fd768fc2d98d630d880b2993a9724f01ae25f33b4ea5aa9631d", "codex.py": "904e75503cd35f16cbb052f66806b3879fe25bfc9f99e33b93c889d862c46324", "common.py": "52825cf5c29f3536d6e046a89e789d5ef9c83aacd7f2f5a07f4f53e77b5229cc", "docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "examiner.py": "8cdffcdd52f043c905f896697403380af95bf485dd4a5edca24f7956e7795ffe", "forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "harness.py": "3cbb90fd3187e700b5df32e5daafb20313d49bb5721c826e3033cbc6aa6e3825", "interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "penalties.py": "ae388cb8953ecca1f2370a7c4cb1db3b6cc8318fc2a7563a4db15f9f5b057429", "platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "pr.py": "2b6bfea0634703469605ce114f9274716b485852d9a55d9185c39893b14e4726", "preflight.py": "448c3120ab64b625abae3891be686c7a214ce4211f7cf651fd90e12c0b298433", "process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "queries.py": "1ef57e292db3e8967a733948371ecc542f743b811890d4fc509df17303b9c4ac", "queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "querytypes.py": "b645f489a2abc27762b4a9bbf4917e72f7b46dc053a74c0dca4a8fc46491b3ef", "replay_calibration.py": "0a4d9b84a9908944c5a945878eb6f5eeda5a4e42ffff4f55c04a680742803d80", "runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "smoke_check.py": "66caf1a01f7aa18432293abe3567ac228ac837a660b08c3dc7bb093f7bd51628", "stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "submission.py": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tasks/1c-platform-official-sample/checks.json": "17a6fcc0c14410829650623eb1443ce99796e000cdfd19905ac0287988b73a00", "tasks/1c-platform-official-sample/private/official-assessment-mapping.json": "303587c0dabe77c1eeebb2017fe85539e3370b17c9090435e6e0325a66bd0644", "tasks/1c-platform-official-sample/private/owner-scoring-policy.json": "d26d534bb838ab1b5facb7bc033ca8ec40912133baadcdbad83b27fc577905f5", "starters/carcass-8.3.25.1445/starter.json": "0f7a7060885ba99a19402bfc6e63cc8fe979b0f491b040d3a01d5d21b304b3a6", "rules/1c-specialist-platform/rules.json": "ea75e34ace5de11ba3de403c63cd2c026db81d1d991f8531e4a779d4ce9788e7", "rules/1c-specialist-platform/examiner.json": "1247486ddd412d600db88d9c1db4ba501fc1994afd1dc2ebe85402fcc332f4c8", "rules/1c-specialist-platform/chistov.json": "800da27601a3f1c7ec1df64482fd4ad035e559ba0b390a274ed5031128487d3d", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" }, "sha256": "349d87e0c7f531acbe35dd2b39c35722d8a877fedde97575b49e8466ab763c1d" }, "method": "saved_platform_observations", "outcome": "complete", "completed_at": "2026-10-26T21:43:42.867449+00:00" } }, { "id": "demo-20261025T112622Z-adapter--owner-2026-10-26T185324876564-0000", "run_id": "demo-20261024T065406Z-45954e", "result": { "run_id": "demo-20261024T065406Z-45954e", "created_at": "2026-10-26T18:53:24.876564+00:00", "model": "gpt-6.1-sol", "harness": "none", "solve_seconds": 3470, "platform": "8.3.27.1644", "counts": { "pass": 64, "fail": 1 }, "rules": [ { "id": "BU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU01.selected_fixture" }, { "id": "BU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU04.selected_fixture" }, { "id": "BU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU05.selected_fixture" }, { "id": "BU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU16.selected_fixture" }, { "id": "BU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU17.selected_fixture" }, { "id": "BU02", "verdict": "pass", "reason": null, "coverage": "partial", "assertion_id": "BU02.posting_cost_and_balance" }, { "id": "BU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU10.selected_fixture" }, { "id": "BU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU12.selected_fixture" }, { "id": "BU03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU03.selected_fixture" }, { "id": "BU06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU06.selected_fixture" }, { "id": "BU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU07.selected_fixture" }, { "id": "BU08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU08.selected_fixture" }, { "id": "BU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU09.selected_fixture" }, { "id": "BU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU11.selected_fixture" }, { "id": "BU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU14.selected_fixture" }, { "id": "BU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU15.selected_fixture" }, { "id": "BU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU13.selected_fixture" }, { "id": "OU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU15.selected_fixture" }, { "id": "OU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU16.selected_fixture" }, { "id": "OU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU17.selected_fixture" }, { "id": "OU02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU02.selected_fixture" }, { "id": "OU18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU18.selected_fixture" }, { "id": "OU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU14.selected_fixture" }, { "id": "OU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU01.selected_fixture" }, { "id": "OU03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU03.selected_fixture" }, { "id": "OU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU05.selected_fixture" }, { "id": "OU06", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "OU06.selected_fixture" }, { "id": "OU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU07.selected_fixture" }, { "id": "OU08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU08.selected_fixture" }, { "id": "OU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU09.selected_fixture" }, { "id": "OU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU10.selected_fixture" }, { "id": "OU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU11.selected_fixture" }, { "id": "OU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU12.selected_fixture" }, { "id": "OU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU13.selected_fixture" }, { "id": "OU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU04.selected_fixture" }, { "id": "OU19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU19.selected_fixture" }, { "id": "OU20", "verdict": "fail", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU20.selected_fixture" }, { "id": "OU21", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU21.selected_fixture" }, { "id": "PR01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR01.selected_fixture" }, { "id": "PR02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR02.selected_fixture" }, { "id": "PR03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR03.selected_fixture" }, { "id": "PR04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR04.selected_fixture" }, { "id": "PR05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR05.selected_fixture" }, { "id": "PR06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR06.selected_fixture" }, { "id": "PR07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR07.selected_fixture" }, { "id": "PR08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR08.selected_fixture" }, { "id": "PR09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR09.selected_fixture" }, { "id": "PR10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR10.selected_fixture" }, { "id": "PR11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR11.selected_fixture" }, { "id": "PR12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR12.selected_fixture" }, { "id": "PR13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR13.selected_fixture" }, { "id": "PR14", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "PR14.selected_fixture" }, { "id": "PR15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR15.selected_fixture" }, { "id": "PR16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR16.selected_fixture" }, { "id": "PR17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR17.selected_fixture" }, { "id": "PR18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR18.selected_fixture" }, { "id": "PR19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR19.selected_fixture" }, { "id": "F01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F01.selected_fixture" }, { "id": "F02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F02.selected_fixture" }, { "id": "F03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F03.selected_fixture" }, { "id": "F04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F04.selected_fixture" }, { "id": "F05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F05.selected_fixture" }, { "id": "G01", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G01.static_sources" }, { "id": "G02", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G02.static_sources" }, { "id": "G03", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G03.static_sources" } ], "charges": [ { "id": "F1C-GEN03", "points": "0.5", "reason": "отчёт не соответствует заданию: OU20" }, { "id": "F1C-GEN15", "points": "0.5", "reason": "Reports/Премии/Ext/ManagerModule.bsl:3 — РегистрРасчета.Начисления: отбор по ВидРасчета, ПериодДействияНачало, индексы таблицы начинаются с ПериодДействия, ПериодРегистрации, Подразделение, Регистратор, Сотрудник" }, { "id": "F1C-GEN14", "points": "1.5", "reason": "Reports/ПродажиБУ/Ext/ManagerModule.bsl:3 — РегистрБухгалтерии.Хозрасчетный: итоги считаются по основной таблице регистра, а не по виртуальной" }, { "id": "F1C-PR14", "points": "0.5", "reason": "после расчёта набор с периодом действия перезаписывается целиком, с пересчётом фактического периода действия (нужно Записать(, Истина)): CommonModules/РасчетыЗарплаты/Ext/Module.bsl:56 Набор.Записать(); CommonModules/РасчетыЗарплаты/Ext/Module.bsl:111 Набор.Записать(); CommonModules/РасчетыЗарплаты/Ext/Module.bsl:126 Пара.Значение.Записать(); CommonModules/РасчетыЗарплаты/Ext/Module.bsl:153 Пара.Значение.Записать()" }, { "id": "F1C-BU05", "points": "0.5", "reason": "аналитика счетов вынесена в измерения регистра бухгалтерии и есть у всех счетов: Номенклатура (Номенклатура)" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "оперативное проведение разрешено у документов с движениями по регистрам расчёта: НачислениеЗарплаты" }, { "id": "F1C-GEN22", "points": "1.0", "reason": "значения графика выбираются без ЕСТЬNULL: CommonModules/РасчетыЗарплаты/Ext/Module.bsl:47 ЗначениеПериодДействия; CommonModules/РасчетыЗарплаты/Ext/Module.bsl:83 ДниФактическийПериодДействия, ЗначениеПериодДействия, ЗначениеФактическийПериодДействия" } ], "score_upper_bound": "-0.5", "score": null, "grade": "unsatisfactory", "deductions": "5.5", "not_assessed": 14, "gates": { "starter_origin": "passed", "load": "loaded", "clients": "compiles", "demo_data": "present" }, "infrastructure_errors": false, "comparison_eligible": false, "binding_compatibility": { "scope": "supplemental_named_subconto_adapter", "original_binding_sha256": "7453f6ba6c67aaa1a3e183d4e7ab50cf384761713dfaf6c9602b444316874a6a", "normalized_binding_sha256": "5bf5c5f62324cd2e03d4a77ce9279e3dcfd379809eb7d04b7d5cbc58485885da", "normalizer_sha256": "7327277143d80a531e4c254ac74a9fc0e0d5c76572d53b8469e0a580eda17d65", "canonical_ledger_sha256": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "changes": [ { "field": "fields.ledger.warehouse_debit", "before": "Склады", "after": "ВидыСубконто.Склады", "kind": "named" }, { "field": "fields.ledger.warehouse_credit", "before": "Склады", "after": "ВидыСубконто.Склады", "kind": "named" } ], "basis": "kind names expanded only to exactly one predefined kind of the account chart on the role side; all role types checked." } }, "measurement": { "operator": { "name": "Вячеслав", "github": "sksibak" }, "environment": { "captured_at": "2026-10-24T06:54:09.737798+00:00", "capture_timing": "before_run", "hardware": { "cpu": "AMD Ryzen 5 4600H with Radeon Graphics ", "logical_cpus": 12, "ram_bytes": 16505962496 }, "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "python": "3.12.14", "platform_version": "8.3.27.1644", "isolation": "dedicated-host", "network_profile": "open-book_shell", "unsafe_action_protection_observed_in_user_config": true, "git_revision": "af85e791b303dbbf0b0b7af924d2489c3e57cfa8", "implementation_files": { "exam_bench/__init__.py": "ad5bf6f05dc6765f40b78bd186870ca2c49be113cfa33f8aa76f4926f2cb2c1e", "exam_bench/assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "exam_bench/bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "exam_bench/calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "exam_bench/calibrate.py": "78b5185cb0888c0c0ac3de95ffc3a80154a6de9ae66fc461f79d012e5a58e1db", "exam_bench/calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "exam_bench/calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "exam_bench/calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "exam_bench/calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "exam_bench/calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "exam_bench/claude.py": "bc1b8550de7573aaed5e39c6e9c0309e0d8175284a75490d61ec27439ed911ad", "exam_bench/cli.py": "1a37ce645633d761f7897dffc9c45e6b8b9600cd7bd233b1cbf78f49d26b099a", "exam_bench/codescan.py": "751e38001b6e65727a31e28172a0623f0bf34bc092a958037c286aa991a197ed", "exam_bench/codex.py": "c3f89d72af11f312d851c73a1610d92e79acadf336be9ccedd1f94ede3b3ccb0", "exam_bench/common.py": "8682603b519063e655eae3574a02a49efee63bde21f582ccee20ddd623fca96d", "exam_bench/docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "exam_bench/examiner.py": "d7294fdd23ed1732216cafebf0a8cf2c24cce4259859aeb7149f62b7607d087d", "exam_bench/finalize.py": "4034f1c63896a940afdb1a83d541cf47fc75c8b5061e3f839047109c04beb620", "exam_bench/forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "exam_bench/gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "exam_bench/grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "exam_bench/harness.py": "3040f6daaf1dc6e6583219f4d925151f8ba7851b2d5417d7f14645892b485ddf", "exam_bench/interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "exam_bench/interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "exam_bench/isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "exam_bench/ledger.py": "7e851523580e22d8490e75f9b6026c07f2c355007e0d11d0b252671f56bef654", "exam_bench/locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "exam_bench/materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "exam_bench/mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "exam_bench/observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "exam_bench/ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "exam_bench/penalties.py": "0d79e2e46102657dca00609b6abbfc0bf7d11fad41429564f876c82bc6b33269", "exam_bench/platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "exam_bench/portable.py": "cad56968ff407983608f5bdbc9ce7234128d7a4580b096ecea8e0e7b4edb9070", "exam_bench/portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "exam_bench/pr.py": "6a3a20caf0e10c0cc94410511a72d62c9fcda785f3abab1be2ad616d4ee16836", "exam_bench/preflight.py": "5619be0131d8641925f3ce2a3c8e5234d42aa5635d95676138ca81536d95cd29", "exam_bench/process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "exam_bench/queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "exam_bench/queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "exam_bench/replay_calibration.py": "c150457b0b23ce4e6814eb8deb4d48f6bc4a2e39d8f84a9dc7644fb99a026c2d", "exam_bench/report.py": "5e4c0757e1c7f189953f9a5302593ab726551835856baed25efd93dad6e8bfcd", "exam_bench/runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "exam_bench/smoke_check.py": "f36922a0027429ead0b414048dcc14bbe67f2f0e79a70d03dffbe1447d253545", "exam_bench/stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "exam_bench/submission.py": "ea862adc63ae67861ddb1d6aeb4d92c10b0b05004d22953f7b03612f82bb4bf4", "exam_bench/telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "exam_bench/windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "exam_bench/workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tools/build_public_site.py": "9682ed696f5ac9e9a82b65a45c0dece556ec7e49eeb20dcd616882cc534a8258", "tools/build_result_site.py": "3294e1d2ec1486058e208735264d61e349a68a4ae2fa2ec7a723c70e3263b496", "tools/check_native_harnesses.py": "4f5f0ed27651f78758eaef077b3b114361781f6b95ec40cb46c3fea689210473", "tools/check_native_toolkit.py": "0272794617121f2932828e5e4e9ae20095183c443666cf3ba466b44fbe875095", "tools/community_results.py": "cbfba30b4e617f5e219637c1c2de57398d01eb2f284eae3aca3ef684e6505a39", "tools/community_service.py": "c374480dbd88d656c0b9054fa04a8e1c6698c69e2f9cf475e82498a2dff61d84", "tools/community_setup.py": "5d7d126ed7d4dd48e1d79f57b99647a92ffcc8c9f80d90915e458888cdd76bf7", "tools/compare_harness_runs.py": "f274df5f3f804cb02504491aec946943833e12fbce6e62d281e12beb8508fc4e", "tools/create_run_plan.py": "871cd81b1eda231c0fba8805f63d2668926be9fc641559e6ddf320e2f47cd37a", "tools/demo_runner.py": "ca7ad17919c53d524cc0418751ba09a540f910eac183dca2961710bc30bba26f", "tools/installers.py": "9a2742780936b17500869e7c89202c1a2549e37d53a42ad9a50a0abbf78bbe09", "tools/machine_bundle.py": "8aa8346f99f537e81ceca6fb6ab9530e844954bab8eff87bf33d3602f81f8a30", "tools/prepare_native_harnesses.py": "aaa75ecf4022883984fa50c42d14d8e1a9fde2eeda03dab03b852bbc5efb2502", "tools/prepare_official_statement.py": "6b7028c78e90e798d6ef1a93b76520cc61a308c354fb9b87f7fad18b99800fad", "tools/prepare_open_exam_requirements.py": "544f4e378b9be5f166186f8788f8d454afdac2deb99d91d98421e39d01ba6d03", "tools/probe_harness.py": "1ed8ef93420d1484cbbfd151b7efc31b9a201ceb942dd05e3103efa22ffa7f27", "tools/probe_native_mcp.py": "9918d324129cba898993e07f8f8b6dbcbaf369398ebf28d464f9f1f00abdb254", "tools/readiness.py": "d34dd3f38334f51cc4574c79194cf0b80769b062a52382989a57d01c46b9aba4", "tools/recheck_community.py": "f0843d7d677f90da31e22bde0b1c86584dd46c022f1532d43d042619e426b230", "tools/regrade_runs.py": "011775afb06d3aac67a4aa81117a368c75896b0fcbe1e6f27ccc6237612fbf59", "tools/render_statement_text.py": "dabc0716a3612c288c671bc20e17fd4986691d732768e1e957d6dddddbea92a3", "tools/replay_calibration.py": "801f5004926c438c21ed3668fe2a4ddf45312b3e75320165a3839aae034eee9b", "tools/run_exam_campaign.py": "2c450d57a1cd0a2682838f5ec7c0a4ffb3aed0f1730d34c408e912d59cab6efd", "tools/serve_result_site.py": "86badfac863cd4ad1fc894a14110c75b28470513f0133eeae9d2799b8b4df3a9", "tools/start_demo.py": "c597e6cad28d245b3191654bb3e2801fa9dd2364e2acb25561923613717b615f", "tools/supplemental_acceptance.py": "c88fc39de1be1fdcacdd819e2ad329f60367b2df1d5deda80b37324bda3f2a01", "tools/sync_sources.py": "b51e889b0f41f9f63bfb19a09fb96d3777693d6b1d76fe0132bdd2a15e155898", "tools/validate_community_pr.py": "796b896dfade07b4529af2088a4b9b9d23484148b3bc0732b3fb837b75c9844b", "tools/verify_official_assessment_mapping.py": "daeb448a016940d5b6b1285979a56e5b9014bd91db40acb131445e4a83a23059", "tools/verify_task_package.py": "9e1e6105f6b5e4e78b36aa57f00117a9fbc8948ab53983c32ab56da88d23ccc4", "profiles/agents.json": "af9c492c08d13b3044aa6b6952589ed6a0a07d5258d8ff72bb18185b3eaebdc5", "profiles/ai-exam-execution-policy.json": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "profiles/bsl-analyzer-0.3.2-macos.json": "83537abdbf38c41ce665e4d0f24128bb51b62e971e0e0f368695f1326a7d2ffb", "profiles/bsl-analyzer-0.3.2-portable.json": "d6ba732e6778e256df34d6bc548593128820a70430c35b279796843606ee40a8", "profiles/bsl-ls-1.1.0-rc.6-macos.json": "245fc10747197e6911b2b4c77cdb15e6fa4eb7bc7c3758b63e768c5adf1df180", "profiles/bsl-ls-1.1.0-rc.6-portable.json": "9f10660881f2ec84794f7d584556b8f75c7e14b3555464af0ed0e60c4c892d86", "profiles/code-index-1.9.0-macos.json": "63a919523ce62ecec274f4c139bc7ad49a75dd4c339568b822cbc695b4e30408", "profiles/code-index-1.9.0-portable.json": "81106cee8f424ffd8a9dc46ecd8e4f57598fc1d49661a83c77b1f0507993fbdc", "profiles/codex-probe-plan.json": "166e41aad5fb3b27d9050bc6de952c6cba363cc6e804d4080568cc71a2a4d289", "profiles/machine.linux.example.json": "408304fd0581098d5d8110dc67dfeab353bc4d4030e32d37e6acf98d2b1aedfd", "profiles/machine.macos.example.json": "52e9f9d17797cb520b9d8955d6806fd550b899bed4da241ebf096dcb6a21a942", "profiles/machine.windows.example.json": "63accac9a2f81d47d03447efbabffd4760aee325193f02f46b9b29a28d50d2d8", "profiles/mcp-toolkit-1.9.0-macos.json": "1d3f9cde5ffa20589a840d01fdae03aa0fc2f412c929f064f203919c4129625b", "profiles/mcp-toolkit-1.9.0-portable.json": "8e370eebe773eef0e08045ee9c6d5be1451f769f65be0710834b262a4336e054", "profiles/none-macos.json": "b1401d9c48159aed3559006c7f6ace6ef4571224d5cf0bb76d1a823505a10056", "profiles/none-portable.json": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "profiles/rlm-tools-bsl-1.43.0-macos.json": "9354421052640ab60bc3e6aa98ff2e7ba9ca2318b0f4026c137487449242cbd2", "profiles/rlm-tools-bsl-1.43.0-portable.json": "2599e5645e0a7d4e44cb2934bc2b272cae79a9bf7ea74a23cd48aacea64bc424", "profiles/rlm-tools-bsl-1.43.0-posix-requirements.txt": "4fdf9a1bd994bf0272e65d231daf76cf19b0a34dad0ae6b50ec4f11a2ce4c330", "profiles/rlm-tools-bsl-1.43.0-windows-requirements.txt": "3730cb46c81cda5181ecd4485e98b11933104632358bc86f8c0eb1a612a8954f", "profiles/shirokov-skills-macos.json": "84f3e89091676884a802035c707e912762a1179425fb8e3faff25be736873cdb", "profiles/shirokov-skills-portable.json": "2b0a461e06602f1456410e70f02ceaa5ac32c6549c486660bcb5ace0c2f87b15", "profiles/shirokov-skills-windows-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/unica-0.12.3-macos.json": "2c39fbb591cf2c2c6e056373823615485397ea83651b7926c6f25a5fe6a0aae6", "profiles/unica-0.13.0-macos.json": "b76b5c8a4dd33f571c4a90993f1a2da5f7223b4f0f8e1042c282e21a66121052", "profiles/unica-0.14.0-rc.1-portable.json": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "rules/1c-specialist-platform/chistov.json": "77e04942f8c947b10759e7cc1eb31af05847d1711a772fbe6f23d525766757a9", "rules/1c-specialist-platform/decisions.json": "f622107423ce3c188c063318d7ab4f7718ceb38e443130677d8987f386641c09", "rules/1c-specialist-platform/examiner.json": "30353aa2a1b6545496b070d9066e9ffba0c3779e5b53ef70a4fd2cee375b18c0", "rules/1c-specialist-platform/ledger.json": "f167c10db2b5799dd9a1ea6a37cd2d7d186810dadf5ea2f50f26ae723c676882", "rules/1c-specialist-platform/rules.json": "1d320a4f8e1bf4701496388931f492315549bd3dce574b17285dd1d7f8652007", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" } } }, "conditions": { "client": "codex", "model": "gpt-6.1-sol", "client_version": "0.163.0-alpha.11.2", "reasoning_effort": "medium", "harness": "none", "billing_channel": "subscription", "solve_timeout_seconds": 3600, "time_series": null, "delegation": "native_disabled", "network_profile": "open-book_shell", "deadline_disclosed": true, "statement_sha256": "8a6ccb3e673826d1f8220fda53eb310e3ec18c136d87ce8f4cebb2a08614e7e5", "starter_dt_sha256": "f40d084818b0d1cfe503fc7653a6a13f1a8e47fcd1688dad6245b12744eb4638", "profile_sha256": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "execution_policy_sha256": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "calibration_sha256": "eced5b2f738ff558afe3d33d03048cf7b3ad00fa4e418c6a0ed72f885d0d221c", "started_at": "2026-10-24T06:54:17.179192+00:00", "timing": { "prepare_ms": 6781, "solve_ms": 3469985, "grade_ms": null }, "original_submission_valid": false, "model_provenance": "requested_only", "tokens": { "input": 16145325, "cached_input": 16011264, "fresh_input": 134061, "output": 117438, "reasoning_output": 43285, "total": 16262763, "coverage": "reported_completed_root_turns" }, "tools": { "mcp_calls": 0, "unica_calls": 0, "failed_calls": 0 }, "process": { "status": "completed", "exit_code": 0, "stop_confirmed": true } }, "verification": "repository_owner", "download": "community-downloads/demo-20261025T112622Z-adapter--owner-2026-10-26T185324876564-0000/solution.zip", "source_context": "community-downloads/demo-20261025T112622Z-adapter--owner-2026-10-26T185324876564-0000/source-context.json", "regrade_required": [ { "id": "grader_changed", "files": [ "calibrate.py", "calibration_periodicity.py", "calibration_query.py", "common.py", "ou.py", "penalties.py", "queries.py", "replay_calibration.py", "rules/1c-specialist-platform/rules.json", "smoke_check.py", "tasks/1c-platform-official-sample/checks.json" ] } ], "grader_revision_sha256": "4a12b62d2c10085e1fc710f377f84903abdf2fb787dda19628d944da990a86b2", "archive_sha256": "327f28e3a00fc7b1c659385403b7abc73453a64ac7526ae5dcab96499ff28b65", "owner_verification": { "kind": "repository_owner", "repository": "zeegin/1c-agent-exam-benchmark", "operator": { "name": "Ingvar Vilkman", "github": "zeegin" }, "started_at": "2026-10-26T18:50:34.345690+00:00", "server": { "name": "Owner Windows stand", "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "hardware": { "cpu": "AMD Ryzen 7 5800X 8-Core Processor ", "logical_cpus": 4, "ram_bytes": 17109000192 }, "isolation": "dedicated-host" }, "platform_version": "8.3.27.2342", "grader": { "profile": "technical-v8", "commit": "45c5511ee520262f83dd0cfe1d9a7f39fae63301", "working_tree_dirty": true, "fingerprint": { "assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "calibrate.py": "1c844971b4977fdcc3b30aebe8aad40fbd45e6828955b8deb043ac8573d61731", "calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "claude.py": "eedabc75fca0faa434f40a1624b71419ec7dc22e2854a0886cf84b4911db8372", "codescan.py": "6d8375210cef1fd768fc2d98d630d880b2993a9724f01ae25f33b4ea5aa9631d", "codex.py": "904e75503cd35f16cbb052f66806b3879fe25bfc9f99e33b93c889d862c46324", "common.py": "7696116dd1a796666518b4c5d2aa3cafa04ee974593d3636333cbe5385bd6ccb", "docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "examiner.py": "8cdffcdd52f043c905f896697403380af95bf485dd4a5edca24f7956e7795ffe", "forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "harness.py": "3cbb90fd3187e700b5df32e5daafb20313d49bb5721c826e3033cbc6aa6e3825", "interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "penalties.py": "b82704e7f47d3dfdf6e501452d7e0abca1f9da63307093d2e257e32358be0489", "platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "pr.py": "2b6bfea0634703469605ce114f9274716b485852d9a55d9185c39893b14e4726", "preflight.py": "448c3120ab64b625abae3891be686c7a214ce4211f7cf651fd90e12c0b298433", "process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "querytypes.py": "b645f489a2abc27762b4a9bbf4917e72f7b46dc053a74c0dca4a8fc46491b3ef", "replay_calibration.py": "3b6f3a289cc8a7f5e458f62bfa2c6cc534cc9076ba3f22d1e4bd8a5f9e175317", "runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "smoke_check.py": "bd6266367e6b769a95258eb383239b89a22deae406d64f6e142c77396f4639ba", "stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "submission.py": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tasks/1c-platform-official-sample/checks.json": "17a6fcc0c14410829650623eb1443ce99796e000cdfd19905ac0287988b73a00", "tasks/1c-platform-official-sample/private/official-assessment-mapping.json": "303587c0dabe77c1eeebb2017fe85539e3370b17c9090435e6e0325a66bd0644", "tasks/1c-platform-official-sample/private/owner-scoring-policy.json": "d26d534bb838ab1b5facb7bc033ca8ec40912133baadcdbad83b27fc577905f5", "starters/carcass-8.3.25.1445/starter.json": "0f7a7060885ba99a19402bfc6e63cc8fe979b0f491b040d3a01d5d21b304b3a6", "rules/1c-specialist-platform/rules.json": "7ec895a7751ef17f4a50cc80b5f7fa986e1e04360ab0b4ce9aa29115195df03c", "rules/1c-specialist-platform/examiner.json": "1247486ddd412d600db88d9c1db4ba501fc1994afd1dc2ebe85402fcc332f4c8", "rules/1c-specialist-platform/chistov.json": "800da27601a3f1c7ec1df64482fd4ad035e559ba0b390a274ed5031128487d3d", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" }, "sha256": "4a12b62d2c10085e1fc710f377f84903abdf2fb787dda19628d944da990a86b2" }, "identity_verified_at": "2026-10-26T18:44:22.364471+00:00", "identity_session_sha256": "950670ab9a82059c65525d0d6e5b8a00f0dc292581edea3eb087c4ecadeaab09", "completed_at": "2026-10-26T18:53:24.876564+00:00" } }, { "id": "demo-20261025T112622Z-adapter", "run_id": "demo-20261024T065406Z-45954e", "result": { "run_id": "demo-20261024T065406Z-45954e", "created_at": "2026-10-25T11:30:13.995411+00:00", "model": "gpt-6.1-sol", "harness": "none", "solve_seconds": 3470, "platform": "8.3.27.1644", "counts": { "pass": 64, "fail": 1 }, "rules": [ { "id": "BU01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU16", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU17", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU02", "verdict": "pass", "coverage": "partial", "reason": null }, { "id": "BU10", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU12", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU06", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU07", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU08", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU09", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU11", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU14", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU15", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU13", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU15", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU16", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU17", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU02", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU18", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU14", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU06", "verdict": "pass", "coverage": "no_violation_found", "reason": null }, { "id": "OU07", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU08", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU09", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU10", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU11", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU12", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU13", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU19", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU20", "verdict": "fail", "coverage": "selected_fixture", "reason": "Ведомость не прошла проверку группировки по значениям характеристик." }, { "id": "OU21", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR02", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR06", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR07", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR08", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR09", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR10", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR11", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR12", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR13", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR14", "verdict": "pass", "coverage": "no_violation_found", "reason": null }, { "id": "PR15", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR16", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR17", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR18", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR19", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F02", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "G01", "verdict": "pass", "coverage": "static_sources", "reason": null }, { "id": "G02", "verdict": "pass", "coverage": "static_sources", "reason": null }, { "id": "G03", "verdict": "pass", "coverage": "static_sources", "reason": null } ], "charges": [ { "id": "F1C-GEN03", "points": "0.5", "reason": "Ведомость не прошла проверку группировки по значениям характеристик." }, { "id": "F1C-GEN15", "points": "0.5", "reason": "Reports/Премии/Ext/ManagerModule.bsl:3 — РегистрРасчета.Начисления: отбор по ВидРасчета, ПериодДействияНачало, индексы таблицы начинаются с ПериодДействия, ПериодРегистрации, Подразделение, Регистратор, Сотрудник" }, { "id": "F1C-GEN14", "points": "1.5", "reason": "Reports/ПродажиБУ/Ext/ManagerModule.bsl:3 — РегистрБухгалтерии.Хозрасчетный: итоги считаются по основной таблице регистра, а не по виртуальной" }, { "id": "F1C-PR14", "points": "0.5", "reason": "после расчёта набор с периодом действия перезаписывается целиком, с пересчётом фактического периода действия (нужно Записать(, Истина)): CommonModules/РасчетыЗарплаты/Ext/Module.bsl:56 Набор.Записать(); CommonModules/РасчетыЗарплаты/Ext/Module.bsl:111 Набор.Записать(); CommonModules/РасчетыЗарплаты/Ext/Module.bsl:126 Пара.Значение.Записать(); CommonModules/РасчетыЗарплаты/Ext/Module.bsl:153 Пара.Значение.Записать()" }, { "id": "F1C-BU05", "points": "0.5", "reason": "аналитика счетов вынесена в измерения регистра бухгалтерии и есть у всех счетов: Номенклатура (Номенклатура)" }, { "id": "F1C-GEN20", "points": "2.0", "reason": "данные базы читаются в цикле по записям: CommonModules/Учет/Ext/Module.bsl:177; CommonModules/Учет/Ext/Module.bsl:236" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "оперативное проведение разрешено у документов с движениями по регистрам расчёта: НачислениеЗарплаты" }, { "id": "F1C-GEN22", "points": "1.0", "reason": "значения графика выбираются без ЕСТЬNULL: CommonModules/РасчетыЗарплаты/Ext/Module.bsl:47 ЗначениеПериодДействия; CommonModules/РасчетыЗарплаты/Ext/Module.bsl:83 ДниФактическийПериодДействия, ЗначениеПериодДействия, ЗначениеФактическийПериодДействия" } ], "score_upper_bound": "-2.5", "score": null, "grade": "unsatisfactory", "deductions": "7.5", "not_assessed": 14, "gates": { "starter_origin": "passed", "load": "loaded", "clients": "compiles", "demo_data": "present" }, "infrastructure_errors": false, "comparison_eligible": false, "binding_compatibility": { "scope": "supplemental_named_subconto_adapter", "original_binding_sha256": "7453f6ba6c67aaa1a3e183d4e7ab50cf384761713dfaf6c9602b444316874a6a", "normalized_binding_sha256": "5bf5c5f62324cd2e03d4a77ce9279e3dcfd379809eb7d04b7d5cbc58485885da", "normalizer_sha256": "7327277143d80a531e4c254ac74a9fc0e0d5c76572d53b8469e0a580eda17d65", "canonical_ledger_sha256": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "changes": [ { "field": "fields.ledger.warehouse_debit", "before": "Склады", "after": "ВидыСубконто.Склады", "kind": "named" }, { "field": "fields.ledger.warehouse_credit", "before": "Склады", "after": "ВидыСубконто.Склады", "kind": "named" } ], "basis": "kind names expanded only to exactly one predefined kind of the account chart on the role side; all role types checked." }, "evaluation_sha256": "9e726ff2099d866aa8db13872a661627933b8772934a4d8e955538dacac0500e", "downloads": [] }, "measurement": { "operator": { "name": "Вячеслав", "github": "sksibak" }, "environment": { "captured_at": "2026-10-24T06:54:09.737798+00:00", "capture_timing": "before_run", "hardware": { "cpu": "AMD Ryzen 5 4600H with Radeon Graphics ", "logical_cpus": 12, "ram_bytes": 16505962496 }, "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "python": "3.12.14", "platform_version": "8.3.27.1644", "isolation": "dedicated-host", "network_profile": "open-book_shell", "unsafe_action_protection_observed_in_user_config": true, "git_revision": "af85e791b303dbbf0b0b7af924d2489c3e57cfa8", "implementation_files": { "exam_bench/__init__.py": "ad5bf6f05dc6765f40b78bd186870ca2c49be113cfa33f8aa76f4926f2cb2c1e", "exam_bench/assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "exam_bench/bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "exam_bench/calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "exam_bench/calibrate.py": "78b5185cb0888c0c0ac3de95ffc3a80154a6de9ae66fc461f79d012e5a58e1db", "exam_bench/calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "exam_bench/calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "exam_bench/calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "exam_bench/calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "exam_bench/calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "exam_bench/claude.py": "bc1b8550de7573aaed5e39c6e9c0309e0d8175284a75490d61ec27439ed911ad", "exam_bench/cli.py": "1a37ce645633d761f7897dffc9c45e6b8b9600cd7bd233b1cbf78f49d26b099a", "exam_bench/codescan.py": "751e38001b6e65727a31e28172a0623f0bf34bc092a958037c286aa991a197ed", "exam_bench/codex.py": "c3f89d72af11f312d851c73a1610d92e79acadf336be9ccedd1f94ede3b3ccb0", "exam_bench/common.py": "8682603b519063e655eae3574a02a49efee63bde21f582ccee20ddd623fca96d", "exam_bench/docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "exam_bench/examiner.py": "d7294fdd23ed1732216cafebf0a8cf2c24cce4259859aeb7149f62b7607d087d", "exam_bench/finalize.py": "4034f1c63896a940afdb1a83d541cf47fc75c8b5061e3f839047109c04beb620", "exam_bench/forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "exam_bench/gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "exam_bench/grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "exam_bench/harness.py": "3040f6daaf1dc6e6583219f4d925151f8ba7851b2d5417d7f14645892b485ddf", "exam_bench/interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "exam_bench/interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "exam_bench/isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "exam_bench/ledger.py": "7e851523580e22d8490e75f9b6026c07f2c355007e0d11d0b252671f56bef654", "exam_bench/locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "exam_bench/materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "exam_bench/mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "exam_bench/observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "exam_bench/ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "exam_bench/penalties.py": "0d79e2e46102657dca00609b6abbfc0bf7d11fad41429564f876c82bc6b33269", "exam_bench/platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "exam_bench/portable.py": "cad56968ff407983608f5bdbc9ce7234128d7a4580b096ecea8e0e7b4edb9070", "exam_bench/portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "exam_bench/pr.py": "6a3a20caf0e10c0cc94410511a72d62c9fcda785f3abab1be2ad616d4ee16836", "exam_bench/preflight.py": "5619be0131d8641925f3ce2a3c8e5234d42aa5635d95676138ca81536d95cd29", "exam_bench/process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "exam_bench/queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "exam_bench/queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "exam_bench/replay_calibration.py": "c150457b0b23ce4e6814eb8deb4d48f6bc4a2e39d8f84a9dc7644fb99a026c2d", "exam_bench/report.py": "5e4c0757e1c7f189953f9a5302593ab726551835856baed25efd93dad6e8bfcd", "exam_bench/runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "exam_bench/smoke_check.py": "f36922a0027429ead0b414048dcc14bbe67f2f0e79a70d03dffbe1447d253545", "exam_bench/stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "exam_bench/submission.py": "ea862adc63ae67861ddb1d6aeb4d92c10b0b05004d22953f7b03612f82bb4bf4", "exam_bench/telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "exam_bench/windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "exam_bench/workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tools/build_public_site.py": "9682ed696f5ac9e9a82b65a45c0dece556ec7e49eeb20dcd616882cc534a8258", "tools/build_result_site.py": "3294e1d2ec1486058e208735264d61e349a68a4ae2fa2ec7a723c70e3263b496", "tools/check_native_harnesses.py": "4f5f0ed27651f78758eaef077b3b114361781f6b95ec40cb46c3fea689210473", "tools/check_native_toolkit.py": "0272794617121f2932828e5e4e9ae20095183c443666cf3ba466b44fbe875095", "tools/community_results.py": "cbfba30b4e617f5e219637c1c2de57398d01eb2f284eae3aca3ef684e6505a39", "tools/community_service.py": "c374480dbd88d656c0b9054fa04a8e1c6698c69e2f9cf475e82498a2dff61d84", "tools/community_setup.py": "5d7d126ed7d4dd48e1d79f57b99647a92ffcc8c9f80d90915e458888cdd76bf7", "tools/compare_harness_runs.py": "f274df5f3f804cb02504491aec946943833e12fbce6e62d281e12beb8508fc4e", "tools/create_run_plan.py": "871cd81b1eda231c0fba8805f63d2668926be9fc641559e6ddf320e2f47cd37a", "tools/demo_runner.py": "ca7ad17919c53d524cc0418751ba09a540f910eac183dca2961710bc30bba26f", "tools/installers.py": "9a2742780936b17500869e7c89202c1a2549e37d53a42ad9a50a0abbf78bbe09", "tools/machine_bundle.py": "8aa8346f99f537e81ceca6fb6ab9530e844954bab8eff87bf33d3602f81f8a30", "tools/prepare_native_harnesses.py": "aaa75ecf4022883984fa50c42d14d8e1a9fde2eeda03dab03b852bbc5efb2502", "tools/prepare_official_statement.py": "6b7028c78e90e798d6ef1a93b76520cc61a308c354fb9b87f7fad18b99800fad", "tools/prepare_open_exam_requirements.py": "544f4e378b9be5f166186f8788f8d454afdac2deb99d91d98421e39d01ba6d03", "tools/probe_harness.py": "1ed8ef93420d1484cbbfd151b7efc31b9a201ceb942dd05e3103efa22ffa7f27", "tools/probe_native_mcp.py": "9918d324129cba898993e07f8f8b6dbcbaf369398ebf28d464f9f1f00abdb254", "tools/readiness.py": "d34dd3f38334f51cc4574c79194cf0b80769b062a52382989a57d01c46b9aba4", "tools/recheck_community.py": "f0843d7d677f90da31e22bde0b1c86584dd46c022f1532d43d042619e426b230", "tools/regrade_runs.py": "011775afb06d3aac67a4aa81117a368c75896b0fcbe1e6f27ccc6237612fbf59", "tools/render_statement_text.py": "dabc0716a3612c288c671bc20e17fd4986691d732768e1e957d6dddddbea92a3", "tools/replay_calibration.py": "801f5004926c438c21ed3668fe2a4ddf45312b3e75320165a3839aae034eee9b", "tools/run_exam_campaign.py": "2c450d57a1cd0a2682838f5ec7c0a4ffb3aed0f1730d34c408e912d59cab6efd", "tools/serve_result_site.py": "86badfac863cd4ad1fc894a14110c75b28470513f0133eeae9d2799b8b4df3a9", "tools/start_demo.py": "c597e6cad28d245b3191654bb3e2801fa9dd2364e2acb25561923613717b615f", "tools/supplemental_acceptance.py": "c88fc39de1be1fdcacdd819e2ad329f60367b2df1d5deda80b37324bda3f2a01", "tools/sync_sources.py": "b51e889b0f41f9f63bfb19a09fb96d3777693d6b1d76fe0132bdd2a15e155898", "tools/validate_community_pr.py": "796b896dfade07b4529af2088a4b9b9d23484148b3bc0732b3fb837b75c9844b", "tools/verify_official_assessment_mapping.py": "daeb448a016940d5b6b1285979a56e5b9014bd91db40acb131445e4a83a23059", "tools/verify_task_package.py": "9e1e6105f6b5e4e78b36aa57f00117a9fbc8948ab53983c32ab56da88d23ccc4", "profiles/agents.json": "af9c492c08d13b3044aa6b6952589ed6a0a07d5258d8ff72bb18185b3eaebdc5", "profiles/ai-exam-execution-policy.json": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "profiles/bsl-analyzer-0.3.2-macos.json": "83537abdbf38c41ce665e4d0f24128bb51b62e971e0e0f368695f1326a7d2ffb", "profiles/bsl-analyzer-0.3.2-portable.json": "d6ba732e6778e256df34d6bc548593128820a70430c35b279796843606ee40a8", "profiles/bsl-ls-1.1.0-rc.6-macos.json": "245fc10747197e6911b2b4c77cdb15e6fa4eb7bc7c3758b63e768c5adf1df180", "profiles/bsl-ls-1.1.0-rc.6-portable.json": "9f10660881f2ec84794f7d584556b8f75c7e14b3555464af0ed0e60c4c892d86", "profiles/code-index-1.9.0-macos.json": "63a919523ce62ecec274f4c139bc7ad49a75dd4c339568b822cbc695b4e30408", "profiles/code-index-1.9.0-portable.json": "81106cee8f424ffd8a9dc46ecd8e4f57598fc1d49661a83c77b1f0507993fbdc", "profiles/codex-probe-plan.json": "166e41aad5fb3b27d9050bc6de952c6cba363cc6e804d4080568cc71a2a4d289", "profiles/machine.linux.example.json": "408304fd0581098d5d8110dc67dfeab353bc4d4030e32d37e6acf98d2b1aedfd", "profiles/machine.macos.example.json": "52e9f9d17797cb520b9d8955d6806fd550b899bed4da241ebf096dcb6a21a942", "profiles/machine.windows.example.json": "63accac9a2f81d47d03447efbabffd4760aee325193f02f46b9b29a28d50d2d8", "profiles/mcp-toolkit-1.9.0-macos.json": "1d3f9cde5ffa20589a840d01fdae03aa0fc2f412c929f064f203919c4129625b", "profiles/mcp-toolkit-1.9.0-portable.json": "8e370eebe773eef0e08045ee9c6d5be1451f769f65be0710834b262a4336e054", "profiles/none-macos.json": "b1401d9c48159aed3559006c7f6ace6ef4571224d5cf0bb76d1a823505a10056", "profiles/none-portable.json": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "profiles/rlm-tools-bsl-1.43.0-macos.json": "9354421052640ab60bc3e6aa98ff2e7ba9ca2318b0f4026c137487449242cbd2", "profiles/rlm-tools-bsl-1.43.0-portable.json": "2599e5645e0a7d4e44cb2934bc2b272cae79a9bf7ea74a23cd48aacea64bc424", "profiles/rlm-tools-bsl-1.43.0-posix-requirements.txt": "4fdf9a1bd994bf0272e65d231daf76cf19b0a34dad0ae6b50ec4f11a2ce4c330", "profiles/rlm-tools-bsl-1.43.0-windows-requirements.txt": "3730cb46c81cda5181ecd4485e98b11933104632358bc86f8c0eb1a612a8954f", "profiles/shirokov-skills-macos.json": "84f3e89091676884a802035c707e912762a1179425fb8e3faff25be736873cdb", "profiles/shirokov-skills-portable.json": "2b0a461e06602f1456410e70f02ceaa5ac32c6549c486660bcb5ace0c2f87b15", "profiles/shirokov-skills-windows-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/unica-0.12.3-macos.json": "2c39fbb591cf2c2c6e056373823615485397ea83651b7926c6f25a5fe6a0aae6", "profiles/unica-0.13.0-macos.json": "b76b5c8a4dd33f571c4a90993f1a2da5f7223b4f0f8e1042c282e21a66121052", "profiles/unica-0.14.0-rc.1-portable.json": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "rules/1c-specialist-platform/chistov.json": "77e04942f8c947b10759e7cc1eb31af05847d1711a772fbe6f23d525766757a9", "rules/1c-specialist-platform/decisions.json": "f622107423ce3c188c063318d7ab4f7718ceb38e443130677d8987f386641c09", "rules/1c-specialist-platform/examiner.json": "30353aa2a1b6545496b070d9066e9ffba0c3779e5b53ef70a4fd2cee375b18c0", "rules/1c-specialist-platform/ledger.json": "f167c10db2b5799dd9a1ea6a37cd2d7d186810dadf5ea2f50f26ae723c676882", "rules/1c-specialist-platform/rules.json": "1d320a4f8e1bf4701496388931f492315549bd3dce574b17285dd1d7f8652007", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" } } }, "conditions": { "client": "codex", "model": "gpt-6.1-sol", "client_version": "0.163.0-alpha.11.2", "reasoning_effort": "medium", "harness": "none", "billing_channel": "subscription", "solve_timeout_seconds": 3600, "time_series": null, "delegation": "native_disabled", "network_profile": "open-book_shell", "deadline_disclosed": true, "statement_sha256": "8a6ccb3e673826d1f8220fda53eb310e3ec18c136d87ce8f4cebb2a08614e7e5", "starter_dt_sha256": "f40d084818b0d1cfe503fc7653a6a13f1a8e47fcd1688dad6245b12744eb4638", "profile_sha256": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "execution_policy_sha256": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "calibration_sha256": "eced5b2f738ff558afe3d33d03048cf7b3ad00fa4e418c6a0ed72f885d0d221c", "started_at": "2026-10-24T06:54:17.179192+00:00", "timing": { "prepare_ms": 6781, "solve_ms": 3469985, "grade_ms": null }, "original_submission_valid": false, "model_provenance": "requested_only", "tokens": { "input": 16145325, "cached_input": 16011264, "fresh_input": 134061, "output": 117438, "reasoning_output": 43285, "total": 16262763, "coverage": "reported_completed_root_turns" }, "tools": { "mcp_calls": 0, "unica_calls": 0, "failed_calls": 0 }, "process": { "status": "completed", "exit_code": 0, "stop_confirmed": true } }, "verification": "contributor_reported", "download": "community-downloads/demo-20261025T112622Z-adapter/solution.zip", "source_context": "community-downloads/demo-20261025T112622Z-adapter/source-context.json", "regrade_required": [ { "id": "grader_changed", "files": [ "assessment.py", "bp.py", "calcwrite.py", "calibrate.py", "calibration_periodicity.py", "calibration_query.py", "claude.py", "codescan.py", "codex.py", "common.py", "docx_text.py", "examiner.py", "harness.py", "interpretations.py", "locking.py", "materials.py", "mcp_toolkit.py", "ou.py", "penalties.py", "portable_harnesses.py", "pr.py", "preflight.py", "queries.py", "queryschema.py", "querytypes.py", "replay_calibration.py", "rules/1c-specialist-platform/chistov.json", "rules/1c-specialist-platform/examiner.json", "rules/1c-specialist-platform/rules.json", "rules/1c-specialist-platform/standards.json", "smoke_check.py", "starters/carcass-8.3.25.1445/starter.json", "stdio_harnesses.py", "tasks/1c-platform-official-sample/checks.json", "tasks/1c-platform-official-sample/private/official-assessment-mapping.json", "tasks/1c-platform-official-sample/private/owner-scoring-policy.json", "telemetry.py" ] } ], "grader_revision_sha256": "855d4f66db31ec9f50ebfc18f596c0d1d157e53e2830c51f853c1338f628e49c", "archive_sha256": "54f902f52cb7b3edacdeb8f0a53722021ae2fc4604e0c86af92f6f2d76161b7b" }, { "id": "demo-20261024T094837Z-recheck-2", "run_id": "demo-20261024T065406Z-45954e", "result": { "run_id": "demo-20261024T065406Z-45954e", "created_at": "2026-10-24T09:52:11.522302+00:00", "model": "gpt-6.1-sol", "harness": "none", "solve_seconds": 3470, "platform": "8.3.27.1644", "counts": { "pass": 64, "fail": 1 }, "rules": [ { "id": "BU01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU16", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU17", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU02", "verdict": "pass", "coverage": "partial", "reason": null }, { "id": "BU10", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU12", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU06", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU07", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU08", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU09", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU11", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU14", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU15", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU13", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU15", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU16", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU17", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU02", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU18", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU14", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU06", "verdict": "pass", "coverage": "no_violation_found", "reason": null }, { "id": "OU07", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU08", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU09", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU10", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU11", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU12", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU13", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU19", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU20", "verdict": "fail", "coverage": "selected_fixture", "reason": "Ведомость не прошла проверку группировки по значениям характеристик." }, { "id": "OU21", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR02", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR06", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR07", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR08", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR09", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR10", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR11", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR12", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR13", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR14", "verdict": "pass", "coverage": "no_violation_found", "reason": null }, { "id": "PR15", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR16", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR17", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR18", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR19", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F02", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "G01", "verdict": "pass", "coverage": "static_sources", "reason": null }, { "id": "G02", "verdict": "pass", "coverage": "static_sources", "reason": null }, { "id": "G03", "verdict": "pass", "coverage": "static_sources", "reason": null } ], "charges": [ { "id": "F1C-GEN03", "points": "0.5", "reason": "Ведомость не прошла проверку группировки по значениям характеристик." }, { "id": "F1C-GEN15", "points": "0.5", "reason": "Reports/Премии/Ext/ManagerModule.bsl:3 — РегистрРасчета.Начисления: отбор по ВидРасчета, ПериодДействияНачало, индексы таблицы начинаются с ПериодДействия, ПериодРегистрации, Подразделение, Регистратор, Сотрудник" }, { "id": "F1C-GEN14", "points": "1.5", "reason": "Reports/ПродажиБУ/Ext/ManagerModule.bsl:3 — РегистрБухгалтерии.Хозрасчетный: итоги считаются по основной таблице регистра, а не по виртуальной" }, { "id": "F1C-PR14", "points": "0.5", "reason": "после расчёта набор с периодом действия перезаписывается целиком, с пересчётом фактического периода действия (нужно Записать(, Истина)): CommonModules/РасчетыЗарплаты/Ext/Module.bsl:56 Набор.Записать(); CommonModules/РасчетыЗарплаты/Ext/Module.bsl:111 Набор.Записать(); CommonModules/РасчетыЗарплаты/Ext/Module.bsl:126 Пара.Значение.Записать(); CommonModules/РасчетыЗарплаты/Ext/Module.bsl:153 Пара.Значение.Записать()" }, { "id": "F1C-BU05", "points": "0.5", "reason": "аналитика счетов вынесена в измерения регистра бухгалтерии и есть у всех счетов: Номенклатура (Номенклатура)" }, { "id": "F1C-GEN20", "points": "2.0", "reason": "данные базы читаются в цикле по записям: CommonModules/Учет/Ext/Module.bsl:177; CommonModules/Учет/Ext/Module.bsl:236" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "оперативное проведение разрешено у документов с движениями по регистрам расчёта: НачислениеЗарплаты" }, { "id": "F1C-GEN22", "points": "1.0", "reason": "значения графика выбираются без ЕСТЬNULL: CommonModules/РасчетыЗарплаты/Ext/Module.bsl:47 ЗначениеПериодДействия; CommonModules/РасчетыЗарплаты/Ext/Module.bsl:83 ДниФактическийПериодДействия, ЗначениеПериодДействия, ЗначениеФактическийПериодДействия" } ], "score_upper_bound": "-2.5", "score": null, "grade": "unsatisfactory", "deductions": "7.5", "not_assessed": 14, "gates": { "starter_origin": "passed", "load": "loaded", "clients": "compiles", "demo_data": "present" }, "infrastructure_errors": false, "comparison_eligible": false, "binding_compatibility": null, "evaluation_sha256": "37f6d9b62389e6b637b85f2a17334a4898673be609f6f1b8bcd3875ffb5109ee", "downloads": [] }, "measurement": { "operator": { "name": "Вячеслав", "github": "sksibak" }, "environment": { "captured_at": "2026-10-24T06:54:09.737798+00:00", "capture_timing": "before_run", "hardware": { "cpu": "AMD Ryzen 5 4600H with Radeon Graphics ", "logical_cpus": 12, "ram_bytes": 16505962496 }, "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "python": "3.12.14", "platform_version": "8.3.27.1644", "isolation": "dedicated-host", "network_profile": "open-book_shell", "unsafe_action_protection_observed_in_user_config": true, "git_revision": "af85e791b303dbbf0b0b7af924d2489c3e57cfa8", "implementation_files": { "exam_bench/__init__.py": "ad5bf6f05dc6765f40b78bd186870ca2c49be113cfa33f8aa76f4926f2cb2c1e", "exam_bench/assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "exam_bench/bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "exam_bench/calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "exam_bench/calibrate.py": "78b5185cb0888c0c0ac3de95ffc3a80154a6de9ae66fc461f79d012e5a58e1db", "exam_bench/calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "exam_bench/calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "exam_bench/calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "exam_bench/calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "exam_bench/calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "exam_bench/claude.py": "bc1b8550de7573aaed5e39c6e9c0309e0d8175284a75490d61ec27439ed911ad", "exam_bench/cli.py": "1a37ce645633d761f7897dffc9c45e6b8b9600cd7bd233b1cbf78f49d26b099a", "exam_bench/codescan.py": "751e38001b6e65727a31e28172a0623f0bf34bc092a958037c286aa991a197ed", "exam_bench/codex.py": "c3f89d72af11f312d851c73a1610d92e79acadf336be9ccedd1f94ede3b3ccb0", "exam_bench/common.py": "8682603b519063e655eae3574a02a49efee63bde21f582ccee20ddd623fca96d", "exam_bench/docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "exam_bench/examiner.py": "d7294fdd23ed1732216cafebf0a8cf2c24cce4259859aeb7149f62b7607d087d", "exam_bench/finalize.py": "4034f1c63896a940afdb1a83d541cf47fc75c8b5061e3f839047109c04beb620", "exam_bench/forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "exam_bench/gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "exam_bench/grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "exam_bench/harness.py": "3040f6daaf1dc6e6583219f4d925151f8ba7851b2d5417d7f14645892b485ddf", "exam_bench/interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "exam_bench/interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "exam_bench/isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "exam_bench/ledger.py": "7e851523580e22d8490e75f9b6026c07f2c355007e0d11d0b252671f56bef654", "exam_bench/locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "exam_bench/materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "exam_bench/mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "exam_bench/observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "exam_bench/ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "exam_bench/penalties.py": "0d79e2e46102657dca00609b6abbfc0bf7d11fad41429564f876c82bc6b33269", "exam_bench/platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "exam_bench/portable.py": "cad56968ff407983608f5bdbc9ce7234128d7a4580b096ecea8e0e7b4edb9070", "exam_bench/portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "exam_bench/pr.py": "6a3a20caf0e10c0cc94410511a72d62c9fcda785f3abab1be2ad616d4ee16836", "exam_bench/preflight.py": "5619be0131d8641925f3ce2a3c8e5234d42aa5635d95676138ca81536d95cd29", "exam_bench/process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "exam_bench/queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "exam_bench/queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "exam_bench/replay_calibration.py": "c150457b0b23ce4e6814eb8deb4d48f6bc4a2e39d8f84a9dc7644fb99a026c2d", "exam_bench/report.py": "5e4c0757e1c7f189953f9a5302593ab726551835856baed25efd93dad6e8bfcd", "exam_bench/runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "exam_bench/smoke_check.py": "f36922a0027429ead0b414048dcc14bbe67f2f0e79a70d03dffbe1447d253545", "exam_bench/stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "exam_bench/submission.py": "ea862adc63ae67861ddb1d6aeb4d92c10b0b05004d22953f7b03612f82bb4bf4", "exam_bench/telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "exam_bench/windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "exam_bench/workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tools/build_public_site.py": "9682ed696f5ac9e9a82b65a45c0dece556ec7e49eeb20dcd616882cc534a8258", "tools/build_result_site.py": "3294e1d2ec1486058e208735264d61e349a68a4ae2fa2ec7a723c70e3263b496", "tools/check_native_harnesses.py": "4f5f0ed27651f78758eaef077b3b114361781f6b95ec40cb46c3fea689210473", "tools/check_native_toolkit.py": "0272794617121f2932828e5e4e9ae20095183c443666cf3ba466b44fbe875095", "tools/community_results.py": "cbfba30b4e617f5e219637c1c2de57398d01eb2f284eae3aca3ef684e6505a39", "tools/community_service.py": "c374480dbd88d656c0b9054fa04a8e1c6698c69e2f9cf475e82498a2dff61d84", "tools/community_setup.py": "5d7d126ed7d4dd48e1d79f57b99647a92ffcc8c9f80d90915e458888cdd76bf7", "tools/compare_harness_runs.py": "f274df5f3f804cb02504491aec946943833e12fbce6e62d281e12beb8508fc4e", "tools/create_run_plan.py": "871cd81b1eda231c0fba8805f63d2668926be9fc641559e6ddf320e2f47cd37a", "tools/demo_runner.py": "ca7ad17919c53d524cc0418751ba09a540f910eac183dca2961710bc30bba26f", "tools/installers.py": "9a2742780936b17500869e7c89202c1a2549e37d53a42ad9a50a0abbf78bbe09", "tools/machine_bundle.py": "8aa8346f99f537e81ceca6fb6ab9530e844954bab8eff87bf33d3602f81f8a30", "tools/prepare_native_harnesses.py": "aaa75ecf4022883984fa50c42d14d8e1a9fde2eeda03dab03b852bbc5efb2502", "tools/prepare_official_statement.py": "6b7028c78e90e798d6ef1a93b76520cc61a308c354fb9b87f7fad18b99800fad", "tools/prepare_open_exam_requirements.py": "544f4e378b9be5f166186f8788f8d454afdac2deb99d91d98421e39d01ba6d03", "tools/probe_harness.py": "1ed8ef93420d1484cbbfd151b7efc31b9a201ceb942dd05e3103efa22ffa7f27", "tools/probe_native_mcp.py": "9918d324129cba898993e07f8f8b6dbcbaf369398ebf28d464f9f1f00abdb254", "tools/readiness.py": "d34dd3f38334f51cc4574c79194cf0b80769b062a52382989a57d01c46b9aba4", "tools/recheck_community.py": "f0843d7d677f90da31e22bde0b1c86584dd46c022f1532d43d042619e426b230", "tools/regrade_runs.py": "011775afb06d3aac67a4aa81117a368c75896b0fcbe1e6f27ccc6237612fbf59", "tools/render_statement_text.py": "dabc0716a3612c288c671bc20e17fd4986691d732768e1e957d6dddddbea92a3", "tools/replay_calibration.py": "801f5004926c438c21ed3668fe2a4ddf45312b3e75320165a3839aae034eee9b", "tools/run_exam_campaign.py": "2c450d57a1cd0a2682838f5ec7c0a4ffb3aed0f1730d34c408e912d59cab6efd", "tools/serve_result_site.py": "86badfac863cd4ad1fc894a14110c75b28470513f0133eeae9d2799b8b4df3a9", "tools/start_demo.py": "c597e6cad28d245b3191654bb3e2801fa9dd2364e2acb25561923613717b615f", "tools/supplemental_acceptance.py": "c88fc39de1be1fdcacdd819e2ad329f60367b2df1d5deda80b37324bda3f2a01", "tools/sync_sources.py": "b51e889b0f41f9f63bfb19a09fb96d3777693d6b1d76fe0132bdd2a15e155898", "tools/validate_community_pr.py": "796b896dfade07b4529af2088a4b9b9d23484148b3bc0732b3fb837b75c9844b", "tools/verify_official_assessment_mapping.py": "daeb448a016940d5b6b1285979a56e5b9014bd91db40acb131445e4a83a23059", "tools/verify_task_package.py": "9e1e6105f6b5e4e78b36aa57f00117a9fbc8948ab53983c32ab56da88d23ccc4", "profiles/agents.json": "af9c492c08d13b3044aa6b6952589ed6a0a07d5258d8ff72bb18185b3eaebdc5", "profiles/ai-exam-execution-policy.json": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "profiles/bsl-analyzer-0.3.2-macos.json": "83537abdbf38c41ce665e4d0f24128bb51b62e971e0e0f368695f1326a7d2ffb", "profiles/bsl-analyzer-0.3.2-portable.json": "d6ba732e6778e256df34d6bc548593128820a70430c35b279796843606ee40a8", "profiles/bsl-ls-1.1.0-rc.6-macos.json": "245fc10747197e6911b2b4c77cdb15e6fa4eb7bc7c3758b63e768c5adf1df180", "profiles/bsl-ls-1.1.0-rc.6-portable.json": "9f10660881f2ec84794f7d584556b8f75c7e14b3555464af0ed0e60c4c892d86", "profiles/code-index-1.9.0-macos.json": "63a919523ce62ecec274f4c139bc7ad49a75dd4c339568b822cbc695b4e30408", "profiles/code-index-1.9.0-portable.json": "81106cee8f424ffd8a9dc46ecd8e4f57598fc1d49661a83c77b1f0507993fbdc", "profiles/codex-probe-plan.json": "166e41aad5fb3b27d9050bc6de952c6cba363cc6e804d4080568cc71a2a4d289", "profiles/machine.linux.example.json": "408304fd0581098d5d8110dc67dfeab353bc4d4030e32d37e6acf98d2b1aedfd", "profiles/machine.macos.example.json": "52e9f9d17797cb520b9d8955d6806fd550b899bed4da241ebf096dcb6a21a942", "profiles/machine.windows.example.json": "63accac9a2f81d47d03447efbabffd4760aee325193f02f46b9b29a28d50d2d8", "profiles/mcp-toolkit-1.9.0-macos.json": "1d3f9cde5ffa20589a840d01fdae03aa0fc2f412c929f064f203919c4129625b", "profiles/mcp-toolkit-1.9.0-portable.json": "8e370eebe773eef0e08045ee9c6d5be1451f769f65be0710834b262a4336e054", "profiles/none-macos.json": "b1401d9c48159aed3559006c7f6ace6ef4571224d5cf0bb76d1a823505a10056", "profiles/none-portable.json": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "profiles/rlm-tools-bsl-1.43.0-macos.json": "9354421052640ab60bc3e6aa98ff2e7ba9ca2318b0f4026c137487449242cbd2", "profiles/rlm-tools-bsl-1.43.0-portable.json": "2599e5645e0a7d4e44cb2934bc2b272cae79a9bf7ea74a23cd48aacea64bc424", "profiles/rlm-tools-bsl-1.43.0-posix-requirements.txt": "4fdf9a1bd994bf0272e65d231daf76cf19b0a34dad0ae6b50ec4f11a2ce4c330", "profiles/rlm-tools-bsl-1.43.0-windows-requirements.txt": "3730cb46c81cda5181ecd4485e98b11933104632358bc86f8c0eb1a612a8954f", "profiles/shirokov-skills-macos.json": "84f3e89091676884a802035c707e912762a1179425fb8e3faff25be736873cdb", "profiles/shirokov-skills-portable.json": "2b0a461e06602f1456410e70f02ceaa5ac32c6549c486660bcb5ace0c2f87b15", "profiles/shirokov-skills-windows-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/unica-0.12.3-macos.json": "2c39fbb591cf2c2c6e056373823615485397ea83651b7926c6f25a5fe6a0aae6", "profiles/unica-0.13.0-macos.json": "b76b5c8a4dd33f571c4a90993f1a2da5f7223b4f0f8e1042c282e21a66121052", "profiles/unica-0.14.0-rc.1-portable.json": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "rules/1c-specialist-platform/chistov.json": "77e04942f8c947b10759e7cc1eb31af05847d1711a772fbe6f23d525766757a9", "rules/1c-specialist-platform/decisions.json": "f622107423ce3c188c063318d7ab4f7718ceb38e443130677d8987f386641c09", "rules/1c-specialist-platform/examiner.json": "30353aa2a1b6545496b070d9066e9ffba0c3779e5b53ef70a4fd2cee375b18c0", "rules/1c-specialist-platform/ledger.json": "f167c10db2b5799dd9a1ea6a37cd2d7d186810dadf5ea2f50f26ae723c676882", "rules/1c-specialist-platform/rules.json": "1d320a4f8e1bf4701496388931f492315549bd3dce574b17285dd1d7f8652007", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" } } }, "conditions": { "client": "codex", "model": "gpt-6.1-sol", "client_version": "0.163.0-alpha.11.2", "reasoning_effort": "medium", "harness": "none", "billing_channel": "subscription", "solve_timeout_seconds": 3600, "time_series": null, "delegation": "native_disabled", "network_profile": "open-book_shell", "deadline_disclosed": true, "statement_sha256": "8a6ccb3e673826d1f8220fda53eb310e3ec18c136d87ce8f4cebb2a08614e7e5", "starter_dt_sha256": "f40d084818b0d1cfe503fc7653a6a13f1a8e47fcd1688dad6245b12744eb4638", "profile_sha256": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "execution_policy_sha256": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "calibration_sha256": "eced5b2f738ff558afe3d33d03048cf7b3ad00fa4e418c6a0ed72f885d0d221c", "started_at": "2026-10-24T06:54:17.179192+00:00", "timing": { "prepare_ms": 6781, "solve_ms": 3469985, "grade_ms": null }, "original_submission_valid": false, "model_provenance": "requested_only", "tokens": { "input": 16145325, "cached_input": 16011264, "fresh_input": 134061, "output": 117438, "reasoning_output": 43285, "total": 16262763, "coverage": "reported_completed_root_turns" }, "tools": { "mcp_calls": 0, "unica_calls": 0, "failed_calls": 0 }, "process": { "status": "completed", "exit_code": 0, "stop_confirmed": true } }, "verification": "contributor_reported", "download": "community-downloads/demo-20261024T094837Z-recheck-2/solution.zip", "source_context": "community-downloads/demo-20261024T094837Z-recheck-2/source-context.json", "regrade_required": [ { "id": "grader_changed", "files": [ "assessment.py", "bp.py", "calcwrite.py", "calibrate.py", "calibration_periodicity.py", "calibration_query.py", "claude.py", "codescan.py", "codex.py", "common.py", "docx_text.py", "examiner.py", "harness.py", "interpretations.py", "locking.py", "materials.py", "mcp_toolkit.py", "ou.py", "penalties.py", "portable_harnesses.py", "pr.py", "preflight.py", "queries.py", "queryschema.py", "querytypes.py", "replay_calibration.py", "rules/1c-specialist-platform/chistov.json", "rules/1c-specialist-platform/examiner.json", "rules/1c-specialist-platform/rules.json", "rules/1c-specialist-platform/standards.json", "smoke_check.py", "starters/carcass-8.3.25.1445/starter.json", "stdio_harnesses.py", "submission.py", "tasks/1c-platform-official-sample/checks.json", "tasks/1c-platform-official-sample/private/official-assessment-mapping.json", "tasks/1c-platform-official-sample/private/owner-scoring-policy.json", "telemetry.py" ] }, { "id": "original_submission_refused" } ], "grader_revision_sha256": "67aea0c386bf75ef0a93d941349bf739c8595bcbaddc9ca13f301d96207d20e2", "archive_sha256": "46e034f5fbf0e1f6789af8c337469c6a5e6a6221f4e2050d4e3094afb2020a1c" } ] }, { "id": "demo-20261025T110836Z-adapter--owner-2026-10-26T223255070325-0000", "run_id": "demo-20261024T095243Z-21ac56", "result": { "run_id": "demo-20261024T095243Z-21ac56", "created_at": "2026-10-26T22:32:55.070325+00:00", "model": "gpt-6.1-sol", "harness": "none", "solve_seconds": 5985, "platform": "8.3.27.1644", "counts": { "pass": 64, "fail": 1 }, "rules": [ { "id": "BU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU01.selected_fixture" }, { "id": "BU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU04.selected_fixture" }, { "id": "BU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU05.selected_fixture" }, { "id": "BU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU16.selected_fixture" }, { "id": "BU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU17.selected_fixture" }, { "id": "BU02", "verdict": "pass", "reason": null, "coverage": "partial", "assertion_id": "BU02.posting_cost_and_balance" }, { "id": "BU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU10.selected_fixture" }, { "id": "BU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU12.selected_fixture" }, { "id": "BU03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU03.selected_fixture" }, { "id": "BU06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU06.selected_fixture" }, { "id": "BU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU07.selected_fixture" }, { "id": "BU08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU08.selected_fixture" }, { "id": "BU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU09.selected_fixture" }, { "id": "BU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU11.selected_fixture" }, { "id": "BU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU14.selected_fixture" }, { "id": "BU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU15.selected_fixture" }, { "id": "BU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU13.selected_fixture" }, { "id": "OU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU15.selected_fixture" }, { "id": "OU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU16.selected_fixture" }, { "id": "OU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU17.selected_fixture" }, { "id": "OU02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU02.selected_fixture" }, { "id": "OU18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU18.selected_fixture" }, { "id": "OU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU14.selected_fixture" }, { "id": "OU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU01.selected_fixture" }, { "id": "OU03", "verdict": "pass", "reason": "История и годовая периодичность регистра подтверждены.", "coverage": "history_and_periodicity", "assertion_id": "OU03.selected_fixture" }, { "id": "OU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU05.selected_fixture" }, { "id": "OU06", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "OU06.selected_fixture" }, { "id": "OU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU07.selected_fixture" }, { "id": "OU08", "verdict": "pass", "reason": "История и дневная периодичность подтверждены; ограничение одной версии в неделю отдельно не проверяется.", "coverage": "history_and_periodicity", "assertion_id": "OU08.selected_fixture" }, { "id": "OU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU09.selected_fixture" }, { "id": "OU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU10.selected_fixture" }, { "id": "OU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU11.selected_fixture" }, { "id": "OU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU12.selected_fixture" }, { "id": "OU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU13.selected_fixture" }, { "id": "OU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU04.selected_fixture" }, { "id": "OU19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU19.selected_fixture" }, { "id": "OU20", "verdict": "fail", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU20.selected_fixture" }, { "id": "OU21", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU21.selected_fixture" }, { "id": "PR01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR01.selected_fixture" }, { "id": "PR02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR02.selected_fixture" }, { "id": "PR03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR03.selected_fixture" }, { "id": "PR04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR04.selected_fixture" }, { "id": "PR05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR05.selected_fixture" }, { "id": "PR06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR06.selected_fixture" }, { "id": "PR07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR07.selected_fixture" }, { "id": "PR08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR08.selected_fixture" }, { "id": "PR09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR09.selected_fixture" }, { "id": "PR10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR10.selected_fixture" }, { "id": "PR11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR11.selected_fixture" }, { "id": "PR12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR12.selected_fixture" }, { "id": "PR13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR13.selected_fixture" }, { "id": "PR14", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "PR14.selected_fixture" }, { "id": "PR15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR15.selected_fixture" }, { "id": "PR16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR16.selected_fixture" }, { "id": "PR17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR17.selected_fixture" }, { "id": "PR18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR18.selected_fixture" }, { "id": "PR19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR19.selected_fixture" }, { "id": "F01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F01.selected_fixture" }, { "id": "F02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F02.selected_fixture" }, { "id": "F03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F03.selected_fixture" }, { "id": "F04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F04.selected_fixture" }, { "id": "F05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F05.selected_fixture" }, { "id": "G01", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G01.static_sources" }, { "id": "G02", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G02.static_sources" }, { "id": "G03", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G03.static_sources" } ], "charges": [ { "id": "F1C-GEN03", "points": "0.5", "reason": "отчёт не соответствует заданию: OU20" }, { "id": "F1C-PR14", "points": "0.5", "reason": "после расчёта набор с периодом действия перезаписывается целиком, с пересчётом фактического периода действия (нужно Записать(, Истина)): CommonModules/Учет/Ext/Module.bsl:374 Набор.Записать()" }, { "id": "F1C-BU06", "points": "1.5", "reason": "у счёта товаров 01.02 не включён признак учёта Количественный" }, { "id": "F1C-PR08", "points": "2.0", "reason": "база берётся из основной таблицы регистра расчёта, БазаНачисления нигде не используется: Documents/НачислениеЗарплаты/Ext/ObjectModule.bsl:6" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "оперативное проведение разрешено у документов с движениями по регистрам расчёта: НачислениеЗарплаты" }, { "id": "F1C-GEN21", "points": "2.0", "reason": "данные графика без отбора по регистратору: CommonModules/Учет/Ext/Module.bsl:450" }, { "id": "F1C-GEN22", "points": "1.0", "reason": "значения графика выбираются без ЕСТЬNULL: CommonModules/Учет/Ext/Module.bsl:450 ДниФактическийПериодДействия, ЧасыПериодДействия, ЧасыФактическийПериодДействия" } ], "score_upper_bound": "-3.5", "score": null, "grade": "unsatisfactory", "deductions": "8.5", "not_assessed": 15, "gates": { "starter_origin": "passed", "load": "loaded", "clients": "compiles", "demo_data": "present" }, "infrastructure_errors": false, "comparison_eligible": false, "binding_compatibility": { "scope": "supplemental_named_subconto_adapter", "original_binding_sha256": "7dd185357a65fd5945433b73122669e0bc5b3ac46a451afc7a72002616268448", "normalized_binding_sha256": "69f3a6b98c1f598333e61ee4b543e66304e709c4de135e0aa265bf76fd8f47b8", "normalizer_sha256": "7327277143d80a531e4c254ac74a9fc0e0d5c76572d53b8469e0a580eda17d65", "canonical_ledger_sha256": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "changes": [ { "field": "fields.ledger.item_debit", "before": "СубконтоДт.Номенклатура", "after": "ВидыСубконто.Номенклатура", "kind": "named" }, { "field": "fields.ledger.item_credit", "before": "СубконтоКт.Номенклатура", "after": "ВидыСубконто.Номенклатура", "kind": "named" }, { "field": "fields.ledger.warehouse_debit", "before": "СубконтоДт.Склад", "after": "ВидыСубконто.Склад", "kind": "named" }, { "field": "fields.ledger.warehouse_credit", "before": "СубконтоКт.Склад", "after": "ВидыСубконто.Склад", "kind": "named" } ], "basis": "kind names expanded only to exactly one predefined kind of the account chart on the role side; all role types checked." } }, "measurement": { "operator": { "name": "Вячеслав", "github": "sksibak" }, "environment": { "captured_at": "2026-10-24T09:52:46.342453+00:00", "capture_timing": "before_run", "hardware": { "cpu": "AMD Ryzen 5 4600H with Radeon Graphics ", "logical_cpus": 12, "ram_bytes": 16505962496 }, "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "python": "3.12.14", "platform_version": "8.3.27.1644", "isolation": "dedicated-host", "network_profile": "open-book_shell", "unsafe_action_protection_observed_in_user_config": true, "git_revision": "af85e791b303dbbf0b0b7af924d2489c3e57cfa8", "implementation_files": { "exam_bench/__init__.py": "ad5bf6f05dc6765f40b78bd186870ca2c49be113cfa33f8aa76f4926f2cb2c1e", "exam_bench/assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "exam_bench/bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "exam_bench/calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "exam_bench/calibrate.py": "78b5185cb0888c0c0ac3de95ffc3a80154a6de9ae66fc461f79d012e5a58e1db", "exam_bench/calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "exam_bench/calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "exam_bench/calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "exam_bench/calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "exam_bench/calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "exam_bench/claude.py": "bc1b8550de7573aaed5e39c6e9c0309e0d8175284a75490d61ec27439ed911ad", "exam_bench/cli.py": "1a37ce645633d761f7897dffc9c45e6b8b9600cd7bd233b1cbf78f49d26b099a", "exam_bench/codescan.py": "751e38001b6e65727a31e28172a0623f0bf34bc092a958037c286aa991a197ed", "exam_bench/codex.py": "c3f89d72af11f312d851c73a1610d92e79acadf336be9ccedd1f94ede3b3ccb0", "exam_bench/common.py": "8682603b519063e655eae3574a02a49efee63bde21f582ccee20ddd623fca96d", "exam_bench/docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "exam_bench/examiner.py": "d7294fdd23ed1732216cafebf0a8cf2c24cce4259859aeb7149f62b7607d087d", "exam_bench/finalize.py": "4034f1c63896a940afdb1a83d541cf47fc75c8b5061e3f839047109c04beb620", "exam_bench/forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "exam_bench/gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "exam_bench/grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "exam_bench/harness.py": "3040f6daaf1dc6e6583219f4d925151f8ba7851b2d5417d7f14645892b485ddf", "exam_bench/interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "exam_bench/interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "exam_bench/isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "exam_bench/ledger.py": "7e851523580e22d8490e75f9b6026c07f2c355007e0d11d0b252671f56bef654", "exam_bench/locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "exam_bench/materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "exam_bench/mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "exam_bench/observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "exam_bench/ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "exam_bench/penalties.py": "0d79e2e46102657dca00609b6abbfc0bf7d11fad41429564f876c82bc6b33269", "exam_bench/platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "exam_bench/portable.py": "cad56968ff407983608f5bdbc9ce7234128d7a4580b096ecea8e0e7b4edb9070", "exam_bench/portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "exam_bench/pr.py": "6a3a20caf0e10c0cc94410511a72d62c9fcda785f3abab1be2ad616d4ee16836", "exam_bench/preflight.py": "5619be0131d8641925f3ce2a3c8e5234d42aa5635d95676138ca81536d95cd29", "exam_bench/process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "exam_bench/queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "exam_bench/queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "exam_bench/replay_calibration.py": "c150457b0b23ce4e6814eb8deb4d48f6bc4a2e39d8f84a9dc7644fb99a026c2d", "exam_bench/report.py": "5e4c0757e1c7f189953f9a5302593ab726551835856baed25efd93dad6e8bfcd", "exam_bench/runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "exam_bench/smoke_check.py": "f36922a0027429ead0b414048dcc14bbe67f2f0e79a70d03dffbe1447d253545", "exam_bench/stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "exam_bench/submission.py": "3c5f703fcd90a1747884624e98b5caa1804dd422153106b96dcbb2810ee00544", "exam_bench/telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "exam_bench/windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "exam_bench/workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tools/build_public_site.py": "9682ed696f5ac9e9a82b65a45c0dece556ec7e49eeb20dcd616882cc534a8258", "tools/build_result_site.py": "3294e1d2ec1486058e208735264d61e349a68a4ae2fa2ec7a723c70e3263b496", "tools/check_native_harnesses.py": "4f5f0ed27651f78758eaef077b3b114361781f6b95ec40cb46c3fea689210473", "tools/check_native_toolkit.py": "0272794617121f2932828e5e4e9ae20095183c443666cf3ba466b44fbe875095", "tools/community_results.py": "cbfba30b4e617f5e219637c1c2de57398d01eb2f284eae3aca3ef684e6505a39", "tools/community_service.py": "c374480dbd88d656c0b9054fa04a8e1c6698c69e2f9cf475e82498a2dff61d84", "tools/community_setup.py": "5d7d126ed7d4dd48e1d79f57b99647a92ffcc8c9f80d90915e458888cdd76bf7", "tools/compare_harness_runs.py": "f274df5f3f804cb02504491aec946943833e12fbce6e62d281e12beb8508fc4e", "tools/create_run_plan.py": "871cd81b1eda231c0fba8805f63d2668926be9fc641559e6ddf320e2f47cd37a", "tools/demo_runner.py": "ca7ad17919c53d524cc0418751ba09a540f910eac183dca2961710bc30bba26f", "tools/installers.py": "9a2742780936b17500869e7c89202c1a2549e37d53a42ad9a50a0abbf78bbe09", "tools/machine_bundle.py": "8aa8346f99f537e81ceca6fb6ab9530e844954bab8eff87bf33d3602f81f8a30", "tools/prepare_native_harnesses.py": "aaa75ecf4022883984fa50c42d14d8e1a9fde2eeda03dab03b852bbc5efb2502", "tools/prepare_official_statement.py": "6b7028c78e90e798d6ef1a93b76520cc61a308c354fb9b87f7fad18b99800fad", "tools/prepare_open_exam_requirements.py": "544f4e378b9be5f166186f8788f8d454afdac2deb99d91d98421e39d01ba6d03", "tools/probe_harness.py": "1ed8ef93420d1484cbbfd151b7efc31b9a201ceb942dd05e3103efa22ffa7f27", "tools/probe_native_mcp.py": "9918d324129cba898993e07f8f8b6dbcbaf369398ebf28d464f9f1f00abdb254", "tools/readiness.py": "d34dd3f38334f51cc4574c79194cf0b80769b062a52382989a57d01c46b9aba4", "tools/recheck_community.py": "f0843d7d677f90da31e22bde0b1c86584dd46c022f1532d43d042619e426b230", "tools/regrade_runs.py": "011775afb06d3aac67a4aa81117a368c75896b0fcbe1e6f27ccc6237612fbf59", "tools/render_statement_text.py": "dabc0716a3612c288c671bc20e17fd4986691d732768e1e957d6dddddbea92a3", "tools/replay_calibration.py": "801f5004926c438c21ed3668fe2a4ddf45312b3e75320165a3839aae034eee9b", "tools/run_exam_campaign.py": "2c450d57a1cd0a2682838f5ec7c0a4ffb3aed0f1730d34c408e912d59cab6efd", "tools/serve_result_site.py": "86badfac863cd4ad1fc894a14110c75b28470513f0133eeae9d2799b8b4df3a9", "tools/start_demo.py": "c597e6cad28d245b3191654bb3e2801fa9dd2364e2acb25561923613717b615f", "tools/supplemental_acceptance.py": "c88fc39de1be1fdcacdd819e2ad329f60367b2df1d5deda80b37324bda3f2a01", "tools/sync_sources.py": "b51e889b0f41f9f63bfb19a09fb96d3777693d6b1d76fe0132bdd2a15e155898", "tools/validate_community_pr.py": "796b896dfade07b4529af2088a4b9b9d23484148b3bc0732b3fb837b75c9844b", "tools/verify_official_assessment_mapping.py": "daeb448a016940d5b6b1285979a56e5b9014bd91db40acb131445e4a83a23059", "tools/verify_task_package.py": "9e1e6105f6b5e4e78b36aa57f00117a9fbc8948ab53983c32ab56da88d23ccc4", "profiles/agents.json": "af9c492c08d13b3044aa6b6952589ed6a0a07d5258d8ff72bb18185b3eaebdc5", "profiles/ai-exam-execution-policy.json": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "profiles/bsl-analyzer-0.3.2-macos.json": "83537abdbf38c41ce665e4d0f24128bb51b62e971e0e0f368695f1326a7d2ffb", "profiles/bsl-analyzer-0.3.2-portable.json": "d6ba732e6778e256df34d6bc548593128820a70430c35b279796843606ee40a8", "profiles/bsl-ls-1.1.0-rc.6-macos.json": "245fc10747197e6911b2b4c77cdb15e6fa4eb7bc7c3758b63e768c5adf1df180", "profiles/bsl-ls-1.1.0-rc.6-portable.json": "9f10660881f2ec84794f7d584556b8f75c7e14b3555464af0ed0e60c4c892d86", "profiles/code-index-1.9.0-macos.json": "63a919523ce62ecec274f4c139bc7ad49a75dd4c339568b822cbc695b4e30408", "profiles/code-index-1.9.0-portable.json": "81106cee8f424ffd8a9dc46ecd8e4f57598fc1d49661a83c77b1f0507993fbdc", "profiles/codex-probe-plan.json": "166e41aad5fb3b27d9050bc6de952c6cba363cc6e804d4080568cc71a2a4d289", "profiles/machine.linux.example.json": "408304fd0581098d5d8110dc67dfeab353bc4d4030e32d37e6acf98d2b1aedfd", "profiles/machine.macos.example.json": "52e9f9d17797cb520b9d8955d6806fd550b899bed4da241ebf096dcb6a21a942", "profiles/machine.windows.example.json": "63accac9a2f81d47d03447efbabffd4760aee325193f02f46b9b29a28d50d2d8", "profiles/mcp-toolkit-1.9.0-macos.json": "1d3f9cde5ffa20589a840d01fdae03aa0fc2f412c929f064f203919c4129625b", "profiles/mcp-toolkit-1.9.0-portable.json": "8e370eebe773eef0e08045ee9c6d5be1451f769f65be0710834b262a4336e054", "profiles/none-macos.json": "b1401d9c48159aed3559006c7f6ace6ef4571224d5cf0bb76d1a823505a10056", "profiles/none-portable.json": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "profiles/rlm-tools-bsl-1.43.0-macos.json": "9354421052640ab60bc3e6aa98ff2e7ba9ca2318b0f4026c137487449242cbd2", "profiles/rlm-tools-bsl-1.43.0-portable.json": "2599e5645e0a7d4e44cb2934bc2b272cae79a9bf7ea74a23cd48aacea64bc424", "profiles/rlm-tools-bsl-1.43.0-posix-requirements.txt": "4fdf9a1bd994bf0272e65d231daf76cf19b0a34dad0ae6b50ec4f11a2ce4c330", "profiles/rlm-tools-bsl-1.43.0-windows-requirements.txt": "3730cb46c81cda5181ecd4485e98b11933104632358bc86f8c0eb1a612a8954f", "profiles/shirokov-skills-macos.json": "84f3e89091676884a802035c707e912762a1179425fb8e3faff25be736873cdb", "profiles/shirokov-skills-portable.json": "2b0a461e06602f1456410e70f02ceaa5ac32c6549c486660bcb5ace0c2f87b15", "profiles/shirokov-skills-windows-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/unica-0.12.3-macos.json": "2c39fbb591cf2c2c6e056373823615485397ea83651b7926c6f25a5fe6a0aae6", "profiles/unica-0.13.0-macos.json": "b76b5c8a4dd33f571c4a90993f1a2da5f7223b4f0f8e1042c282e21a66121052", "profiles/unica-0.14.0-rc.1-portable.json": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "rules/1c-specialist-platform/chistov.json": "77e04942f8c947b10759e7cc1eb31af05847d1711a772fbe6f23d525766757a9", "rules/1c-specialist-platform/decisions.json": "f622107423ce3c188c063318d7ab4f7718ceb38e443130677d8987f386641c09", "rules/1c-specialist-platform/examiner.json": "30353aa2a1b6545496b070d9066e9ffba0c3779e5b53ef70a4fd2cee375b18c0", "rules/1c-specialist-platform/ledger.json": "f167c10db2b5799dd9a1ea6a37cd2d7d186810dadf5ea2f50f26ae723c676882", "rules/1c-specialist-platform/rules.json": "1d320a4f8e1bf4701496388931f492315549bd3dce574b17285dd1d7f8652007", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" } } }, "conditions": { "client": "codex", "model": "gpt-6.1-sol", "client_version": "0.163.0-alpha.11.2", "reasoning_effort": "medium", "harness": "none", "billing_channel": "subscription", "solve_timeout_seconds": 7200, "time_series": null, "delegation": "native_disabled", "network_profile": "open-book_shell", "deadline_disclosed": true, "statement_sha256": "8a6ccb3e673826d1f8220fda53eb310e3ec18c136d87ce8f4cebb2a08614e7e5", "starter_dt_sha256": "f40d084818b0d1cfe503fc7653a6a13f1a8e47fcd1688dad6245b12744eb4638", "profile_sha256": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "execution_policy_sha256": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "calibration_sha256": "bacf42331c3b67ba858daa0123015ab0a965f13a20aa238eda22a7fcafa6237b", "started_at": "2026-10-24T09:52:52.981372+00:00", "timing": { "prepare_ms": 6203, "solve_ms": 5985485, "grade_ms": null }, "original_submission_valid": false, "model_provenance": "requested_only", "tokens": { "input": 21798127, "cached_input": 21643648, "fresh_input": 154479, "output": 167351, "reasoning_output": 81651, "total": 21965478, "coverage": "reported_completed_root_turns" }, "tools": { "mcp_calls": 0, "unica_calls": 0, "failed_calls": 0 }, "process": { "status": "completed", "exit_code": 0, "stop_confirmed": true } }, "verification": "repository_owner", "download": "community-downloads/demo-20261025T110836Z-adapter--owner-2026-10-26T223255070325-0000/solution.zip", "source_context": "community-downloads/demo-20261025T110836Z-adapter--owner-2026-10-26T223255070325-0000/source-context.json", "regrade_required": [], "grader_revision_sha256": "9aee1ffe0e1d04f9158fbbbeed3a403a5f0550ad8a590d7a6394977590760e1a", "archive_sha256": "4445735faae796a38d1753b3f85bc7c59816653217f86a5509cd2609837f7a1b", "owner_verification": { "kind": "repository_owner", "repository": "zeegin/1c-agent-exam-benchmark", "operator": { "name": "Ingvar Vilkman", "github": "zeegin" }, "started_at": "2026-10-26T22:32:54.919500+00:00", "server": { "name": "Owner Windows stand", "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "hardware": { "cpu": "AMD Ryzen 7 5800X 8-Core Processor ", "logical_cpus": 4, "ram_bytes": 17109000192 }, "isolation": "dedicated-host" }, "platform_version": "8.3.27.2342", "grader": { "profile": "technical-v8", "commit": "e15c8ea80263c0b38baa3a1fc19611983270e8a7", "working_tree_dirty": false, "fingerprint": { "assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "calibrate.py": "aac127e03744907fd52ef149b88aa6d88a54a2b7497d56084484ee1b99e0da99", "calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "calibration_periodicity.py": "0b1953d7781e236467897cd2ed66705b75d9719353a2de60b36f2bbdfe799108", "calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "calibration_query.py": "3555b103cde8ea0519955cf52358d09223f5ab183a9df00533bdb48c89237a8c", "claude.py": "5bae98af6e2021e2718afa3a71ed04bee812deaae31a43d4e7324814139ccc82", "codescan.py": "6d8375210cef1fd768fc2d98d630d880b2993a9724f01ae25f33b4ea5aa9631d", "codex.py": "904e75503cd35f16cbb052f66806b3879fe25bfc9f99e33b93c889d862c46324", "common.py": "739b39e2bb9bdd4a571fc69df5843190cddcad094ef7e68964061bc1266b20dc", "docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "examiner.py": "8cdffcdd52f043c905f896697403380af95bf485dd4a5edca24f7956e7795ffe", "forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "harness.py": "3cbb90fd3187e700b5df32e5daafb20313d49bb5721c826e3033cbc6aa6e3825", "interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "ou.py": "f62784b54a3f85576a078a2ff1908c9395f3159e55f6bb5b1a3c564392241abe", "penalties.py": "ae388cb8953ecca1f2370a7c4cb1db3b6cc8318fc2a7563a4db15f9f5b057429", "platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "pr.py": "2b6bfea0634703469605ce114f9274716b485852d9a55d9185c39893b14e4726", "preflight.py": "448c3120ab64b625abae3891be686c7a214ce4211f7cf651fd90e12c0b298433", "process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "queries.py": "1ef57e292db3e8967a733948371ecc542f743b811890d4fc509df17303b9c4ac", "queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "querytypes.py": "b645f489a2abc27762b4a9bbf4917e72f7b46dc053a74c0dca4a8fc46491b3ef", "replay_calibration.py": "e0e3d5ca6416934715b9735aa516046b8d19ad4ae690220eeacd96b198a5f86c", "runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "smoke_check.py": "7837e980986bcb54dc8bc1dfb5d0003deef11e05f6e11df3910fa509e1f74c8d", "stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "submission.py": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tasks/1c-platform-official-sample/checks.json": "7447a9b42d3e348d29d07f001cfb6bd269acd953b7117eba7cca2ce9f5a9a60d", "tasks/1c-platform-official-sample/private/official-assessment-mapping.json": "303587c0dabe77c1eeebb2017fe85539e3370b17c9090435e6e0325a66bd0644", "tasks/1c-platform-official-sample/private/owner-scoring-policy.json": "d26d534bb838ab1b5facb7bc033ca8ec40912133baadcdbad83b27fc577905f5", "starters/carcass-8.3.25.1445/starter.json": "0f7a7060885ba99a19402bfc6e63cc8fe979b0f491b040d3a01d5d21b304b3a6", "rules/1c-specialist-platform/rules.json": "ea75e34ace5de11ba3de403c63cd2c026db81d1d991f8531e4a779d4ce9788e7", "rules/1c-specialist-platform/examiner.json": "1247486ddd412d600db88d9c1db4ba501fc1994afd1dc2ebe85402fcc332f4c8", "rules/1c-specialist-platform/chistov.json": "800da27601a3f1c7ec1df64482fd4ad035e559ba0b390a274ed5031128487d3d", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" }, "sha256": "9aee1ffe0e1d04f9158fbbbeed3a403a5f0550ad8a590d7a6394977590760e1a" }, "method": "saved_platform_observations", "outcome": "complete", "completed_at": "2026-10-26T22:32:55.070325+00:00" }, "previous_evaluations": [ { "id": "demo-20261025T110836Z-adapter--owner-2026-10-26T214331344039-0000", "run_id": "demo-20261024T095243Z-21ac56", "result": { "run_id": "demo-20261024T095243Z-21ac56", "created_at": "2026-10-26T21:43:31.344039+00:00", "model": "gpt-6.1-sol", "harness": "none", "solve_seconds": 5985, "platform": "8.3.27.1644", "counts": { "pass": 64, "fail": 1 }, "rules": [ { "id": "BU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU01.selected_fixture" }, { "id": "BU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU04.selected_fixture" }, { "id": "BU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU05.selected_fixture" }, { "id": "BU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU16.selected_fixture" }, { "id": "BU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU17.selected_fixture" }, { "id": "BU02", "verdict": "pass", "reason": null, "coverage": "partial", "assertion_id": "BU02.posting_cost_and_balance" }, { "id": "BU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU10.selected_fixture" }, { "id": "BU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU12.selected_fixture" }, { "id": "BU03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU03.selected_fixture" }, { "id": "BU06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU06.selected_fixture" }, { "id": "BU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU07.selected_fixture" }, { "id": "BU08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU08.selected_fixture" }, { "id": "BU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU09.selected_fixture" }, { "id": "BU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU11.selected_fixture" }, { "id": "BU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU14.selected_fixture" }, { "id": "BU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU15.selected_fixture" }, { "id": "BU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU13.selected_fixture" }, { "id": "OU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU15.selected_fixture" }, { "id": "OU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU16.selected_fixture" }, { "id": "OU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU17.selected_fixture" }, { "id": "OU02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU02.selected_fixture" }, { "id": "OU18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU18.selected_fixture" }, { "id": "OU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU14.selected_fixture" }, { "id": "OU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU01.selected_fixture" }, { "id": "OU03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU03.selected_fixture" }, { "id": "OU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU05.selected_fixture" }, { "id": "OU06", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "OU06.selected_fixture" }, { "id": "OU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU07.selected_fixture" }, { "id": "OU08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU08.selected_fixture" }, { "id": "OU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU09.selected_fixture" }, { "id": "OU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU10.selected_fixture" }, { "id": "OU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU11.selected_fixture" }, { "id": "OU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU12.selected_fixture" }, { "id": "OU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU13.selected_fixture" }, { "id": "OU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU04.selected_fixture" }, { "id": "OU19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU19.selected_fixture" }, { "id": "OU20", "verdict": "fail", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU20.selected_fixture" }, { "id": "OU21", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU21.selected_fixture" }, { "id": "PR01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR01.selected_fixture" }, { "id": "PR02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR02.selected_fixture" }, { "id": "PR03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR03.selected_fixture" }, { "id": "PR04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR04.selected_fixture" }, { "id": "PR05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR05.selected_fixture" }, { "id": "PR06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR06.selected_fixture" }, { "id": "PR07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR07.selected_fixture" }, { "id": "PR08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR08.selected_fixture" }, { "id": "PR09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR09.selected_fixture" }, { "id": "PR10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR10.selected_fixture" }, { "id": "PR11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR11.selected_fixture" }, { "id": "PR12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR12.selected_fixture" }, { "id": "PR13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR13.selected_fixture" }, { "id": "PR14", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "PR14.selected_fixture" }, { "id": "PR15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR15.selected_fixture" }, { "id": "PR16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR16.selected_fixture" }, { "id": "PR17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR17.selected_fixture" }, { "id": "PR18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR18.selected_fixture" }, { "id": "PR19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR19.selected_fixture" }, { "id": "F01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F01.selected_fixture" }, { "id": "F02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F02.selected_fixture" }, { "id": "F03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F03.selected_fixture" }, { "id": "F04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F04.selected_fixture" }, { "id": "F05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F05.selected_fixture" }, { "id": "G01", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G01.static_sources" }, { "id": "G02", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G02.static_sources" }, { "id": "G03", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G03.static_sources" } ], "charges": [ { "id": "F1C-GEN03", "points": "0.5", "reason": "отчёт не соответствует заданию: OU20" }, { "id": "F1C-PR14", "points": "0.5", "reason": "после расчёта набор с периодом действия перезаписывается целиком, с пересчётом фактического периода действия (нужно Записать(, Истина)): CommonModules/Учет/Ext/Module.bsl:374 Набор.Записать()" }, { "id": "F1C-BU06", "points": "1.5", "reason": "у счёта товаров 01.02 не включён признак учёта Количественный" }, { "id": "F1C-PR08", "points": "2.0", "reason": "база берётся из основной таблицы регистра расчёта, БазаНачисления нигде не используется: Documents/НачислениеЗарплаты/Ext/ObjectModule.bsl:6" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "оперативное проведение разрешено у документов с движениями по регистрам расчёта: НачислениеЗарплаты" }, { "id": "F1C-GEN21", "points": "2.0", "reason": "данные графика без отбора по регистратору: CommonModules/Учет/Ext/Module.bsl:450" }, { "id": "F1C-GEN22", "points": "1.0", "reason": "значения графика выбираются без ЕСТЬNULL: CommonModules/Учет/Ext/Module.bsl:450 ДниФактическийПериодДействия, ЧасыПериодДействия, ЧасыФактическийПериодДействия" } ], "score_upper_bound": "-3.5", "score": null, "grade": "unsatisfactory", "deductions": "8.5", "not_assessed": 15, "gates": { "starter_origin": "passed", "load": "loaded", "clients": "compiles", "demo_data": "present" }, "infrastructure_errors": false, "comparison_eligible": false, "binding_compatibility": { "scope": "supplemental_named_subconto_adapter", "original_binding_sha256": "7dd185357a65fd5945433b73122669e0bc5b3ac46a451afc7a72002616268448", "normalized_binding_sha256": "69f3a6b98c1f598333e61ee4b543e66304e709c4de135e0aa265bf76fd8f47b8", "normalizer_sha256": "7327277143d80a531e4c254ac74a9fc0e0d5c76572d53b8469e0a580eda17d65", "canonical_ledger_sha256": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "changes": [ { "field": "fields.ledger.item_debit", "before": "СубконтоДт.Номенклатура", "after": "ВидыСубконто.Номенклатура", "kind": "named" }, { "field": "fields.ledger.item_credit", "before": "СубконтоКт.Номенклатура", "after": "ВидыСубконто.Номенклатура", "kind": "named" }, { "field": "fields.ledger.warehouse_debit", "before": "СубконтоДт.Склад", "after": "ВидыСубконто.Склад", "kind": "named" }, { "field": "fields.ledger.warehouse_credit", "before": "СубконтоКт.Склад", "after": "ВидыСубконто.Склад", "kind": "named" } ], "basis": "kind names expanded only to exactly one predefined kind of the account chart on the role side; all role types checked." } }, "measurement": { "operator": { "name": "Вячеслав", "github": "sksibak" }, "environment": { "captured_at": "2026-10-24T09:52:46.342453+00:00", "capture_timing": "before_run", "hardware": { "cpu": "AMD Ryzen 5 4600H with Radeon Graphics ", "logical_cpus": 12, "ram_bytes": 16505962496 }, "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "python": "3.12.14", "platform_version": "8.3.27.1644", "isolation": "dedicated-host", "network_profile": "open-book_shell", "unsafe_action_protection_observed_in_user_config": true, "git_revision": "af85e791b303dbbf0b0b7af924d2489c3e57cfa8", "implementation_files": { "exam_bench/__init__.py": "ad5bf6f05dc6765f40b78bd186870ca2c49be113cfa33f8aa76f4926f2cb2c1e", "exam_bench/assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "exam_bench/bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "exam_bench/calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "exam_bench/calibrate.py": "78b5185cb0888c0c0ac3de95ffc3a80154a6de9ae66fc461f79d012e5a58e1db", "exam_bench/calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "exam_bench/calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "exam_bench/calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "exam_bench/calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "exam_bench/calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "exam_bench/claude.py": "bc1b8550de7573aaed5e39c6e9c0309e0d8175284a75490d61ec27439ed911ad", "exam_bench/cli.py": "1a37ce645633d761f7897dffc9c45e6b8b9600cd7bd233b1cbf78f49d26b099a", "exam_bench/codescan.py": "751e38001b6e65727a31e28172a0623f0bf34bc092a958037c286aa991a197ed", "exam_bench/codex.py": "c3f89d72af11f312d851c73a1610d92e79acadf336be9ccedd1f94ede3b3ccb0", "exam_bench/common.py": "8682603b519063e655eae3574a02a49efee63bde21f582ccee20ddd623fca96d", "exam_bench/docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "exam_bench/examiner.py": "d7294fdd23ed1732216cafebf0a8cf2c24cce4259859aeb7149f62b7607d087d", "exam_bench/finalize.py": "4034f1c63896a940afdb1a83d541cf47fc75c8b5061e3f839047109c04beb620", "exam_bench/forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "exam_bench/gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "exam_bench/grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "exam_bench/harness.py": "3040f6daaf1dc6e6583219f4d925151f8ba7851b2d5417d7f14645892b485ddf", "exam_bench/interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "exam_bench/interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "exam_bench/isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "exam_bench/ledger.py": "7e851523580e22d8490e75f9b6026c07f2c355007e0d11d0b252671f56bef654", "exam_bench/locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "exam_bench/materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "exam_bench/mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "exam_bench/observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "exam_bench/ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "exam_bench/penalties.py": "0d79e2e46102657dca00609b6abbfc0bf7d11fad41429564f876c82bc6b33269", "exam_bench/platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "exam_bench/portable.py": "cad56968ff407983608f5bdbc9ce7234128d7a4580b096ecea8e0e7b4edb9070", "exam_bench/portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "exam_bench/pr.py": "6a3a20caf0e10c0cc94410511a72d62c9fcda785f3abab1be2ad616d4ee16836", "exam_bench/preflight.py": "5619be0131d8641925f3ce2a3c8e5234d42aa5635d95676138ca81536d95cd29", "exam_bench/process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "exam_bench/queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "exam_bench/queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "exam_bench/replay_calibration.py": "c150457b0b23ce4e6814eb8deb4d48f6bc4a2e39d8f84a9dc7644fb99a026c2d", "exam_bench/report.py": "5e4c0757e1c7f189953f9a5302593ab726551835856baed25efd93dad6e8bfcd", "exam_bench/runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "exam_bench/smoke_check.py": "f36922a0027429ead0b414048dcc14bbe67f2f0e79a70d03dffbe1447d253545", "exam_bench/stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "exam_bench/submission.py": "3c5f703fcd90a1747884624e98b5caa1804dd422153106b96dcbb2810ee00544", "exam_bench/telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "exam_bench/windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "exam_bench/workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tools/build_public_site.py": "9682ed696f5ac9e9a82b65a45c0dece556ec7e49eeb20dcd616882cc534a8258", "tools/build_result_site.py": "3294e1d2ec1486058e208735264d61e349a68a4ae2fa2ec7a723c70e3263b496", "tools/check_native_harnesses.py": "4f5f0ed27651f78758eaef077b3b114361781f6b95ec40cb46c3fea689210473", "tools/check_native_toolkit.py": "0272794617121f2932828e5e4e9ae20095183c443666cf3ba466b44fbe875095", "tools/community_results.py": "cbfba30b4e617f5e219637c1c2de57398d01eb2f284eae3aca3ef684e6505a39", "tools/community_service.py": "c374480dbd88d656c0b9054fa04a8e1c6698c69e2f9cf475e82498a2dff61d84", "tools/community_setup.py": "5d7d126ed7d4dd48e1d79f57b99647a92ffcc8c9f80d90915e458888cdd76bf7", "tools/compare_harness_runs.py": "f274df5f3f804cb02504491aec946943833e12fbce6e62d281e12beb8508fc4e", "tools/create_run_plan.py": "871cd81b1eda231c0fba8805f63d2668926be9fc641559e6ddf320e2f47cd37a", "tools/demo_runner.py": "ca7ad17919c53d524cc0418751ba09a540f910eac183dca2961710bc30bba26f", "tools/installers.py": "9a2742780936b17500869e7c89202c1a2549e37d53a42ad9a50a0abbf78bbe09", "tools/machine_bundle.py": "8aa8346f99f537e81ceca6fb6ab9530e844954bab8eff87bf33d3602f81f8a30", "tools/prepare_native_harnesses.py": "aaa75ecf4022883984fa50c42d14d8e1a9fde2eeda03dab03b852bbc5efb2502", "tools/prepare_official_statement.py": "6b7028c78e90e798d6ef1a93b76520cc61a308c354fb9b87f7fad18b99800fad", "tools/prepare_open_exam_requirements.py": "544f4e378b9be5f166186f8788f8d454afdac2deb99d91d98421e39d01ba6d03", "tools/probe_harness.py": "1ed8ef93420d1484cbbfd151b7efc31b9a201ceb942dd05e3103efa22ffa7f27", "tools/probe_native_mcp.py": "9918d324129cba898993e07f8f8b6dbcbaf369398ebf28d464f9f1f00abdb254", "tools/readiness.py": "d34dd3f38334f51cc4574c79194cf0b80769b062a52382989a57d01c46b9aba4", "tools/recheck_community.py": "f0843d7d677f90da31e22bde0b1c86584dd46c022f1532d43d042619e426b230", "tools/regrade_runs.py": "011775afb06d3aac67a4aa81117a368c75896b0fcbe1e6f27ccc6237612fbf59", "tools/render_statement_text.py": "dabc0716a3612c288c671bc20e17fd4986691d732768e1e957d6dddddbea92a3", "tools/replay_calibration.py": "801f5004926c438c21ed3668fe2a4ddf45312b3e75320165a3839aae034eee9b", "tools/run_exam_campaign.py": "2c450d57a1cd0a2682838f5ec7c0a4ffb3aed0f1730d34c408e912d59cab6efd", "tools/serve_result_site.py": "86badfac863cd4ad1fc894a14110c75b28470513f0133eeae9d2799b8b4df3a9", "tools/start_demo.py": "c597e6cad28d245b3191654bb3e2801fa9dd2364e2acb25561923613717b615f", "tools/supplemental_acceptance.py": "c88fc39de1be1fdcacdd819e2ad329f60367b2df1d5deda80b37324bda3f2a01", "tools/sync_sources.py": "b51e889b0f41f9f63bfb19a09fb96d3777693d6b1d76fe0132bdd2a15e155898", "tools/validate_community_pr.py": "796b896dfade07b4529af2088a4b9b9d23484148b3bc0732b3fb837b75c9844b", "tools/verify_official_assessment_mapping.py": "daeb448a016940d5b6b1285979a56e5b9014bd91db40acb131445e4a83a23059", "tools/verify_task_package.py": "9e1e6105f6b5e4e78b36aa57f00117a9fbc8948ab53983c32ab56da88d23ccc4", "profiles/agents.json": "af9c492c08d13b3044aa6b6952589ed6a0a07d5258d8ff72bb18185b3eaebdc5", "profiles/ai-exam-execution-policy.json": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "profiles/bsl-analyzer-0.3.2-macos.json": "83537abdbf38c41ce665e4d0f24128bb51b62e971e0e0f368695f1326a7d2ffb", "profiles/bsl-analyzer-0.3.2-portable.json": "d6ba732e6778e256df34d6bc548593128820a70430c35b279796843606ee40a8", "profiles/bsl-ls-1.1.0-rc.6-macos.json": "245fc10747197e6911b2b4c77cdb15e6fa4eb7bc7c3758b63e768c5adf1df180", "profiles/bsl-ls-1.1.0-rc.6-portable.json": "9f10660881f2ec84794f7d584556b8f75c7e14b3555464af0ed0e60c4c892d86", "profiles/code-index-1.9.0-macos.json": "63a919523ce62ecec274f4c139bc7ad49a75dd4c339568b822cbc695b4e30408", "profiles/code-index-1.9.0-portable.json": "81106cee8f424ffd8a9dc46ecd8e4f57598fc1d49661a83c77b1f0507993fbdc", "profiles/codex-probe-plan.json": "166e41aad5fb3b27d9050bc6de952c6cba363cc6e804d4080568cc71a2a4d289", "profiles/machine.linux.example.json": "408304fd0581098d5d8110dc67dfeab353bc4d4030e32d37e6acf98d2b1aedfd", "profiles/machine.macos.example.json": "52e9f9d17797cb520b9d8955d6806fd550b899bed4da241ebf096dcb6a21a942", "profiles/machine.windows.example.json": "63accac9a2f81d47d03447efbabffd4760aee325193f02f46b9b29a28d50d2d8", "profiles/mcp-toolkit-1.9.0-macos.json": "1d3f9cde5ffa20589a840d01fdae03aa0fc2f412c929f064f203919c4129625b", "profiles/mcp-toolkit-1.9.0-portable.json": "8e370eebe773eef0e08045ee9c6d5be1451f769f65be0710834b262a4336e054", "profiles/none-macos.json": "b1401d9c48159aed3559006c7f6ace6ef4571224d5cf0bb76d1a823505a10056", "profiles/none-portable.json": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "profiles/rlm-tools-bsl-1.43.0-macos.json": "9354421052640ab60bc3e6aa98ff2e7ba9ca2318b0f4026c137487449242cbd2", "profiles/rlm-tools-bsl-1.43.0-portable.json": "2599e5645e0a7d4e44cb2934bc2b272cae79a9bf7ea74a23cd48aacea64bc424", "profiles/rlm-tools-bsl-1.43.0-posix-requirements.txt": "4fdf9a1bd994bf0272e65d231daf76cf19b0a34dad0ae6b50ec4f11a2ce4c330", "profiles/rlm-tools-bsl-1.43.0-windows-requirements.txt": "3730cb46c81cda5181ecd4485e98b11933104632358bc86f8c0eb1a612a8954f", "profiles/shirokov-skills-macos.json": "84f3e89091676884a802035c707e912762a1179425fb8e3faff25be736873cdb", "profiles/shirokov-skills-portable.json": "2b0a461e06602f1456410e70f02ceaa5ac32c6549c486660bcb5ace0c2f87b15", "profiles/shirokov-skills-windows-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/unica-0.12.3-macos.json": "2c39fbb591cf2c2c6e056373823615485397ea83651b7926c6f25a5fe6a0aae6", "profiles/unica-0.13.0-macos.json": "b76b5c8a4dd33f571c4a90993f1a2da5f7223b4f0f8e1042c282e21a66121052", "profiles/unica-0.14.0-rc.1-portable.json": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "rules/1c-specialist-platform/chistov.json": "77e04942f8c947b10759e7cc1eb31af05847d1711a772fbe6f23d525766757a9", "rules/1c-specialist-platform/decisions.json": "f622107423ce3c188c063318d7ab4f7718ceb38e443130677d8987f386641c09", "rules/1c-specialist-platform/examiner.json": "30353aa2a1b6545496b070d9066e9ffba0c3779e5b53ef70a4fd2cee375b18c0", "rules/1c-specialist-platform/ledger.json": "f167c10db2b5799dd9a1ea6a37cd2d7d186810dadf5ea2f50f26ae723c676882", "rules/1c-specialist-platform/rules.json": "1d320a4f8e1bf4701496388931f492315549bd3dce574b17285dd1d7f8652007", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" } } }, "conditions": { "client": "codex", "model": "gpt-6.1-sol", "client_version": "0.163.0-alpha.11.2", "reasoning_effort": "medium", "harness": "none", "billing_channel": "subscription", "solve_timeout_seconds": 7200, "time_series": null, "delegation": "native_disabled", "network_profile": "open-book_shell", "deadline_disclosed": true, "statement_sha256": "8a6ccb3e673826d1f8220fda53eb310e3ec18c136d87ce8f4cebb2a08614e7e5", "starter_dt_sha256": "f40d084818b0d1cfe503fc7653a6a13f1a8e47fcd1688dad6245b12744eb4638", "profile_sha256": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "execution_policy_sha256": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "calibration_sha256": "bacf42331c3b67ba858daa0123015ab0a965f13a20aa238eda22a7fcafa6237b", "started_at": "2026-10-24T09:52:52.981372+00:00", "timing": { "prepare_ms": 6203, "solve_ms": 5985485, "grade_ms": null }, "original_submission_valid": false, "model_provenance": "requested_only", "tokens": { "input": 21798127, "cached_input": 21643648, "fresh_input": 154479, "output": 167351, "reasoning_output": 81651, "total": 21965478, "coverage": "reported_completed_root_turns" }, "tools": { "mcp_calls": 0, "unica_calls": 0, "failed_calls": 0 }, "process": { "status": "completed", "exit_code": 0, "stop_confirmed": true } }, "verification": "repository_owner", "download": "community-downloads/demo-20261025T110836Z-adapter--owner-2026-10-26T214331344039-0000/solution.zip", "source_context": "community-downloads/demo-20261025T110836Z-adapter--owner-2026-10-26T214331344039-0000/source-context.json", "regrade_required": [ { "id": "grader_changed", "files": [ "calibrate.py", "calibration_periodicity.py", "common.py", "ou.py", "replay_calibration.py", "smoke_check.py", "tasks/1c-platform-official-sample/checks.json" ] } ], "grader_revision_sha256": "349d87e0c7f531acbe35dd2b39c35722d8a877fedde97575b49e8466ab763c1d", "archive_sha256": "5b312ad6ca2cf588dabc8330c8f0e1faaed857b0a4478af266d3c862de1f6c08", "owner_verification": { "kind": "repository_owner", "repository": "zeegin/1c-agent-exam-benchmark", "operator": { "name": "Ingvar Vilkman", "github": "zeegin" }, "started_at": "2026-10-26T21:43:31.145499+00:00", "server": { "name": "Owner Windows stand", "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "hardware": { "cpu": "AMD Ryzen 7 5800X 8-Core Processor ", "logical_cpus": 4, "ram_bytes": 17109000192 }, "isolation": "dedicated-host" }, "platform_version": "8.3.27.2342", "grader": { "profile": "technical-v8", "commit": "e8fd8ced03a85b549c5472fbbda29225749f54d1", "working_tree_dirty": false, "fingerprint": { "assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "calibrate.py": "3162d431f3cab5e7976aa39f665d6286dce45499cf362d85109b7123fa8403a2", "calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "calibration_query.py": "3555b103cde8ea0519955cf52358d09223f5ab183a9df00533bdb48c89237a8c", "claude.py": "eedabc75fca0faa434f40a1624b71419ec7dc22e2854a0886cf84b4911db8372", "codescan.py": "6d8375210cef1fd768fc2d98d630d880b2993a9724f01ae25f33b4ea5aa9631d", "codex.py": "904e75503cd35f16cbb052f66806b3879fe25bfc9f99e33b93c889d862c46324", "common.py": "52825cf5c29f3536d6e046a89e789d5ef9c83aacd7f2f5a07f4f53e77b5229cc", "docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "examiner.py": "8cdffcdd52f043c905f896697403380af95bf485dd4a5edca24f7956e7795ffe", "forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "harness.py": "3cbb90fd3187e700b5df32e5daafb20313d49bb5721c826e3033cbc6aa6e3825", "interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "penalties.py": "ae388cb8953ecca1f2370a7c4cb1db3b6cc8318fc2a7563a4db15f9f5b057429", "platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "pr.py": "2b6bfea0634703469605ce114f9274716b485852d9a55d9185c39893b14e4726", "preflight.py": "448c3120ab64b625abae3891be686c7a214ce4211f7cf651fd90e12c0b298433", "process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "queries.py": "1ef57e292db3e8967a733948371ecc542f743b811890d4fc509df17303b9c4ac", "queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "querytypes.py": "b645f489a2abc27762b4a9bbf4917e72f7b46dc053a74c0dca4a8fc46491b3ef", "replay_calibration.py": "0a4d9b84a9908944c5a945878eb6f5eeda5a4e42ffff4f55c04a680742803d80", "runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "smoke_check.py": "66caf1a01f7aa18432293abe3567ac228ac837a660b08c3dc7bb093f7bd51628", "stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "submission.py": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tasks/1c-platform-official-sample/checks.json": "17a6fcc0c14410829650623eb1443ce99796e000cdfd19905ac0287988b73a00", "tasks/1c-platform-official-sample/private/official-assessment-mapping.json": "303587c0dabe77c1eeebb2017fe85539e3370b17c9090435e6e0325a66bd0644", "tasks/1c-platform-official-sample/private/owner-scoring-policy.json": "d26d534bb838ab1b5facb7bc033ca8ec40912133baadcdbad83b27fc577905f5", "starters/carcass-8.3.25.1445/starter.json": "0f7a7060885ba99a19402bfc6e63cc8fe979b0f491b040d3a01d5d21b304b3a6", "rules/1c-specialist-platform/rules.json": "ea75e34ace5de11ba3de403c63cd2c026db81d1d991f8531e4a779d4ce9788e7", "rules/1c-specialist-platform/examiner.json": "1247486ddd412d600db88d9c1db4ba501fc1994afd1dc2ebe85402fcc332f4c8", "rules/1c-specialist-platform/chistov.json": "800da27601a3f1c7ec1df64482fd4ad035e559ba0b390a274ed5031128487d3d", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" }, "sha256": "349d87e0c7f531acbe35dd2b39c35722d8a877fedde97575b49e8466ab763c1d" }, "method": "saved_platform_observations", "outcome": "complete", "completed_at": "2026-10-26T21:43:31.344039+00:00" } }, { "id": "demo-20261025T110836Z-adapter--owner-2026-10-26T185615030750-0000", "run_id": "demo-20261024T095243Z-21ac56", "result": { "run_id": "demo-20261024T095243Z-21ac56", "created_at": "2026-10-26T18:56:15.030750+00:00", "model": "gpt-6.1-sol", "harness": "none", "solve_seconds": 5985, "platform": "8.3.27.1644", "counts": { "pass": 64, "fail": 1 }, "rules": [ { "id": "BU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU01.selected_fixture" }, { "id": "BU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU04.selected_fixture" }, { "id": "BU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU05.selected_fixture" }, { "id": "BU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU16.selected_fixture" }, { "id": "BU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU17.selected_fixture" }, { "id": "BU02", "verdict": "pass", "reason": null, "coverage": "partial", "assertion_id": "BU02.posting_cost_and_balance" }, { "id": "BU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU10.selected_fixture" }, { "id": "BU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU12.selected_fixture" }, { "id": "BU03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU03.selected_fixture" }, { "id": "BU06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU06.selected_fixture" }, { "id": "BU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU07.selected_fixture" }, { "id": "BU08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU08.selected_fixture" }, { "id": "BU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU09.selected_fixture" }, { "id": "BU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU11.selected_fixture" }, { "id": "BU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU14.selected_fixture" }, { "id": "BU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU15.selected_fixture" }, { "id": "BU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU13.selected_fixture" }, { "id": "OU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU15.selected_fixture" }, { "id": "OU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU16.selected_fixture" }, { "id": "OU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU17.selected_fixture" }, { "id": "OU02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU02.selected_fixture" }, { "id": "OU18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU18.selected_fixture" }, { "id": "OU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU14.selected_fixture" }, { "id": "OU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU01.selected_fixture" }, { "id": "OU03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU03.selected_fixture" }, { "id": "OU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU05.selected_fixture" }, { "id": "OU06", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "OU06.selected_fixture" }, { "id": "OU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU07.selected_fixture" }, { "id": "OU08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU08.selected_fixture" }, { "id": "OU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU09.selected_fixture" }, { "id": "OU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU10.selected_fixture" }, { "id": "OU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU11.selected_fixture" }, { "id": "OU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU12.selected_fixture" }, { "id": "OU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU13.selected_fixture" }, { "id": "OU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU04.selected_fixture" }, { "id": "OU19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU19.selected_fixture" }, { "id": "OU20", "verdict": "fail", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU20.selected_fixture" }, { "id": "OU21", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU21.selected_fixture" }, { "id": "PR01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR01.selected_fixture" }, { "id": "PR02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR02.selected_fixture" }, { "id": "PR03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR03.selected_fixture" }, { "id": "PR04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR04.selected_fixture" }, { "id": "PR05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR05.selected_fixture" }, { "id": "PR06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR06.selected_fixture" }, { "id": "PR07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR07.selected_fixture" }, { "id": "PR08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR08.selected_fixture" }, { "id": "PR09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR09.selected_fixture" }, { "id": "PR10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR10.selected_fixture" }, { "id": "PR11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR11.selected_fixture" }, { "id": "PR12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR12.selected_fixture" }, { "id": "PR13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR13.selected_fixture" }, { "id": "PR14", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "PR14.selected_fixture" }, { "id": "PR15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR15.selected_fixture" }, { "id": "PR16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR16.selected_fixture" }, { "id": "PR17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR17.selected_fixture" }, { "id": "PR18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR18.selected_fixture" }, { "id": "PR19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR19.selected_fixture" }, { "id": "F01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F01.selected_fixture" }, { "id": "F02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F02.selected_fixture" }, { "id": "F03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F03.selected_fixture" }, { "id": "F04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F04.selected_fixture" }, { "id": "F05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F05.selected_fixture" }, { "id": "G01", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G01.static_sources" }, { "id": "G02", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G02.static_sources" }, { "id": "G03", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G03.static_sources" } ], "charges": [ { "id": "F1C-GEN03", "points": "0.5", "reason": "отчёт не соответствует заданию: OU20" }, { "id": "F1C-PR14", "points": "0.5", "reason": "после расчёта набор с периодом действия перезаписывается целиком, с пересчётом фактического периода действия (нужно Записать(, Истина)): CommonModules/Учет/Ext/Module.bsl:374 Набор.Записать()" }, { "id": "F1C-BU06", "points": "1.5", "reason": "у счёта товаров 01.02 не включён признак учёта Количественный" }, { "id": "F1C-PR08", "points": "2.0", "reason": "база берётся из основной таблицы регистра расчёта, БазаНачисления нигде не используется: Documents/НачислениеЗарплаты/Ext/ObjectModule.bsl:6" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "оперативное проведение разрешено у документов с движениями по регистрам расчёта: НачислениеЗарплаты" }, { "id": "F1C-GEN21", "points": "2.0", "reason": "данные графика без отбора по регистратору: CommonModules/Учет/Ext/Module.bsl:450" }, { "id": "F1C-GEN22", "points": "1.0", "reason": "значения графика выбираются без ЕСТЬNULL: CommonModules/Учет/Ext/Module.bsl:450 ДниФактическийПериодДействия, ЧасыПериодДействия, ЧасыФактическийПериодДействия" } ], "score_upper_bound": "-3.5", "score": null, "grade": "unsatisfactory", "deductions": "8.5", "not_assessed": 15, "gates": { "starter_origin": "passed", "load": "loaded", "clients": "compiles", "demo_data": "present" }, "infrastructure_errors": false, "comparison_eligible": false, "binding_compatibility": { "scope": "supplemental_named_subconto_adapter", "original_binding_sha256": "7dd185357a65fd5945433b73122669e0bc5b3ac46a451afc7a72002616268448", "normalized_binding_sha256": "69f3a6b98c1f598333e61ee4b543e66304e709c4de135e0aa265bf76fd8f47b8", "normalizer_sha256": "7327277143d80a531e4c254ac74a9fc0e0d5c76572d53b8469e0a580eda17d65", "canonical_ledger_sha256": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "changes": [ { "field": "fields.ledger.item_debit", "before": "СубконтоДт.Номенклатура", "after": "ВидыСубконто.Номенклатура", "kind": "named" }, { "field": "fields.ledger.item_credit", "before": "СубконтоКт.Номенклатура", "after": "ВидыСубконто.Номенклатура", "kind": "named" }, { "field": "fields.ledger.warehouse_debit", "before": "СубконтоДт.Склад", "after": "ВидыСубконто.Склад", "kind": "named" }, { "field": "fields.ledger.warehouse_credit", "before": "СубконтоКт.Склад", "after": "ВидыСубконто.Склад", "kind": "named" } ], "basis": "kind names expanded only to exactly one predefined kind of the account chart on the role side; all role types checked." } }, "measurement": { "operator": { "name": "Вячеслав", "github": "sksibak" }, "environment": { "captured_at": "2026-10-24T09:52:46.342453+00:00", "capture_timing": "before_run", "hardware": { "cpu": "AMD Ryzen 5 4600H with Radeon Graphics ", "logical_cpus": 12, "ram_bytes": 16505962496 }, "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "python": "3.12.14", "platform_version": "8.3.27.1644", "isolation": "dedicated-host", "network_profile": "open-book_shell", "unsafe_action_protection_observed_in_user_config": true, "git_revision": "af85e791b303dbbf0b0b7af924d2489c3e57cfa8", "implementation_files": { "exam_bench/__init__.py": "ad5bf6f05dc6765f40b78bd186870ca2c49be113cfa33f8aa76f4926f2cb2c1e", "exam_bench/assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "exam_bench/bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "exam_bench/calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "exam_bench/calibrate.py": "78b5185cb0888c0c0ac3de95ffc3a80154a6de9ae66fc461f79d012e5a58e1db", "exam_bench/calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "exam_bench/calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "exam_bench/calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "exam_bench/calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "exam_bench/calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "exam_bench/claude.py": "bc1b8550de7573aaed5e39c6e9c0309e0d8175284a75490d61ec27439ed911ad", "exam_bench/cli.py": "1a37ce645633d761f7897dffc9c45e6b8b9600cd7bd233b1cbf78f49d26b099a", "exam_bench/codescan.py": "751e38001b6e65727a31e28172a0623f0bf34bc092a958037c286aa991a197ed", "exam_bench/codex.py": "c3f89d72af11f312d851c73a1610d92e79acadf336be9ccedd1f94ede3b3ccb0", "exam_bench/common.py": "8682603b519063e655eae3574a02a49efee63bde21f582ccee20ddd623fca96d", "exam_bench/docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "exam_bench/examiner.py": "d7294fdd23ed1732216cafebf0a8cf2c24cce4259859aeb7149f62b7607d087d", "exam_bench/finalize.py": "4034f1c63896a940afdb1a83d541cf47fc75c8b5061e3f839047109c04beb620", "exam_bench/forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "exam_bench/gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "exam_bench/grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "exam_bench/harness.py": "3040f6daaf1dc6e6583219f4d925151f8ba7851b2d5417d7f14645892b485ddf", "exam_bench/interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "exam_bench/interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "exam_bench/isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "exam_bench/ledger.py": "7e851523580e22d8490e75f9b6026c07f2c355007e0d11d0b252671f56bef654", "exam_bench/locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "exam_bench/materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "exam_bench/mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "exam_bench/observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "exam_bench/ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "exam_bench/penalties.py": "0d79e2e46102657dca00609b6abbfc0bf7d11fad41429564f876c82bc6b33269", "exam_bench/platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "exam_bench/portable.py": "cad56968ff407983608f5bdbc9ce7234128d7a4580b096ecea8e0e7b4edb9070", "exam_bench/portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "exam_bench/pr.py": "6a3a20caf0e10c0cc94410511a72d62c9fcda785f3abab1be2ad616d4ee16836", "exam_bench/preflight.py": "5619be0131d8641925f3ce2a3c8e5234d42aa5635d95676138ca81536d95cd29", "exam_bench/process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "exam_bench/queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "exam_bench/queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "exam_bench/replay_calibration.py": "c150457b0b23ce4e6814eb8deb4d48f6bc4a2e39d8f84a9dc7644fb99a026c2d", "exam_bench/report.py": "5e4c0757e1c7f189953f9a5302593ab726551835856baed25efd93dad6e8bfcd", "exam_bench/runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "exam_bench/smoke_check.py": "f36922a0027429ead0b414048dcc14bbe67f2f0e79a70d03dffbe1447d253545", "exam_bench/stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "exam_bench/submission.py": "3c5f703fcd90a1747884624e98b5caa1804dd422153106b96dcbb2810ee00544", "exam_bench/telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "exam_bench/windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "exam_bench/workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tools/build_public_site.py": "9682ed696f5ac9e9a82b65a45c0dece556ec7e49eeb20dcd616882cc534a8258", "tools/build_result_site.py": "3294e1d2ec1486058e208735264d61e349a68a4ae2fa2ec7a723c70e3263b496", "tools/check_native_harnesses.py": "4f5f0ed27651f78758eaef077b3b114361781f6b95ec40cb46c3fea689210473", "tools/check_native_toolkit.py": "0272794617121f2932828e5e4e9ae20095183c443666cf3ba466b44fbe875095", "tools/community_results.py": "cbfba30b4e617f5e219637c1c2de57398d01eb2f284eae3aca3ef684e6505a39", "tools/community_service.py": "c374480dbd88d656c0b9054fa04a8e1c6698c69e2f9cf475e82498a2dff61d84", "tools/community_setup.py": "5d7d126ed7d4dd48e1d79f57b99647a92ffcc8c9f80d90915e458888cdd76bf7", "tools/compare_harness_runs.py": "f274df5f3f804cb02504491aec946943833e12fbce6e62d281e12beb8508fc4e", "tools/create_run_plan.py": "871cd81b1eda231c0fba8805f63d2668926be9fc641559e6ddf320e2f47cd37a", "tools/demo_runner.py": "ca7ad17919c53d524cc0418751ba09a540f910eac183dca2961710bc30bba26f", "tools/installers.py": "9a2742780936b17500869e7c89202c1a2549e37d53a42ad9a50a0abbf78bbe09", "tools/machine_bundle.py": "8aa8346f99f537e81ceca6fb6ab9530e844954bab8eff87bf33d3602f81f8a30", "tools/prepare_native_harnesses.py": "aaa75ecf4022883984fa50c42d14d8e1a9fde2eeda03dab03b852bbc5efb2502", "tools/prepare_official_statement.py": "6b7028c78e90e798d6ef1a93b76520cc61a308c354fb9b87f7fad18b99800fad", "tools/prepare_open_exam_requirements.py": "544f4e378b9be5f166186f8788f8d454afdac2deb99d91d98421e39d01ba6d03", "tools/probe_harness.py": "1ed8ef93420d1484cbbfd151b7efc31b9a201ceb942dd05e3103efa22ffa7f27", "tools/probe_native_mcp.py": "9918d324129cba898993e07f8f8b6dbcbaf369398ebf28d464f9f1f00abdb254", "tools/readiness.py": "d34dd3f38334f51cc4574c79194cf0b80769b062a52382989a57d01c46b9aba4", "tools/recheck_community.py": "f0843d7d677f90da31e22bde0b1c86584dd46c022f1532d43d042619e426b230", "tools/regrade_runs.py": "011775afb06d3aac67a4aa81117a368c75896b0fcbe1e6f27ccc6237612fbf59", "tools/render_statement_text.py": "dabc0716a3612c288c671bc20e17fd4986691d732768e1e957d6dddddbea92a3", "tools/replay_calibration.py": "801f5004926c438c21ed3668fe2a4ddf45312b3e75320165a3839aae034eee9b", "tools/run_exam_campaign.py": "2c450d57a1cd0a2682838f5ec7c0a4ffb3aed0f1730d34c408e912d59cab6efd", "tools/serve_result_site.py": "86badfac863cd4ad1fc894a14110c75b28470513f0133eeae9d2799b8b4df3a9", "tools/start_demo.py": "c597e6cad28d245b3191654bb3e2801fa9dd2364e2acb25561923613717b615f", "tools/supplemental_acceptance.py": "c88fc39de1be1fdcacdd819e2ad329f60367b2df1d5deda80b37324bda3f2a01", "tools/sync_sources.py": "b51e889b0f41f9f63bfb19a09fb96d3777693d6b1d76fe0132bdd2a15e155898", "tools/validate_community_pr.py": "796b896dfade07b4529af2088a4b9b9d23484148b3bc0732b3fb837b75c9844b", "tools/verify_official_assessment_mapping.py": "daeb448a016940d5b6b1285979a56e5b9014bd91db40acb131445e4a83a23059", "tools/verify_task_package.py": "9e1e6105f6b5e4e78b36aa57f00117a9fbc8948ab53983c32ab56da88d23ccc4", "profiles/agents.json": "af9c492c08d13b3044aa6b6952589ed6a0a07d5258d8ff72bb18185b3eaebdc5", "profiles/ai-exam-execution-policy.json": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "profiles/bsl-analyzer-0.3.2-macos.json": "83537abdbf38c41ce665e4d0f24128bb51b62e971e0e0f368695f1326a7d2ffb", "profiles/bsl-analyzer-0.3.2-portable.json": "d6ba732e6778e256df34d6bc548593128820a70430c35b279796843606ee40a8", "profiles/bsl-ls-1.1.0-rc.6-macos.json": "245fc10747197e6911b2b4c77cdb15e6fa4eb7bc7c3758b63e768c5adf1df180", "profiles/bsl-ls-1.1.0-rc.6-portable.json": "9f10660881f2ec84794f7d584556b8f75c7e14b3555464af0ed0e60c4c892d86", "profiles/code-index-1.9.0-macos.json": "63a919523ce62ecec274f4c139bc7ad49a75dd4c339568b822cbc695b4e30408", "profiles/code-index-1.9.0-portable.json": "81106cee8f424ffd8a9dc46ecd8e4f57598fc1d49661a83c77b1f0507993fbdc", "profiles/codex-probe-plan.json": "166e41aad5fb3b27d9050bc6de952c6cba363cc6e804d4080568cc71a2a4d289", "profiles/machine.linux.example.json": "408304fd0581098d5d8110dc67dfeab353bc4d4030e32d37e6acf98d2b1aedfd", "profiles/machine.macos.example.json": "52e9f9d17797cb520b9d8955d6806fd550b899bed4da241ebf096dcb6a21a942", "profiles/machine.windows.example.json": "63accac9a2f81d47d03447efbabffd4760aee325193f02f46b9b29a28d50d2d8", "profiles/mcp-toolkit-1.9.0-macos.json": "1d3f9cde5ffa20589a840d01fdae03aa0fc2f412c929f064f203919c4129625b", "profiles/mcp-toolkit-1.9.0-portable.json": "8e370eebe773eef0e08045ee9c6d5be1451f769f65be0710834b262a4336e054", "profiles/none-macos.json": "b1401d9c48159aed3559006c7f6ace6ef4571224d5cf0bb76d1a823505a10056", "profiles/none-portable.json": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "profiles/rlm-tools-bsl-1.43.0-macos.json": "9354421052640ab60bc3e6aa98ff2e7ba9ca2318b0f4026c137487449242cbd2", "profiles/rlm-tools-bsl-1.43.0-portable.json": "2599e5645e0a7d4e44cb2934bc2b272cae79a9bf7ea74a23cd48aacea64bc424", "profiles/rlm-tools-bsl-1.43.0-posix-requirements.txt": "4fdf9a1bd994bf0272e65d231daf76cf19b0a34dad0ae6b50ec4f11a2ce4c330", "profiles/rlm-tools-bsl-1.43.0-windows-requirements.txt": "3730cb46c81cda5181ecd4485e98b11933104632358bc86f8c0eb1a612a8954f", "profiles/shirokov-skills-macos.json": "84f3e89091676884a802035c707e912762a1179425fb8e3faff25be736873cdb", "profiles/shirokov-skills-portable.json": "2b0a461e06602f1456410e70f02ceaa5ac32c6549c486660bcb5ace0c2f87b15", "profiles/shirokov-skills-windows-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/unica-0.12.3-macos.json": "2c39fbb591cf2c2c6e056373823615485397ea83651b7926c6f25a5fe6a0aae6", "profiles/unica-0.13.0-macos.json": "b76b5c8a4dd33f571c4a90993f1a2da5f7223b4f0f8e1042c282e21a66121052", "profiles/unica-0.14.0-rc.1-portable.json": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "rules/1c-specialist-platform/chistov.json": "77e04942f8c947b10759e7cc1eb31af05847d1711a772fbe6f23d525766757a9", "rules/1c-specialist-platform/decisions.json": "f622107423ce3c188c063318d7ab4f7718ceb38e443130677d8987f386641c09", "rules/1c-specialist-platform/examiner.json": "30353aa2a1b6545496b070d9066e9ffba0c3779e5b53ef70a4fd2cee375b18c0", "rules/1c-specialist-platform/ledger.json": "f167c10db2b5799dd9a1ea6a37cd2d7d186810dadf5ea2f50f26ae723c676882", "rules/1c-specialist-platform/rules.json": "1d320a4f8e1bf4701496388931f492315549bd3dce574b17285dd1d7f8652007", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" } } }, "conditions": { "client": "codex", "model": "gpt-6.1-sol", "client_version": "0.163.0-alpha.11.2", "reasoning_effort": "medium", "harness": "none", "billing_channel": "subscription", "solve_timeout_seconds": 7200, "time_series": null, "delegation": "native_disabled", "network_profile": "open-book_shell", "deadline_disclosed": true, "statement_sha256": "8a6ccb3e673826d1f8220fda53eb310e3ec18c136d87ce8f4cebb2a08614e7e5", "starter_dt_sha256": "f40d084818b0d1cfe503fc7653a6a13f1a8e47fcd1688dad6245b12744eb4638", "profile_sha256": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "execution_policy_sha256": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "calibration_sha256": "bacf42331c3b67ba858daa0123015ab0a965f13a20aa238eda22a7fcafa6237b", "started_at": "2026-10-24T09:52:52.981372+00:00", "timing": { "prepare_ms": 6203, "solve_ms": 5985485, "grade_ms": null }, "original_submission_valid": false, "model_provenance": "requested_only", "tokens": { "input": 21798127, "cached_input": 21643648, "fresh_input": 154479, "output": 167351, "reasoning_output": 81651, "total": 21965478, "coverage": "reported_completed_root_turns" }, "tools": { "mcp_calls": 0, "unica_calls": 0, "failed_calls": 0 }, "process": { "status": "completed", "exit_code": 0, "stop_confirmed": true } }, "verification": "repository_owner", "download": "community-downloads/demo-20261025T110836Z-adapter--owner-2026-10-26T185615030750-0000/solution.zip", "source_context": "community-downloads/demo-20261025T110836Z-adapter--owner-2026-10-26T185615030750-0000/source-context.json", "regrade_required": [ { "id": "grader_changed", "files": [ "calibrate.py", "calibration_periodicity.py", "calibration_query.py", "common.py", "ou.py", "penalties.py", "queries.py", "replay_calibration.py", "rules/1c-specialist-platform/rules.json", "smoke_check.py", "tasks/1c-platform-official-sample/checks.json" ] } ], "grader_revision_sha256": "4a12b62d2c10085e1fc710f377f84903abdf2fb787dda19628d944da990a86b2", "archive_sha256": "a081599fad5235708d9342d53560615be2045b5b1306b5ebe369b9297bbef282", "owner_verification": { "kind": "repository_owner", "repository": "zeegin/1c-agent-exam-benchmark", "operator": { "name": "Ingvar Vilkman", "github": "zeegin" }, "started_at": "2026-10-26T18:53:25.077885+00:00", "server": { "name": "Owner Windows stand", "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "hardware": { "cpu": "AMD Ryzen 7 5800X 8-Core Processor ", "logical_cpus": 4, "ram_bytes": 17109000192 }, "isolation": "dedicated-host" }, "platform_version": "8.3.27.2342", "grader": { "profile": "technical-v8", "commit": "5b6a28372b253e81e22b83f8559df897297e28ff", "working_tree_dirty": true, "fingerprint": { "assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "calibrate.py": "1c844971b4977fdcc3b30aebe8aad40fbd45e6828955b8deb043ac8573d61731", "calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "claude.py": "eedabc75fca0faa434f40a1624b71419ec7dc22e2854a0886cf84b4911db8372", "codescan.py": "6d8375210cef1fd768fc2d98d630d880b2993a9724f01ae25f33b4ea5aa9631d", "codex.py": "904e75503cd35f16cbb052f66806b3879fe25bfc9f99e33b93c889d862c46324", "common.py": "7696116dd1a796666518b4c5d2aa3cafa04ee974593d3636333cbe5385bd6ccb", "docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "examiner.py": "8cdffcdd52f043c905f896697403380af95bf485dd4a5edca24f7956e7795ffe", "forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "harness.py": "3cbb90fd3187e700b5df32e5daafb20313d49bb5721c826e3033cbc6aa6e3825", "interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "penalties.py": "b82704e7f47d3dfdf6e501452d7e0abca1f9da63307093d2e257e32358be0489", "platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "pr.py": "2b6bfea0634703469605ce114f9274716b485852d9a55d9185c39893b14e4726", "preflight.py": "448c3120ab64b625abae3891be686c7a214ce4211f7cf651fd90e12c0b298433", "process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "querytypes.py": "b645f489a2abc27762b4a9bbf4917e72f7b46dc053a74c0dca4a8fc46491b3ef", "replay_calibration.py": "3b6f3a289cc8a7f5e458f62bfa2c6cc534cc9076ba3f22d1e4bd8a5f9e175317", "runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "smoke_check.py": "bd6266367e6b769a95258eb383239b89a22deae406d64f6e142c77396f4639ba", "stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "submission.py": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tasks/1c-platform-official-sample/checks.json": "17a6fcc0c14410829650623eb1443ce99796e000cdfd19905ac0287988b73a00", "tasks/1c-platform-official-sample/private/official-assessment-mapping.json": "303587c0dabe77c1eeebb2017fe85539e3370b17c9090435e6e0325a66bd0644", "tasks/1c-platform-official-sample/private/owner-scoring-policy.json": "d26d534bb838ab1b5facb7bc033ca8ec40912133baadcdbad83b27fc577905f5", "starters/carcass-8.3.25.1445/starter.json": "0f7a7060885ba99a19402bfc6e63cc8fe979b0f491b040d3a01d5d21b304b3a6", "rules/1c-specialist-platform/rules.json": "7ec895a7751ef17f4a50cc80b5f7fa986e1e04360ab0b4ce9aa29115195df03c", "rules/1c-specialist-platform/examiner.json": "1247486ddd412d600db88d9c1db4ba501fc1994afd1dc2ebe85402fcc332f4c8", "rules/1c-specialist-platform/chistov.json": "800da27601a3f1c7ec1df64482fd4ad035e559ba0b390a274ed5031128487d3d", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" }, "sha256": "4a12b62d2c10085e1fc710f377f84903abdf2fb787dda19628d944da990a86b2" }, "identity_verified_at": "2026-10-26T18:44:22.364471+00:00", "identity_session_sha256": "950670ab9a82059c65525d0d6e5b8a00f0dc292581edea3eb087c4ecadeaab09", "completed_at": "2026-10-26T18:56:15.030750+00:00" } }, { "id": "demo-20261025T110836Z-adapter", "run_id": "demo-20261024T095243Z-21ac56", "result": { "run_id": "demo-20261024T095243Z-21ac56", "created_at": "2026-10-25T11:12:31.096905+00:00", "model": "gpt-6.1-sol", "harness": "none", "solve_seconds": 5985, "platform": "8.3.27.1644", "counts": { "pass": 64, "fail": 1 }, "rules": [ { "id": "BU01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU16", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU17", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU02", "verdict": "pass", "coverage": "partial", "reason": null }, { "id": "BU10", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU12", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU06", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU07", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU08", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU09", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU11", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU14", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU15", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU13", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU15", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU16", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU17", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU02", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU18", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU14", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU06", "verdict": "pass", "coverage": "no_violation_found", "reason": null }, { "id": "OU07", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU08", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU09", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU10", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU11", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU12", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU13", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU19", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU20", "verdict": "fail", "coverage": "selected_fixture", "reason": "Ведомость не прошла проверку группировки по значениям характеристик." }, { "id": "OU21", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR02", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR06", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR07", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR08", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR09", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR10", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR11", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR12", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR13", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR14", "verdict": "pass", "coverage": "no_violation_found", "reason": null }, { "id": "PR15", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR16", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR17", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR18", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR19", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F02", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "G01", "verdict": "pass", "coverage": "static_sources", "reason": null }, { "id": "G02", "verdict": "pass", "coverage": "static_sources", "reason": null }, { "id": "G03", "verdict": "pass", "coverage": "static_sources", "reason": null } ], "charges": [ { "id": "F1C-GEN03", "points": "0.5", "reason": "Ведомость не прошла проверку группировки по значениям характеристик." }, { "id": "F1C-PR14", "points": "0.5", "reason": "после расчёта набор с периодом действия перезаписывается целиком, с пересчётом фактического периода действия (нужно Записать(, Истина)): CommonModules/Учет/Ext/Module.bsl:374 Набор.Записать()" }, { "id": "F1C-BU06", "points": "1.5", "reason": "у счёта товаров 01.02 не включён признак учёта Количественный" }, { "id": "F1C-PR08", "points": "2.0", "reason": "база берётся из основной таблицы регистра расчёта, БазаНачисления нигде не используется: Documents/НачислениеЗарплаты/Ext/ObjectModule.bsl:6" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "оперативное проведение разрешено у документов с движениями по регистрам расчёта: НачислениеЗарплаты" }, { "id": "F1C-GEN21", "points": "2.0", "reason": "данные графика без отбора по регистратору: CommonModules/Учет/Ext/Module.bsl:450" }, { "id": "F1C-GEN22", "points": "1.0", "reason": "значения графика выбираются без ЕСТЬNULL: CommonModules/Учет/Ext/Module.bsl:450 ДниФактическийПериодДействия, ЧасыПериодДействия, ЧасыФактическийПериодДействия" } ], "score_upper_bound": "-3.5", "score": null, "grade": "unsatisfactory", "deductions": "8.5", "not_assessed": 15, "gates": { "starter_origin": "passed", "load": "loaded", "clients": "compiles", "demo_data": "present" }, "infrastructure_errors": false, "comparison_eligible": false, "binding_compatibility": { "scope": "supplemental_named_subconto_adapter", "original_binding_sha256": "7dd185357a65fd5945433b73122669e0bc5b3ac46a451afc7a72002616268448", "normalized_binding_sha256": "69f3a6b98c1f598333e61ee4b543e66304e709c4de135e0aa265bf76fd8f47b8", "normalizer_sha256": "7327277143d80a531e4c254ac74a9fc0e0d5c76572d53b8469e0a580eda17d65", "canonical_ledger_sha256": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "changes": [ { "field": "fields.ledger.item_debit", "before": "СубконтоДт.Номенклатура", "after": "ВидыСубконто.Номенклатура", "kind": "named" }, { "field": "fields.ledger.item_credit", "before": "СубконтоКт.Номенклатура", "after": "ВидыСубконто.Номенклатура", "kind": "named" }, { "field": "fields.ledger.warehouse_debit", "before": "СубконтоДт.Склад", "after": "ВидыСубконто.Склад", "kind": "named" }, { "field": "fields.ledger.warehouse_credit", "before": "СубконтоКт.Склад", "after": "ВидыСубконто.Склад", "kind": "named" } ], "basis": "kind names expanded only to exactly one predefined kind of the account chart on the role side; all role types checked." }, "evaluation_sha256": "8ff2d06ab88bfa2f75dd1d57b017d455e4c98d85d59b35994d235231ca18a240", "downloads": [] }, "measurement": { "operator": { "name": "Вячеслав", "github": "sksibak" }, "environment": { "captured_at": "2026-10-24T09:52:46.342453+00:00", "capture_timing": "before_run", "hardware": { "cpu": "AMD Ryzen 5 4600H with Radeon Graphics ", "logical_cpus": 12, "ram_bytes": 16505962496 }, "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "python": "3.12.14", "platform_version": "8.3.27.1644", "isolation": "dedicated-host", "network_profile": "open-book_shell", "unsafe_action_protection_observed_in_user_config": true, "git_revision": "af85e791b303dbbf0b0b7af924d2489c3e57cfa8", "implementation_files": { "exam_bench/__init__.py": "ad5bf6f05dc6765f40b78bd186870ca2c49be113cfa33f8aa76f4926f2cb2c1e", "exam_bench/assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "exam_bench/bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "exam_bench/calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "exam_bench/calibrate.py": "78b5185cb0888c0c0ac3de95ffc3a80154a6de9ae66fc461f79d012e5a58e1db", "exam_bench/calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "exam_bench/calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "exam_bench/calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "exam_bench/calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "exam_bench/calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "exam_bench/claude.py": "bc1b8550de7573aaed5e39c6e9c0309e0d8175284a75490d61ec27439ed911ad", "exam_bench/cli.py": "1a37ce645633d761f7897dffc9c45e6b8b9600cd7bd233b1cbf78f49d26b099a", "exam_bench/codescan.py": "751e38001b6e65727a31e28172a0623f0bf34bc092a958037c286aa991a197ed", "exam_bench/codex.py": "c3f89d72af11f312d851c73a1610d92e79acadf336be9ccedd1f94ede3b3ccb0", "exam_bench/common.py": "8682603b519063e655eae3574a02a49efee63bde21f582ccee20ddd623fca96d", "exam_bench/docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "exam_bench/examiner.py": "d7294fdd23ed1732216cafebf0a8cf2c24cce4259859aeb7149f62b7607d087d", "exam_bench/finalize.py": "4034f1c63896a940afdb1a83d541cf47fc75c8b5061e3f839047109c04beb620", "exam_bench/forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "exam_bench/gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "exam_bench/grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "exam_bench/harness.py": "3040f6daaf1dc6e6583219f4d925151f8ba7851b2d5417d7f14645892b485ddf", "exam_bench/interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "exam_bench/interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "exam_bench/isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "exam_bench/ledger.py": "7e851523580e22d8490e75f9b6026c07f2c355007e0d11d0b252671f56bef654", "exam_bench/locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "exam_bench/materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "exam_bench/mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "exam_bench/observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "exam_bench/ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "exam_bench/penalties.py": "0d79e2e46102657dca00609b6abbfc0bf7d11fad41429564f876c82bc6b33269", "exam_bench/platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "exam_bench/portable.py": "cad56968ff407983608f5bdbc9ce7234128d7a4580b096ecea8e0e7b4edb9070", "exam_bench/portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "exam_bench/pr.py": "6a3a20caf0e10c0cc94410511a72d62c9fcda785f3abab1be2ad616d4ee16836", "exam_bench/preflight.py": "5619be0131d8641925f3ce2a3c8e5234d42aa5635d95676138ca81536d95cd29", "exam_bench/process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "exam_bench/queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "exam_bench/queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "exam_bench/replay_calibration.py": "c150457b0b23ce4e6814eb8deb4d48f6bc4a2e39d8f84a9dc7644fb99a026c2d", "exam_bench/report.py": "5e4c0757e1c7f189953f9a5302593ab726551835856baed25efd93dad6e8bfcd", "exam_bench/runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "exam_bench/smoke_check.py": "f36922a0027429ead0b414048dcc14bbe67f2f0e79a70d03dffbe1447d253545", "exam_bench/stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "exam_bench/submission.py": "3c5f703fcd90a1747884624e98b5caa1804dd422153106b96dcbb2810ee00544", "exam_bench/telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "exam_bench/windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "exam_bench/workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tools/build_public_site.py": "9682ed696f5ac9e9a82b65a45c0dece556ec7e49eeb20dcd616882cc534a8258", "tools/build_result_site.py": "3294e1d2ec1486058e208735264d61e349a68a4ae2fa2ec7a723c70e3263b496", "tools/check_native_harnesses.py": "4f5f0ed27651f78758eaef077b3b114361781f6b95ec40cb46c3fea689210473", "tools/check_native_toolkit.py": "0272794617121f2932828e5e4e9ae20095183c443666cf3ba466b44fbe875095", "tools/community_results.py": "cbfba30b4e617f5e219637c1c2de57398d01eb2f284eae3aca3ef684e6505a39", "tools/community_service.py": "c374480dbd88d656c0b9054fa04a8e1c6698c69e2f9cf475e82498a2dff61d84", "tools/community_setup.py": "5d7d126ed7d4dd48e1d79f57b99647a92ffcc8c9f80d90915e458888cdd76bf7", "tools/compare_harness_runs.py": "f274df5f3f804cb02504491aec946943833e12fbce6e62d281e12beb8508fc4e", "tools/create_run_plan.py": "871cd81b1eda231c0fba8805f63d2668926be9fc641559e6ddf320e2f47cd37a", "tools/demo_runner.py": "ca7ad17919c53d524cc0418751ba09a540f910eac183dca2961710bc30bba26f", "tools/installers.py": "9a2742780936b17500869e7c89202c1a2549e37d53a42ad9a50a0abbf78bbe09", "tools/machine_bundle.py": "8aa8346f99f537e81ceca6fb6ab9530e844954bab8eff87bf33d3602f81f8a30", "tools/prepare_native_harnesses.py": "aaa75ecf4022883984fa50c42d14d8e1a9fde2eeda03dab03b852bbc5efb2502", "tools/prepare_official_statement.py": "6b7028c78e90e798d6ef1a93b76520cc61a308c354fb9b87f7fad18b99800fad", "tools/prepare_open_exam_requirements.py": "544f4e378b9be5f166186f8788f8d454afdac2deb99d91d98421e39d01ba6d03", "tools/probe_harness.py": "1ed8ef93420d1484cbbfd151b7efc31b9a201ceb942dd05e3103efa22ffa7f27", "tools/probe_native_mcp.py": "9918d324129cba898993e07f8f8b6dbcbaf369398ebf28d464f9f1f00abdb254", "tools/readiness.py": "d34dd3f38334f51cc4574c79194cf0b80769b062a52382989a57d01c46b9aba4", "tools/recheck_community.py": "f0843d7d677f90da31e22bde0b1c86584dd46c022f1532d43d042619e426b230", "tools/regrade_runs.py": "011775afb06d3aac67a4aa81117a368c75896b0fcbe1e6f27ccc6237612fbf59", "tools/render_statement_text.py": "dabc0716a3612c288c671bc20e17fd4986691d732768e1e957d6dddddbea92a3", "tools/replay_calibration.py": "801f5004926c438c21ed3668fe2a4ddf45312b3e75320165a3839aae034eee9b", "tools/run_exam_campaign.py": "2c450d57a1cd0a2682838f5ec7c0a4ffb3aed0f1730d34c408e912d59cab6efd", "tools/serve_result_site.py": "86badfac863cd4ad1fc894a14110c75b28470513f0133eeae9d2799b8b4df3a9", "tools/start_demo.py": "c597e6cad28d245b3191654bb3e2801fa9dd2364e2acb25561923613717b615f", "tools/supplemental_acceptance.py": "c88fc39de1be1fdcacdd819e2ad329f60367b2df1d5deda80b37324bda3f2a01", "tools/sync_sources.py": "b51e889b0f41f9f63bfb19a09fb96d3777693d6b1d76fe0132bdd2a15e155898", "tools/validate_community_pr.py": "796b896dfade07b4529af2088a4b9b9d23484148b3bc0732b3fb837b75c9844b", "tools/verify_official_assessment_mapping.py": "daeb448a016940d5b6b1285979a56e5b9014bd91db40acb131445e4a83a23059", "tools/verify_task_package.py": "9e1e6105f6b5e4e78b36aa57f00117a9fbc8948ab53983c32ab56da88d23ccc4", "profiles/agents.json": "af9c492c08d13b3044aa6b6952589ed6a0a07d5258d8ff72bb18185b3eaebdc5", "profiles/ai-exam-execution-policy.json": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "profiles/bsl-analyzer-0.3.2-macos.json": "83537abdbf38c41ce665e4d0f24128bb51b62e971e0e0f368695f1326a7d2ffb", "profiles/bsl-analyzer-0.3.2-portable.json": "d6ba732e6778e256df34d6bc548593128820a70430c35b279796843606ee40a8", "profiles/bsl-ls-1.1.0-rc.6-macos.json": "245fc10747197e6911b2b4c77cdb15e6fa4eb7bc7c3758b63e768c5adf1df180", "profiles/bsl-ls-1.1.0-rc.6-portable.json": "9f10660881f2ec84794f7d584556b8f75c7e14b3555464af0ed0e60c4c892d86", "profiles/code-index-1.9.0-macos.json": "63a919523ce62ecec274f4c139bc7ad49a75dd4c339568b822cbc695b4e30408", "profiles/code-index-1.9.0-portable.json": "81106cee8f424ffd8a9dc46ecd8e4f57598fc1d49661a83c77b1f0507993fbdc", "profiles/codex-probe-plan.json": "166e41aad5fb3b27d9050bc6de952c6cba363cc6e804d4080568cc71a2a4d289", "profiles/machine.linux.example.json": "408304fd0581098d5d8110dc67dfeab353bc4d4030e32d37e6acf98d2b1aedfd", "profiles/machine.macos.example.json": "52e9f9d17797cb520b9d8955d6806fd550b899bed4da241ebf096dcb6a21a942", "profiles/machine.windows.example.json": "63accac9a2f81d47d03447efbabffd4760aee325193f02f46b9b29a28d50d2d8", "profiles/mcp-toolkit-1.9.0-macos.json": "1d3f9cde5ffa20589a840d01fdae03aa0fc2f412c929f064f203919c4129625b", "profiles/mcp-toolkit-1.9.0-portable.json": "8e370eebe773eef0e08045ee9c6d5be1451f769f65be0710834b262a4336e054", "profiles/none-macos.json": "b1401d9c48159aed3559006c7f6ace6ef4571224d5cf0bb76d1a823505a10056", "profiles/none-portable.json": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "profiles/rlm-tools-bsl-1.43.0-macos.json": "9354421052640ab60bc3e6aa98ff2e7ba9ca2318b0f4026c137487449242cbd2", "profiles/rlm-tools-bsl-1.43.0-portable.json": "2599e5645e0a7d4e44cb2934bc2b272cae79a9bf7ea74a23cd48aacea64bc424", "profiles/rlm-tools-bsl-1.43.0-posix-requirements.txt": "4fdf9a1bd994bf0272e65d231daf76cf19b0a34dad0ae6b50ec4f11a2ce4c330", "profiles/rlm-tools-bsl-1.43.0-windows-requirements.txt": "3730cb46c81cda5181ecd4485e98b11933104632358bc86f8c0eb1a612a8954f", "profiles/shirokov-skills-macos.json": "84f3e89091676884a802035c707e912762a1179425fb8e3faff25be736873cdb", "profiles/shirokov-skills-portable.json": "2b0a461e06602f1456410e70f02ceaa5ac32c6549c486660bcb5ace0c2f87b15", "profiles/shirokov-skills-windows-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/unica-0.12.3-macos.json": "2c39fbb591cf2c2c6e056373823615485397ea83651b7926c6f25a5fe6a0aae6", "profiles/unica-0.13.0-macos.json": "b76b5c8a4dd33f571c4a90993f1a2da5f7223b4f0f8e1042c282e21a66121052", "profiles/unica-0.14.0-rc.1-portable.json": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "rules/1c-specialist-platform/chistov.json": "77e04942f8c947b10759e7cc1eb31af05847d1711a772fbe6f23d525766757a9", "rules/1c-specialist-platform/decisions.json": "f622107423ce3c188c063318d7ab4f7718ceb38e443130677d8987f386641c09", "rules/1c-specialist-platform/examiner.json": "30353aa2a1b6545496b070d9066e9ffba0c3779e5b53ef70a4fd2cee375b18c0", "rules/1c-specialist-platform/ledger.json": "f167c10db2b5799dd9a1ea6a37cd2d7d186810dadf5ea2f50f26ae723c676882", "rules/1c-specialist-platform/rules.json": "1d320a4f8e1bf4701496388931f492315549bd3dce574b17285dd1d7f8652007", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" } } }, "conditions": { "client": "codex", "model": "gpt-6.1-sol", "client_version": "0.163.0-alpha.11.2", "reasoning_effort": "medium", "harness": "none", "billing_channel": "subscription", "solve_timeout_seconds": 7200, "time_series": null, "delegation": "native_disabled", "network_profile": "open-book_shell", "deadline_disclosed": true, "statement_sha256": "8a6ccb3e673826d1f8220fda53eb310e3ec18c136d87ce8f4cebb2a08614e7e5", "starter_dt_sha256": "f40d084818b0d1cfe503fc7653a6a13f1a8e47fcd1688dad6245b12744eb4638", "profile_sha256": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "execution_policy_sha256": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "calibration_sha256": "bacf42331c3b67ba858daa0123015ab0a965f13a20aa238eda22a7fcafa6237b", "started_at": "2026-10-24T09:52:52.981372+00:00", "timing": { "prepare_ms": 6203, "solve_ms": 5985485, "grade_ms": null }, "original_submission_valid": false, "model_provenance": "requested_only", "tokens": { "input": 21798127, "cached_input": 21643648, "fresh_input": 154479, "output": 167351, "reasoning_output": 81651, "total": 21965478, "coverage": "reported_completed_root_turns" }, "tools": { "mcp_calls": 0, "unica_calls": 0, "failed_calls": 0 }, "process": { "status": "completed", "exit_code": 0, "stop_confirmed": true } }, "verification": "contributor_reported", "download": "community-downloads/demo-20261025T110836Z-adapter/solution.zip", "source_context": "community-downloads/demo-20261025T110836Z-adapter/source-context.json", "regrade_required": [ { "id": "grader_changed", "files": [ "assessment.py", "bp.py", "calcwrite.py", "calibrate.py", "calibration_periodicity.py", "calibration_query.py", "claude.py", "codescan.py", "codex.py", "common.py", "docx_text.py", "examiner.py", "harness.py", "interpretations.py", "locking.py", "materials.py", "mcp_toolkit.py", "ou.py", "penalties.py", "portable_harnesses.py", "pr.py", "preflight.py", "queries.py", "queryschema.py", "querytypes.py", "replay_calibration.py", "rules/1c-specialist-platform/chistov.json", "rules/1c-specialist-platform/examiner.json", "rules/1c-specialist-platform/rules.json", "rules/1c-specialist-platform/standards.json", "smoke_check.py", "starters/carcass-8.3.25.1445/starter.json", "stdio_harnesses.py", "tasks/1c-platform-official-sample/checks.json", "tasks/1c-platform-official-sample/private/official-assessment-mapping.json", "tasks/1c-platform-official-sample/private/owner-scoring-policy.json", "telemetry.py" ] } ], "grader_revision_sha256": "855d4f66db31ec9f50ebfc18f596c0d1d157e53e2830c51f853c1338f628e49c", "archive_sha256": "436266377547a3bec13f09a95d2d14a0090336d65a4e618c86991e25c9d3b2a4" }, { "id": "demo-20261024T122808Z-side-recheck", "run_id": "demo-20261024T095243Z-21ac56", "result": { "run_id": "demo-20261024T095243Z-21ac56", "created_at": "2026-10-24T12:31:40.514862+00:00", "model": "gpt-6.1-sol", "harness": "none", "solve_seconds": 5985, "platform": "8.3.27.1644", "counts": { "pass": 64, "fail": 1 }, "rules": [ { "id": "BU01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU16", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU17", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU02", "verdict": "pass", "coverage": "partial", "reason": null }, { "id": "BU10", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU12", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU06", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU07", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU08", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU09", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU11", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU14", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU15", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU13", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU15", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU16", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU17", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU02", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU18", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU14", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU06", "verdict": "pass", "coverage": "no_violation_found", "reason": null }, { "id": "OU07", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU08", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU09", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU10", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU11", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU12", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU13", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU19", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU20", "verdict": "fail", "coverage": "selected_fixture", "reason": "Ведомость не прошла проверку группировки по значениям характеристик." }, { "id": "OU21", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR02", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR06", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR07", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR08", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR09", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR10", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR11", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR12", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR13", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR14", "verdict": "pass", "coverage": "no_violation_found", "reason": null }, { "id": "PR15", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR16", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR17", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR18", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR19", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F02", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "G01", "verdict": "pass", "coverage": "static_sources", "reason": null }, { "id": "G02", "verdict": "pass", "coverage": "static_sources", "reason": null }, { "id": "G03", "verdict": "pass", "coverage": "static_sources", "reason": null } ], "charges": [ { "id": "F1C-GEN03", "points": "0.5", "reason": "Ведомость не прошла проверку группировки по значениям характеристик." }, { "id": "F1C-PR14", "points": "0.5", "reason": "после расчёта набор с периодом действия перезаписывается целиком, с пересчётом фактического периода действия (нужно Записать(, Истина)): CommonModules/Учет/Ext/Module.bsl:374 Набор.Записать()" }, { "id": "F1C-BU06", "points": "1.5", "reason": "у счёта товаров 01.02 не включён признак учёта Количественный" }, { "id": "F1C-PR08", "points": "2.0", "reason": "база берётся из основной таблицы регистра расчёта, БазаНачисления нигде не используется: Documents/НачислениеЗарплаты/Ext/ObjectModule.bsl:6" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "оперативное проведение разрешено у документов с движениями по регистрам расчёта: НачислениеЗарплаты" }, { "id": "F1C-GEN21", "points": "2.0", "reason": "данные графика без отбора по регистратору: CommonModules/Учет/Ext/Module.bsl:450" }, { "id": "F1C-GEN22", "points": "1.0", "reason": "значения графика выбираются без ЕСТЬNULL: CommonModules/Учет/Ext/Module.bsl:450 ДниФактическийПериодДействия, ЧасыПериодДействия, ЧасыФактическийПериодДействия" } ], "score_upper_bound": "-3.5", "score": null, "grade": "unsatisfactory", "deductions": "8.5", "not_assessed": 15, "gates": { "starter_origin": "passed", "load": "loaded", "clients": "compiles", "demo_data": "present" }, "infrastructure_errors": false, "comparison_eligible": false, "binding_compatibility": { "scope": "supplemental_side_qualified_subconto_adapter", "original_binding_sha256": "7dd185357a65fd5945433b73122669e0bc5b3ac46a451afc7a72002616268448", "normalized_binding_sha256": "69f3a6b98c1f598333e61ee4b543e66304e709c4de135e0aa265bf76fd8f47b8", "normalizer_sha256": "d6f9d20704181c51714f1138affe4965d860ae21475ab7bb49aa5c5cefebb9f5", "changes": [ { "field": "fields.ledger.item_debit", "before": "СубконтоДт.Номенклатура", "after": "ВидыСубконто.Номенклатура" }, { "field": "fields.ledger.item_credit", "before": "СубконтоКт.Номенклатура", "after": "ВидыСубконто.Номенклатура" }, { "field": "fields.ledger.warehouse_debit", "before": "СубконтоДт.Склад", "after": "ВидыСубконто.Склад" }, { "field": "fields.ledger.warehouse_credit", "before": "СубконтоКт.Склад", "after": "ВидыСубконто.Склад" } ], "basis": "Exact predefined kinds of the declared account chart; matching debit/credit side and all role types checked." }, "evaluation_sha256": "f7ad77451176d728c2d8d666ead1afaf358e59534fd99550a30691fa7c5185aa", "downloads": [] }, "measurement": { "operator": { "name": "Вячеслав", "github": "sksibak" }, "environment": { "captured_at": "2026-10-24T09:52:46.342453+00:00", "capture_timing": "before_run", "hardware": { "cpu": "AMD Ryzen 5 4600H with Radeon Graphics ", "logical_cpus": 12, "ram_bytes": 16505962496 }, "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "python": "3.12.14", "platform_version": "8.3.27.1644", "isolation": "dedicated-host", "network_profile": "open-book_shell", "unsafe_action_protection_observed_in_user_config": true, "git_revision": "af85e791b303dbbf0b0b7af924d2489c3e57cfa8", "implementation_files": { "exam_bench/__init__.py": "ad5bf6f05dc6765f40b78bd186870ca2c49be113cfa33f8aa76f4926f2cb2c1e", "exam_bench/assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "exam_bench/bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "exam_bench/calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "exam_bench/calibrate.py": "78b5185cb0888c0c0ac3de95ffc3a80154a6de9ae66fc461f79d012e5a58e1db", "exam_bench/calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "exam_bench/calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "exam_bench/calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "exam_bench/calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "exam_bench/calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "exam_bench/claude.py": "bc1b8550de7573aaed5e39c6e9c0309e0d8175284a75490d61ec27439ed911ad", "exam_bench/cli.py": "1a37ce645633d761f7897dffc9c45e6b8b9600cd7bd233b1cbf78f49d26b099a", "exam_bench/codescan.py": "751e38001b6e65727a31e28172a0623f0bf34bc092a958037c286aa991a197ed", "exam_bench/codex.py": "c3f89d72af11f312d851c73a1610d92e79acadf336be9ccedd1f94ede3b3ccb0", "exam_bench/common.py": "8682603b519063e655eae3574a02a49efee63bde21f582ccee20ddd623fca96d", "exam_bench/docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "exam_bench/examiner.py": "d7294fdd23ed1732216cafebf0a8cf2c24cce4259859aeb7149f62b7607d087d", "exam_bench/finalize.py": "4034f1c63896a940afdb1a83d541cf47fc75c8b5061e3f839047109c04beb620", "exam_bench/forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "exam_bench/gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "exam_bench/grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "exam_bench/harness.py": "3040f6daaf1dc6e6583219f4d925151f8ba7851b2d5417d7f14645892b485ddf", "exam_bench/interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "exam_bench/interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "exam_bench/isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "exam_bench/ledger.py": "7e851523580e22d8490e75f9b6026c07f2c355007e0d11d0b252671f56bef654", "exam_bench/locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "exam_bench/materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "exam_bench/mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "exam_bench/observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "exam_bench/ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "exam_bench/penalties.py": "0d79e2e46102657dca00609b6abbfc0bf7d11fad41429564f876c82bc6b33269", "exam_bench/platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "exam_bench/portable.py": "cad56968ff407983608f5bdbc9ce7234128d7a4580b096ecea8e0e7b4edb9070", "exam_bench/portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "exam_bench/pr.py": "6a3a20caf0e10c0cc94410511a72d62c9fcda785f3abab1be2ad616d4ee16836", "exam_bench/preflight.py": "5619be0131d8641925f3ce2a3c8e5234d42aa5635d95676138ca81536d95cd29", "exam_bench/process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "exam_bench/queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "exam_bench/queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "exam_bench/replay_calibration.py": "c150457b0b23ce4e6814eb8deb4d48f6bc4a2e39d8f84a9dc7644fb99a026c2d", "exam_bench/report.py": "5e4c0757e1c7f189953f9a5302593ab726551835856baed25efd93dad6e8bfcd", "exam_bench/runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "exam_bench/smoke_check.py": "f36922a0027429ead0b414048dcc14bbe67f2f0e79a70d03dffbe1447d253545", "exam_bench/stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "exam_bench/submission.py": "3c5f703fcd90a1747884624e98b5caa1804dd422153106b96dcbb2810ee00544", "exam_bench/telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "exam_bench/windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "exam_bench/workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tools/build_public_site.py": "9682ed696f5ac9e9a82b65a45c0dece556ec7e49eeb20dcd616882cc534a8258", "tools/build_result_site.py": "3294e1d2ec1486058e208735264d61e349a68a4ae2fa2ec7a723c70e3263b496", "tools/check_native_harnesses.py": "4f5f0ed27651f78758eaef077b3b114361781f6b95ec40cb46c3fea689210473", "tools/check_native_toolkit.py": "0272794617121f2932828e5e4e9ae20095183c443666cf3ba466b44fbe875095", "tools/community_results.py": "cbfba30b4e617f5e219637c1c2de57398d01eb2f284eae3aca3ef684e6505a39", "tools/community_service.py": "c374480dbd88d656c0b9054fa04a8e1c6698c69e2f9cf475e82498a2dff61d84", "tools/community_setup.py": "5d7d126ed7d4dd48e1d79f57b99647a92ffcc8c9f80d90915e458888cdd76bf7", "tools/compare_harness_runs.py": "f274df5f3f804cb02504491aec946943833e12fbce6e62d281e12beb8508fc4e", "tools/create_run_plan.py": "871cd81b1eda231c0fba8805f63d2668926be9fc641559e6ddf320e2f47cd37a", "tools/demo_runner.py": "ca7ad17919c53d524cc0418751ba09a540f910eac183dca2961710bc30bba26f", "tools/installers.py": "9a2742780936b17500869e7c89202c1a2549e37d53a42ad9a50a0abbf78bbe09", "tools/machine_bundle.py": "8aa8346f99f537e81ceca6fb6ab9530e844954bab8eff87bf33d3602f81f8a30", "tools/prepare_native_harnesses.py": "aaa75ecf4022883984fa50c42d14d8e1a9fde2eeda03dab03b852bbc5efb2502", "tools/prepare_official_statement.py": "6b7028c78e90e798d6ef1a93b76520cc61a308c354fb9b87f7fad18b99800fad", "tools/prepare_open_exam_requirements.py": "544f4e378b9be5f166186f8788f8d454afdac2deb99d91d98421e39d01ba6d03", "tools/probe_harness.py": "1ed8ef93420d1484cbbfd151b7efc31b9a201ceb942dd05e3103efa22ffa7f27", "tools/probe_native_mcp.py": "9918d324129cba898993e07f8f8b6dbcbaf369398ebf28d464f9f1f00abdb254", "tools/readiness.py": "d34dd3f38334f51cc4574c79194cf0b80769b062a52382989a57d01c46b9aba4", "tools/recheck_community.py": "f0843d7d677f90da31e22bde0b1c86584dd46c022f1532d43d042619e426b230", "tools/regrade_runs.py": "011775afb06d3aac67a4aa81117a368c75896b0fcbe1e6f27ccc6237612fbf59", "tools/render_statement_text.py": "dabc0716a3612c288c671bc20e17fd4986691d732768e1e957d6dddddbea92a3", "tools/replay_calibration.py": "801f5004926c438c21ed3668fe2a4ddf45312b3e75320165a3839aae034eee9b", "tools/run_exam_campaign.py": "2c450d57a1cd0a2682838f5ec7c0a4ffb3aed0f1730d34c408e912d59cab6efd", "tools/serve_result_site.py": "86badfac863cd4ad1fc894a14110c75b28470513f0133eeae9d2799b8b4df3a9", "tools/start_demo.py": "c597e6cad28d245b3191654bb3e2801fa9dd2364e2acb25561923613717b615f", "tools/supplemental_acceptance.py": "c88fc39de1be1fdcacdd819e2ad329f60367b2df1d5deda80b37324bda3f2a01", "tools/sync_sources.py": "b51e889b0f41f9f63bfb19a09fb96d3777693d6b1d76fe0132bdd2a15e155898", "tools/validate_community_pr.py": "796b896dfade07b4529af2088a4b9b9d23484148b3bc0732b3fb837b75c9844b", "tools/verify_official_assessment_mapping.py": "daeb448a016940d5b6b1285979a56e5b9014bd91db40acb131445e4a83a23059", "tools/verify_task_package.py": "9e1e6105f6b5e4e78b36aa57f00117a9fbc8948ab53983c32ab56da88d23ccc4", "profiles/agents.json": "af9c492c08d13b3044aa6b6952589ed6a0a07d5258d8ff72bb18185b3eaebdc5", "profiles/ai-exam-execution-policy.json": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "profiles/bsl-analyzer-0.3.2-macos.json": "83537abdbf38c41ce665e4d0f24128bb51b62e971e0e0f368695f1326a7d2ffb", "profiles/bsl-analyzer-0.3.2-portable.json": "d6ba732e6778e256df34d6bc548593128820a70430c35b279796843606ee40a8", "profiles/bsl-ls-1.1.0-rc.6-macos.json": "245fc10747197e6911b2b4c77cdb15e6fa4eb7bc7c3758b63e768c5adf1df180", "profiles/bsl-ls-1.1.0-rc.6-portable.json": "9f10660881f2ec84794f7d584556b8f75c7e14b3555464af0ed0e60c4c892d86", "profiles/code-index-1.9.0-macos.json": "63a919523ce62ecec274f4c139bc7ad49a75dd4c339568b822cbc695b4e30408", "profiles/code-index-1.9.0-portable.json": "81106cee8f424ffd8a9dc46ecd8e4f57598fc1d49661a83c77b1f0507993fbdc", "profiles/codex-probe-plan.json": "166e41aad5fb3b27d9050bc6de952c6cba363cc6e804d4080568cc71a2a4d289", "profiles/machine.linux.example.json": "408304fd0581098d5d8110dc67dfeab353bc4d4030e32d37e6acf98d2b1aedfd", "profiles/machine.macos.example.json": "52e9f9d17797cb520b9d8955d6806fd550b899bed4da241ebf096dcb6a21a942", "profiles/machine.windows.example.json": "63accac9a2f81d47d03447efbabffd4760aee325193f02f46b9b29a28d50d2d8", "profiles/mcp-toolkit-1.9.0-macos.json": "1d3f9cde5ffa20589a840d01fdae03aa0fc2f412c929f064f203919c4129625b", "profiles/mcp-toolkit-1.9.0-portable.json": "8e370eebe773eef0e08045ee9c6d5be1451f769f65be0710834b262a4336e054", "profiles/none-macos.json": "b1401d9c48159aed3559006c7f6ace6ef4571224d5cf0bb76d1a823505a10056", "profiles/none-portable.json": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "profiles/rlm-tools-bsl-1.43.0-macos.json": "9354421052640ab60bc3e6aa98ff2e7ba9ca2318b0f4026c137487449242cbd2", "profiles/rlm-tools-bsl-1.43.0-portable.json": "2599e5645e0a7d4e44cb2934bc2b272cae79a9bf7ea74a23cd48aacea64bc424", "profiles/rlm-tools-bsl-1.43.0-posix-requirements.txt": "4fdf9a1bd994bf0272e65d231daf76cf19b0a34dad0ae6b50ec4f11a2ce4c330", "profiles/rlm-tools-bsl-1.43.0-windows-requirements.txt": "3730cb46c81cda5181ecd4485e98b11933104632358bc86f8c0eb1a612a8954f", "profiles/shirokov-skills-macos.json": "84f3e89091676884a802035c707e912762a1179425fb8e3faff25be736873cdb", "profiles/shirokov-skills-portable.json": "2b0a461e06602f1456410e70f02ceaa5ac32c6549c486660bcb5ace0c2f87b15", "profiles/shirokov-skills-windows-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/unica-0.12.3-macos.json": "2c39fbb591cf2c2c6e056373823615485397ea83651b7926c6f25a5fe6a0aae6", "profiles/unica-0.13.0-macos.json": "b76b5c8a4dd33f571c4a90993f1a2da5f7223b4f0f8e1042c282e21a66121052", "profiles/unica-0.14.0-rc.1-portable.json": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "rules/1c-specialist-platform/chistov.json": "77e04942f8c947b10759e7cc1eb31af05847d1711a772fbe6f23d525766757a9", "rules/1c-specialist-platform/decisions.json": "f622107423ce3c188c063318d7ab4f7718ceb38e443130677d8987f386641c09", "rules/1c-specialist-platform/examiner.json": "30353aa2a1b6545496b070d9066e9ffba0c3779e5b53ef70a4fd2cee375b18c0", "rules/1c-specialist-platform/ledger.json": "f167c10db2b5799dd9a1ea6a37cd2d7d186810dadf5ea2f50f26ae723c676882", "rules/1c-specialist-platform/rules.json": "1d320a4f8e1bf4701496388931f492315549bd3dce574b17285dd1d7f8652007", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" } } }, "conditions": { "client": "codex", "model": "gpt-6.1-sol", "client_version": "0.163.0-alpha.11.2", "reasoning_effort": "medium", "harness": "none", "billing_channel": "subscription", "solve_timeout_seconds": 7200, "time_series": null, "delegation": "native_disabled", "network_profile": "open-book_shell", "deadline_disclosed": true, "statement_sha256": "8a6ccb3e673826d1f8220fda53eb310e3ec18c136d87ce8f4cebb2a08614e7e5", "starter_dt_sha256": "f40d084818b0d1cfe503fc7653a6a13f1a8e47fcd1688dad6245b12744eb4638", "profile_sha256": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "execution_policy_sha256": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "calibration_sha256": "bacf42331c3b67ba858daa0123015ab0a965f13a20aa238eda22a7fcafa6237b", "started_at": "2026-10-24T09:52:52.981372+00:00", "timing": { "prepare_ms": 6203, "solve_ms": 5985485, "grade_ms": null }, "original_submission_valid": false, "model_provenance": "requested_only", "tokens": { "input": 21798127, "cached_input": 21643648, "fresh_input": 154479, "output": 167351, "reasoning_output": 81651, "total": 21965478, "coverage": "reported_completed_root_turns" }, "tools": { "mcp_calls": 0, "unica_calls": 0, "failed_calls": 0 }, "process": { "status": "completed", "exit_code": 0, "stop_confirmed": true } }, "verification": "contributor_reported", "download": "community-downloads/demo-20261024T122808Z-side-recheck/solution.zip", "source_context": "community-downloads/demo-20261024T122808Z-side-recheck/source-context.json", "regrade_required": [ { "id": "grader_changed", "files": [ "assessment.py", "bp.py", "calcwrite.py", "calibrate.py", "calibration_periodicity.py", "calibration_query.py", "claude.py", "codescan.py", "codex.py", "common.py", "docx_text.py", "examiner.py", "harness.py", "interpretations.py", "locking.py", "materials.py", "mcp_toolkit.py", "ou.py", "penalties.py", "portable_harnesses.py", "pr.py", "preflight.py", "queries.py", "queryschema.py", "querytypes.py", "replay_calibration.py", "rules/1c-specialist-platform/chistov.json", "rules/1c-specialist-platform/examiner.json", "rules/1c-specialist-platform/rules.json", "rules/1c-specialist-platform/standards.json", "smoke_check.py", "starters/carcass-8.3.25.1445/starter.json", "stdio_harnesses.py", "submission.py", "tasks/1c-platform-official-sample/checks.json", "tasks/1c-platform-official-sample/private/official-assessment-mapping.json", "tasks/1c-platform-official-sample/private/owner-scoring-policy.json", "telemetry.py" ] }, { "id": "adapter_not_in_repository" } ], "grader_revision_sha256": "13710d802a08278385c484500f48f1678e0b002e5c7a3d8c00e14c1e75b1fbe9", "archive_sha256": "edd02ca2ba7a8b6cc11b8d22e8798030bfba2e43eaa8e5b69c42cad770150c07" } ] }, { "id": "demo-20261025T113017Z-40b49c--owner-2026-10-26T223312210970-0000", "run_id": "demo-20261024T123219Z-93678e", "result": { "run_id": "demo-20261024T123219Z-93678e", "created_at": "2026-10-26T22:33:12.210970+00:00", "model": "gpt-6.1-sol", "harness": "none", "solve_seconds": 10418, "platform": "8.3.27.1644", "counts": { "pass": 63, "inconclusive": 1, "fail": 1 }, "rules": [ { "id": "BU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU01.selected_fixture" }, { "id": "BU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU04.selected_fixture" }, { "id": "BU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU05.selected_fixture" }, { "id": "BU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU16.selected_fixture" }, { "id": "BU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU17.selected_fixture" }, { "id": "BU02", "verdict": "pass", "reason": null, "coverage": "partial", "assertion_id": "BU02.posting_cost_and_balance" }, { "id": "BU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU10.selected_fixture" }, { "id": "BU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU12.selected_fixture" }, { "id": "BU03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU03.selected_fixture" }, { "id": "BU06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU06.selected_fixture" }, { "id": "BU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU07.selected_fixture" }, { "id": "BU08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU08.selected_fixture" }, { "id": "BU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU09.selected_fixture" }, { "id": "BU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU11.selected_fixture" }, { "id": "BU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU14.selected_fixture" }, { "id": "BU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU15.selected_fixture" }, { "id": "BU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU13.selected_fixture" }, { "id": "OU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU15.selected_fixture" }, { "id": "OU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU16.selected_fixture" }, { "id": "OU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU17.selected_fixture" }, { "id": "OU02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU02.selected_fixture" }, { "id": "OU18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU18.selected_fixture" }, { "id": "OU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU14.selected_fixture" }, { "id": "OU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU01.selected_fixture" }, { "id": "OU03", "verdict": "pass", "reason": "История и годовая периодичность регистра подтверждены.", "coverage": "history_and_periodicity", "assertion_id": "OU03.selected_fixture" }, { "id": "OU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU05.selected_fixture" }, { "id": "OU06", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "OU06.selected_fixture" }, { "id": "OU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU07.selected_fixture" }, { "id": "OU08", "verdict": "inconclusive", "reason": "Недостаточно данных: периодичность регистра specification — Second, ожидается Day; проверка другим способом не исключена", "coverage": "history_and_periodicity", "assertion_id": "OU08.selected_fixture" }, { "id": "OU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU09.selected_fixture" }, { "id": "OU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU10.selected_fixture" }, { "id": "OU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU11.selected_fixture" }, { "id": "OU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU12.selected_fixture" }, { "id": "OU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU13.selected_fixture" }, { "id": "OU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU04.selected_fixture" }, { "id": "OU19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU19.selected_fixture" }, { "id": "OU20", "verdict": "fail", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU20.selected_fixture" }, { "id": "OU21", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU21.selected_fixture" }, { "id": "PR01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR01.selected_fixture" }, { "id": "PR02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR02.selected_fixture" }, { "id": "PR03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR03.selected_fixture" }, { "id": "PR04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR04.selected_fixture" }, { "id": "PR05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR05.selected_fixture" }, { "id": "PR06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR06.selected_fixture" }, { "id": "PR07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR07.selected_fixture" }, { "id": "PR08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR08.selected_fixture" }, { "id": "PR09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR09.selected_fixture" }, { "id": "PR10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR10.selected_fixture" }, { "id": "PR11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR11.selected_fixture" }, { "id": "PR12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR12.selected_fixture" }, { "id": "PR13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR13.selected_fixture" }, { "id": "PR14", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "PR14.selected_fixture" }, { "id": "PR15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR15.selected_fixture" }, { "id": "PR16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR16.selected_fixture" }, { "id": "PR17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR17.selected_fixture" }, { "id": "PR18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR18.selected_fixture" }, { "id": "PR19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR19.selected_fixture" }, { "id": "F01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F01.selected_fixture" }, { "id": "F02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F02.selected_fixture" }, { "id": "F03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F03.selected_fixture" }, { "id": "F04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F04.selected_fixture" }, { "id": "F05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F05.selected_fixture" }, { "id": "G01", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G01.static_sources" }, { "id": "G02", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G02.static_sources" }, { "id": "G03", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G03.static_sources" } ], "charges": [ { "id": "F1C-GEN03", "points": "0.5", "reason": "отчёт не соответствует заданию: OU20" }, { "id": "F1C-PR09", "points": "0.5", "reason": "CommonModules/РасчетЗарплаты/Ext/Module.bsl:124 — РегистрРасчета.Начисления.БазаНачисления: база получается без отбора по регистратору — по всем записям регистра" }, { "id": "F1C-PR09", "points": "0.5", "reason": "CommonModules/РасчетЗарплаты/Ext/Module.bsl:138 — РегистрРасчета.Начисления.БазаНачисления: база получается без отбора по регистратору — по всем записям регистра" }, { "id": "F1C-GEN15", "points": "0.5", "reason": "Reports/Премии/Ext/ManagerModule.bsl:4 — РегистрРасчета.Начисления: отбор по ВидРасчета, ПериодДействияНачало, индексы таблицы начинаются с ПериодДействия, ПериодРегистрации, Подразделение, Регистратор, Сотрудник" }, { "id": "F1C-PR14", "points": "0.5", "reason": "после расчёта набор с периодом действия перезаписывается целиком, с пересчётом фактического периода действия (нужно Записать(, Истина)): CommonModules/РасчетЗарплаты/Ext/Module.bsl:182 Н.Записать(Истина)" }, { "id": "F1C-BU05", "points": "0.5", "reason": "аналитика счетов вынесена в измерения регистра бухгалтерии и есть у всех счетов: Номенклатура (Номенклатура)" }, { "id": "F1C-GEN20", "points": "2.0", "reason": "данные базы читаются в цикле по записям: CommonModules/ОтчетыСервер/Ext/Module.bsl:25; CommonModules/ОтчетыСервер/Ext/Module.bsl:79; CommonModules/УчетСервер/Ext/Module.bsl:71 и ещё 3" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "оперативное проведение разрешено у документов с движениями по регистрам расчёта: НачислениеЗарплаты" }, { "id": "F1C-GEN21", "points": "2.0", "reason": "данные графика без отбора по регистратору: CommonModules/РасчетЗарплаты/Ext/Module.bsl:78" }, { "id": "F1C-GEN22", "points": "1.0", "reason": "значения графика выбираются без ЕСТЬNULL: CommonModules/РасчетЗарплаты/Ext/Module.bsl:78 ДниПериодДействия, ДниФактическийПериодДействия, ЗначениеПериодДействия, ЗначениеФактическийПериодДействия" } ], "score_upper_bound": "-4.0", "score": null, "grade": "unsatisfactory", "deductions": "9.0", "not_assessed": 16, "gates": { "starter_origin": "passed", "load": "loaded", "clients": "compiles", "demo_data": "present" }, "infrastructure_errors": false, "comparison_eligible": false, "binding_compatibility": null }, "measurement": { "operator": { "name": "Вячеслав", "github": "sksibak" }, "environment": { "captured_at": "2026-10-24T12:32:21.466495+00:00", "capture_timing": "before_run", "hardware": { "cpu": "AMD Ryzen 5 4600H with Radeon Graphics ", "logical_cpus": 12, "ram_bytes": 16505962496 }, "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "python": "3.12.14", "platform_version": "8.3.27.1644", "isolation": "dedicated-host", "network_profile": "open-book_shell", "unsafe_action_protection_observed_in_user_config": true, "git_revision": "af85e791b303dbbf0b0b7af924d2489c3e57cfa8", "implementation_files": { "exam_bench/__init__.py": "ad5bf6f05dc6765f40b78bd186870ca2c49be113cfa33f8aa76f4926f2cb2c1e", "exam_bench/assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "exam_bench/bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "exam_bench/calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "exam_bench/calibrate.py": "78b5185cb0888c0c0ac3de95ffc3a80154a6de9ae66fc461f79d012e5a58e1db", "exam_bench/calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "exam_bench/calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "exam_bench/calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "exam_bench/calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "exam_bench/calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "exam_bench/claude.py": "bc1b8550de7573aaed5e39c6e9c0309e0d8175284a75490d61ec27439ed911ad", "exam_bench/cli.py": "1a37ce645633d761f7897dffc9c45e6b8b9600cd7bd233b1cbf78f49d26b099a", "exam_bench/codescan.py": "751e38001b6e65727a31e28172a0623f0bf34bc092a958037c286aa991a197ed", "exam_bench/codex.py": "c3f89d72af11f312d851c73a1610d92e79acadf336be9ccedd1f94ede3b3ccb0", "exam_bench/common.py": "8682603b519063e655eae3574a02a49efee63bde21f582ccee20ddd623fca96d", "exam_bench/docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "exam_bench/examiner.py": "d7294fdd23ed1732216cafebf0a8cf2c24cce4259859aeb7149f62b7607d087d", "exam_bench/finalize.py": "4034f1c63896a940afdb1a83d541cf47fc75c8b5061e3f839047109c04beb620", "exam_bench/forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "exam_bench/gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "exam_bench/grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "exam_bench/harness.py": "3040f6daaf1dc6e6583219f4d925151f8ba7851b2d5417d7f14645892b485ddf", "exam_bench/interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "exam_bench/interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "exam_bench/isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "exam_bench/ledger.py": "7e851523580e22d8490e75f9b6026c07f2c355007e0d11d0b252671f56bef654", "exam_bench/locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "exam_bench/materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "exam_bench/mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "exam_bench/observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "exam_bench/ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "exam_bench/penalties.py": "0d79e2e46102657dca00609b6abbfc0bf7d11fad41429564f876c82bc6b33269", "exam_bench/platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "exam_bench/portable.py": "cad56968ff407983608f5bdbc9ce7234128d7a4580b096ecea8e0e7b4edb9070", "exam_bench/portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "exam_bench/pr.py": "6a3a20caf0e10c0cc94410511a72d62c9fcda785f3abab1be2ad616d4ee16836", "exam_bench/preflight.py": "5619be0131d8641925f3ce2a3c8e5234d42aa5635d95676138ca81536d95cd29", "exam_bench/process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "exam_bench/queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "exam_bench/queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "exam_bench/replay_calibration.py": "c150457b0b23ce4e6814eb8deb4d48f6bc4a2e39d8f84a9dc7644fb99a026c2d", "exam_bench/report.py": "5e4c0757e1c7f189953f9a5302593ab726551835856baed25efd93dad6e8bfcd", "exam_bench/runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "exam_bench/smoke_check.py": "f36922a0027429ead0b414048dcc14bbe67f2f0e79a70d03dffbe1447d253545", "exam_bench/stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "exam_bench/submission.py": "d6f9d20704181c51714f1138affe4965d860ae21475ab7bb49aa5c5cefebb9f5", "exam_bench/telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "exam_bench/windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "exam_bench/workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tools/build_public_site.py": "9682ed696f5ac9e9a82b65a45c0dece556ec7e49eeb20dcd616882cc534a8258", "tools/build_result_site.py": "3294e1d2ec1486058e208735264d61e349a68a4ae2fa2ec7a723c70e3263b496", "tools/check_native_harnesses.py": "4f5f0ed27651f78758eaef077b3b114361781f6b95ec40cb46c3fea689210473", "tools/check_native_toolkit.py": "0272794617121f2932828e5e4e9ae20095183c443666cf3ba466b44fbe875095", "tools/community_results.py": "9db56a44697d94f326efcbd7a3ae1aecdb569d43bba6c47e80ce525dc045f1f7", "tools/community_service.py": "c374480dbd88d656c0b9054fa04a8e1c6698c69e2f9cf475e82498a2dff61d84", "tools/community_setup.py": "5d7d126ed7d4dd48e1d79f57b99647a92ffcc8c9f80d90915e458888cdd76bf7", "tools/compare_harness_runs.py": "f274df5f3f804cb02504491aec946943833e12fbce6e62d281e12beb8508fc4e", "tools/create_run_plan.py": "871cd81b1eda231c0fba8805f63d2668926be9fc641559e6ddf320e2f47cd37a", "tools/demo_runner.py": "230e6e49068f2bab3a0db64e6da5889e8f1834158fed8c5ec334b7694695a87b", "tools/installers.py": "9a2742780936b17500869e7c89202c1a2549e37d53a42ad9a50a0abbf78bbe09", "tools/machine_bundle.py": "8aa8346f99f537e81ceca6fb6ab9530e844954bab8eff87bf33d3602f81f8a30", "tools/prepare_native_harnesses.py": "aaa75ecf4022883984fa50c42d14d8e1a9fde2eeda03dab03b852bbc5efb2502", "tools/prepare_official_statement.py": "6b7028c78e90e798d6ef1a93b76520cc61a308c354fb9b87f7fad18b99800fad", "tools/prepare_open_exam_requirements.py": "544f4e378b9be5f166186f8788f8d454afdac2deb99d91d98421e39d01ba6d03", "tools/probe_harness.py": "1ed8ef93420d1484cbbfd151b7efc31b9a201ceb942dd05e3103efa22ffa7f27", "tools/probe_native_mcp.py": "9918d324129cba898993e07f8f8b6dbcbaf369398ebf28d464f9f1f00abdb254", "tools/readiness.py": "d34dd3f38334f51cc4574c79194cf0b80769b062a52382989a57d01c46b9aba4", "tools/recheck_community.py": "f0843d7d677f90da31e22bde0b1c86584dd46c022f1532d43d042619e426b230", "tools/regrade_runs.py": "011775afb06d3aac67a4aa81117a368c75896b0fcbe1e6f27ccc6237612fbf59", "tools/render_statement_text.py": "dabc0716a3612c288c671bc20e17fd4986691d732768e1e957d6dddddbea92a3", "tools/replay_calibration.py": "801f5004926c438c21ed3668fe2a4ddf45312b3e75320165a3839aae034eee9b", "tools/run_exam_campaign.py": "2c450d57a1cd0a2682838f5ec7c0a4ffb3aed0f1730d34c408e912d59cab6efd", "tools/serve_result_site.py": "86badfac863cd4ad1fc894a14110c75b28470513f0133eeae9d2799b8b4df3a9", "tools/start_demo.py": "c597e6cad28d245b3191654bb3e2801fa9dd2364e2acb25561923613717b615f", "tools/supplemental_acceptance.py": "c88fc39de1be1fdcacdd819e2ad329f60367b2df1d5deda80b37324bda3f2a01", "tools/sync_sources.py": "b51e889b0f41f9f63bfb19a09fb96d3777693d6b1d76fe0132bdd2a15e155898", "tools/validate_community_pr.py": "796b896dfade07b4529af2088a4b9b9d23484148b3bc0732b3fb837b75c9844b", "tools/verify_official_assessment_mapping.py": "daeb448a016940d5b6b1285979a56e5b9014bd91db40acb131445e4a83a23059", "tools/verify_task_package.py": "9e1e6105f6b5e4e78b36aa57f00117a9fbc8948ab53983c32ab56da88d23ccc4", "profiles/agents.json": "af9c492c08d13b3044aa6b6952589ed6a0a07d5258d8ff72bb18185b3eaebdc5", "profiles/ai-exam-execution-policy.json": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "profiles/bsl-analyzer-0.3.2-macos.json": "83537abdbf38c41ce665e4d0f24128bb51b62e971e0e0f368695f1326a7d2ffb", "profiles/bsl-analyzer-0.3.2-portable.json": "d6ba732e6778e256df34d6bc548593128820a70430c35b279796843606ee40a8", "profiles/bsl-ls-1.1.0-rc.6-macos.json": "245fc10747197e6911b2b4c77cdb15e6fa4eb7bc7c3758b63e768c5adf1df180", "profiles/bsl-ls-1.1.0-rc.6-portable.json": "9f10660881f2ec84794f7d584556b8f75c7e14b3555464af0ed0e60c4c892d86", "profiles/code-index-1.9.0-macos.json": "63a919523ce62ecec274f4c139bc7ad49a75dd4c339568b822cbc695b4e30408", "profiles/code-index-1.9.0-portable.json": "81106cee8f424ffd8a9dc46ecd8e4f57598fc1d49661a83c77b1f0507993fbdc", "profiles/codex-probe-plan.json": "166e41aad5fb3b27d9050bc6de952c6cba363cc6e804d4080568cc71a2a4d289", "profiles/machine.linux.example.json": "408304fd0581098d5d8110dc67dfeab353bc4d4030e32d37e6acf98d2b1aedfd", "profiles/machine.macos.example.json": "52e9f9d17797cb520b9d8955d6806fd550b899bed4da241ebf096dcb6a21a942", "profiles/machine.windows.example.json": "63accac9a2f81d47d03447efbabffd4760aee325193f02f46b9b29a28d50d2d8", "profiles/mcp-toolkit-1.9.0-macos.json": "1d3f9cde5ffa20589a840d01fdae03aa0fc2f412c929f064f203919c4129625b", "profiles/mcp-toolkit-1.9.0-portable.json": "8e370eebe773eef0e08045ee9c6d5be1451f769f65be0710834b262a4336e054", "profiles/none-macos.json": "b1401d9c48159aed3559006c7f6ace6ef4571224d5cf0bb76d1a823505a10056", "profiles/none-portable.json": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "profiles/rlm-tools-bsl-1.43.0-macos.json": "9354421052640ab60bc3e6aa98ff2e7ba9ca2318b0f4026c137487449242cbd2", "profiles/rlm-tools-bsl-1.43.0-portable.json": "2599e5645e0a7d4e44cb2934bc2b272cae79a9bf7ea74a23cd48aacea64bc424", "profiles/rlm-tools-bsl-1.43.0-posix-requirements.txt": "4fdf9a1bd994bf0272e65d231daf76cf19b0a34dad0ae6b50ec4f11a2ce4c330", "profiles/rlm-tools-bsl-1.43.0-windows-requirements.txt": "3730cb46c81cda5181ecd4485e98b11933104632358bc86f8c0eb1a612a8954f", "profiles/shirokov-skills-macos.json": "84f3e89091676884a802035c707e912762a1179425fb8e3faff25be736873cdb", "profiles/shirokov-skills-portable.json": "2b0a461e06602f1456410e70f02ceaa5ac32c6549c486660bcb5ace0c2f87b15", "profiles/shirokov-skills-windows-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/unica-0.12.3-macos.json": "2c39fbb591cf2c2c6e056373823615485397ea83651b7926c6f25a5fe6a0aae6", "profiles/unica-0.13.0-macos.json": "b76b5c8a4dd33f571c4a90993f1a2da5f7223b4f0f8e1042c282e21a66121052", "profiles/unica-0.14.0-rc.1-portable.json": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "rules/1c-specialist-platform/chistov.json": "77e04942f8c947b10759e7cc1eb31af05847d1711a772fbe6f23d525766757a9", "rules/1c-specialist-platform/decisions.json": "f622107423ce3c188c063318d7ab4f7718ceb38e443130677d8987f386641c09", "rules/1c-specialist-platform/examiner.json": "30353aa2a1b6545496b070d9066e9ffba0c3779e5b53ef70a4fd2cee375b18c0", "rules/1c-specialist-platform/ledger.json": "f167c10db2b5799dd9a1ea6a37cd2d7d186810dadf5ea2f50f26ae723c676882", "rules/1c-specialist-platform/rules.json": "1d320a4f8e1bf4701496388931f492315549bd3dce574b17285dd1d7f8652007", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" } } }, "conditions": { "client": "codex", "model": "gpt-6.1-sol", "client_version": "0.163.0-alpha.11.2", "reasoning_effort": "medium", "harness": "none", "billing_channel": "subscription", "solve_timeout_seconds": 10800, "time_series": null, "delegation": "native_disabled", "network_profile": "open-book_shell", "deadline_disclosed": true, "statement_sha256": "8a6ccb3e673826d1f8220fda53eb310e3ec18c136d87ce8f4cebb2a08614e7e5", "starter_dt_sha256": "f40d084818b0d1cfe503fc7653a6a13f1a8e47fcd1688dad6245b12744eb4638", "profile_sha256": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "execution_policy_sha256": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "calibration_sha256": "e8981744a194aa56f954d2965aa66cd53cd4f899f09fa7b5abda6f6b27a5ed65", "started_at": "2026-10-24T12:32:28.378363+00:00", "timing": { "prepare_ms": 6422, "solve_ms": 10418234, "grade_ms": null }, "original_submission_valid": true, "model_provenance": "requested_only", "tokens": { "input": 31056671, "cached_input": 30889088, "fresh_input": 167583, "output": 265179, "reasoning_output": 159437, "total": 31321850, "coverage": "reported_completed_root_turns" }, "tools": { "mcp_calls": 0, "unica_calls": 0, "failed_calls": 0 }, "process": { "status": "completed", "exit_code": 0, "stop_confirmed": true } }, "verification": "repository_owner", "download": "community-downloads/demo-20261025T113017Z-40b49c--owner-2026-10-26T223312210970-0000/solution.zip", "source_context": "community-downloads/demo-20261025T113017Z-40b49c--owner-2026-10-26T223312210970-0000/source-context.json", "regrade_required": [], "grader_revision_sha256": "9aee1ffe0e1d04f9158fbbbeed3a403a5f0550ad8a590d7a6394977590760e1a", "archive_sha256": "c3b8e8189068f1a39624db41bf3e5384714b04996db72d101b04c36f6c2fb43a", "owner_verification": { "kind": "repository_owner", "repository": "zeegin/1c-agent-exam-benchmark", "operator": { "name": "Ingvar Vilkman", "github": "zeegin" }, "started_at": "2026-10-26T22:33:12.056428+00:00", "server": { "name": "Owner Windows stand", "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "hardware": { "cpu": "AMD Ryzen 7 5800X 8-Core Processor ", "logical_cpus": 4, "ram_bytes": 17109000192 }, "isolation": "dedicated-host" }, "platform_version": "8.3.27.2342", "grader": { "profile": "technical-v8", "commit": "e15c8ea80263c0b38baa3a1fc19611983270e8a7", "working_tree_dirty": false, "fingerprint": { "assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "calibrate.py": "aac127e03744907fd52ef149b88aa6d88a54a2b7497d56084484ee1b99e0da99", "calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "calibration_periodicity.py": "0b1953d7781e236467897cd2ed66705b75d9719353a2de60b36f2bbdfe799108", "calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "calibration_query.py": "3555b103cde8ea0519955cf52358d09223f5ab183a9df00533bdb48c89237a8c", "claude.py": "5bae98af6e2021e2718afa3a71ed04bee812deaae31a43d4e7324814139ccc82", "codescan.py": "6d8375210cef1fd768fc2d98d630d880b2993a9724f01ae25f33b4ea5aa9631d", "codex.py": "904e75503cd35f16cbb052f66806b3879fe25bfc9f99e33b93c889d862c46324", "common.py": "739b39e2bb9bdd4a571fc69df5843190cddcad094ef7e68964061bc1266b20dc", "docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "examiner.py": "8cdffcdd52f043c905f896697403380af95bf485dd4a5edca24f7956e7795ffe", "forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "harness.py": "3cbb90fd3187e700b5df32e5daafb20313d49bb5721c826e3033cbc6aa6e3825", "interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "ou.py": "f62784b54a3f85576a078a2ff1908c9395f3159e55f6bb5b1a3c564392241abe", "penalties.py": "ae388cb8953ecca1f2370a7c4cb1db3b6cc8318fc2a7563a4db15f9f5b057429", "platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "pr.py": "2b6bfea0634703469605ce114f9274716b485852d9a55d9185c39893b14e4726", "preflight.py": "448c3120ab64b625abae3891be686c7a214ce4211f7cf651fd90e12c0b298433", "process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "queries.py": "1ef57e292db3e8967a733948371ecc542f743b811890d4fc509df17303b9c4ac", "queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "querytypes.py": "b645f489a2abc27762b4a9bbf4917e72f7b46dc053a74c0dca4a8fc46491b3ef", "replay_calibration.py": "e0e3d5ca6416934715b9735aa516046b8d19ad4ae690220eeacd96b198a5f86c", "runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "smoke_check.py": "7837e980986bcb54dc8bc1dfb5d0003deef11e05f6e11df3910fa509e1f74c8d", "stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "submission.py": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tasks/1c-platform-official-sample/checks.json": "7447a9b42d3e348d29d07f001cfb6bd269acd953b7117eba7cca2ce9f5a9a60d", "tasks/1c-platform-official-sample/private/official-assessment-mapping.json": "303587c0dabe77c1eeebb2017fe85539e3370b17c9090435e6e0325a66bd0644", "tasks/1c-platform-official-sample/private/owner-scoring-policy.json": "d26d534bb838ab1b5facb7bc033ca8ec40912133baadcdbad83b27fc577905f5", "starters/carcass-8.3.25.1445/starter.json": "0f7a7060885ba99a19402bfc6e63cc8fe979b0f491b040d3a01d5d21b304b3a6", "rules/1c-specialist-platform/rules.json": "ea75e34ace5de11ba3de403c63cd2c026db81d1d991f8531e4a779d4ce9788e7", "rules/1c-specialist-platform/examiner.json": "1247486ddd412d600db88d9c1db4ba501fc1994afd1dc2ebe85402fcc332f4c8", "rules/1c-specialist-platform/chistov.json": "800da27601a3f1c7ec1df64482fd4ad035e559ba0b390a274ed5031128487d3d", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" }, "sha256": "9aee1ffe0e1d04f9158fbbbeed3a403a5f0550ad8a590d7a6394977590760e1a" }, "method": "saved_platform_observations", "outcome": "complete", "completed_at": "2026-10-26T22:33:12.210970+00:00" }, "previous_evaluations": [ { "id": "demo-20261025T113017Z-40b49c--owner-2026-10-26T214349521774-0000", "run_id": "demo-20261024T123219Z-93678e", "result": { "run_id": "demo-20261024T123219Z-93678e", "created_at": "2026-10-26T21:43:49.521774+00:00", "model": "gpt-6.1-sol", "harness": "none", "solve_seconds": 10418, "platform": "8.3.27.1644", "counts": { "pass": 64, "fail": 1 }, "rules": [ { "id": "BU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU01.selected_fixture" }, { "id": "BU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU04.selected_fixture" }, { "id": "BU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU05.selected_fixture" }, { "id": "BU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU16.selected_fixture" }, { "id": "BU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU17.selected_fixture" }, { "id": "BU02", "verdict": "pass", "reason": null, "coverage": "partial", "assertion_id": "BU02.posting_cost_and_balance" }, { "id": "BU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU10.selected_fixture" }, { "id": "BU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU12.selected_fixture" }, { "id": "BU03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU03.selected_fixture" }, { "id": "BU06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU06.selected_fixture" }, { "id": "BU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU07.selected_fixture" }, { "id": "BU08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU08.selected_fixture" }, { "id": "BU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU09.selected_fixture" }, { "id": "BU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU11.selected_fixture" }, { "id": "BU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU14.selected_fixture" }, { "id": "BU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU15.selected_fixture" }, { "id": "BU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU13.selected_fixture" }, { "id": "OU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU15.selected_fixture" }, { "id": "OU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU16.selected_fixture" }, { "id": "OU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU17.selected_fixture" }, { "id": "OU02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU02.selected_fixture" }, { "id": "OU18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU18.selected_fixture" }, { "id": "OU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU14.selected_fixture" }, { "id": "OU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU01.selected_fixture" }, { "id": "OU03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU03.selected_fixture" }, { "id": "OU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU05.selected_fixture" }, { "id": "OU06", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "OU06.selected_fixture" }, { "id": "OU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU07.selected_fixture" }, { "id": "OU08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU08.selected_fixture" }, { "id": "OU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU09.selected_fixture" }, { "id": "OU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU10.selected_fixture" }, { "id": "OU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU11.selected_fixture" }, { "id": "OU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU12.selected_fixture" }, { "id": "OU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU13.selected_fixture" }, { "id": "OU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU04.selected_fixture" }, { "id": "OU19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU19.selected_fixture" }, { "id": "OU20", "verdict": "fail", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU20.selected_fixture" }, { "id": "OU21", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU21.selected_fixture" }, { "id": "PR01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR01.selected_fixture" }, { "id": "PR02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR02.selected_fixture" }, { "id": "PR03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR03.selected_fixture" }, { "id": "PR04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR04.selected_fixture" }, { "id": "PR05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR05.selected_fixture" }, { "id": "PR06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR06.selected_fixture" }, { "id": "PR07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR07.selected_fixture" }, { "id": "PR08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR08.selected_fixture" }, { "id": "PR09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR09.selected_fixture" }, { "id": "PR10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR10.selected_fixture" }, { "id": "PR11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR11.selected_fixture" }, { "id": "PR12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR12.selected_fixture" }, { "id": "PR13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR13.selected_fixture" }, { "id": "PR14", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "PR14.selected_fixture" }, { "id": "PR15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR15.selected_fixture" }, { "id": "PR16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR16.selected_fixture" }, { "id": "PR17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR17.selected_fixture" }, { "id": "PR18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR18.selected_fixture" }, { "id": "PR19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR19.selected_fixture" }, { "id": "F01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F01.selected_fixture" }, { "id": "F02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F02.selected_fixture" }, { "id": "F03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F03.selected_fixture" }, { "id": "F04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F04.selected_fixture" }, { "id": "F05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F05.selected_fixture" }, { "id": "G01", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G01.static_sources" }, { "id": "G02", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G02.static_sources" }, { "id": "G03", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G03.static_sources" } ], "charges": [ { "id": "F1C-GEN03", "points": "0.5", "reason": "отчёт не соответствует заданию: OU20" }, { "id": "F1C-PR09", "points": "0.5", "reason": "CommonModules/РасчетЗарплаты/Ext/Module.bsl:124 — РегистрРасчета.Начисления.БазаНачисления: база получается без отбора по регистратору — по всем записям регистра" }, { "id": "F1C-PR09", "points": "0.5", "reason": "CommonModules/РасчетЗарплаты/Ext/Module.bsl:138 — РегистрРасчета.Начисления.БазаНачисления: база получается без отбора по регистратору — по всем записям регистра" }, { "id": "F1C-GEN15", "points": "0.5", "reason": "Reports/Премии/Ext/ManagerModule.bsl:4 — РегистрРасчета.Начисления: отбор по ВидРасчета, ПериодДействияНачало, индексы таблицы начинаются с ПериодДействия, ПериодРегистрации, Подразделение, Регистратор, Сотрудник" }, { "id": "F1C-PR14", "points": "0.5", "reason": "после расчёта набор с периодом действия перезаписывается целиком, с пересчётом фактического периода действия (нужно Записать(, Истина)): CommonModules/РасчетЗарплаты/Ext/Module.bsl:182 Н.Записать(Истина)" }, { "id": "F1C-BU05", "points": "0.5", "reason": "аналитика счетов вынесена в измерения регистра бухгалтерии и есть у всех счетов: Номенклатура (Номенклатура)" }, { "id": "F1C-GEN20", "points": "2.0", "reason": "данные базы читаются в цикле по записям: CommonModules/ОтчетыСервер/Ext/Module.bsl:25; CommonModules/ОтчетыСервер/Ext/Module.bsl:79; CommonModules/УчетСервер/Ext/Module.bsl:71 и ещё 3" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "оперативное проведение разрешено у документов с движениями по регистрам расчёта: НачислениеЗарплаты" }, { "id": "F1C-GEN21", "points": "2.0", "reason": "данные графика без отбора по регистратору: CommonModules/РасчетЗарплаты/Ext/Module.bsl:78" }, { "id": "F1C-GEN22", "points": "1.0", "reason": "значения графика выбираются без ЕСТЬNULL: CommonModules/РасчетЗарплаты/Ext/Module.bsl:78 ДниПериодДействия, ДниФактическийПериодДействия, ЗначениеПериодДействия, ЗначениеФактическийПериодДействия" } ], "score_upper_bound": "-4.0", "score": null, "grade": "unsatisfactory", "deductions": "9.0", "not_assessed": 16, "gates": { "starter_origin": "passed", "load": "loaded", "clients": "compiles", "demo_data": "present" }, "infrastructure_errors": false, "comparison_eligible": false, "binding_compatibility": null }, "measurement": { "operator": { "name": "Вячеслав", "github": "sksibak" }, "environment": { "captured_at": "2026-10-24T12:32:21.466495+00:00", "capture_timing": "before_run", "hardware": { "cpu": "AMD Ryzen 5 4600H with Radeon Graphics ", "logical_cpus": 12, "ram_bytes": 16505962496 }, "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "python": "3.12.14", "platform_version": "8.3.27.1644", "isolation": "dedicated-host", "network_profile": "open-book_shell", "unsafe_action_protection_observed_in_user_config": true, "git_revision": "af85e791b303dbbf0b0b7af924d2489c3e57cfa8", "implementation_files": { "exam_bench/__init__.py": "ad5bf6f05dc6765f40b78bd186870ca2c49be113cfa33f8aa76f4926f2cb2c1e", "exam_bench/assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "exam_bench/bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "exam_bench/calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "exam_bench/calibrate.py": "78b5185cb0888c0c0ac3de95ffc3a80154a6de9ae66fc461f79d012e5a58e1db", "exam_bench/calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "exam_bench/calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "exam_bench/calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "exam_bench/calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "exam_bench/calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "exam_bench/claude.py": "bc1b8550de7573aaed5e39c6e9c0309e0d8175284a75490d61ec27439ed911ad", "exam_bench/cli.py": "1a37ce645633d761f7897dffc9c45e6b8b9600cd7bd233b1cbf78f49d26b099a", "exam_bench/codescan.py": "751e38001b6e65727a31e28172a0623f0bf34bc092a958037c286aa991a197ed", "exam_bench/codex.py": "c3f89d72af11f312d851c73a1610d92e79acadf336be9ccedd1f94ede3b3ccb0", "exam_bench/common.py": "8682603b519063e655eae3574a02a49efee63bde21f582ccee20ddd623fca96d", "exam_bench/docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "exam_bench/examiner.py": "d7294fdd23ed1732216cafebf0a8cf2c24cce4259859aeb7149f62b7607d087d", "exam_bench/finalize.py": "4034f1c63896a940afdb1a83d541cf47fc75c8b5061e3f839047109c04beb620", "exam_bench/forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "exam_bench/gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "exam_bench/grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "exam_bench/harness.py": "3040f6daaf1dc6e6583219f4d925151f8ba7851b2d5417d7f14645892b485ddf", "exam_bench/interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "exam_bench/interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "exam_bench/isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "exam_bench/ledger.py": "7e851523580e22d8490e75f9b6026c07f2c355007e0d11d0b252671f56bef654", "exam_bench/locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "exam_bench/materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "exam_bench/mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "exam_bench/observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "exam_bench/ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "exam_bench/penalties.py": "0d79e2e46102657dca00609b6abbfc0bf7d11fad41429564f876c82bc6b33269", "exam_bench/platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "exam_bench/portable.py": "cad56968ff407983608f5bdbc9ce7234128d7a4580b096ecea8e0e7b4edb9070", "exam_bench/portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "exam_bench/pr.py": "6a3a20caf0e10c0cc94410511a72d62c9fcda785f3abab1be2ad616d4ee16836", "exam_bench/preflight.py": "5619be0131d8641925f3ce2a3c8e5234d42aa5635d95676138ca81536d95cd29", "exam_bench/process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "exam_bench/queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "exam_bench/queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "exam_bench/replay_calibration.py": "c150457b0b23ce4e6814eb8deb4d48f6bc4a2e39d8f84a9dc7644fb99a026c2d", "exam_bench/report.py": "5e4c0757e1c7f189953f9a5302593ab726551835856baed25efd93dad6e8bfcd", "exam_bench/runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "exam_bench/smoke_check.py": "f36922a0027429ead0b414048dcc14bbe67f2f0e79a70d03dffbe1447d253545", "exam_bench/stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "exam_bench/submission.py": "d6f9d20704181c51714f1138affe4965d860ae21475ab7bb49aa5c5cefebb9f5", "exam_bench/telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "exam_bench/windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "exam_bench/workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tools/build_public_site.py": "9682ed696f5ac9e9a82b65a45c0dece556ec7e49eeb20dcd616882cc534a8258", "tools/build_result_site.py": "3294e1d2ec1486058e208735264d61e349a68a4ae2fa2ec7a723c70e3263b496", "tools/check_native_harnesses.py": "4f5f0ed27651f78758eaef077b3b114361781f6b95ec40cb46c3fea689210473", "tools/check_native_toolkit.py": "0272794617121f2932828e5e4e9ae20095183c443666cf3ba466b44fbe875095", "tools/community_results.py": "9db56a44697d94f326efcbd7a3ae1aecdb569d43bba6c47e80ce525dc045f1f7", "tools/community_service.py": "c374480dbd88d656c0b9054fa04a8e1c6698c69e2f9cf475e82498a2dff61d84", "tools/community_setup.py": "5d7d126ed7d4dd48e1d79f57b99647a92ffcc8c9f80d90915e458888cdd76bf7", "tools/compare_harness_runs.py": "f274df5f3f804cb02504491aec946943833e12fbce6e62d281e12beb8508fc4e", "tools/create_run_plan.py": "871cd81b1eda231c0fba8805f63d2668926be9fc641559e6ddf320e2f47cd37a", "tools/demo_runner.py": "230e6e49068f2bab3a0db64e6da5889e8f1834158fed8c5ec334b7694695a87b", "tools/installers.py": "9a2742780936b17500869e7c89202c1a2549e37d53a42ad9a50a0abbf78bbe09", "tools/machine_bundle.py": "8aa8346f99f537e81ceca6fb6ab9530e844954bab8eff87bf33d3602f81f8a30", "tools/prepare_native_harnesses.py": "aaa75ecf4022883984fa50c42d14d8e1a9fde2eeda03dab03b852bbc5efb2502", "tools/prepare_official_statement.py": "6b7028c78e90e798d6ef1a93b76520cc61a308c354fb9b87f7fad18b99800fad", "tools/prepare_open_exam_requirements.py": "544f4e378b9be5f166186f8788f8d454afdac2deb99d91d98421e39d01ba6d03", "tools/probe_harness.py": "1ed8ef93420d1484cbbfd151b7efc31b9a201ceb942dd05e3103efa22ffa7f27", "tools/probe_native_mcp.py": "9918d324129cba898993e07f8f8b6dbcbaf369398ebf28d464f9f1f00abdb254", "tools/readiness.py": "d34dd3f38334f51cc4574c79194cf0b80769b062a52382989a57d01c46b9aba4", "tools/recheck_community.py": "f0843d7d677f90da31e22bde0b1c86584dd46c022f1532d43d042619e426b230", "tools/regrade_runs.py": "011775afb06d3aac67a4aa81117a368c75896b0fcbe1e6f27ccc6237612fbf59", "tools/render_statement_text.py": "dabc0716a3612c288c671bc20e17fd4986691d732768e1e957d6dddddbea92a3", "tools/replay_calibration.py": "801f5004926c438c21ed3668fe2a4ddf45312b3e75320165a3839aae034eee9b", "tools/run_exam_campaign.py": "2c450d57a1cd0a2682838f5ec7c0a4ffb3aed0f1730d34c408e912d59cab6efd", "tools/serve_result_site.py": "86badfac863cd4ad1fc894a14110c75b28470513f0133eeae9d2799b8b4df3a9", "tools/start_demo.py": "c597e6cad28d245b3191654bb3e2801fa9dd2364e2acb25561923613717b615f", "tools/supplemental_acceptance.py": "c88fc39de1be1fdcacdd819e2ad329f60367b2df1d5deda80b37324bda3f2a01", "tools/sync_sources.py": "b51e889b0f41f9f63bfb19a09fb96d3777693d6b1d76fe0132bdd2a15e155898", "tools/validate_community_pr.py": "796b896dfade07b4529af2088a4b9b9d23484148b3bc0732b3fb837b75c9844b", "tools/verify_official_assessment_mapping.py": "daeb448a016940d5b6b1285979a56e5b9014bd91db40acb131445e4a83a23059", "tools/verify_task_package.py": "9e1e6105f6b5e4e78b36aa57f00117a9fbc8948ab53983c32ab56da88d23ccc4", "profiles/agents.json": "af9c492c08d13b3044aa6b6952589ed6a0a07d5258d8ff72bb18185b3eaebdc5", "profiles/ai-exam-execution-policy.json": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "profiles/bsl-analyzer-0.3.2-macos.json": "83537abdbf38c41ce665e4d0f24128bb51b62e971e0e0f368695f1326a7d2ffb", "profiles/bsl-analyzer-0.3.2-portable.json": "d6ba732e6778e256df34d6bc548593128820a70430c35b279796843606ee40a8", "profiles/bsl-ls-1.1.0-rc.6-macos.json": "245fc10747197e6911b2b4c77cdb15e6fa4eb7bc7c3758b63e768c5adf1df180", "profiles/bsl-ls-1.1.0-rc.6-portable.json": "9f10660881f2ec84794f7d584556b8f75c7e14b3555464af0ed0e60c4c892d86", "profiles/code-index-1.9.0-macos.json": "63a919523ce62ecec274f4c139bc7ad49a75dd4c339568b822cbc695b4e30408", "profiles/code-index-1.9.0-portable.json": "81106cee8f424ffd8a9dc46ecd8e4f57598fc1d49661a83c77b1f0507993fbdc", "profiles/codex-probe-plan.json": "166e41aad5fb3b27d9050bc6de952c6cba363cc6e804d4080568cc71a2a4d289", "profiles/machine.linux.example.json": "408304fd0581098d5d8110dc67dfeab353bc4d4030e32d37e6acf98d2b1aedfd", "profiles/machine.macos.example.json": "52e9f9d17797cb520b9d8955d6806fd550b899bed4da241ebf096dcb6a21a942", "profiles/machine.windows.example.json": "63accac9a2f81d47d03447efbabffd4760aee325193f02f46b9b29a28d50d2d8", "profiles/mcp-toolkit-1.9.0-macos.json": "1d3f9cde5ffa20589a840d01fdae03aa0fc2f412c929f064f203919c4129625b", "profiles/mcp-toolkit-1.9.0-portable.json": "8e370eebe773eef0e08045ee9c6d5be1451f769f65be0710834b262a4336e054", "profiles/none-macos.json": "b1401d9c48159aed3559006c7f6ace6ef4571224d5cf0bb76d1a823505a10056", "profiles/none-portable.json": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "profiles/rlm-tools-bsl-1.43.0-macos.json": "9354421052640ab60bc3e6aa98ff2e7ba9ca2318b0f4026c137487449242cbd2", "profiles/rlm-tools-bsl-1.43.0-portable.json": "2599e5645e0a7d4e44cb2934bc2b272cae79a9bf7ea74a23cd48aacea64bc424", "profiles/rlm-tools-bsl-1.43.0-posix-requirements.txt": "4fdf9a1bd994bf0272e65d231daf76cf19b0a34dad0ae6b50ec4f11a2ce4c330", "profiles/rlm-tools-bsl-1.43.0-windows-requirements.txt": "3730cb46c81cda5181ecd4485e98b11933104632358bc86f8c0eb1a612a8954f", "profiles/shirokov-skills-macos.json": "84f3e89091676884a802035c707e912762a1179425fb8e3faff25be736873cdb", "profiles/shirokov-skills-portable.json": "2b0a461e06602f1456410e70f02ceaa5ac32c6549c486660bcb5ace0c2f87b15", "profiles/shirokov-skills-windows-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/unica-0.12.3-macos.json": "2c39fbb591cf2c2c6e056373823615485397ea83651b7926c6f25a5fe6a0aae6", "profiles/unica-0.13.0-macos.json": "b76b5c8a4dd33f571c4a90993f1a2da5f7223b4f0f8e1042c282e21a66121052", "profiles/unica-0.14.0-rc.1-portable.json": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "rules/1c-specialist-platform/chistov.json": "77e04942f8c947b10759e7cc1eb31af05847d1711a772fbe6f23d525766757a9", "rules/1c-specialist-platform/decisions.json": "f622107423ce3c188c063318d7ab4f7718ceb38e443130677d8987f386641c09", "rules/1c-specialist-platform/examiner.json": "30353aa2a1b6545496b070d9066e9ffba0c3779e5b53ef70a4fd2cee375b18c0", "rules/1c-specialist-platform/ledger.json": "f167c10db2b5799dd9a1ea6a37cd2d7d186810dadf5ea2f50f26ae723c676882", "rules/1c-specialist-platform/rules.json": "1d320a4f8e1bf4701496388931f492315549bd3dce574b17285dd1d7f8652007", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" } } }, "conditions": { "client": "codex", "model": "gpt-6.1-sol", "client_version": "0.163.0-alpha.11.2", "reasoning_effort": "medium", "harness": "none", "billing_channel": "subscription", "solve_timeout_seconds": 10800, "time_series": null, "delegation": "native_disabled", "network_profile": "open-book_shell", "deadline_disclosed": true, "statement_sha256": "8a6ccb3e673826d1f8220fda53eb310e3ec18c136d87ce8f4cebb2a08614e7e5", "starter_dt_sha256": "f40d084818b0d1cfe503fc7653a6a13f1a8e47fcd1688dad6245b12744eb4638", "profile_sha256": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "execution_policy_sha256": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "calibration_sha256": "e8981744a194aa56f954d2965aa66cd53cd4f899f09fa7b5abda6f6b27a5ed65", "started_at": "2026-10-24T12:32:28.378363+00:00", "timing": { "prepare_ms": 6422, "solve_ms": 10418234, "grade_ms": null }, "original_submission_valid": true, "model_provenance": "requested_only", "tokens": { "input": 31056671, "cached_input": 30889088, "fresh_input": 167583, "output": 265179, "reasoning_output": 159437, "total": 31321850, "coverage": "reported_completed_root_turns" }, "tools": { "mcp_calls": 0, "unica_calls": 0, "failed_calls": 0 }, "process": { "status": "completed", "exit_code": 0, "stop_confirmed": true } }, "verification": "repository_owner", "download": "community-downloads/demo-20261025T113017Z-40b49c--owner-2026-10-26T214349521774-0000/solution.zip", "source_context": "community-downloads/demo-20261025T113017Z-40b49c--owner-2026-10-26T214349521774-0000/source-context.json", "regrade_required": [ { "id": "grader_changed", "files": [ "calibrate.py", "calibration_periodicity.py", "common.py", "ou.py", "replay_calibration.py", "smoke_check.py", "tasks/1c-platform-official-sample/checks.json" ] } ], "grader_revision_sha256": "349d87e0c7f531acbe35dd2b39c35722d8a877fedde97575b49e8466ab763c1d", "archive_sha256": "0c0eab8ae3d83279f2cc88b20816022cd0d064458743415a01444c06aa26ac2f", "owner_verification": { "kind": "repository_owner", "repository": "zeegin/1c-agent-exam-benchmark", "operator": { "name": "Ingvar Vilkman", "github": "zeegin" }, "started_at": "2026-10-26T21:43:49.327538+00:00", "server": { "name": "Owner Windows stand", "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "hardware": { "cpu": "AMD Ryzen 7 5800X 8-Core Processor ", "logical_cpus": 4, "ram_bytes": 17109000192 }, "isolation": "dedicated-host" }, "platform_version": "8.3.27.2342", "grader": { "profile": "technical-v8", "commit": "e8fd8ced03a85b549c5472fbbda29225749f54d1", "working_tree_dirty": false, "fingerprint": { "assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "calibrate.py": "3162d431f3cab5e7976aa39f665d6286dce45499cf362d85109b7123fa8403a2", "calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "calibration_query.py": "3555b103cde8ea0519955cf52358d09223f5ab183a9df00533bdb48c89237a8c", "claude.py": "eedabc75fca0faa434f40a1624b71419ec7dc22e2854a0886cf84b4911db8372", "codescan.py": "6d8375210cef1fd768fc2d98d630d880b2993a9724f01ae25f33b4ea5aa9631d", "codex.py": "904e75503cd35f16cbb052f66806b3879fe25bfc9f99e33b93c889d862c46324", "common.py": "52825cf5c29f3536d6e046a89e789d5ef9c83aacd7f2f5a07f4f53e77b5229cc", "docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "examiner.py": "8cdffcdd52f043c905f896697403380af95bf485dd4a5edca24f7956e7795ffe", "forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "harness.py": "3cbb90fd3187e700b5df32e5daafb20313d49bb5721c826e3033cbc6aa6e3825", "interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "penalties.py": "ae388cb8953ecca1f2370a7c4cb1db3b6cc8318fc2a7563a4db15f9f5b057429", "platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "pr.py": "2b6bfea0634703469605ce114f9274716b485852d9a55d9185c39893b14e4726", "preflight.py": "448c3120ab64b625abae3891be686c7a214ce4211f7cf651fd90e12c0b298433", "process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "queries.py": "1ef57e292db3e8967a733948371ecc542f743b811890d4fc509df17303b9c4ac", "queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "querytypes.py": "b645f489a2abc27762b4a9bbf4917e72f7b46dc053a74c0dca4a8fc46491b3ef", "replay_calibration.py": "0a4d9b84a9908944c5a945878eb6f5eeda5a4e42ffff4f55c04a680742803d80", "runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "smoke_check.py": "66caf1a01f7aa18432293abe3567ac228ac837a660b08c3dc7bb093f7bd51628", "stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "submission.py": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tasks/1c-platform-official-sample/checks.json": "17a6fcc0c14410829650623eb1443ce99796e000cdfd19905ac0287988b73a00", "tasks/1c-platform-official-sample/private/official-assessment-mapping.json": "303587c0dabe77c1eeebb2017fe85539e3370b17c9090435e6e0325a66bd0644", "tasks/1c-platform-official-sample/private/owner-scoring-policy.json": "d26d534bb838ab1b5facb7bc033ca8ec40912133baadcdbad83b27fc577905f5", "starters/carcass-8.3.25.1445/starter.json": "0f7a7060885ba99a19402bfc6e63cc8fe979b0f491b040d3a01d5d21b304b3a6", "rules/1c-specialist-platform/rules.json": "ea75e34ace5de11ba3de403c63cd2c026db81d1d991f8531e4a779d4ce9788e7", "rules/1c-specialist-platform/examiner.json": "1247486ddd412d600db88d9c1db4ba501fc1994afd1dc2ebe85402fcc332f4c8", "rules/1c-specialist-platform/chistov.json": "800da27601a3f1c7ec1df64482fd4ad035e559ba0b390a274ed5031128487d3d", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" }, "sha256": "349d87e0c7f531acbe35dd2b39c35722d8a877fedde97575b49e8466ab763c1d" }, "method": "saved_platform_observations", "outcome": "complete", "completed_at": "2026-10-26T21:43:49.521774+00:00" } }, { "id": "demo-20261025T113017Z-40b49c--owner-2026-10-26T185907525280-0000", "run_id": "demo-20261024T123219Z-93678e", "result": { "run_id": "demo-20261024T123219Z-93678e", "created_at": "2026-10-26T18:59:07.525280+00:00", "model": "gpt-6.1-sol", "harness": "none", "solve_seconds": 10418, "platform": "8.3.27.1644", "counts": { "pass": 64, "fail": 1 }, "rules": [ { "id": "BU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU01.selected_fixture" }, { "id": "BU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU04.selected_fixture" }, { "id": "BU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU05.selected_fixture" }, { "id": "BU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU16.selected_fixture" }, { "id": "BU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU17.selected_fixture" }, { "id": "BU02", "verdict": "pass", "reason": null, "coverage": "partial", "assertion_id": "BU02.posting_cost_and_balance" }, { "id": "BU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU10.selected_fixture" }, { "id": "BU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU12.selected_fixture" }, { "id": "BU03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU03.selected_fixture" }, { "id": "BU06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU06.selected_fixture" }, { "id": "BU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU07.selected_fixture" }, { "id": "BU08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU08.selected_fixture" }, { "id": "BU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU09.selected_fixture" }, { "id": "BU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU11.selected_fixture" }, { "id": "BU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU14.selected_fixture" }, { "id": "BU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU15.selected_fixture" }, { "id": "BU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU13.selected_fixture" }, { "id": "OU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU15.selected_fixture" }, { "id": "OU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU16.selected_fixture" }, { "id": "OU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU17.selected_fixture" }, { "id": "OU02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU02.selected_fixture" }, { "id": "OU18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU18.selected_fixture" }, { "id": "OU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU14.selected_fixture" }, { "id": "OU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU01.selected_fixture" }, { "id": "OU03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU03.selected_fixture" }, { "id": "OU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU05.selected_fixture" }, { "id": "OU06", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "OU06.selected_fixture" }, { "id": "OU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU07.selected_fixture" }, { "id": "OU08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU08.selected_fixture" }, { "id": "OU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU09.selected_fixture" }, { "id": "OU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU10.selected_fixture" }, { "id": "OU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU11.selected_fixture" }, { "id": "OU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU12.selected_fixture" }, { "id": "OU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU13.selected_fixture" }, { "id": "OU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU04.selected_fixture" }, { "id": "OU19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU19.selected_fixture" }, { "id": "OU20", "verdict": "fail", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU20.selected_fixture" }, { "id": "OU21", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU21.selected_fixture" }, { "id": "PR01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR01.selected_fixture" }, { "id": "PR02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR02.selected_fixture" }, { "id": "PR03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR03.selected_fixture" }, { "id": "PR04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR04.selected_fixture" }, { "id": "PR05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR05.selected_fixture" }, { "id": "PR06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR06.selected_fixture" }, { "id": "PR07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR07.selected_fixture" }, { "id": "PR08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR08.selected_fixture" }, { "id": "PR09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR09.selected_fixture" }, { "id": "PR10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR10.selected_fixture" }, { "id": "PR11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR11.selected_fixture" }, { "id": "PR12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR12.selected_fixture" }, { "id": "PR13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR13.selected_fixture" }, { "id": "PR14", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "PR14.selected_fixture" }, { "id": "PR15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR15.selected_fixture" }, { "id": "PR16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR16.selected_fixture" }, { "id": "PR17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR17.selected_fixture" }, { "id": "PR18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR18.selected_fixture" }, { "id": "PR19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR19.selected_fixture" }, { "id": "F01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F01.selected_fixture" }, { "id": "F02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F02.selected_fixture" }, { "id": "F03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F03.selected_fixture" }, { "id": "F04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F04.selected_fixture" }, { "id": "F05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F05.selected_fixture" }, { "id": "G01", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G01.static_sources" }, { "id": "G02", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G02.static_sources" }, { "id": "G03", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G03.static_sources" } ], "charges": [ { "id": "F1C-GEN03", "points": "0.5", "reason": "отчёт не соответствует заданию: OU20" }, { "id": "F1C-GEN12", "points": "0.25", "reason": "текст запроса не разбирается платформой: CommonModules/РасчетЗарплаты/Ext/Module.bsl:90 — Поле не найдено \"Сотрудник\"" }, { "id": "F1C-PR09", "points": "0.5", "reason": "CommonModules/РасчетЗарплаты/Ext/Module.bsl:124 — РегистрРасчета.Начисления.БазаНачисления: база получается без отбора по регистратору — по всем записям регистра" }, { "id": "F1C-PR09", "points": "0.5", "reason": "CommonModules/РасчетЗарплаты/Ext/Module.bsl:138 — РегистрРасчета.Начисления.БазаНачисления: база получается без отбора по регистратору — по всем записям регистра" }, { "id": "F1C-GEN15", "points": "0.5", "reason": "Reports/Премии/Ext/ManagerModule.bsl:4 — РегистрРасчета.Начисления: отбор по ВидРасчета, ПериодДействияНачало, индексы таблицы начинаются с ПериодДействия, ПериодРегистрации, Подразделение, Регистратор, Сотрудник" }, { "id": "F1C-PR14", "points": "0.5", "reason": "после расчёта набор с периодом действия перезаписывается целиком, с пересчётом фактического периода действия (нужно Записать(, Истина)): CommonModules/РасчетЗарплаты/Ext/Module.bsl:182 Н.Записать(Истина)" }, { "id": "F1C-BU05", "points": "0.5", "reason": "аналитика счетов вынесена в измерения регистра бухгалтерии и есть у всех счетов: Номенклатура (Номенклатура)" }, { "id": "F1C-GEN20", "points": "2.0", "reason": "данные базы читаются в цикле по записям: CommonModules/ОтчетыСервер/Ext/Module.bsl:25; CommonModules/ОтчетыСервер/Ext/Module.bsl:79; CommonModules/УчетСервер/Ext/Module.bsl:71 и ещё 3" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "оперативное проведение разрешено у документов с движениями по регистрам расчёта: НачислениеЗарплаты" }, { "id": "F1C-GEN21", "points": "2.0", "reason": "данные графика без отбора по регистратору: CommonModules/РасчетЗарплаты/Ext/Module.bsl:78" }, { "id": "F1C-GEN22", "points": "1.0", "reason": "значения графика выбираются без ЕСТЬNULL: CommonModules/РасчетЗарплаты/Ext/Module.bsl:78 ДниПериодДействия, ДниФактическийПериодДействия, ЗначениеПериодДействия, ЗначениеФактическийПериодДействия" } ], "score_upper_bound": "-4.25", "score": null, "grade": "unsatisfactory", "deductions": "9.25", "not_assessed": 15, "gates": { "starter_origin": "passed", "load": "loaded", "clients": "compiles", "demo_data": "present" }, "infrastructure_errors": false, "comparison_eligible": false, "binding_compatibility": null }, "measurement": { "operator": { "name": "Вячеслав", "github": "sksibak" }, "environment": { "captured_at": "2026-10-24T12:32:21.466495+00:00", "capture_timing": "before_run", "hardware": { "cpu": "AMD Ryzen 5 4600H with Radeon Graphics ", "logical_cpus": 12, "ram_bytes": 16505962496 }, "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "python": "3.12.14", "platform_version": "8.3.27.1644", "isolation": "dedicated-host", "network_profile": "open-book_shell", "unsafe_action_protection_observed_in_user_config": true, "git_revision": "af85e791b303dbbf0b0b7af924d2489c3e57cfa8", "implementation_files": { "exam_bench/__init__.py": "ad5bf6f05dc6765f40b78bd186870ca2c49be113cfa33f8aa76f4926f2cb2c1e", "exam_bench/assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "exam_bench/bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "exam_bench/calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "exam_bench/calibrate.py": "78b5185cb0888c0c0ac3de95ffc3a80154a6de9ae66fc461f79d012e5a58e1db", "exam_bench/calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "exam_bench/calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "exam_bench/calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "exam_bench/calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "exam_bench/calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "exam_bench/claude.py": "bc1b8550de7573aaed5e39c6e9c0309e0d8175284a75490d61ec27439ed911ad", "exam_bench/cli.py": "1a37ce645633d761f7897dffc9c45e6b8b9600cd7bd233b1cbf78f49d26b099a", "exam_bench/codescan.py": "751e38001b6e65727a31e28172a0623f0bf34bc092a958037c286aa991a197ed", "exam_bench/codex.py": "c3f89d72af11f312d851c73a1610d92e79acadf336be9ccedd1f94ede3b3ccb0", "exam_bench/common.py": "8682603b519063e655eae3574a02a49efee63bde21f582ccee20ddd623fca96d", "exam_bench/docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "exam_bench/examiner.py": "d7294fdd23ed1732216cafebf0a8cf2c24cce4259859aeb7149f62b7607d087d", "exam_bench/finalize.py": "4034f1c63896a940afdb1a83d541cf47fc75c8b5061e3f839047109c04beb620", "exam_bench/forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "exam_bench/gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "exam_bench/grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "exam_bench/harness.py": "3040f6daaf1dc6e6583219f4d925151f8ba7851b2d5417d7f14645892b485ddf", "exam_bench/interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "exam_bench/interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "exam_bench/isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "exam_bench/ledger.py": "7e851523580e22d8490e75f9b6026c07f2c355007e0d11d0b252671f56bef654", "exam_bench/locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "exam_bench/materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "exam_bench/mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "exam_bench/observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "exam_bench/ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "exam_bench/penalties.py": "0d79e2e46102657dca00609b6abbfc0bf7d11fad41429564f876c82bc6b33269", "exam_bench/platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "exam_bench/portable.py": "cad56968ff407983608f5bdbc9ce7234128d7a4580b096ecea8e0e7b4edb9070", "exam_bench/portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "exam_bench/pr.py": "6a3a20caf0e10c0cc94410511a72d62c9fcda785f3abab1be2ad616d4ee16836", "exam_bench/preflight.py": "5619be0131d8641925f3ce2a3c8e5234d42aa5635d95676138ca81536d95cd29", "exam_bench/process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "exam_bench/queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "exam_bench/queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "exam_bench/replay_calibration.py": "c150457b0b23ce4e6814eb8deb4d48f6bc4a2e39d8f84a9dc7644fb99a026c2d", "exam_bench/report.py": "5e4c0757e1c7f189953f9a5302593ab726551835856baed25efd93dad6e8bfcd", "exam_bench/runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "exam_bench/smoke_check.py": "f36922a0027429ead0b414048dcc14bbe67f2f0e79a70d03dffbe1447d253545", "exam_bench/stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "exam_bench/submission.py": "d6f9d20704181c51714f1138affe4965d860ae21475ab7bb49aa5c5cefebb9f5", "exam_bench/telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "exam_bench/windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "exam_bench/workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tools/build_public_site.py": "9682ed696f5ac9e9a82b65a45c0dece556ec7e49eeb20dcd616882cc534a8258", "tools/build_result_site.py": "3294e1d2ec1486058e208735264d61e349a68a4ae2fa2ec7a723c70e3263b496", "tools/check_native_harnesses.py": "4f5f0ed27651f78758eaef077b3b114361781f6b95ec40cb46c3fea689210473", "tools/check_native_toolkit.py": "0272794617121f2932828e5e4e9ae20095183c443666cf3ba466b44fbe875095", "tools/community_results.py": "9db56a44697d94f326efcbd7a3ae1aecdb569d43bba6c47e80ce525dc045f1f7", "tools/community_service.py": "c374480dbd88d656c0b9054fa04a8e1c6698c69e2f9cf475e82498a2dff61d84", "tools/community_setup.py": "5d7d126ed7d4dd48e1d79f57b99647a92ffcc8c9f80d90915e458888cdd76bf7", "tools/compare_harness_runs.py": "f274df5f3f804cb02504491aec946943833e12fbce6e62d281e12beb8508fc4e", "tools/create_run_plan.py": "871cd81b1eda231c0fba8805f63d2668926be9fc641559e6ddf320e2f47cd37a", "tools/demo_runner.py": "230e6e49068f2bab3a0db64e6da5889e8f1834158fed8c5ec334b7694695a87b", "tools/installers.py": "9a2742780936b17500869e7c89202c1a2549e37d53a42ad9a50a0abbf78bbe09", "tools/machine_bundle.py": "8aa8346f99f537e81ceca6fb6ab9530e844954bab8eff87bf33d3602f81f8a30", "tools/prepare_native_harnesses.py": "aaa75ecf4022883984fa50c42d14d8e1a9fde2eeda03dab03b852bbc5efb2502", "tools/prepare_official_statement.py": "6b7028c78e90e798d6ef1a93b76520cc61a308c354fb9b87f7fad18b99800fad", "tools/prepare_open_exam_requirements.py": "544f4e378b9be5f166186f8788f8d454afdac2deb99d91d98421e39d01ba6d03", "tools/probe_harness.py": "1ed8ef93420d1484cbbfd151b7efc31b9a201ceb942dd05e3103efa22ffa7f27", "tools/probe_native_mcp.py": "9918d324129cba898993e07f8f8b6dbcbaf369398ebf28d464f9f1f00abdb254", "tools/readiness.py": "d34dd3f38334f51cc4574c79194cf0b80769b062a52382989a57d01c46b9aba4", "tools/recheck_community.py": "f0843d7d677f90da31e22bde0b1c86584dd46c022f1532d43d042619e426b230", "tools/regrade_runs.py": "011775afb06d3aac67a4aa81117a368c75896b0fcbe1e6f27ccc6237612fbf59", "tools/render_statement_text.py": "dabc0716a3612c288c671bc20e17fd4986691d732768e1e957d6dddddbea92a3", "tools/replay_calibration.py": "801f5004926c438c21ed3668fe2a4ddf45312b3e75320165a3839aae034eee9b", "tools/run_exam_campaign.py": "2c450d57a1cd0a2682838f5ec7c0a4ffb3aed0f1730d34c408e912d59cab6efd", "tools/serve_result_site.py": "86badfac863cd4ad1fc894a14110c75b28470513f0133eeae9d2799b8b4df3a9", "tools/start_demo.py": "c597e6cad28d245b3191654bb3e2801fa9dd2364e2acb25561923613717b615f", "tools/supplemental_acceptance.py": "c88fc39de1be1fdcacdd819e2ad329f60367b2df1d5deda80b37324bda3f2a01", "tools/sync_sources.py": "b51e889b0f41f9f63bfb19a09fb96d3777693d6b1d76fe0132bdd2a15e155898", "tools/validate_community_pr.py": "796b896dfade07b4529af2088a4b9b9d23484148b3bc0732b3fb837b75c9844b", "tools/verify_official_assessment_mapping.py": "daeb448a016940d5b6b1285979a56e5b9014bd91db40acb131445e4a83a23059", "tools/verify_task_package.py": "9e1e6105f6b5e4e78b36aa57f00117a9fbc8948ab53983c32ab56da88d23ccc4", "profiles/agents.json": "af9c492c08d13b3044aa6b6952589ed6a0a07d5258d8ff72bb18185b3eaebdc5", "profiles/ai-exam-execution-policy.json": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "profiles/bsl-analyzer-0.3.2-macos.json": "83537abdbf38c41ce665e4d0f24128bb51b62e971e0e0f368695f1326a7d2ffb", "profiles/bsl-analyzer-0.3.2-portable.json": "d6ba732e6778e256df34d6bc548593128820a70430c35b279796843606ee40a8", "profiles/bsl-ls-1.1.0-rc.6-macos.json": "245fc10747197e6911b2b4c77cdb15e6fa4eb7bc7c3758b63e768c5adf1df180", "profiles/bsl-ls-1.1.0-rc.6-portable.json": "9f10660881f2ec84794f7d584556b8f75c7e14b3555464af0ed0e60c4c892d86", "profiles/code-index-1.9.0-macos.json": "63a919523ce62ecec274f4c139bc7ad49a75dd4c339568b822cbc695b4e30408", "profiles/code-index-1.9.0-portable.json": "81106cee8f424ffd8a9dc46ecd8e4f57598fc1d49661a83c77b1f0507993fbdc", "profiles/codex-probe-plan.json": "166e41aad5fb3b27d9050bc6de952c6cba363cc6e804d4080568cc71a2a4d289", "profiles/machine.linux.example.json": "408304fd0581098d5d8110dc67dfeab353bc4d4030e32d37e6acf98d2b1aedfd", "profiles/machine.macos.example.json": "52e9f9d17797cb520b9d8955d6806fd550b899bed4da241ebf096dcb6a21a942", "profiles/machine.windows.example.json": "63accac9a2f81d47d03447efbabffd4760aee325193f02f46b9b29a28d50d2d8", "profiles/mcp-toolkit-1.9.0-macos.json": "1d3f9cde5ffa20589a840d01fdae03aa0fc2f412c929f064f203919c4129625b", "profiles/mcp-toolkit-1.9.0-portable.json": "8e370eebe773eef0e08045ee9c6d5be1451f769f65be0710834b262a4336e054", "profiles/none-macos.json": "b1401d9c48159aed3559006c7f6ace6ef4571224d5cf0bb76d1a823505a10056", "profiles/none-portable.json": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "profiles/rlm-tools-bsl-1.43.0-macos.json": "9354421052640ab60bc3e6aa98ff2e7ba9ca2318b0f4026c137487449242cbd2", "profiles/rlm-tools-bsl-1.43.0-portable.json": "2599e5645e0a7d4e44cb2934bc2b272cae79a9bf7ea74a23cd48aacea64bc424", "profiles/rlm-tools-bsl-1.43.0-posix-requirements.txt": "4fdf9a1bd994bf0272e65d231daf76cf19b0a34dad0ae6b50ec4f11a2ce4c330", "profiles/rlm-tools-bsl-1.43.0-windows-requirements.txt": "3730cb46c81cda5181ecd4485e98b11933104632358bc86f8c0eb1a612a8954f", "profiles/shirokov-skills-macos.json": "84f3e89091676884a802035c707e912762a1179425fb8e3faff25be736873cdb", "profiles/shirokov-skills-portable.json": "2b0a461e06602f1456410e70f02ceaa5ac32c6549c486660bcb5ace0c2f87b15", "profiles/shirokov-skills-windows-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/unica-0.12.3-macos.json": "2c39fbb591cf2c2c6e056373823615485397ea83651b7926c6f25a5fe6a0aae6", "profiles/unica-0.13.0-macos.json": "b76b5c8a4dd33f571c4a90993f1a2da5f7223b4f0f8e1042c282e21a66121052", "profiles/unica-0.14.0-rc.1-portable.json": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "rules/1c-specialist-platform/chistov.json": "77e04942f8c947b10759e7cc1eb31af05847d1711a772fbe6f23d525766757a9", "rules/1c-specialist-platform/decisions.json": "f622107423ce3c188c063318d7ab4f7718ceb38e443130677d8987f386641c09", "rules/1c-specialist-platform/examiner.json": "30353aa2a1b6545496b070d9066e9ffba0c3779e5b53ef70a4fd2cee375b18c0", "rules/1c-specialist-platform/ledger.json": "f167c10db2b5799dd9a1ea6a37cd2d7d186810dadf5ea2f50f26ae723c676882", "rules/1c-specialist-platform/rules.json": "1d320a4f8e1bf4701496388931f492315549bd3dce574b17285dd1d7f8652007", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" } } }, "conditions": { "client": "codex", "model": "gpt-6.1-sol", "client_version": "0.163.0-alpha.11.2", "reasoning_effort": "medium", "harness": "none", "billing_channel": "subscription", "solve_timeout_seconds": 10800, "time_series": null, "delegation": "native_disabled", "network_profile": "open-book_shell", "deadline_disclosed": true, "statement_sha256": "8a6ccb3e673826d1f8220fda53eb310e3ec18c136d87ce8f4cebb2a08614e7e5", "starter_dt_sha256": "f40d084818b0d1cfe503fc7653a6a13f1a8e47fcd1688dad6245b12744eb4638", "profile_sha256": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "execution_policy_sha256": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "calibration_sha256": "e8981744a194aa56f954d2965aa66cd53cd4f899f09fa7b5abda6f6b27a5ed65", "started_at": "2026-10-24T12:32:28.378363+00:00", "timing": { "prepare_ms": 6422, "solve_ms": 10418234, "grade_ms": null }, "original_submission_valid": true, "model_provenance": "requested_only", "tokens": { "input": 31056671, "cached_input": 30889088, "fresh_input": 167583, "output": 265179, "reasoning_output": 159437, "total": 31321850, "coverage": "reported_completed_root_turns" }, "tools": { "mcp_calls": 0, "unica_calls": 0, "failed_calls": 0 }, "process": { "status": "completed", "exit_code": 0, "stop_confirmed": true } }, "verification": "repository_owner", "download": "community-downloads/demo-20261025T113017Z-40b49c--owner-2026-10-26T185907525280-0000/solution.zip", "source_context": "community-downloads/demo-20261025T113017Z-40b49c--owner-2026-10-26T185907525280-0000/source-context.json", "regrade_required": [ { "id": "grader_changed", "files": [ "calibrate.py", "calibration_periodicity.py", "calibration_query.py", "common.py", "ou.py", "penalties.py", "queries.py", "replay_calibration.py", "rules/1c-specialist-platform/rules.json", "smoke_check.py", "tasks/1c-platform-official-sample/checks.json" ] } ], "grader_revision_sha256": "4a12b62d2c10085e1fc710f377f84903abdf2fb787dda19628d944da990a86b2", "archive_sha256": "d93efec8e15f53974c69f08029726633a7c8a2e9cb748f613a2b06b73d7ad3f7", "owner_verification": { "kind": "repository_owner", "repository": "zeegin/1c-agent-exam-benchmark", "operator": { "name": "Ingvar Vilkman", "github": "zeegin" }, "started_at": "2026-10-26T18:56:15.248929+00:00", "server": { "name": "Owner Windows stand", "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "hardware": { "cpu": "AMD Ryzen 7 5800X 8-Core Processor ", "logical_cpus": 4, "ram_bytes": 17109000192 }, "isolation": "dedicated-host" }, "platform_version": "8.3.27.2342", "grader": { "profile": "technical-v8", "commit": "5b6a28372b253e81e22b83f8559df897297e28ff", "working_tree_dirty": true, "fingerprint": { "assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "calibrate.py": "1c844971b4977fdcc3b30aebe8aad40fbd45e6828955b8deb043ac8573d61731", "calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "claude.py": "eedabc75fca0faa434f40a1624b71419ec7dc22e2854a0886cf84b4911db8372", "codescan.py": "6d8375210cef1fd768fc2d98d630d880b2993a9724f01ae25f33b4ea5aa9631d", "codex.py": "904e75503cd35f16cbb052f66806b3879fe25bfc9f99e33b93c889d862c46324", "common.py": "7696116dd1a796666518b4c5d2aa3cafa04ee974593d3636333cbe5385bd6ccb", "docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "examiner.py": "8cdffcdd52f043c905f896697403380af95bf485dd4a5edca24f7956e7795ffe", "forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "harness.py": "3cbb90fd3187e700b5df32e5daafb20313d49bb5721c826e3033cbc6aa6e3825", "interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "penalties.py": "b82704e7f47d3dfdf6e501452d7e0abca1f9da63307093d2e257e32358be0489", "platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "pr.py": "2b6bfea0634703469605ce114f9274716b485852d9a55d9185c39893b14e4726", "preflight.py": "448c3120ab64b625abae3891be686c7a214ce4211f7cf651fd90e12c0b298433", "process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "querytypes.py": "b645f489a2abc27762b4a9bbf4917e72f7b46dc053a74c0dca4a8fc46491b3ef", "replay_calibration.py": "3b6f3a289cc8a7f5e458f62bfa2c6cc534cc9076ba3f22d1e4bd8a5f9e175317", "runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "smoke_check.py": "bd6266367e6b769a95258eb383239b89a22deae406d64f6e142c77396f4639ba", "stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "submission.py": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tasks/1c-platform-official-sample/checks.json": "17a6fcc0c14410829650623eb1443ce99796e000cdfd19905ac0287988b73a00", "tasks/1c-platform-official-sample/private/official-assessment-mapping.json": "303587c0dabe77c1eeebb2017fe85539e3370b17c9090435e6e0325a66bd0644", "tasks/1c-platform-official-sample/private/owner-scoring-policy.json": "d26d534bb838ab1b5facb7bc033ca8ec40912133baadcdbad83b27fc577905f5", "starters/carcass-8.3.25.1445/starter.json": "0f7a7060885ba99a19402bfc6e63cc8fe979b0f491b040d3a01d5d21b304b3a6", "rules/1c-specialist-platform/rules.json": "7ec895a7751ef17f4a50cc80b5f7fa986e1e04360ab0b4ce9aa29115195df03c", "rules/1c-specialist-platform/examiner.json": "1247486ddd412d600db88d9c1db4ba501fc1994afd1dc2ebe85402fcc332f4c8", "rules/1c-specialist-platform/chistov.json": "800da27601a3f1c7ec1df64482fd4ad035e559ba0b390a274ed5031128487d3d", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" }, "sha256": "4a12b62d2c10085e1fc710f377f84903abdf2fb787dda19628d944da990a86b2" }, "identity_verified_at": "2026-10-26T18:44:22.364471+00:00", "identity_session_sha256": "950670ab9a82059c65525d0d6e5b8a00f0dc292581edea3eb087c4ecadeaab09", "completed_at": "2026-10-26T18:59:07.525280+00:00" } }, { "id": "demo-20261025T113017Z-40b49c", "run_id": "demo-20261024T123219Z-93678e", "result": { "run_id": "demo-20261024T123219Z-93678e", "created_at": "2026-10-25T11:34:16.597374+00:00", "model": "gpt-6.1-sol", "harness": "none", "solve_seconds": 10418, "platform": "8.3.27.1644", "counts": { "pass": 64, "fail": 1 }, "rules": [ { "id": "BU01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU16", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU17", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU02", "verdict": "pass", "coverage": "partial", "reason": null }, { "id": "BU10", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU12", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU06", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU07", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU08", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU09", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU11", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU14", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU15", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU13", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU15", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU16", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU17", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU02", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU18", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU14", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU06", "verdict": "pass", "coverage": "no_violation_found", "reason": null }, { "id": "OU07", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU08", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU09", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU10", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU11", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU12", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU13", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU19", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU20", "verdict": "fail", "coverage": "selected_fixture", "reason": "Ведомость не прошла проверку группировки по значениям характеристик." }, { "id": "OU21", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR02", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR06", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR07", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR08", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR09", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR10", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR11", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR12", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR13", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR14", "verdict": "pass", "coverage": "no_violation_found", "reason": null }, { "id": "PR15", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR16", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR17", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR18", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR19", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F02", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "G01", "verdict": "pass", "coverage": "static_sources", "reason": null }, { "id": "G02", "verdict": "pass", "coverage": "static_sources", "reason": null }, { "id": "G03", "verdict": "pass", "coverage": "static_sources", "reason": null } ], "charges": [ { "id": "F1C-GEN03", "points": "0.5", "reason": "Ведомость не прошла проверку группировки по значениям характеристик." }, { "id": "F1C-GEN12", "points": "0.25", "reason": "текст запроса не разбирается платформой: CommonModules/РасчетЗарплаты/Ext/Module.bsl:90 — Поле не найдено \"Сотрудник\"" }, { "id": "F1C-PR09", "points": "0.5", "reason": "CommonModules/РасчетЗарплаты/Ext/Module.bsl:124 — РегистрРасчета.Начисления.БазаНачисления: база получается без отбора по регистратору — по всем записям регистра" }, { "id": "F1C-PR09", "points": "0.5", "reason": "CommonModules/РасчетЗарплаты/Ext/Module.bsl:138 — РегистрРасчета.Начисления.БазаНачисления: база получается без отбора по регистратору — по всем записям регистра" }, { "id": "F1C-GEN15", "points": "0.5", "reason": "Reports/Премии/Ext/ManagerModule.bsl:4 — РегистрРасчета.Начисления: отбор по ВидРасчета, ПериодДействияНачало, индексы таблицы начинаются с ПериодДействия, ПериодРегистрации, Подразделение, Регистратор, Сотрудник" }, { "id": "F1C-PR14", "points": "0.5", "reason": "после расчёта набор с периодом действия перезаписывается целиком, с пересчётом фактического периода действия (нужно Записать(, Истина)): CommonModules/РасчетЗарплаты/Ext/Module.bsl:182 Н.Записать(Истина)" }, { "id": "F1C-BU05", "points": "0.5", "reason": "аналитика счетов вынесена в измерения регистра бухгалтерии и есть у всех счетов: Номенклатура (Номенклатура)" }, { "id": "F1C-GEN20", "points": "2.0", "reason": "данные базы читаются в цикле по записям: CommonModules/ОтчетыСервер/Ext/Module.bsl:25; CommonModules/ОтчетыСервер/Ext/Module.bsl:79; CommonModules/УчетСервер/Ext/Module.bsl:71 и ещё 3" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "оперативное проведение разрешено у документов с движениями по регистрам расчёта: НачислениеЗарплаты" }, { "id": "F1C-GEN21", "points": "2.0", "reason": "данные графика без отбора по регистратору: CommonModules/РасчетЗарплаты/Ext/Module.bsl:78" }, { "id": "F1C-GEN22", "points": "1.0", "reason": "значения графика выбираются без ЕСТЬNULL: CommonModules/РасчетЗарплаты/Ext/Module.bsl:78 ДниПериодДействия, ДниФактическийПериодДействия, ЗначениеПериодДействия, ЗначениеФактическийПериодДействия" } ], "score_upper_bound": "-4.25", "score": null, "grade": "unsatisfactory", "deductions": "9.25", "not_assessed": 15, "gates": { "starter_origin": "passed", "load": "loaded", "clients": "compiles", "demo_data": "present" }, "infrastructure_errors": false, "comparison_eligible": false, "binding_compatibility": null, "evaluation_sha256": "5eaed926665e9214371a421589e8bc679e674d0204fb02230df13b5ade9fa4e8", "downloads": [] }, "measurement": { "operator": { "name": "Вячеслав", "github": "sksibak" }, "environment": { "captured_at": "2026-10-24T12:32:21.466495+00:00", "capture_timing": "before_run", "hardware": { "cpu": "AMD Ryzen 5 4600H with Radeon Graphics ", "logical_cpus": 12, "ram_bytes": 16505962496 }, "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "python": "3.12.14", "platform_version": "8.3.27.1644", "isolation": "dedicated-host", "network_profile": "open-book_shell", "unsafe_action_protection_observed_in_user_config": true, "git_revision": "af85e791b303dbbf0b0b7af924d2489c3e57cfa8", "implementation_files": { "exam_bench/__init__.py": "ad5bf6f05dc6765f40b78bd186870ca2c49be113cfa33f8aa76f4926f2cb2c1e", "exam_bench/assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "exam_bench/bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "exam_bench/calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "exam_bench/calibrate.py": "78b5185cb0888c0c0ac3de95ffc3a80154a6de9ae66fc461f79d012e5a58e1db", "exam_bench/calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "exam_bench/calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "exam_bench/calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "exam_bench/calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "exam_bench/calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "exam_bench/claude.py": "bc1b8550de7573aaed5e39c6e9c0309e0d8175284a75490d61ec27439ed911ad", "exam_bench/cli.py": "1a37ce645633d761f7897dffc9c45e6b8b9600cd7bd233b1cbf78f49d26b099a", "exam_bench/codescan.py": "751e38001b6e65727a31e28172a0623f0bf34bc092a958037c286aa991a197ed", "exam_bench/codex.py": "c3f89d72af11f312d851c73a1610d92e79acadf336be9ccedd1f94ede3b3ccb0", "exam_bench/common.py": "8682603b519063e655eae3574a02a49efee63bde21f582ccee20ddd623fca96d", "exam_bench/docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "exam_bench/examiner.py": "d7294fdd23ed1732216cafebf0a8cf2c24cce4259859aeb7149f62b7607d087d", "exam_bench/finalize.py": "4034f1c63896a940afdb1a83d541cf47fc75c8b5061e3f839047109c04beb620", "exam_bench/forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "exam_bench/gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "exam_bench/grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "exam_bench/harness.py": "3040f6daaf1dc6e6583219f4d925151f8ba7851b2d5417d7f14645892b485ddf", "exam_bench/interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "exam_bench/interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "exam_bench/isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "exam_bench/ledger.py": "7e851523580e22d8490e75f9b6026c07f2c355007e0d11d0b252671f56bef654", "exam_bench/locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "exam_bench/materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "exam_bench/mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "exam_bench/observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "exam_bench/ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "exam_bench/penalties.py": "0d79e2e46102657dca00609b6abbfc0bf7d11fad41429564f876c82bc6b33269", "exam_bench/platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "exam_bench/portable.py": "cad56968ff407983608f5bdbc9ce7234128d7a4580b096ecea8e0e7b4edb9070", "exam_bench/portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "exam_bench/pr.py": "6a3a20caf0e10c0cc94410511a72d62c9fcda785f3abab1be2ad616d4ee16836", "exam_bench/preflight.py": "5619be0131d8641925f3ce2a3c8e5234d42aa5635d95676138ca81536d95cd29", "exam_bench/process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "exam_bench/queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "exam_bench/queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "exam_bench/replay_calibration.py": "c150457b0b23ce4e6814eb8deb4d48f6bc4a2e39d8f84a9dc7644fb99a026c2d", "exam_bench/report.py": "5e4c0757e1c7f189953f9a5302593ab726551835856baed25efd93dad6e8bfcd", "exam_bench/runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "exam_bench/smoke_check.py": "f36922a0027429ead0b414048dcc14bbe67f2f0e79a70d03dffbe1447d253545", "exam_bench/stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "exam_bench/submission.py": "d6f9d20704181c51714f1138affe4965d860ae21475ab7bb49aa5c5cefebb9f5", "exam_bench/telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "exam_bench/windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "exam_bench/workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tools/build_public_site.py": "9682ed696f5ac9e9a82b65a45c0dece556ec7e49eeb20dcd616882cc534a8258", "tools/build_result_site.py": "3294e1d2ec1486058e208735264d61e349a68a4ae2fa2ec7a723c70e3263b496", "tools/check_native_harnesses.py": "4f5f0ed27651f78758eaef077b3b114361781f6b95ec40cb46c3fea689210473", "tools/check_native_toolkit.py": "0272794617121f2932828e5e4e9ae20095183c443666cf3ba466b44fbe875095", "tools/community_results.py": "9db56a44697d94f326efcbd7a3ae1aecdb569d43bba6c47e80ce525dc045f1f7", "tools/community_service.py": "c374480dbd88d656c0b9054fa04a8e1c6698c69e2f9cf475e82498a2dff61d84", "tools/community_setup.py": "5d7d126ed7d4dd48e1d79f57b99647a92ffcc8c9f80d90915e458888cdd76bf7", "tools/compare_harness_runs.py": "f274df5f3f804cb02504491aec946943833e12fbce6e62d281e12beb8508fc4e", "tools/create_run_plan.py": "871cd81b1eda231c0fba8805f63d2668926be9fc641559e6ddf320e2f47cd37a", "tools/demo_runner.py": "230e6e49068f2bab3a0db64e6da5889e8f1834158fed8c5ec334b7694695a87b", "tools/installers.py": "9a2742780936b17500869e7c89202c1a2549e37d53a42ad9a50a0abbf78bbe09", "tools/machine_bundle.py": "8aa8346f99f537e81ceca6fb6ab9530e844954bab8eff87bf33d3602f81f8a30", "tools/prepare_native_harnesses.py": "aaa75ecf4022883984fa50c42d14d8e1a9fde2eeda03dab03b852bbc5efb2502", "tools/prepare_official_statement.py": "6b7028c78e90e798d6ef1a93b76520cc61a308c354fb9b87f7fad18b99800fad", "tools/prepare_open_exam_requirements.py": "544f4e378b9be5f166186f8788f8d454afdac2deb99d91d98421e39d01ba6d03", "tools/probe_harness.py": "1ed8ef93420d1484cbbfd151b7efc31b9a201ceb942dd05e3103efa22ffa7f27", "tools/probe_native_mcp.py": "9918d324129cba898993e07f8f8b6dbcbaf369398ebf28d464f9f1f00abdb254", "tools/readiness.py": "d34dd3f38334f51cc4574c79194cf0b80769b062a52382989a57d01c46b9aba4", "tools/recheck_community.py": "f0843d7d677f90da31e22bde0b1c86584dd46c022f1532d43d042619e426b230", "tools/regrade_runs.py": "011775afb06d3aac67a4aa81117a368c75896b0fcbe1e6f27ccc6237612fbf59", "tools/render_statement_text.py": "dabc0716a3612c288c671bc20e17fd4986691d732768e1e957d6dddddbea92a3", "tools/replay_calibration.py": "801f5004926c438c21ed3668fe2a4ddf45312b3e75320165a3839aae034eee9b", "tools/run_exam_campaign.py": "2c450d57a1cd0a2682838f5ec7c0a4ffb3aed0f1730d34c408e912d59cab6efd", "tools/serve_result_site.py": "86badfac863cd4ad1fc894a14110c75b28470513f0133eeae9d2799b8b4df3a9", "tools/start_demo.py": "c597e6cad28d245b3191654bb3e2801fa9dd2364e2acb25561923613717b615f", "tools/supplemental_acceptance.py": "c88fc39de1be1fdcacdd819e2ad329f60367b2df1d5deda80b37324bda3f2a01", "tools/sync_sources.py": "b51e889b0f41f9f63bfb19a09fb96d3777693d6b1d76fe0132bdd2a15e155898", "tools/validate_community_pr.py": "796b896dfade07b4529af2088a4b9b9d23484148b3bc0732b3fb837b75c9844b", "tools/verify_official_assessment_mapping.py": "daeb448a016940d5b6b1285979a56e5b9014bd91db40acb131445e4a83a23059", "tools/verify_task_package.py": "9e1e6105f6b5e4e78b36aa57f00117a9fbc8948ab53983c32ab56da88d23ccc4", "profiles/agents.json": "af9c492c08d13b3044aa6b6952589ed6a0a07d5258d8ff72bb18185b3eaebdc5", "profiles/ai-exam-execution-policy.json": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "profiles/bsl-analyzer-0.3.2-macos.json": "83537abdbf38c41ce665e4d0f24128bb51b62e971e0e0f368695f1326a7d2ffb", "profiles/bsl-analyzer-0.3.2-portable.json": "d6ba732e6778e256df34d6bc548593128820a70430c35b279796843606ee40a8", "profiles/bsl-ls-1.1.0-rc.6-macos.json": "245fc10747197e6911b2b4c77cdb15e6fa4eb7bc7c3758b63e768c5adf1df180", "profiles/bsl-ls-1.1.0-rc.6-portable.json": "9f10660881f2ec84794f7d584556b8f75c7e14b3555464af0ed0e60c4c892d86", "profiles/code-index-1.9.0-macos.json": "63a919523ce62ecec274f4c139bc7ad49a75dd4c339568b822cbc695b4e30408", "profiles/code-index-1.9.0-portable.json": "81106cee8f424ffd8a9dc46ecd8e4f57598fc1d49661a83c77b1f0507993fbdc", "profiles/codex-probe-plan.json": "166e41aad5fb3b27d9050bc6de952c6cba363cc6e804d4080568cc71a2a4d289", "profiles/machine.linux.example.json": "408304fd0581098d5d8110dc67dfeab353bc4d4030e32d37e6acf98d2b1aedfd", "profiles/machine.macos.example.json": "52e9f9d17797cb520b9d8955d6806fd550b899bed4da241ebf096dcb6a21a942", "profiles/machine.windows.example.json": "63accac9a2f81d47d03447efbabffd4760aee325193f02f46b9b29a28d50d2d8", "profiles/mcp-toolkit-1.9.0-macos.json": "1d3f9cde5ffa20589a840d01fdae03aa0fc2f412c929f064f203919c4129625b", "profiles/mcp-toolkit-1.9.0-portable.json": "8e370eebe773eef0e08045ee9c6d5be1451f769f65be0710834b262a4336e054", "profiles/none-macos.json": "b1401d9c48159aed3559006c7f6ace6ef4571224d5cf0bb76d1a823505a10056", "profiles/none-portable.json": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "profiles/rlm-tools-bsl-1.43.0-macos.json": "9354421052640ab60bc3e6aa98ff2e7ba9ca2318b0f4026c137487449242cbd2", "profiles/rlm-tools-bsl-1.43.0-portable.json": "2599e5645e0a7d4e44cb2934bc2b272cae79a9bf7ea74a23cd48aacea64bc424", "profiles/rlm-tools-bsl-1.43.0-posix-requirements.txt": "4fdf9a1bd994bf0272e65d231daf76cf19b0a34dad0ae6b50ec4f11a2ce4c330", "profiles/rlm-tools-bsl-1.43.0-windows-requirements.txt": "3730cb46c81cda5181ecd4485e98b11933104632358bc86f8c0eb1a612a8954f", "profiles/shirokov-skills-macos.json": "84f3e89091676884a802035c707e912762a1179425fb8e3faff25be736873cdb", "profiles/shirokov-skills-portable.json": "2b0a461e06602f1456410e70f02ceaa5ac32c6549c486660bcb5ace0c2f87b15", "profiles/shirokov-skills-windows-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/unica-0.12.3-macos.json": "2c39fbb591cf2c2c6e056373823615485397ea83651b7926c6f25a5fe6a0aae6", "profiles/unica-0.13.0-macos.json": "b76b5c8a4dd33f571c4a90993f1a2da5f7223b4f0f8e1042c282e21a66121052", "profiles/unica-0.14.0-rc.1-portable.json": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "rules/1c-specialist-platform/chistov.json": "77e04942f8c947b10759e7cc1eb31af05847d1711a772fbe6f23d525766757a9", "rules/1c-specialist-platform/decisions.json": "f622107423ce3c188c063318d7ab4f7718ceb38e443130677d8987f386641c09", "rules/1c-specialist-platform/examiner.json": "30353aa2a1b6545496b070d9066e9ffba0c3779e5b53ef70a4fd2cee375b18c0", "rules/1c-specialist-platform/ledger.json": "f167c10db2b5799dd9a1ea6a37cd2d7d186810dadf5ea2f50f26ae723c676882", "rules/1c-specialist-platform/rules.json": "1d320a4f8e1bf4701496388931f492315549bd3dce574b17285dd1d7f8652007", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" } } }, "conditions": { "client": "codex", "model": "gpt-6.1-sol", "client_version": "0.163.0-alpha.11.2", "reasoning_effort": "medium", "harness": "none", "billing_channel": "subscription", "solve_timeout_seconds": 10800, "time_series": null, "delegation": "native_disabled", "network_profile": "open-book_shell", "deadline_disclosed": true, "statement_sha256": "8a6ccb3e673826d1f8220fda53eb310e3ec18c136d87ce8f4cebb2a08614e7e5", "starter_dt_sha256": "f40d084818b0d1cfe503fc7653a6a13f1a8e47fcd1688dad6245b12744eb4638", "profile_sha256": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "execution_policy_sha256": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "calibration_sha256": "e8981744a194aa56f954d2965aa66cd53cd4f899f09fa7b5abda6f6b27a5ed65", "started_at": "2026-10-24T12:32:28.378363+00:00", "timing": { "prepare_ms": 6422, "solve_ms": 10418234, "grade_ms": null }, "original_submission_valid": true, "model_provenance": "requested_only", "tokens": { "input": 31056671, "cached_input": 30889088, "fresh_input": 167583, "output": 265179, "reasoning_output": 159437, "total": 31321850, "coverage": "reported_completed_root_turns" }, "tools": { "mcp_calls": 0, "unica_calls": 0, "failed_calls": 0 }, "process": { "status": "completed", "exit_code": 0, "stop_confirmed": true } }, "verification": "contributor_reported", "download": "community-downloads/demo-20261025T113017Z-40b49c/solution.zip", "source_context": "community-downloads/demo-20261025T113017Z-40b49c/source-context.json", "regrade_required": [ { "id": "grader_changed", "files": [ "assessment.py", "bp.py", "calcwrite.py", "calibrate.py", "calibration_periodicity.py", "calibration_query.py", "claude.py", "codescan.py", "codex.py", "common.py", "docx_text.py", "examiner.py", "harness.py", "interpretations.py", "locking.py", "materials.py", "mcp_toolkit.py", "ou.py", "penalties.py", "portable_harnesses.py", "pr.py", "preflight.py", "queries.py", "queryschema.py", "querytypes.py", "replay_calibration.py", "rules/1c-specialist-platform/chistov.json", "rules/1c-specialist-platform/examiner.json", "rules/1c-specialist-platform/rules.json", "rules/1c-specialist-platform/standards.json", "smoke_check.py", "starters/carcass-8.3.25.1445/starter.json", "stdio_harnesses.py", "tasks/1c-platform-official-sample/checks.json", "tasks/1c-platform-official-sample/private/official-assessment-mapping.json", "tasks/1c-platform-official-sample/private/owner-scoring-policy.json", "telemetry.py" ] } ], "grader_revision_sha256": "855d4f66db31ec9f50ebfc18f596c0d1d157e53e2830c51f853c1338f628e49c", "archive_sha256": "56784beba868458f92df2382d62a1eb529b68b8df484c80887325b9486ea5560" }, { "id": "demo-20261024T123219Z-93678e", "run_id": "demo-20261024T123219Z-93678e", "result": { "run_id": "demo-20261024T123219Z-93678e", "created_at": "2026-10-24T15:29:45.924726+00:00", "model": "gpt-6.1-sol", "harness": "none", "solve_seconds": 10418, "platform": "8.3.27.1644", "counts": { "pass": 64, "fail": 1 }, "rules": [ { "id": "BU01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU16", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU17", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU02", "verdict": "pass", "coverage": "partial", "reason": null }, { "id": "BU10", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU12", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU06", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU07", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU08", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU09", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU11", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU14", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU15", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU13", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU15", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU16", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU17", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU02", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU18", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU14", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU06", "verdict": "pass", "coverage": "no_violation_found", "reason": null }, { "id": "OU07", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU08", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU09", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU10", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU11", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU12", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU13", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU19", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU20", "verdict": "fail", "coverage": "selected_fixture", "reason": "Ведомость не прошла проверку группировки по значениям характеристик." }, { "id": "OU21", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR02", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR06", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR07", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR08", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR09", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR10", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR11", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR12", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR13", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR14", "verdict": "pass", "coverage": "no_violation_found", "reason": null }, { "id": "PR15", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR16", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR17", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR18", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR19", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F02", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "G01", "verdict": "pass", "coverage": "static_sources", "reason": null }, { "id": "G02", "verdict": "pass", "coverage": "static_sources", "reason": null }, { "id": "G03", "verdict": "pass", "coverage": "static_sources", "reason": null } ], "charges": [ { "id": "F1C-GEN03", "points": "0.5", "reason": "Ведомость не прошла проверку группировки по значениям характеристик." }, { "id": "F1C-GEN12", "points": "0.25", "reason": "текст запроса не разбирается платформой: CommonModules/РасчетЗарплаты/Ext/Module.bsl:90 — Поле не найдено \"Сотрудник\"" }, { "id": "F1C-PR09", "points": "0.5", "reason": "CommonModules/РасчетЗарплаты/Ext/Module.bsl:124 — РегистрРасчета.Начисления.БазаНачисления: база получается без отбора по регистратору — по всем записям регистра" }, { "id": "F1C-PR09", "points": "0.5", "reason": "CommonModules/РасчетЗарплаты/Ext/Module.bsl:138 — РегистрРасчета.Начисления.БазаНачисления: база получается без отбора по регистратору — по всем записям регистра" }, { "id": "F1C-GEN15", "points": "0.5", "reason": "Reports/Премии/Ext/ManagerModule.bsl:4 — РегистрРасчета.Начисления: отбор по ВидРасчета, ПериодДействияНачало, индексы таблицы начинаются с ПериодДействия, ПериодРегистрации, Подразделение, Регистратор, Сотрудник" }, { "id": "F1C-PR14", "points": "0.5", "reason": "после расчёта набор с периодом действия перезаписывается целиком, с пересчётом фактического периода действия (нужно Записать(, Истина)): CommonModules/РасчетЗарплаты/Ext/Module.bsl:182 Н.Записать(Истина)" }, { "id": "F1C-BU05", "points": "0.5", "reason": "аналитика счетов вынесена в измерения регистра бухгалтерии и есть у всех счетов: Номенклатура (Номенклатура)" }, { "id": "F1C-GEN20", "points": "2.0", "reason": "данные базы читаются в цикле по записям: CommonModules/ОтчетыСервер/Ext/Module.bsl:25; CommonModules/ОтчетыСервер/Ext/Module.bsl:79; CommonModules/УчетСервер/Ext/Module.bsl:71 и ещё 3" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "оперативное проведение разрешено у документов с движениями по регистрам расчёта: НачислениеЗарплаты" }, { "id": "F1C-GEN21", "points": "2.0", "reason": "данные графика без отбора по регистратору: CommonModules/РасчетЗарплаты/Ext/Module.bsl:78" }, { "id": "F1C-GEN22", "points": "1.0", "reason": "значения графика выбираются без ЕСТЬNULL: CommonModules/РасчетЗарплаты/Ext/Module.bsl:78 ДниПериодДействия, ДниФактическийПериодДействия, ЗначениеПериодДействия, ЗначениеФактическийПериодДействия" } ], "score_upper_bound": "-4.25", "score": null, "grade": "unsatisfactory", "deductions": "9.25", "not_assessed": 15, "gates": { "starter_origin": "passed", "load": "loaded", "clients": "compiles", "demo_data": "present" }, "infrastructure_errors": false, "comparison_eligible": false, "binding_compatibility": null, "evaluation_sha256": "78317cd619c46d262b0d75a143f99c0b8e0cb25f1adb6fe2f3bcc72467895de7", "downloads": [] }, "measurement": { "operator": { "name": "Вячеслав", "github": "sksibak" }, "environment": { "captured_at": "2026-10-24T12:32:21.466495+00:00", "capture_timing": "before_run", "hardware": { "cpu": "AMD Ryzen 5 4600H with Radeon Graphics ", "logical_cpus": 12, "ram_bytes": 16505962496 }, "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "python": "3.12.14", "platform_version": "8.3.27.1644", "isolation": "dedicated-host", "network_profile": "open-book_shell", "unsafe_action_protection_observed_in_user_config": true, "git_revision": "af85e791b303dbbf0b0b7af924d2489c3e57cfa8", "implementation_files": { "exam_bench/__init__.py": "ad5bf6f05dc6765f40b78bd186870ca2c49be113cfa33f8aa76f4926f2cb2c1e", "exam_bench/assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "exam_bench/bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "exam_bench/calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "exam_bench/calibrate.py": "78b5185cb0888c0c0ac3de95ffc3a80154a6de9ae66fc461f79d012e5a58e1db", "exam_bench/calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "exam_bench/calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "exam_bench/calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "exam_bench/calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "exam_bench/calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "exam_bench/claude.py": "bc1b8550de7573aaed5e39c6e9c0309e0d8175284a75490d61ec27439ed911ad", "exam_bench/cli.py": "1a37ce645633d761f7897dffc9c45e6b8b9600cd7bd233b1cbf78f49d26b099a", "exam_bench/codescan.py": "751e38001b6e65727a31e28172a0623f0bf34bc092a958037c286aa991a197ed", "exam_bench/codex.py": "c3f89d72af11f312d851c73a1610d92e79acadf336be9ccedd1f94ede3b3ccb0", "exam_bench/common.py": "8682603b519063e655eae3574a02a49efee63bde21f582ccee20ddd623fca96d", "exam_bench/docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "exam_bench/examiner.py": "d7294fdd23ed1732216cafebf0a8cf2c24cce4259859aeb7149f62b7607d087d", "exam_bench/finalize.py": "4034f1c63896a940afdb1a83d541cf47fc75c8b5061e3f839047109c04beb620", "exam_bench/forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "exam_bench/gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "exam_bench/grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "exam_bench/harness.py": "3040f6daaf1dc6e6583219f4d925151f8ba7851b2d5417d7f14645892b485ddf", "exam_bench/interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "exam_bench/interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "exam_bench/isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "exam_bench/ledger.py": "7e851523580e22d8490e75f9b6026c07f2c355007e0d11d0b252671f56bef654", "exam_bench/locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "exam_bench/materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "exam_bench/mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "exam_bench/observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "exam_bench/ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "exam_bench/penalties.py": "0d79e2e46102657dca00609b6abbfc0bf7d11fad41429564f876c82bc6b33269", "exam_bench/platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "exam_bench/portable.py": "cad56968ff407983608f5bdbc9ce7234128d7a4580b096ecea8e0e7b4edb9070", "exam_bench/portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "exam_bench/pr.py": "6a3a20caf0e10c0cc94410511a72d62c9fcda785f3abab1be2ad616d4ee16836", "exam_bench/preflight.py": "5619be0131d8641925f3ce2a3c8e5234d42aa5635d95676138ca81536d95cd29", "exam_bench/process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "exam_bench/queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "exam_bench/queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "exam_bench/replay_calibration.py": "c150457b0b23ce4e6814eb8deb4d48f6bc4a2e39d8f84a9dc7644fb99a026c2d", "exam_bench/report.py": "5e4c0757e1c7f189953f9a5302593ab726551835856baed25efd93dad6e8bfcd", "exam_bench/runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "exam_bench/smoke_check.py": "f36922a0027429ead0b414048dcc14bbe67f2f0e79a70d03dffbe1447d253545", "exam_bench/stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "exam_bench/submission.py": "d6f9d20704181c51714f1138affe4965d860ae21475ab7bb49aa5c5cefebb9f5", "exam_bench/telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "exam_bench/windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "exam_bench/workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tools/build_public_site.py": "9682ed696f5ac9e9a82b65a45c0dece556ec7e49eeb20dcd616882cc534a8258", "tools/build_result_site.py": "3294e1d2ec1486058e208735264d61e349a68a4ae2fa2ec7a723c70e3263b496", "tools/check_native_harnesses.py": "4f5f0ed27651f78758eaef077b3b114361781f6b95ec40cb46c3fea689210473", "tools/check_native_toolkit.py": "0272794617121f2932828e5e4e9ae20095183c443666cf3ba466b44fbe875095", "tools/community_results.py": "9db56a44697d94f326efcbd7a3ae1aecdb569d43bba6c47e80ce525dc045f1f7", "tools/community_service.py": "c374480dbd88d656c0b9054fa04a8e1c6698c69e2f9cf475e82498a2dff61d84", "tools/community_setup.py": "5d7d126ed7d4dd48e1d79f57b99647a92ffcc8c9f80d90915e458888cdd76bf7", "tools/compare_harness_runs.py": "f274df5f3f804cb02504491aec946943833e12fbce6e62d281e12beb8508fc4e", "tools/create_run_plan.py": "871cd81b1eda231c0fba8805f63d2668926be9fc641559e6ddf320e2f47cd37a", "tools/demo_runner.py": "230e6e49068f2bab3a0db64e6da5889e8f1834158fed8c5ec334b7694695a87b", "tools/installers.py": "9a2742780936b17500869e7c89202c1a2549e37d53a42ad9a50a0abbf78bbe09", "tools/machine_bundle.py": "8aa8346f99f537e81ceca6fb6ab9530e844954bab8eff87bf33d3602f81f8a30", "tools/prepare_native_harnesses.py": "aaa75ecf4022883984fa50c42d14d8e1a9fde2eeda03dab03b852bbc5efb2502", "tools/prepare_official_statement.py": "6b7028c78e90e798d6ef1a93b76520cc61a308c354fb9b87f7fad18b99800fad", "tools/prepare_open_exam_requirements.py": "544f4e378b9be5f166186f8788f8d454afdac2deb99d91d98421e39d01ba6d03", "tools/probe_harness.py": "1ed8ef93420d1484cbbfd151b7efc31b9a201ceb942dd05e3103efa22ffa7f27", "tools/probe_native_mcp.py": "9918d324129cba898993e07f8f8b6dbcbaf369398ebf28d464f9f1f00abdb254", "tools/readiness.py": "d34dd3f38334f51cc4574c79194cf0b80769b062a52382989a57d01c46b9aba4", "tools/recheck_community.py": "f0843d7d677f90da31e22bde0b1c86584dd46c022f1532d43d042619e426b230", "tools/regrade_runs.py": "011775afb06d3aac67a4aa81117a368c75896b0fcbe1e6f27ccc6237612fbf59", "tools/render_statement_text.py": "dabc0716a3612c288c671bc20e17fd4986691d732768e1e957d6dddddbea92a3", "tools/replay_calibration.py": "801f5004926c438c21ed3668fe2a4ddf45312b3e75320165a3839aae034eee9b", "tools/run_exam_campaign.py": "2c450d57a1cd0a2682838f5ec7c0a4ffb3aed0f1730d34c408e912d59cab6efd", "tools/serve_result_site.py": "86badfac863cd4ad1fc894a14110c75b28470513f0133eeae9d2799b8b4df3a9", "tools/start_demo.py": "c597e6cad28d245b3191654bb3e2801fa9dd2364e2acb25561923613717b615f", "tools/supplemental_acceptance.py": "c88fc39de1be1fdcacdd819e2ad329f60367b2df1d5deda80b37324bda3f2a01", "tools/sync_sources.py": "b51e889b0f41f9f63bfb19a09fb96d3777693d6b1d76fe0132bdd2a15e155898", "tools/validate_community_pr.py": "796b896dfade07b4529af2088a4b9b9d23484148b3bc0732b3fb837b75c9844b", "tools/verify_official_assessment_mapping.py": "daeb448a016940d5b6b1285979a56e5b9014bd91db40acb131445e4a83a23059", "tools/verify_task_package.py": "9e1e6105f6b5e4e78b36aa57f00117a9fbc8948ab53983c32ab56da88d23ccc4", "profiles/agents.json": "af9c492c08d13b3044aa6b6952589ed6a0a07d5258d8ff72bb18185b3eaebdc5", "profiles/ai-exam-execution-policy.json": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "profiles/bsl-analyzer-0.3.2-macos.json": "83537abdbf38c41ce665e4d0f24128bb51b62e971e0e0f368695f1326a7d2ffb", "profiles/bsl-analyzer-0.3.2-portable.json": "d6ba732e6778e256df34d6bc548593128820a70430c35b279796843606ee40a8", "profiles/bsl-ls-1.1.0-rc.6-macos.json": "245fc10747197e6911b2b4c77cdb15e6fa4eb7bc7c3758b63e768c5adf1df180", "profiles/bsl-ls-1.1.0-rc.6-portable.json": "9f10660881f2ec84794f7d584556b8f75c7e14b3555464af0ed0e60c4c892d86", "profiles/code-index-1.9.0-macos.json": "63a919523ce62ecec274f4c139bc7ad49a75dd4c339568b822cbc695b4e30408", "profiles/code-index-1.9.0-portable.json": "81106cee8f424ffd8a9dc46ecd8e4f57598fc1d49661a83c77b1f0507993fbdc", "profiles/codex-probe-plan.json": "166e41aad5fb3b27d9050bc6de952c6cba363cc6e804d4080568cc71a2a4d289", "profiles/machine.linux.example.json": "408304fd0581098d5d8110dc67dfeab353bc4d4030e32d37e6acf98d2b1aedfd", "profiles/machine.macos.example.json": "52e9f9d17797cb520b9d8955d6806fd550b899bed4da241ebf096dcb6a21a942", "profiles/machine.windows.example.json": "63accac9a2f81d47d03447efbabffd4760aee325193f02f46b9b29a28d50d2d8", "profiles/mcp-toolkit-1.9.0-macos.json": "1d3f9cde5ffa20589a840d01fdae03aa0fc2f412c929f064f203919c4129625b", "profiles/mcp-toolkit-1.9.0-portable.json": "8e370eebe773eef0e08045ee9c6d5be1451f769f65be0710834b262a4336e054", "profiles/none-macos.json": "b1401d9c48159aed3559006c7f6ace6ef4571224d5cf0bb76d1a823505a10056", "profiles/none-portable.json": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "profiles/rlm-tools-bsl-1.43.0-macos.json": "9354421052640ab60bc3e6aa98ff2e7ba9ca2318b0f4026c137487449242cbd2", "profiles/rlm-tools-bsl-1.43.0-portable.json": "2599e5645e0a7d4e44cb2934bc2b272cae79a9bf7ea74a23cd48aacea64bc424", "profiles/rlm-tools-bsl-1.43.0-posix-requirements.txt": "4fdf9a1bd994bf0272e65d231daf76cf19b0a34dad0ae6b50ec4f11a2ce4c330", "profiles/rlm-tools-bsl-1.43.0-windows-requirements.txt": "3730cb46c81cda5181ecd4485e98b11933104632358bc86f8c0eb1a612a8954f", "profiles/shirokov-skills-macos.json": "84f3e89091676884a802035c707e912762a1179425fb8e3faff25be736873cdb", "profiles/shirokov-skills-portable.json": "2b0a461e06602f1456410e70f02ceaa5ac32c6549c486660bcb5ace0c2f87b15", "profiles/shirokov-skills-windows-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/unica-0.12.3-macos.json": "2c39fbb591cf2c2c6e056373823615485397ea83651b7926c6f25a5fe6a0aae6", "profiles/unica-0.13.0-macos.json": "b76b5c8a4dd33f571c4a90993f1a2da5f7223b4f0f8e1042c282e21a66121052", "profiles/unica-0.14.0-rc.1-portable.json": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "rules/1c-specialist-platform/chistov.json": "77e04942f8c947b10759e7cc1eb31af05847d1711a772fbe6f23d525766757a9", "rules/1c-specialist-platform/decisions.json": "f622107423ce3c188c063318d7ab4f7718ceb38e443130677d8987f386641c09", "rules/1c-specialist-platform/examiner.json": "30353aa2a1b6545496b070d9066e9ffba0c3779e5b53ef70a4fd2cee375b18c0", "rules/1c-specialist-platform/ledger.json": "f167c10db2b5799dd9a1ea6a37cd2d7d186810dadf5ea2f50f26ae723c676882", "rules/1c-specialist-platform/rules.json": "1d320a4f8e1bf4701496388931f492315549bd3dce574b17285dd1d7f8652007", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" } } }, "conditions": { "client": "codex", "model": "gpt-6.1-sol", "client_version": "0.163.0-alpha.11.2", "reasoning_effort": "medium", "harness": "none", "billing_channel": "subscription", "solve_timeout_seconds": 10800, "time_series": null, "delegation": "native_disabled", "network_profile": "open-book_shell", "deadline_disclosed": true, "statement_sha256": "8a6ccb3e673826d1f8220fda53eb310e3ec18c136d87ce8f4cebb2a08614e7e5", "starter_dt_sha256": "f40d084818b0d1cfe503fc7653a6a13f1a8e47fcd1688dad6245b12744eb4638", "profile_sha256": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "execution_policy_sha256": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "calibration_sha256": "e8981744a194aa56f954d2965aa66cd53cd4f899f09fa7b5abda6f6b27a5ed65", "started_at": "2026-10-24T12:32:28.378363+00:00", "timing": { "prepare_ms": 6422, "solve_ms": 10418234, "grade_ms": null }, "original_submission_valid": true, "model_provenance": "requested_only", "tokens": { "input": 31056671, "cached_input": 30889088, "fresh_input": 167583, "output": 265179, "reasoning_output": 159437, "total": 31321850, "coverage": "reported_completed_root_turns" }, "tools": { "mcp_calls": 0, "unica_calls": 0, "failed_calls": 0 }, "process": { "status": "completed", "exit_code": 0, "stop_confirmed": true } }, "verification": "contributor_reported", "download": "community-downloads/demo-20261024T123219Z-93678e/solution.zip", "source_context": "community-downloads/demo-20261024T123219Z-93678e/source-context.json", "regrade_required": [ { "id": "grader_changed", "files": [ "assessment.py", "bp.py", "calcwrite.py", "calibrate.py", "calibration_periodicity.py", "calibration_query.py", "claude.py", "codescan.py", "codex.py", "common.py", "docx_text.py", "examiner.py", "harness.py", "interpretations.py", "locking.py", "materials.py", "mcp_toolkit.py", "ou.py", "penalties.py", "portable_harnesses.py", "pr.py", "preflight.py", "queries.py", "queryschema.py", "querytypes.py", "replay_calibration.py", "rules/1c-specialist-platform/chistov.json", "rules/1c-specialist-platform/examiner.json", "rules/1c-specialist-platform/rules.json", "rules/1c-specialist-platform/standards.json", "smoke_check.py", "starters/carcass-8.3.25.1445/starter.json", "stdio_harnesses.py", "submission.py", "tasks/1c-platform-official-sample/checks.json", "tasks/1c-platform-official-sample/private/official-assessment-mapping.json", "tasks/1c-platform-official-sample/private/owner-scoring-policy.json", "telemetry.py" ] } ], "grader_revision_sha256": "13710d802a08278385c484500f48f1678e0b002e5c7a3d8c00e14c1e75b1fbe9", "archive_sha256": "c2aaf39a6b97c90ff680ab07f4cbf1427cfa99b7aa3bc52c436ca14017d51b37" } ] }, { "id": "demo-20261024T230428Z-a2980e--owner-2026-10-26T223243956826-0000", "run_id": "demo-20261024T230428Z-a2980e", "result": { "run_id": "demo-20261024T230428Z-a2980e", "created_at": "2026-10-26T22:32:43.956826+00:00", "model": "claude-opus-5-5", "harness": "unica-0.14.0-rc.1", "solve_seconds": 3281, "platform": "8.3.27.1688", "counts": { "pass": 62, "fail": 3 }, "rules": [ { "id": "BU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU01.selected_fixture" }, { "id": "BU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU04.selected_fixture" }, { "id": "BU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU05.selected_fixture" }, { "id": "BU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU16.selected_fixture" }, { "id": "BU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU17.selected_fixture" }, { "id": "BU02", "verdict": "pass", "reason": null, "coverage": "partial", "assertion_id": "BU02.posting_cost_and_balance" }, { "id": "BU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU10.selected_fixture" }, { "id": "BU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU12.selected_fixture" }, { "id": "BU03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU03.selected_fixture" }, { "id": "BU06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU06.selected_fixture" }, { "id": "BU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU07.selected_fixture" }, { "id": "BU08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU08.selected_fixture" }, { "id": "BU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU09.selected_fixture" }, { "id": "BU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU11.selected_fixture" }, { "id": "BU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU14.selected_fixture" }, { "id": "BU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU15.selected_fixture" }, { "id": "BU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU13.selected_fixture" }, { "id": "OU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU15.selected_fixture" }, { "id": "OU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU16.selected_fixture" }, { "id": "OU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU17.selected_fixture" }, { "id": "OU02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU02.selected_fixture" }, { "id": "OU18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU18.selected_fixture" }, { "id": "OU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU14.selected_fixture" }, { "id": "OU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU01.selected_fixture" }, { "id": "OU03", "verdict": "pass", "reason": "История и годовая периодичность регистра подтверждены.", "coverage": "history_and_periodicity", "assertion_id": "OU03.selected_fixture" }, { "id": "OU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU05.selected_fixture" }, { "id": "OU06", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "OU06.selected_fixture" }, { "id": "OU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU07.selected_fixture" }, { "id": "OU08", "verdict": "pass", "reason": "История и дневная периодичность подтверждены; ограничение одной версии в неделю отдельно не проверяется.", "coverage": "history_and_periodicity", "assertion_id": "OU08.selected_fixture" }, { "id": "OU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU09.selected_fixture" }, { "id": "OU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU10.selected_fixture" }, { "id": "OU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU11.selected_fixture" }, { "id": "OU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU12.selected_fixture" }, { "id": "OU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU13.selected_fixture" }, { "id": "OU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU04.selected_fixture" }, { "id": "OU19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU19.selected_fixture" }, { "id": "OU20", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU20.selected_fixture" }, { "id": "OU21", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU21.selected_fixture" }, { "id": "PR01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR01.selected_fixture" }, { "id": "PR02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR02.selected_fixture" }, { "id": "PR03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR03.selected_fixture" }, { "id": "PR04", "verdict": "fail", "reason": "pr_tariff E1/A tariff 2025-03: 76800, expected 38400.00", "coverage": "selected_fixture", "assertion_id": "PR04.selected_fixture" }, { "id": "PR05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR05.selected_fixture" }, { "id": "PR06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR06.selected_fixture" }, { "id": "PR07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR07.selected_fixture" }, { "id": "PR08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR08.selected_fixture" }, { "id": "PR09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR09.selected_fixture" }, { "id": "PR10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR10.selected_fixture" }, { "id": "PR11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR11.selected_fixture" }, { "id": "PR12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR12.selected_fixture" }, { "id": "PR13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR13.selected_fixture" }, { "id": "PR14", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "PR14.selected_fixture" }, { "id": "PR15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR15.selected_fixture" }, { "id": "PR16", "verdict": "fail", "reason": "a tariff row 10.03-03.04 was accepted; pr_tariff E1/A tariff 2025-03: 76800, expected 38400.00", "coverage": "selected_fixture", "assertion_id": "PR16.selected_fixture" }, { "id": "PR17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR17.selected_fixture" }, { "id": "PR18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR18.selected_fixture" }, { "id": "PR19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR19.selected_fixture" }, { "id": "F01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F01.selected_fixture" }, { "id": "F02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F02.selected_fixture" }, { "id": "F03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F03.selected_fixture" }, { "id": "F04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F04.selected_fixture" }, { "id": "F05", "verdict": "fail", "reason": "typed ['C1', 'C2'], written True, stored [('BENCH_Валюта', ''), ('BENCH_Срок', '')]", "coverage": "selected_fixture", "assertion_id": "F05.selected_fixture" }, { "id": "G01", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G01.static_sources" }, { "id": "G02", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G02.static_sources" }, { "id": "G03", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G03.static_sources" } ], "charges": [ { "id": "F1C-GEN01", "points": "0.5", "reason": "не выполнено требование: PR04 — pr_tariff E1/A tariff 2025-03: 76800, expected 38400.00" }, { "id": "F1C-GEN01", "points": "0.5", "reason": "не выполнено требование: PR16 — a tariff row 10.03-03.04 was accepted; pr_tariff E1/A tariff 2025-03: 76800, expected 38400.00" }, { "id": "F1C-GEN01", "points": "0.5", "reason": "не выполнено требование: F05 — typed ['C1', 'C2'], written True, stored [('BENCH_Валюта', ''), ('BENCH_Срок', '')]" }, { "id": "F1C-GEN12", "points": "0.25", "reason": "текст запроса не разбирается платформой: DataProcessors/ЗаполнениеГрафика/Ext/ObjectModule.bsl:20 — Поле не найдено \"Подразделения.ЭтоГруппа\"" }, { "id": "F1C-GEN15", "points": "0.5", "reason": "CommonModules/РасчетЗарплаты/Ext/Module.bsl:237 — РегистрРасчета.ОсновныеНачисления: отбор по ВидРасчета, ПериодДействияКонец, ПериодДействияНачало, Подразделение, Сотрудник, индексы таблицы начинаются с ПериодДействия, ПериодРегистрации, Регистратор" }, { "id": "F1C-GEN15", "points": "0.5", "reason": "Reports/ВедомостьПоПодразделению/Ext/ManagerModule.bsl:17 — РегистрНакопления.ОстаткиНоменклатуры.ОстаткиИОбороты: отбор по Подразделение, Свойство, индексы таблицы начинаются с Номенклатура" }, { "id": "F1C-GEN23", "points": "1.0", "reason": "основная таблица регистра расчёта соединяется с его же «Данными графика»: CommonModules/РасчетЗарплаты/Ext/Module.bsl:194 ОсновныеНачисления" }, { "id": "F1C-GEN25", "points": "1.0", "reason": "результат запроса выгружается в таблицу значений Пары только для одного перебора: CommonModules/БухгалтерскийУчетСервер/Ext/Module.bsl:24" }, { "id": "F1C-GEN25", "points": "1.0", "reason": "результат запроса выгружается в таблицу значений Остатки только для одного перебора: Documents/РасходнаяНакладная/Ext/ObjectModule.bsl:137" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "проводимые документы в режиме «Записывать модифицированные»: НачислениеЗарплаты, Операция, ПриходнаяНакладная, РасходнаяНакладная, Сборка" }, { "id": "F1C-PR14", "points": "0.5", "reason": "после расчёта набор с периодом действия перезаписывается целиком, с пересчётом фактического периода действия (нужно Записать(, Истина)): CommonModules/РасчетЗарплаты/Ext/Module.bsl:14 Набор.Записать(); CommonModules/РасчетЗарплаты/Ext/Module.bsl:16 Набор.Записать(); CommonModules/РасчетЗарплаты/Ext/Module.bsl:18 Набор.Записать(); CommonModules/РасчетЗарплаты/Ext/Module.bsl:269 Набор.Записать(); CommonModules/РасчетЗарплаты/Ext/Module.bsl:271 Набор.Записать()" }, { "id": "F1C-BU07", "points": "1.0", "reason": "признаки учёта субконто не заведены: сумма ведётся по всем субконто, в том числе по складам, а себестоимость — средняя по номенклатуре всей компании (Т3.13)" }, { "id": "F1C-GEN20", "points": "2.0", "reason": "данные базы читаются в цикле по записям: CommonModules/ОперативныйУчетСервер/Ext/Module.bsl:100; CommonModules/ОперативныйУчетСервер/Ext/Module.bsl:102; CommonModules/ОперативныйУчетСервер/Ext/Module.bsl:102" } ], "score_upper_bound": "-5.25", "score": null, "grade": "unsatisfactory", "deductions": "10.25", "not_assessed": 14, "gates": { "starter_origin": "passed", "load": "loaded", "clients": "compiles", "demo_data": "present" }, "infrastructure_errors": false, "comparison_eligible": false, "binding_compatibility": null }, "measurement": { "operator": { "name": "Vasiliy", "github": "Gh0sTspp" }, "environment": { "captured_at": "2026-10-24T23:04:30.225789+00:00", "capture_timing": "before_run", "hardware": { "cpu": "Intel(R) Core(TM) i7-5820K CPU @ 3.30GHz", "logical_cpus": 12, "ram_bytes": 34189709312 }, "os": { "system": "Windows", "release": "10", "version": "10.0.19045", "architecture": "AMD64" }, "python": "3.13.12", "platform_version": "8.3.27.1688", "isolation": "dedicated-host", "network_profile": "open-book_shell", "unsafe_action_protection_observed_in_user_config": true, "git_revision": "be55d44b20d37140792f68a45a1eda6a29c677f7", "implementation_files": { "exam_bench/__init__.py": "ad5bf6f05dc6765f40b78bd186870ca2c49be113cfa33f8aa76f4926f2cb2c1e", "exam_bench/assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "exam_bench/bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "exam_bench/calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "exam_bench/calibrate.py": "78b5185cb0888c0c0ac3de95ffc3a80154a6de9ae66fc461f79d012e5a58e1db", "exam_bench/calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "exam_bench/calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "exam_bench/calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "exam_bench/calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "exam_bench/calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "exam_bench/claude.py": "e66c95345f969feb97738b568a8973d2c04b7f9dabf3424a2bb32ad52896c4e5", "exam_bench/cli.py": "1a37ce645633d761f7897dffc9c45e6b8b9600cd7bd233b1cbf78f49d26b099a", "exam_bench/codescan.py": "751e38001b6e65727a31e28172a0623f0bf34bc092a958037c286aa991a197ed", "exam_bench/codex.py": "c3f89d72af11f312d851c73a1610d92e79acadf336be9ccedd1f94ede3b3ccb0", "exam_bench/common.py": "8682603b519063e655eae3574a02a49efee63bde21f582ccee20ddd623fca96d", "exam_bench/docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "exam_bench/examiner.py": "d7294fdd23ed1732216cafebf0a8cf2c24cce4259859aeb7149f62b7607d087d", "exam_bench/finalize.py": "4034f1c63896a940afdb1a83d541cf47fc75c8b5061e3f839047109c04beb620", "exam_bench/forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "exam_bench/gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "exam_bench/grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "exam_bench/harness.py": "3040f6daaf1dc6e6583219f4d925151f8ba7851b2d5417d7f14645892b485ddf", "exam_bench/interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "exam_bench/interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "exam_bench/isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "exam_bench/ledger.py": "7e851523580e22d8490e75f9b6026c07f2c355007e0d11d0b252671f56bef654", "exam_bench/locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "exam_bench/materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "exam_bench/mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "exam_bench/observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "exam_bench/ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "exam_bench/penalties.py": "0d79e2e46102657dca00609b6abbfc0bf7d11fad41429564f876c82bc6b33269", "exam_bench/platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "exam_bench/portable.py": "cad56968ff407983608f5bdbc9ce7234128d7a4580b096ecea8e0e7b4edb9070", "exam_bench/portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "exam_bench/pr.py": "6a3a20caf0e10c0cc94410511a72d62c9fcda785f3abab1be2ad616d4ee16836", "exam_bench/preflight.py": "5619be0131d8641925f3ce2a3c8e5234d42aa5635d95676138ca81536d95cd29", "exam_bench/process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "exam_bench/queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "exam_bench/queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "exam_bench/replay_calibration.py": "e2d79cb508f2d5e3846d6dad36c3898d41dec1c573c1a1b7d8a2ec43e33c8c08", "exam_bench/report.py": "5e4c0757e1c7f189953f9a5302593ab726551835856baed25efd93dad6e8bfcd", "exam_bench/runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "exam_bench/smoke_check.py": "f36922a0027429ead0b414048dcc14bbe67f2f0e79a70d03dffbe1447d253545", "exam_bench/stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "exam_bench/submission.py": "3c5f703fcd90a1747884624e98b5caa1804dd422153106b96dcbb2810ee00544", "exam_bench/telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "exam_bench/windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "exam_bench/workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tools/build_public_site.py": "9682ed696f5ac9e9a82b65a45c0dece556ec7e49eeb20dcd616882cc534a8258", "tools/build_result_site.py": "3294e1d2ec1486058e208735264d61e349a68a4ae2fa2ec7a723c70e3263b496", "tools/check_native_harnesses.py": "4f5f0ed27651f78758eaef077b3b114361781f6b95ec40cb46c3fea689210473", "tools/check_native_toolkit.py": "0272794617121f2932828e5e4e9ae20095183c443666cf3ba466b44fbe875095", "tools/community_results.py": "9db56a44697d94f326efcbd7a3ae1aecdb569d43bba6c47e80ce525dc045f1f7", "tools/community_service.py": "c374480dbd88d656c0b9054fa04a8e1c6698c69e2f9cf475e82498a2dff61d84", "tools/community_setup.py": "5d7d126ed7d4dd48e1d79f57b99647a92ffcc8c9f80d90915e458888cdd76bf7", "tools/compare_harness_runs.py": "f274df5f3f804cb02504491aec946943833e12fbce6e62d281e12beb8508fc4e", "tools/create_run_plan.py": "871cd81b1eda231c0fba8805f63d2668926be9fc641559e6ddf320e2f47cd37a", "tools/demo_runner.py": "bf5cf11165b7a37bdbbf4bb7b24505bbbd74cd39cab24c4af70f111fc27ef466", "tools/installers.py": "9a2742780936b17500869e7c89202c1a2549e37d53a42ad9a50a0abbf78bbe09", "tools/machine_bundle.py": "8aa8346f99f537e81ceca6fb6ab9530e844954bab8eff87bf33d3602f81f8a30", "tools/prepare_native_harnesses.py": "7718ed341fcc7cc9e17f7bb9dd6a9f6fbfd6435411433f5acc9b12f63a8c699c", "tools/prepare_official_statement.py": "6b7028c78e90e798d6ef1a93b76520cc61a308c354fb9b87f7fad18b99800fad", "tools/prepare_open_exam_requirements.py": "544f4e378b9be5f166186f8788f8d454afdac2deb99d91d98421e39d01ba6d03", "tools/probe_harness.py": "1ed8ef93420d1484cbbfd151b7efc31b9a201ceb942dd05e3103efa22ffa7f27", "tools/probe_native_mcp.py": "9918d324129cba898993e07f8f8b6dbcbaf369398ebf28d464f9f1f00abdb254", "tools/readiness.py": "0b71ab667e6b2d9979fb3e5a769ebb8a453edec80a71090fb0b21b45af7986ce", "tools/recheck_community.py": "f0843d7d677f90da31e22bde0b1c86584dd46c022f1532d43d042619e426b230", "tools/regrade_runs.py": "011775afb06d3aac67a4aa81117a368c75896b0fcbe1e6f27ccc6237612fbf59", "tools/render_statement_text.py": "dabc0716a3612c288c671bc20e17fd4986691d732768e1e957d6dddddbea92a3", "tools/replay_calibration.py": "801f5004926c438c21ed3668fe2a4ddf45312b3e75320165a3839aae034eee9b", "tools/run_exam_campaign.py": "2c450d57a1cd0a2682838f5ec7c0a4ffb3aed0f1730d34c408e912d59cab6efd", "tools/serve_result_site.py": "86badfac863cd4ad1fc894a14110c75b28470513f0133eeae9d2799b8b4df3a9", "tools/start_demo.py": "c597e6cad28d245b3191654bb3e2801fa9dd2364e2acb25561923613717b615f", "tools/supplemental_acceptance.py": "c88fc39de1be1fdcacdd819e2ad329f60367b2df1d5deda80b37324bda3f2a01", "tools/sync_sources.py": "b51e889b0f41f9f63bfb19a09fb96d3777693d6b1d76fe0132bdd2a15e155898", "tools/validate_community_pr.py": "796b896dfade07b4529af2088a4b9b9d23484148b3bc0732b3fb837b75c9844b", "tools/verify_official_assessment_mapping.py": "daeb448a016940d5b6b1285979a56e5b9014bd91db40acb131445e4a83a23059", "tools/verify_task_package.py": "9e1e6105f6b5e4e78b36aa57f00117a9fbc8948ab53983c32ab56da88d23ccc4", "profiles/agents.json": "af9c492c08d13b3044aa6b6952589ed6a0a07d5258d8ff72bb18185b3eaebdc5", "profiles/ai-exam-execution-policy.json": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "profiles/bsl-analyzer-0.3.2-macos.json": "83537abdbf38c41ce665e4d0f24128bb51b62e971e0e0f368695f1326a7d2ffb", "profiles/bsl-analyzer-0.3.2-portable.json": "d6ba732e6778e256df34d6bc548593128820a70430c35b279796843606ee40a8", "profiles/bsl-ls-1.1.0-rc.6-macos.json": "245fc10747197e6911b2b4c77cdb15e6fa4eb7bc7c3758b63e768c5adf1df180", "profiles/bsl-ls-1.1.0-rc.6-portable.json": "9f10660881f2ec84794f7d584556b8f75c7e14b3555464af0ed0e60c4c892d86", "profiles/code-index-1.9.0-macos.json": "63a919523ce62ecec274f4c139bc7ad49a75dd4c339568b822cbc695b4e30408", "profiles/code-index-1.9.0-portable.json": "81106cee8f424ffd8a9dc46ecd8e4f57598fc1d49661a83c77b1f0507993fbdc", "profiles/codex-probe-plan.json": "166e41aad5fb3b27d9050bc6de952c6cba363cc6e804d4080568cc71a2a4d289", "profiles/machine.linux.example.json": "408304fd0581098d5d8110dc67dfeab353bc4d4030e32d37e6acf98d2b1aedfd", "profiles/machine.macos.example.json": "52e9f9d17797cb520b9d8955d6806fd550b899bed4da241ebf096dcb6a21a942", "profiles/machine.windows.example.json": "63accac9a2f81d47d03447efbabffd4760aee325193f02f46b9b29a28d50d2d8", "profiles/mcp-toolkit-1.9.0-macos.json": "1d3f9cde5ffa20589a840d01fdae03aa0fc2f412c929f064f203919c4129625b", "profiles/mcp-toolkit-1.9.0-portable.json": "8e370eebe773eef0e08045ee9c6d5be1451f769f65be0710834b262a4336e054", "profiles/none-macos.json": "b1401d9c48159aed3559006c7f6ace6ef4571224d5cf0bb76d1a823505a10056", "profiles/none-portable.json": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "profiles/rlm-tools-bsl-1.43.0-macos.json": "9354421052640ab60bc3e6aa98ff2e7ba9ca2318b0f4026c137487449242cbd2", "profiles/rlm-tools-bsl-1.43.0-portable.json": "2599e5645e0a7d4e44cb2934bc2b272cae79a9bf7ea74a23cd48aacea64bc424", "profiles/rlm-tools-bsl-1.43.0-posix-requirements.txt": "4fdf9a1bd994bf0272e65d231daf76cf19b0a34dad0ae6b50ec4f11a2ce4c330", "profiles/rlm-tools-bsl-1.43.0-windows-requirements.txt": "3730cb46c81cda5181ecd4485e98b11933104632358bc86f8c0eb1a612a8954f", "profiles/shirokov-skills-macos.json": "84f3e89091676884a802035c707e912762a1179425fb8e3faff25be736873cdb", "profiles/shirokov-skills-portable.json": "2b0a461e06602f1456410e70f02ceaa5ac32c6549c486660bcb5ace0c2f87b15", "profiles/shirokov-skills-windows-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/unica-0.12.3-macos.json": "2c39fbb591cf2c2c6e056373823615485397ea83651b7926c6f25a5fe6a0aae6", "profiles/unica-0.13.0-macos.json": "b76b5c8a4dd33f571c4a90993f1a2da5f7223b4f0f8e1042c282e21a66121052", "profiles/unica-0.14.0-rc.1-portable.json": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "rules/1c-specialist-platform/chistov.json": "77e04942f8c947b10759e7cc1eb31af05847d1711a772fbe6f23d525766757a9", "rules/1c-specialist-platform/decisions.json": "f622107423ce3c188c063318d7ab4f7718ceb38e443130677d8987f386641c09", "rules/1c-specialist-platform/examiner.json": "30353aa2a1b6545496b070d9066e9ffba0c3779e5b53ef70a4fd2cee375b18c0", "rules/1c-specialist-platform/ledger.json": "f167c10db2b5799dd9a1ea6a37cd2d7d186810dadf5ea2f50f26ae723c676882", "rules/1c-specialist-platform/rules.json": "1d320a4f8e1bf4701496388931f492315549bd3dce574b17285dd1d7f8652007", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" } } }, "conditions": { "client": "claude", "model": "claude-opus-5-5", "client_version": "2.1.310", "reasoning_effort": "medium", "harness": "unica-0.14.0-rc.1", "billing_channel": "subscription", "solve_timeout_seconds": 7200, "time_series": null, "delegation": "native_disabled", "network_profile": "open-book_shell", "deadline_disclosed": true, "statement_sha256": "8a6ccb3e673826d1f8220fda53eb310e3ec18c136d87ce8f4cebb2a08614e7e5", "starter_dt_sha256": "f40d084818b0d1cfe503fc7653a6a13f1a8e47fcd1688dad6245b12744eb4638", "profile_sha256": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "execution_policy_sha256": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "calibration_sha256": "4225306bf705e7d6754aacd8cc6f77f6e688e9d0c0e7ed742260ba25d7f8795c", "started_at": "2026-10-24T23:04:54.979409+00:00", "timing": { "prepare_ms": 23945, "solve_ms": 3281172, "grade_ms": null }, "original_submission_valid": true, "model_provenance": "client_reported", "tokens": { "input": 30119936, "cached_input": 29752812, "fresh_input": 367124, "output": 227116, "reasoning_output": null, "total": 30347052, "coverage": "final_result_model_usage" }, "tools": { "mcp_calls": 4, "unica_calls": 4, "failed_calls": 0 }, "process": { "status": "completed", "exit_code": 0, "stop_confirmed": true } }, "verification": "repository_owner", "download": "community-downloads/demo-20261024T230428Z-a2980e--owner-2026-10-26T223243956826-0000/solution.zip", "source_context": "community-downloads/demo-20261024T230428Z-a2980e--owner-2026-10-26T223243956826-0000/source-context.json", "regrade_required": [], "grader_revision_sha256": "9aee1ffe0e1d04f9158fbbbeed3a403a5f0550ad8a590d7a6394977590760e1a", "archive_sha256": "ff94bc604595152a6e7e68afde44df3ccc173df090acfd1c770c3c901cebabe6", "owner_verification": { "kind": "repository_owner", "repository": "zeegin/1c-agent-exam-benchmark", "operator": { "name": "Ingvar Vilkman", "github": "zeegin" }, "started_at": "2026-10-26T22:32:43.792054+00:00", "server": { "name": "Owner Windows stand", "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "hardware": { "cpu": "AMD Ryzen 7 5800X 8-Core Processor ", "logical_cpus": 4, "ram_bytes": 17109000192 }, "isolation": "dedicated-host" }, "platform_version": "8.3.27.2342", "grader": { "profile": "technical-v8", "commit": "e15c8ea80263c0b38baa3a1fc19611983270e8a7", "working_tree_dirty": false, "fingerprint": { "assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "calibrate.py": "aac127e03744907fd52ef149b88aa6d88a54a2b7497d56084484ee1b99e0da99", "calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "calibration_periodicity.py": "0b1953d7781e236467897cd2ed66705b75d9719353a2de60b36f2bbdfe799108", "calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "calibration_query.py": "3555b103cde8ea0519955cf52358d09223f5ab183a9df00533bdb48c89237a8c", "claude.py": "5bae98af6e2021e2718afa3a71ed04bee812deaae31a43d4e7324814139ccc82", "codescan.py": "6d8375210cef1fd768fc2d98d630d880b2993a9724f01ae25f33b4ea5aa9631d", "codex.py": "904e75503cd35f16cbb052f66806b3879fe25bfc9f99e33b93c889d862c46324", "common.py": "739b39e2bb9bdd4a571fc69df5843190cddcad094ef7e68964061bc1266b20dc", "docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "examiner.py": "8cdffcdd52f043c905f896697403380af95bf485dd4a5edca24f7956e7795ffe", "forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "harness.py": "3cbb90fd3187e700b5df32e5daafb20313d49bb5721c826e3033cbc6aa6e3825", "interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "ou.py": "f62784b54a3f85576a078a2ff1908c9395f3159e55f6bb5b1a3c564392241abe", "penalties.py": "ae388cb8953ecca1f2370a7c4cb1db3b6cc8318fc2a7563a4db15f9f5b057429", "platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "pr.py": "2b6bfea0634703469605ce114f9274716b485852d9a55d9185c39893b14e4726", "preflight.py": "448c3120ab64b625abae3891be686c7a214ce4211f7cf651fd90e12c0b298433", "process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "queries.py": "1ef57e292db3e8967a733948371ecc542f743b811890d4fc509df17303b9c4ac", "queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "querytypes.py": "b645f489a2abc27762b4a9bbf4917e72f7b46dc053a74c0dca4a8fc46491b3ef", "replay_calibration.py": "e0e3d5ca6416934715b9735aa516046b8d19ad4ae690220eeacd96b198a5f86c", "runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "smoke_check.py": "7837e980986bcb54dc8bc1dfb5d0003deef11e05f6e11df3910fa509e1f74c8d", "stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "submission.py": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tasks/1c-platform-official-sample/checks.json": "7447a9b42d3e348d29d07f001cfb6bd269acd953b7117eba7cca2ce9f5a9a60d", "tasks/1c-platform-official-sample/private/official-assessment-mapping.json": "303587c0dabe77c1eeebb2017fe85539e3370b17c9090435e6e0325a66bd0644", "tasks/1c-platform-official-sample/private/owner-scoring-policy.json": "d26d534bb838ab1b5facb7bc033ca8ec40912133baadcdbad83b27fc577905f5", "starters/carcass-8.3.25.1445/starter.json": "0f7a7060885ba99a19402bfc6e63cc8fe979b0f491b040d3a01d5d21b304b3a6", "rules/1c-specialist-platform/rules.json": "ea75e34ace5de11ba3de403c63cd2c026db81d1d991f8531e4a779d4ce9788e7", "rules/1c-specialist-platform/examiner.json": "1247486ddd412d600db88d9c1db4ba501fc1994afd1dc2ebe85402fcc332f4c8", "rules/1c-specialist-platform/chistov.json": "800da27601a3f1c7ec1df64482fd4ad035e559ba0b390a274ed5031128487d3d", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" }, "sha256": "9aee1ffe0e1d04f9158fbbbeed3a403a5f0550ad8a590d7a6394977590760e1a" }, "method": "saved_platform_observations", "outcome": "complete", "completed_at": "2026-10-26T22:32:43.956826+00:00" }, "previous_evaluations": [ { "id": "demo-20261024T230428Z-a2980e--owner-2026-10-26T214319526992-0000", "run_id": "demo-20261024T230428Z-a2980e", "result": { "run_id": "demo-20261024T230428Z-a2980e", "created_at": "2026-10-26T21:43:19.526992+00:00", "model": "claude-opus-5-5", "harness": "unica-0.14.0-rc.1", "solve_seconds": 3281, "platform": "8.3.27.1688", "counts": { "pass": 62, "fail": 3 }, "rules": [ { "id": "BU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU01.selected_fixture" }, { "id": "BU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU04.selected_fixture" }, { "id": "BU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU05.selected_fixture" }, { "id": "BU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU16.selected_fixture" }, { "id": "BU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU17.selected_fixture" }, { "id": "BU02", "verdict": "pass", "reason": null, "coverage": "partial", "assertion_id": "BU02.posting_cost_and_balance" }, { "id": "BU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU10.selected_fixture" }, { "id": "BU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU12.selected_fixture" }, { "id": "BU03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU03.selected_fixture" }, { "id": "BU06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU06.selected_fixture" }, { "id": "BU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU07.selected_fixture" }, { "id": "BU08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU08.selected_fixture" }, { "id": "BU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU09.selected_fixture" }, { "id": "BU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU11.selected_fixture" }, { "id": "BU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU14.selected_fixture" }, { "id": "BU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU15.selected_fixture" }, { "id": "BU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU13.selected_fixture" }, { "id": "OU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU15.selected_fixture" }, { "id": "OU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU16.selected_fixture" }, { "id": "OU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU17.selected_fixture" }, { "id": "OU02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU02.selected_fixture" }, { "id": "OU18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU18.selected_fixture" }, { "id": "OU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU14.selected_fixture" }, { "id": "OU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU01.selected_fixture" }, { "id": "OU03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU03.selected_fixture" }, { "id": "OU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU05.selected_fixture" }, { "id": "OU06", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "OU06.selected_fixture" }, { "id": "OU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU07.selected_fixture" }, { "id": "OU08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU08.selected_fixture" }, { "id": "OU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU09.selected_fixture" }, { "id": "OU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU10.selected_fixture" }, { "id": "OU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU11.selected_fixture" }, { "id": "OU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU12.selected_fixture" }, { "id": "OU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU13.selected_fixture" }, { "id": "OU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU04.selected_fixture" }, { "id": "OU19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU19.selected_fixture" }, { "id": "OU20", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU20.selected_fixture" }, { "id": "OU21", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU21.selected_fixture" }, { "id": "PR01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR01.selected_fixture" }, { "id": "PR02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR02.selected_fixture" }, { "id": "PR03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR03.selected_fixture" }, { "id": "PR04", "verdict": "fail", "reason": "pr_tariff E1/A tariff 2025-03: 76800, expected 38400.00", "coverage": "selected_fixture", "assertion_id": "PR04.selected_fixture" }, { "id": "PR05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR05.selected_fixture" }, { "id": "PR06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR06.selected_fixture" }, { "id": "PR07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR07.selected_fixture" }, { "id": "PR08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR08.selected_fixture" }, { "id": "PR09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR09.selected_fixture" }, { "id": "PR10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR10.selected_fixture" }, { "id": "PR11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR11.selected_fixture" }, { "id": "PR12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR12.selected_fixture" }, { "id": "PR13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR13.selected_fixture" }, { "id": "PR14", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "PR14.selected_fixture" }, { "id": "PR15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR15.selected_fixture" }, { "id": "PR16", "verdict": "fail", "reason": "a tariff row 10.03-03.04 was accepted; pr_tariff E1/A tariff 2025-03: 76800, expected 38400.00", "coverage": "selected_fixture", "assertion_id": "PR16.selected_fixture" }, { "id": "PR17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR17.selected_fixture" }, { "id": "PR18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR18.selected_fixture" }, { "id": "PR19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR19.selected_fixture" }, { "id": "F01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F01.selected_fixture" }, { "id": "F02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F02.selected_fixture" }, { "id": "F03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F03.selected_fixture" }, { "id": "F04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F04.selected_fixture" }, { "id": "F05", "verdict": "fail", "reason": "typed ['C1', 'C2'], written True, stored [('BENCH_Валюта', ''), ('BENCH_Срок', '')]", "coverage": "selected_fixture", "assertion_id": "F05.selected_fixture" }, { "id": "G01", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G01.static_sources" }, { "id": "G02", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G02.static_sources" }, { "id": "G03", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G03.static_sources" } ], "charges": [ { "id": "F1C-GEN01", "points": "0.5", "reason": "не выполнено требование: PR04 — pr_tariff E1/A tariff 2025-03: 76800, expected 38400.00" }, { "id": "F1C-GEN01", "points": "0.5", "reason": "не выполнено требование: PR16 — a tariff row 10.03-03.04 was accepted; pr_tariff E1/A tariff 2025-03: 76800, expected 38400.00" }, { "id": "F1C-GEN01", "points": "0.5", "reason": "не выполнено требование: F05 — typed ['C1', 'C2'], written True, stored [('BENCH_Валюта', ''), ('BENCH_Срок', '')]" }, { "id": "F1C-GEN12", "points": "0.25", "reason": "текст запроса не разбирается платформой: DataProcessors/ЗаполнениеГрафика/Ext/ObjectModule.bsl:20 — Поле не найдено \"Подразделения.ЭтоГруппа\"" }, { "id": "F1C-GEN15", "points": "0.5", "reason": "CommonModules/РасчетЗарплаты/Ext/Module.bsl:237 — РегистрРасчета.ОсновныеНачисления: отбор по ВидРасчета, ПериодДействияКонец, ПериодДействияНачало, Подразделение, Сотрудник, индексы таблицы начинаются с ПериодДействия, ПериодРегистрации, Регистратор" }, { "id": "F1C-GEN15", "points": "0.5", "reason": "Reports/ВедомостьПоПодразделению/Ext/ManagerModule.bsl:17 — РегистрНакопления.ОстаткиНоменклатуры.ОстаткиИОбороты: отбор по Подразделение, Свойство, индексы таблицы начинаются с Номенклатура" }, { "id": "F1C-GEN23", "points": "1.0", "reason": "основная таблица регистра расчёта соединяется с его же «Данными графика»: CommonModules/РасчетЗарплаты/Ext/Module.bsl:194 ОсновныеНачисления" }, { "id": "F1C-GEN25", "points": "1.0", "reason": "результат запроса выгружается в таблицу значений Пары только для одного перебора: CommonModules/БухгалтерскийУчетСервер/Ext/Module.bsl:24" }, { "id": "F1C-GEN25", "points": "1.0", "reason": "результат запроса выгружается в таблицу значений Остатки только для одного перебора: Documents/РасходнаяНакладная/Ext/ObjectModule.bsl:137" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "проводимые документы в режиме «Записывать модифицированные»: НачислениеЗарплаты, Операция, ПриходнаяНакладная, РасходнаяНакладная, Сборка" }, { "id": "F1C-PR14", "points": "0.5", "reason": "после расчёта набор с периодом действия перезаписывается целиком, с пересчётом фактического периода действия (нужно Записать(, Истина)): CommonModules/РасчетЗарплаты/Ext/Module.bsl:14 Набор.Записать(); CommonModules/РасчетЗарплаты/Ext/Module.bsl:16 Набор.Записать(); CommonModules/РасчетЗарплаты/Ext/Module.bsl:18 Набор.Записать(); CommonModules/РасчетЗарплаты/Ext/Module.bsl:269 Набор.Записать(); CommonModules/РасчетЗарплаты/Ext/Module.bsl:271 Набор.Записать()" }, { "id": "F1C-BU07", "points": "1.0", "reason": "признаки учёта субконто не заведены: сумма ведётся по всем субконто, в том числе по складам, а себестоимость — средняя по номенклатуре всей компании (Т3.13)" }, { "id": "F1C-GEN20", "points": "2.0", "reason": "данные базы читаются в цикле по записям: CommonModules/ОперативныйУчетСервер/Ext/Module.bsl:100; CommonModules/ОперативныйУчетСервер/Ext/Module.bsl:102; CommonModules/ОперативныйУчетСервер/Ext/Module.bsl:102" } ], "score_upper_bound": "-5.25", "score": null, "grade": "unsatisfactory", "deductions": "10.25", "not_assessed": 14, "gates": { "starter_origin": "passed", "load": "loaded", "clients": "compiles", "demo_data": "present" }, "infrastructure_errors": false, "comparison_eligible": false, "binding_compatibility": null }, "measurement": { "operator": { "name": "Vasiliy", "github": "Gh0sTspp" }, "environment": { "captured_at": "2026-10-24T23:04:30.225789+00:00", "capture_timing": "before_run", "hardware": { "cpu": "Intel(R) Core(TM) i7-5820K CPU @ 3.30GHz", "logical_cpus": 12, "ram_bytes": 34189709312 }, "os": { "system": "Windows", "release": "10", "version": "10.0.19045", "architecture": "AMD64" }, "python": "3.13.12", "platform_version": "8.3.27.1688", "isolation": "dedicated-host", "network_profile": "open-book_shell", "unsafe_action_protection_observed_in_user_config": true, "git_revision": "be55d44b20d37140792f68a45a1eda6a29c677f7", "implementation_files": { "exam_bench/__init__.py": "ad5bf6f05dc6765f40b78bd186870ca2c49be113cfa33f8aa76f4926f2cb2c1e", "exam_bench/assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "exam_bench/bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "exam_bench/calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "exam_bench/calibrate.py": "78b5185cb0888c0c0ac3de95ffc3a80154a6de9ae66fc461f79d012e5a58e1db", "exam_bench/calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "exam_bench/calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "exam_bench/calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "exam_bench/calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "exam_bench/calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "exam_bench/claude.py": "e66c95345f969feb97738b568a8973d2c04b7f9dabf3424a2bb32ad52896c4e5", "exam_bench/cli.py": "1a37ce645633d761f7897dffc9c45e6b8b9600cd7bd233b1cbf78f49d26b099a", "exam_bench/codescan.py": "751e38001b6e65727a31e28172a0623f0bf34bc092a958037c286aa991a197ed", "exam_bench/codex.py": "c3f89d72af11f312d851c73a1610d92e79acadf336be9ccedd1f94ede3b3ccb0", "exam_bench/common.py": "8682603b519063e655eae3574a02a49efee63bde21f582ccee20ddd623fca96d", "exam_bench/docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "exam_bench/examiner.py": "d7294fdd23ed1732216cafebf0a8cf2c24cce4259859aeb7149f62b7607d087d", "exam_bench/finalize.py": "4034f1c63896a940afdb1a83d541cf47fc75c8b5061e3f839047109c04beb620", "exam_bench/forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "exam_bench/gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "exam_bench/grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "exam_bench/harness.py": "3040f6daaf1dc6e6583219f4d925151f8ba7851b2d5417d7f14645892b485ddf", "exam_bench/interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "exam_bench/interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "exam_bench/isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "exam_bench/ledger.py": "7e851523580e22d8490e75f9b6026c07f2c355007e0d11d0b252671f56bef654", "exam_bench/locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "exam_bench/materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "exam_bench/mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "exam_bench/observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "exam_bench/ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "exam_bench/penalties.py": "0d79e2e46102657dca00609b6abbfc0bf7d11fad41429564f876c82bc6b33269", "exam_bench/platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "exam_bench/portable.py": "cad56968ff407983608f5bdbc9ce7234128d7a4580b096ecea8e0e7b4edb9070", "exam_bench/portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "exam_bench/pr.py": "6a3a20caf0e10c0cc94410511a72d62c9fcda785f3abab1be2ad616d4ee16836", "exam_bench/preflight.py": "5619be0131d8641925f3ce2a3c8e5234d42aa5635d95676138ca81536d95cd29", "exam_bench/process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "exam_bench/queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "exam_bench/queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "exam_bench/replay_calibration.py": "e2d79cb508f2d5e3846d6dad36c3898d41dec1c573c1a1b7d8a2ec43e33c8c08", "exam_bench/report.py": "5e4c0757e1c7f189953f9a5302593ab726551835856baed25efd93dad6e8bfcd", "exam_bench/runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "exam_bench/smoke_check.py": "f36922a0027429ead0b414048dcc14bbe67f2f0e79a70d03dffbe1447d253545", "exam_bench/stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "exam_bench/submission.py": "3c5f703fcd90a1747884624e98b5caa1804dd422153106b96dcbb2810ee00544", "exam_bench/telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "exam_bench/windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "exam_bench/workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tools/build_public_site.py": "9682ed696f5ac9e9a82b65a45c0dece556ec7e49eeb20dcd616882cc534a8258", "tools/build_result_site.py": "3294e1d2ec1486058e208735264d61e349a68a4ae2fa2ec7a723c70e3263b496", "tools/check_native_harnesses.py": "4f5f0ed27651f78758eaef077b3b114361781f6b95ec40cb46c3fea689210473", "tools/check_native_toolkit.py": "0272794617121f2932828e5e4e9ae20095183c443666cf3ba466b44fbe875095", "tools/community_results.py": "9db56a44697d94f326efcbd7a3ae1aecdb569d43bba6c47e80ce525dc045f1f7", "tools/community_service.py": "c374480dbd88d656c0b9054fa04a8e1c6698c69e2f9cf475e82498a2dff61d84", "tools/community_setup.py": "5d7d126ed7d4dd48e1d79f57b99647a92ffcc8c9f80d90915e458888cdd76bf7", "tools/compare_harness_runs.py": "f274df5f3f804cb02504491aec946943833e12fbce6e62d281e12beb8508fc4e", "tools/create_run_plan.py": "871cd81b1eda231c0fba8805f63d2668926be9fc641559e6ddf320e2f47cd37a", "tools/demo_runner.py": "bf5cf11165b7a37bdbbf4bb7b24505bbbd74cd39cab24c4af70f111fc27ef466", "tools/installers.py": "9a2742780936b17500869e7c89202c1a2549e37d53a42ad9a50a0abbf78bbe09", "tools/machine_bundle.py": "8aa8346f99f537e81ceca6fb6ab9530e844954bab8eff87bf33d3602f81f8a30", "tools/prepare_native_harnesses.py": "7718ed341fcc7cc9e17f7bb9dd6a9f6fbfd6435411433f5acc9b12f63a8c699c", "tools/prepare_official_statement.py": "6b7028c78e90e798d6ef1a93b76520cc61a308c354fb9b87f7fad18b99800fad", "tools/prepare_open_exam_requirements.py": "544f4e378b9be5f166186f8788f8d454afdac2deb99d91d98421e39d01ba6d03", "tools/probe_harness.py": "1ed8ef93420d1484cbbfd151b7efc31b9a201ceb942dd05e3103efa22ffa7f27", "tools/probe_native_mcp.py": "9918d324129cba898993e07f8f8b6dbcbaf369398ebf28d464f9f1f00abdb254", "tools/readiness.py": "0b71ab667e6b2d9979fb3e5a769ebb8a453edec80a71090fb0b21b45af7986ce", "tools/recheck_community.py": "f0843d7d677f90da31e22bde0b1c86584dd46c022f1532d43d042619e426b230", "tools/regrade_runs.py": "011775afb06d3aac67a4aa81117a368c75896b0fcbe1e6f27ccc6237612fbf59", "tools/render_statement_text.py": "dabc0716a3612c288c671bc20e17fd4986691d732768e1e957d6dddddbea92a3", "tools/replay_calibration.py": "801f5004926c438c21ed3668fe2a4ddf45312b3e75320165a3839aae034eee9b", "tools/run_exam_campaign.py": "2c450d57a1cd0a2682838f5ec7c0a4ffb3aed0f1730d34c408e912d59cab6efd", "tools/serve_result_site.py": "86badfac863cd4ad1fc894a14110c75b28470513f0133eeae9d2799b8b4df3a9", "tools/start_demo.py": "c597e6cad28d245b3191654bb3e2801fa9dd2364e2acb25561923613717b615f", "tools/supplemental_acceptance.py": "c88fc39de1be1fdcacdd819e2ad329f60367b2df1d5deda80b37324bda3f2a01", "tools/sync_sources.py": "b51e889b0f41f9f63bfb19a09fb96d3777693d6b1d76fe0132bdd2a15e155898", "tools/validate_community_pr.py": "796b896dfade07b4529af2088a4b9b9d23484148b3bc0732b3fb837b75c9844b", "tools/verify_official_assessment_mapping.py": "daeb448a016940d5b6b1285979a56e5b9014bd91db40acb131445e4a83a23059", "tools/verify_task_package.py": "9e1e6105f6b5e4e78b36aa57f00117a9fbc8948ab53983c32ab56da88d23ccc4", "profiles/agents.json": "af9c492c08d13b3044aa6b6952589ed6a0a07d5258d8ff72bb18185b3eaebdc5", "profiles/ai-exam-execution-policy.json": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "profiles/bsl-analyzer-0.3.2-macos.json": "83537abdbf38c41ce665e4d0f24128bb51b62e971e0e0f368695f1326a7d2ffb", "profiles/bsl-analyzer-0.3.2-portable.json": "d6ba732e6778e256df34d6bc548593128820a70430c35b279796843606ee40a8", "profiles/bsl-ls-1.1.0-rc.6-macos.json": "245fc10747197e6911b2b4c77cdb15e6fa4eb7bc7c3758b63e768c5adf1df180", "profiles/bsl-ls-1.1.0-rc.6-portable.json": "9f10660881f2ec84794f7d584556b8f75c7e14b3555464af0ed0e60c4c892d86", "profiles/code-index-1.9.0-macos.json": "63a919523ce62ecec274f4c139bc7ad49a75dd4c339568b822cbc695b4e30408", "profiles/code-index-1.9.0-portable.json": "81106cee8f424ffd8a9dc46ecd8e4f57598fc1d49661a83c77b1f0507993fbdc", "profiles/codex-probe-plan.json": "166e41aad5fb3b27d9050bc6de952c6cba363cc6e804d4080568cc71a2a4d289", "profiles/machine.linux.example.json": "408304fd0581098d5d8110dc67dfeab353bc4d4030e32d37e6acf98d2b1aedfd", "profiles/machine.macos.example.json": "52e9f9d17797cb520b9d8955d6806fd550b899bed4da241ebf096dcb6a21a942", "profiles/machine.windows.example.json": "63accac9a2f81d47d03447efbabffd4760aee325193f02f46b9b29a28d50d2d8", "profiles/mcp-toolkit-1.9.0-macos.json": "1d3f9cde5ffa20589a840d01fdae03aa0fc2f412c929f064f203919c4129625b", "profiles/mcp-toolkit-1.9.0-portable.json": "8e370eebe773eef0e08045ee9c6d5be1451f769f65be0710834b262a4336e054", "profiles/none-macos.json": "b1401d9c48159aed3559006c7f6ace6ef4571224d5cf0bb76d1a823505a10056", "profiles/none-portable.json": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "profiles/rlm-tools-bsl-1.43.0-macos.json": "9354421052640ab60bc3e6aa98ff2e7ba9ca2318b0f4026c137487449242cbd2", "profiles/rlm-tools-bsl-1.43.0-portable.json": "2599e5645e0a7d4e44cb2934bc2b272cae79a9bf7ea74a23cd48aacea64bc424", "profiles/rlm-tools-bsl-1.43.0-posix-requirements.txt": "4fdf9a1bd994bf0272e65d231daf76cf19b0a34dad0ae6b50ec4f11a2ce4c330", "profiles/rlm-tools-bsl-1.43.0-windows-requirements.txt": "3730cb46c81cda5181ecd4485e98b11933104632358bc86f8c0eb1a612a8954f", "profiles/shirokov-skills-macos.json": "84f3e89091676884a802035c707e912762a1179425fb8e3faff25be736873cdb", "profiles/shirokov-skills-portable.json": "2b0a461e06602f1456410e70f02ceaa5ac32c6549c486660bcb5ace0c2f87b15", "profiles/shirokov-skills-windows-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/unica-0.12.3-macos.json": "2c39fbb591cf2c2c6e056373823615485397ea83651b7926c6f25a5fe6a0aae6", "profiles/unica-0.13.0-macos.json": "b76b5c8a4dd33f571c4a90993f1a2da5f7223b4f0f8e1042c282e21a66121052", "profiles/unica-0.14.0-rc.1-portable.json": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "rules/1c-specialist-platform/chistov.json": "77e04942f8c947b10759e7cc1eb31af05847d1711a772fbe6f23d525766757a9", "rules/1c-specialist-platform/decisions.json": "f622107423ce3c188c063318d7ab4f7718ceb38e443130677d8987f386641c09", "rules/1c-specialist-platform/examiner.json": "30353aa2a1b6545496b070d9066e9ffba0c3779e5b53ef70a4fd2cee375b18c0", "rules/1c-specialist-platform/ledger.json": "f167c10db2b5799dd9a1ea6a37cd2d7d186810dadf5ea2f50f26ae723c676882", "rules/1c-specialist-platform/rules.json": "1d320a4f8e1bf4701496388931f492315549bd3dce574b17285dd1d7f8652007", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" } } }, "conditions": { "client": "claude", "model": "claude-opus-5-5", "client_version": "2.1.310", "reasoning_effort": "medium", "harness": "unica-0.14.0-rc.1", "billing_channel": "subscription", "solve_timeout_seconds": 7200, "time_series": null, "delegation": "native_disabled", "network_profile": "open-book_shell", "deadline_disclosed": true, "statement_sha256": "8a6ccb3e673826d1f8220fda53eb310e3ec18c136d87ce8f4cebb2a08614e7e5", "starter_dt_sha256": "f40d084818b0d1cfe503fc7653a6a13f1a8e47fcd1688dad6245b12744eb4638", "profile_sha256": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "execution_policy_sha256": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "calibration_sha256": "4225306bf705e7d6754aacd8cc6f77f6e688e9d0c0e7ed742260ba25d7f8795c", "started_at": "2026-10-24T23:04:54.979409+00:00", "timing": { "prepare_ms": 23945, "solve_ms": 3281172, "grade_ms": null }, "original_submission_valid": true, "model_provenance": "client_reported", "tokens": { "input": 30119936, "cached_input": 29752812, "fresh_input": 367124, "output": 227116, "reasoning_output": null, "total": 30347052, "coverage": "final_result_model_usage" }, "tools": { "mcp_calls": 4, "unica_calls": 4, "failed_calls": 0 }, "process": { "status": "completed", "exit_code": 0, "stop_confirmed": true } }, "verification": "repository_owner", "download": "community-downloads/demo-20261024T230428Z-a2980e--owner-2026-10-26T214319526992-0000/solution.zip", "source_context": "community-downloads/demo-20261024T230428Z-a2980e--owner-2026-10-26T214319526992-0000/source-context.json", "regrade_required": [ { "id": "grader_changed", "files": [ "calibrate.py", "calibration_periodicity.py", "common.py", "ou.py", "replay_calibration.py", "smoke_check.py", "tasks/1c-platform-official-sample/checks.json" ] } ], "grader_revision_sha256": "349d87e0c7f531acbe35dd2b39c35722d8a877fedde97575b49e8466ab763c1d", "archive_sha256": "7bdb5480e9ef073a02fc6d1087b3d7200d36dee4fdc5c9827cb3201bc3907b02", "owner_verification": { "kind": "repository_owner", "repository": "zeegin/1c-agent-exam-benchmark", "operator": { "name": "Ingvar Vilkman", "github": "zeegin" }, "started_at": "2026-10-26T21:43:19.365614+00:00", "server": { "name": "Owner Windows stand", "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "hardware": { "cpu": "AMD Ryzen 7 5800X 8-Core Processor ", "logical_cpus": 4, "ram_bytes": 17109000192 }, "isolation": "dedicated-host" }, "platform_version": "8.3.27.2342", "grader": { "profile": "technical-v8", "commit": "e8fd8ced03a85b549c5472fbbda29225749f54d1", "working_tree_dirty": false, "fingerprint": { "assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "calibrate.py": "3162d431f3cab5e7976aa39f665d6286dce45499cf362d85109b7123fa8403a2", "calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "calibration_query.py": "3555b103cde8ea0519955cf52358d09223f5ab183a9df00533bdb48c89237a8c", "claude.py": "eedabc75fca0faa434f40a1624b71419ec7dc22e2854a0886cf84b4911db8372", "codescan.py": "6d8375210cef1fd768fc2d98d630d880b2993a9724f01ae25f33b4ea5aa9631d", "codex.py": "904e75503cd35f16cbb052f66806b3879fe25bfc9f99e33b93c889d862c46324", "common.py": "52825cf5c29f3536d6e046a89e789d5ef9c83aacd7f2f5a07f4f53e77b5229cc", "docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "examiner.py": "8cdffcdd52f043c905f896697403380af95bf485dd4a5edca24f7956e7795ffe", "forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "harness.py": "3cbb90fd3187e700b5df32e5daafb20313d49bb5721c826e3033cbc6aa6e3825", "interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "penalties.py": "ae388cb8953ecca1f2370a7c4cb1db3b6cc8318fc2a7563a4db15f9f5b057429", "platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "pr.py": "2b6bfea0634703469605ce114f9274716b485852d9a55d9185c39893b14e4726", "preflight.py": "448c3120ab64b625abae3891be686c7a214ce4211f7cf651fd90e12c0b298433", "process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "queries.py": "1ef57e292db3e8967a733948371ecc542f743b811890d4fc509df17303b9c4ac", "queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "querytypes.py": "b645f489a2abc27762b4a9bbf4917e72f7b46dc053a74c0dca4a8fc46491b3ef", "replay_calibration.py": "0a4d9b84a9908944c5a945878eb6f5eeda5a4e42ffff4f55c04a680742803d80", "runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "smoke_check.py": "66caf1a01f7aa18432293abe3567ac228ac837a660b08c3dc7bb093f7bd51628", "stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "submission.py": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tasks/1c-platform-official-sample/checks.json": "17a6fcc0c14410829650623eb1443ce99796e000cdfd19905ac0287988b73a00", "tasks/1c-platform-official-sample/private/official-assessment-mapping.json": "303587c0dabe77c1eeebb2017fe85539e3370b17c9090435e6e0325a66bd0644", "tasks/1c-platform-official-sample/private/owner-scoring-policy.json": "d26d534bb838ab1b5facb7bc033ca8ec40912133baadcdbad83b27fc577905f5", "starters/carcass-8.3.25.1445/starter.json": "0f7a7060885ba99a19402bfc6e63cc8fe979b0f491b040d3a01d5d21b304b3a6", "rules/1c-specialist-platform/rules.json": "ea75e34ace5de11ba3de403c63cd2c026db81d1d991f8531e4a779d4ce9788e7", "rules/1c-specialist-platform/examiner.json": "1247486ddd412d600db88d9c1db4ba501fc1994afd1dc2ebe85402fcc332f4c8", "rules/1c-specialist-platform/chistov.json": "800da27601a3f1c7ec1df64482fd4ad035e559ba0b390a274ed5031128487d3d", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" }, "sha256": "349d87e0c7f531acbe35dd2b39c35722d8a877fedde97575b49e8466ab763c1d" }, "method": "saved_platform_observations", "outcome": "complete", "completed_at": "2026-10-26T21:43:19.526992+00:00" } }, { "id": "demo-20261024T230428Z-a2980e--owner-2026-10-26T190154240368-0000", "run_id": "demo-20261024T230428Z-a2980e", "result": { "run_id": "demo-20261024T230428Z-a2980e", "created_at": "2026-10-26T19:01:54.240368+00:00", "model": "claude-opus-5-5", "harness": "unica-0.14.0-rc.1", "solve_seconds": 3281, "platform": "8.3.27.1688", "counts": { "pass": 62, "fail": 3 }, "rules": [ { "id": "BU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU01.selected_fixture" }, { "id": "BU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU04.selected_fixture" }, { "id": "BU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU05.selected_fixture" }, { "id": "BU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU16.selected_fixture" }, { "id": "BU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU17.selected_fixture" }, { "id": "BU02", "verdict": "pass", "reason": null, "coverage": "partial", "assertion_id": "BU02.posting_cost_and_balance" }, { "id": "BU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU10.selected_fixture" }, { "id": "BU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU12.selected_fixture" }, { "id": "BU03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU03.selected_fixture" }, { "id": "BU06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU06.selected_fixture" }, { "id": "BU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU07.selected_fixture" }, { "id": "BU08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU08.selected_fixture" }, { "id": "BU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU09.selected_fixture" }, { "id": "BU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU11.selected_fixture" }, { "id": "BU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU14.selected_fixture" }, { "id": "BU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU15.selected_fixture" }, { "id": "BU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU13.selected_fixture" }, { "id": "OU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU15.selected_fixture" }, { "id": "OU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU16.selected_fixture" }, { "id": "OU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU17.selected_fixture" }, { "id": "OU02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU02.selected_fixture" }, { "id": "OU18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU18.selected_fixture" }, { "id": "OU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU14.selected_fixture" }, { "id": "OU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU01.selected_fixture" }, { "id": "OU03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU03.selected_fixture" }, { "id": "OU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU05.selected_fixture" }, { "id": "OU06", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "OU06.selected_fixture" }, { "id": "OU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU07.selected_fixture" }, { "id": "OU08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU08.selected_fixture" }, { "id": "OU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU09.selected_fixture" }, { "id": "OU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU10.selected_fixture" }, { "id": "OU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU11.selected_fixture" }, { "id": "OU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU12.selected_fixture" }, { "id": "OU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU13.selected_fixture" }, { "id": "OU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU04.selected_fixture" }, { "id": "OU19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU19.selected_fixture" }, { "id": "OU20", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU20.selected_fixture" }, { "id": "OU21", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU21.selected_fixture" }, { "id": "PR01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR01.selected_fixture" }, { "id": "PR02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR02.selected_fixture" }, { "id": "PR03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR03.selected_fixture" }, { "id": "PR04", "verdict": "fail", "reason": "pr_tariff E1/A tariff 2025-03: 76800, expected 38400.00", "coverage": "selected_fixture", "assertion_id": "PR04.selected_fixture" }, { "id": "PR05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR05.selected_fixture" }, { "id": "PR06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR06.selected_fixture" }, { "id": "PR07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR07.selected_fixture" }, { "id": "PR08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR08.selected_fixture" }, { "id": "PR09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR09.selected_fixture" }, { "id": "PR10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR10.selected_fixture" }, { "id": "PR11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR11.selected_fixture" }, { "id": "PR12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR12.selected_fixture" }, { "id": "PR13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR13.selected_fixture" }, { "id": "PR14", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "PR14.selected_fixture" }, { "id": "PR15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR15.selected_fixture" }, { "id": "PR16", "verdict": "fail", "reason": "a tariff row 10.03-03.04 was accepted; pr_tariff E1/A tariff 2025-03: 76800, expected 38400.00", "coverage": "selected_fixture", "assertion_id": "PR16.selected_fixture" }, { "id": "PR17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR17.selected_fixture" }, { "id": "PR18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR18.selected_fixture" }, { "id": "PR19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR19.selected_fixture" }, { "id": "F01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F01.selected_fixture" }, { "id": "F02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F02.selected_fixture" }, { "id": "F03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F03.selected_fixture" }, { "id": "F04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F04.selected_fixture" }, { "id": "F05", "verdict": "fail", "reason": "typed ['C1', 'C2'], written True, stored [('BENCH_Валюта', ''), ('BENCH_Срок', '')]", "coverage": "selected_fixture", "assertion_id": "F05.selected_fixture" }, { "id": "G01", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G01.static_sources" }, { "id": "G02", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G02.static_sources" }, { "id": "G03", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G03.static_sources" } ], "charges": [ { "id": "F1C-GEN01", "points": "0.5", "reason": "не выполнено требование: PR04 — pr_tariff E1/A tariff 2025-03: 76800, expected 38400.00" }, { "id": "F1C-GEN01", "points": "0.5", "reason": "не выполнено требование: PR16 — a tariff row 10.03-03.04 was accepted; pr_tariff E1/A tariff 2025-03: 76800, expected 38400.00" }, { "id": "F1C-GEN01", "points": "0.5", "reason": "не выполнено требование: F05 — typed ['C1', 'C2'], written True, stored [('BENCH_Валюта', ''), ('BENCH_Срок', '')]" }, { "id": "F1C-GEN12", "points": "0.25", "reason": "текст запроса не разбирается платформой: DataProcessors/ЗаполнениеГрафика/Ext/ObjectModule.bsl:20 — Поле не найдено \"Подразделения.ЭтоГруппа\"" }, { "id": "F1C-GEN15", "points": "0.5", "reason": "CommonModules/РасчетЗарплаты/Ext/Module.bsl:237 — РегистрРасчета.ОсновныеНачисления: отбор по ВидРасчета, ПериодДействияКонец, ПериодДействияНачало, Подразделение, Сотрудник, индексы таблицы начинаются с ПериодДействия, ПериодРегистрации, Регистратор" }, { "id": "F1C-GEN15", "points": "0.5", "reason": "Reports/ВедомостьПоПодразделению/Ext/ManagerModule.bsl:17 — РегистрНакопления.ОстаткиНоменклатуры.ОстаткиИОбороты: отбор по Подразделение, Свойство, индексы таблицы начинаются с Номенклатура" }, { "id": "F1C-GEN23", "points": "1.0", "reason": "основная таблица регистра расчёта соединяется с его же «Данными графика»: CommonModules/РасчетЗарплаты/Ext/Module.bsl:194 ОсновныеНачисления" }, { "id": "F1C-GEN25", "points": "1.0", "reason": "результат запроса выгружается в таблицу значений Пары только для одного перебора: CommonModules/БухгалтерскийУчетСервер/Ext/Module.bsl:24" }, { "id": "F1C-GEN25", "points": "1.0", "reason": "результат запроса выгружается в таблицу значений Остатки только для одного перебора: Documents/РасходнаяНакладная/Ext/ObjectModule.bsl:137" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "проводимые документы в режиме «Записывать модифицированные»: НачислениеЗарплаты, Операция, ПриходнаяНакладная, РасходнаяНакладная, Сборка" }, { "id": "F1C-PR14", "points": "0.5", "reason": "после расчёта набор с периодом действия перезаписывается целиком, с пересчётом фактического периода действия (нужно Записать(, Истина)): CommonModules/РасчетЗарплаты/Ext/Module.bsl:14 Набор.Записать(); CommonModules/РасчетЗарплаты/Ext/Module.bsl:16 Набор.Записать(); CommonModules/РасчетЗарплаты/Ext/Module.bsl:18 Набор.Записать(); CommonModules/РасчетЗарплаты/Ext/Module.bsl:269 Набор.Записать(); CommonModules/РасчетЗарплаты/Ext/Module.bsl:271 Набор.Записать()" }, { "id": "F1C-BU07", "points": "1.0", "reason": "признаки учёта субконто не заведены: сумма ведётся по всем субконто, в том числе по складам, а себестоимость — средняя по номенклатуре всей компании (Т3.13)" }, { "id": "F1C-GEN20", "points": "2.0", "reason": "данные базы читаются в цикле по записям: CommonModules/ОперативныйУчетСервер/Ext/Module.bsl:100; CommonModules/ОперативныйУчетСервер/Ext/Module.bsl:102; CommonModules/ОперативныйУчетСервер/Ext/Module.bsl:102" } ], "score_upper_bound": "-5.25", "score": null, "grade": "unsatisfactory", "deductions": "10.25", "not_assessed": 14, "gates": { "starter_origin": "passed", "load": "loaded", "clients": "compiles", "demo_data": "present" }, "infrastructure_errors": false, "comparison_eligible": false, "binding_compatibility": null }, "measurement": { "operator": { "name": "Vasiliy", "github": "Gh0sTspp" }, "environment": { "captured_at": "2026-10-24T23:04:30.225789+00:00", "capture_timing": "before_run", "hardware": { "cpu": "Intel(R) Core(TM) i7-5820K CPU @ 3.30GHz", "logical_cpus": 12, "ram_bytes": 34189709312 }, "os": { "system": "Windows", "release": "10", "version": "10.0.19045", "architecture": "AMD64" }, "python": "3.13.12", "platform_version": "8.3.27.1688", "isolation": "dedicated-host", "network_profile": "open-book_shell", "unsafe_action_protection_observed_in_user_config": true, "git_revision": "be55d44b20d37140792f68a45a1eda6a29c677f7", "implementation_files": { "exam_bench/__init__.py": "ad5bf6f05dc6765f40b78bd186870ca2c49be113cfa33f8aa76f4926f2cb2c1e", "exam_bench/assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "exam_bench/bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "exam_bench/calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "exam_bench/calibrate.py": "78b5185cb0888c0c0ac3de95ffc3a80154a6de9ae66fc461f79d012e5a58e1db", "exam_bench/calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "exam_bench/calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "exam_bench/calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "exam_bench/calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "exam_bench/calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "exam_bench/claude.py": "e66c95345f969feb97738b568a8973d2c04b7f9dabf3424a2bb32ad52896c4e5", "exam_bench/cli.py": "1a37ce645633d761f7897dffc9c45e6b8b9600cd7bd233b1cbf78f49d26b099a", "exam_bench/codescan.py": "751e38001b6e65727a31e28172a0623f0bf34bc092a958037c286aa991a197ed", "exam_bench/codex.py": "c3f89d72af11f312d851c73a1610d92e79acadf336be9ccedd1f94ede3b3ccb0", "exam_bench/common.py": "8682603b519063e655eae3574a02a49efee63bde21f582ccee20ddd623fca96d", "exam_bench/docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "exam_bench/examiner.py": "d7294fdd23ed1732216cafebf0a8cf2c24cce4259859aeb7149f62b7607d087d", "exam_bench/finalize.py": "4034f1c63896a940afdb1a83d541cf47fc75c8b5061e3f839047109c04beb620", "exam_bench/forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "exam_bench/gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "exam_bench/grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "exam_bench/harness.py": "3040f6daaf1dc6e6583219f4d925151f8ba7851b2d5417d7f14645892b485ddf", "exam_bench/interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "exam_bench/interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "exam_bench/isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "exam_bench/ledger.py": "7e851523580e22d8490e75f9b6026c07f2c355007e0d11d0b252671f56bef654", "exam_bench/locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "exam_bench/materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "exam_bench/mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "exam_bench/observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "exam_bench/ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "exam_bench/penalties.py": "0d79e2e46102657dca00609b6abbfc0bf7d11fad41429564f876c82bc6b33269", "exam_bench/platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "exam_bench/portable.py": "cad56968ff407983608f5bdbc9ce7234128d7a4580b096ecea8e0e7b4edb9070", "exam_bench/portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "exam_bench/pr.py": "6a3a20caf0e10c0cc94410511a72d62c9fcda785f3abab1be2ad616d4ee16836", "exam_bench/preflight.py": "5619be0131d8641925f3ce2a3c8e5234d42aa5635d95676138ca81536d95cd29", "exam_bench/process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "exam_bench/queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "exam_bench/queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "exam_bench/replay_calibration.py": "e2d79cb508f2d5e3846d6dad36c3898d41dec1c573c1a1b7d8a2ec43e33c8c08", "exam_bench/report.py": "5e4c0757e1c7f189953f9a5302593ab726551835856baed25efd93dad6e8bfcd", "exam_bench/runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "exam_bench/smoke_check.py": "f36922a0027429ead0b414048dcc14bbe67f2f0e79a70d03dffbe1447d253545", "exam_bench/stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "exam_bench/submission.py": "3c5f703fcd90a1747884624e98b5caa1804dd422153106b96dcbb2810ee00544", "exam_bench/telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "exam_bench/windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "exam_bench/workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tools/build_public_site.py": "9682ed696f5ac9e9a82b65a45c0dece556ec7e49eeb20dcd616882cc534a8258", "tools/build_result_site.py": "3294e1d2ec1486058e208735264d61e349a68a4ae2fa2ec7a723c70e3263b496", "tools/check_native_harnesses.py": "4f5f0ed27651f78758eaef077b3b114361781f6b95ec40cb46c3fea689210473", "tools/check_native_toolkit.py": "0272794617121f2932828e5e4e9ae20095183c443666cf3ba466b44fbe875095", "tools/community_results.py": "9db56a44697d94f326efcbd7a3ae1aecdb569d43bba6c47e80ce525dc045f1f7", "tools/community_service.py": "c374480dbd88d656c0b9054fa04a8e1c6698c69e2f9cf475e82498a2dff61d84", "tools/community_setup.py": "5d7d126ed7d4dd48e1d79f57b99647a92ffcc8c9f80d90915e458888cdd76bf7", "tools/compare_harness_runs.py": "f274df5f3f804cb02504491aec946943833e12fbce6e62d281e12beb8508fc4e", "tools/create_run_plan.py": "871cd81b1eda231c0fba8805f63d2668926be9fc641559e6ddf320e2f47cd37a", "tools/demo_runner.py": "bf5cf11165b7a37bdbbf4bb7b24505bbbd74cd39cab24c4af70f111fc27ef466", "tools/installers.py": "9a2742780936b17500869e7c89202c1a2549e37d53a42ad9a50a0abbf78bbe09", "tools/machine_bundle.py": "8aa8346f99f537e81ceca6fb6ab9530e844954bab8eff87bf33d3602f81f8a30", "tools/prepare_native_harnesses.py": "7718ed341fcc7cc9e17f7bb9dd6a9f6fbfd6435411433f5acc9b12f63a8c699c", "tools/prepare_official_statement.py": "6b7028c78e90e798d6ef1a93b76520cc61a308c354fb9b87f7fad18b99800fad", "tools/prepare_open_exam_requirements.py": "544f4e378b9be5f166186f8788f8d454afdac2deb99d91d98421e39d01ba6d03", "tools/probe_harness.py": "1ed8ef93420d1484cbbfd151b7efc31b9a201ceb942dd05e3103efa22ffa7f27", "tools/probe_native_mcp.py": "9918d324129cba898993e07f8f8b6dbcbaf369398ebf28d464f9f1f00abdb254", "tools/readiness.py": "0b71ab667e6b2d9979fb3e5a769ebb8a453edec80a71090fb0b21b45af7986ce", "tools/recheck_community.py": "f0843d7d677f90da31e22bde0b1c86584dd46c022f1532d43d042619e426b230", "tools/regrade_runs.py": "011775afb06d3aac67a4aa81117a368c75896b0fcbe1e6f27ccc6237612fbf59", "tools/render_statement_text.py": "dabc0716a3612c288c671bc20e17fd4986691d732768e1e957d6dddddbea92a3", "tools/replay_calibration.py": "801f5004926c438c21ed3668fe2a4ddf45312b3e75320165a3839aae034eee9b", "tools/run_exam_campaign.py": "2c450d57a1cd0a2682838f5ec7c0a4ffb3aed0f1730d34c408e912d59cab6efd", "tools/serve_result_site.py": "86badfac863cd4ad1fc894a14110c75b28470513f0133eeae9d2799b8b4df3a9", "tools/start_demo.py": "c597e6cad28d245b3191654bb3e2801fa9dd2364e2acb25561923613717b615f", "tools/supplemental_acceptance.py": "c88fc39de1be1fdcacdd819e2ad329f60367b2df1d5deda80b37324bda3f2a01", "tools/sync_sources.py": "b51e889b0f41f9f63bfb19a09fb96d3777693d6b1d76fe0132bdd2a15e155898", "tools/validate_community_pr.py": "796b896dfade07b4529af2088a4b9b9d23484148b3bc0732b3fb837b75c9844b", "tools/verify_official_assessment_mapping.py": "daeb448a016940d5b6b1285979a56e5b9014bd91db40acb131445e4a83a23059", "tools/verify_task_package.py": "9e1e6105f6b5e4e78b36aa57f00117a9fbc8948ab53983c32ab56da88d23ccc4", "profiles/agents.json": "af9c492c08d13b3044aa6b6952589ed6a0a07d5258d8ff72bb18185b3eaebdc5", "profiles/ai-exam-execution-policy.json": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "profiles/bsl-analyzer-0.3.2-macos.json": "83537abdbf38c41ce665e4d0f24128bb51b62e971e0e0f368695f1326a7d2ffb", "profiles/bsl-analyzer-0.3.2-portable.json": "d6ba732e6778e256df34d6bc548593128820a70430c35b279796843606ee40a8", "profiles/bsl-ls-1.1.0-rc.6-macos.json": "245fc10747197e6911b2b4c77cdb15e6fa4eb7bc7c3758b63e768c5adf1df180", "profiles/bsl-ls-1.1.0-rc.6-portable.json": "9f10660881f2ec84794f7d584556b8f75c7e14b3555464af0ed0e60c4c892d86", "profiles/code-index-1.9.0-macos.json": "63a919523ce62ecec274f4c139bc7ad49a75dd4c339568b822cbc695b4e30408", "profiles/code-index-1.9.0-portable.json": "81106cee8f424ffd8a9dc46ecd8e4f57598fc1d49661a83c77b1f0507993fbdc", "profiles/codex-probe-plan.json": "166e41aad5fb3b27d9050bc6de952c6cba363cc6e804d4080568cc71a2a4d289", "profiles/machine.linux.example.json": "408304fd0581098d5d8110dc67dfeab353bc4d4030e32d37e6acf98d2b1aedfd", "profiles/machine.macos.example.json": "52e9f9d17797cb520b9d8955d6806fd550b899bed4da241ebf096dcb6a21a942", "profiles/machine.windows.example.json": "63accac9a2f81d47d03447efbabffd4760aee325193f02f46b9b29a28d50d2d8", "profiles/mcp-toolkit-1.9.0-macos.json": "1d3f9cde5ffa20589a840d01fdae03aa0fc2f412c929f064f203919c4129625b", "profiles/mcp-toolkit-1.9.0-portable.json": "8e370eebe773eef0e08045ee9c6d5be1451f769f65be0710834b262a4336e054", "profiles/none-macos.json": "b1401d9c48159aed3559006c7f6ace6ef4571224d5cf0bb76d1a823505a10056", "profiles/none-portable.json": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "profiles/rlm-tools-bsl-1.43.0-macos.json": "9354421052640ab60bc3e6aa98ff2e7ba9ca2318b0f4026c137487449242cbd2", "profiles/rlm-tools-bsl-1.43.0-portable.json": "2599e5645e0a7d4e44cb2934bc2b272cae79a9bf7ea74a23cd48aacea64bc424", "profiles/rlm-tools-bsl-1.43.0-posix-requirements.txt": "4fdf9a1bd994bf0272e65d231daf76cf19b0a34dad0ae6b50ec4f11a2ce4c330", "profiles/rlm-tools-bsl-1.43.0-windows-requirements.txt": "3730cb46c81cda5181ecd4485e98b11933104632358bc86f8c0eb1a612a8954f", "profiles/shirokov-skills-macos.json": "84f3e89091676884a802035c707e912762a1179425fb8e3faff25be736873cdb", "profiles/shirokov-skills-portable.json": "2b0a461e06602f1456410e70f02ceaa5ac32c6549c486660bcb5ace0c2f87b15", "profiles/shirokov-skills-windows-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/unica-0.12.3-macos.json": "2c39fbb591cf2c2c6e056373823615485397ea83651b7926c6f25a5fe6a0aae6", "profiles/unica-0.13.0-macos.json": "b76b5c8a4dd33f571c4a90993f1a2da5f7223b4f0f8e1042c282e21a66121052", "profiles/unica-0.14.0-rc.1-portable.json": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "rules/1c-specialist-platform/chistov.json": "77e04942f8c947b10759e7cc1eb31af05847d1711a772fbe6f23d525766757a9", "rules/1c-specialist-platform/decisions.json": "f622107423ce3c188c063318d7ab4f7718ceb38e443130677d8987f386641c09", "rules/1c-specialist-platform/examiner.json": "30353aa2a1b6545496b070d9066e9ffba0c3779e5b53ef70a4fd2cee375b18c0", "rules/1c-specialist-platform/ledger.json": "f167c10db2b5799dd9a1ea6a37cd2d7d186810dadf5ea2f50f26ae723c676882", "rules/1c-specialist-platform/rules.json": "1d320a4f8e1bf4701496388931f492315549bd3dce574b17285dd1d7f8652007", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" } } }, "conditions": { "client": "claude", "model": "claude-opus-5-5", "client_version": "2.1.310", "reasoning_effort": "medium", "harness": "unica-0.14.0-rc.1", "billing_channel": "subscription", "solve_timeout_seconds": 7200, "time_series": null, "delegation": "native_disabled", "network_profile": "open-book_shell", "deadline_disclosed": true, "statement_sha256": "8a6ccb3e673826d1f8220fda53eb310e3ec18c136d87ce8f4cebb2a08614e7e5", "starter_dt_sha256": "f40d084818b0d1cfe503fc7653a6a13f1a8e47fcd1688dad6245b12744eb4638", "profile_sha256": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "execution_policy_sha256": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "calibration_sha256": "4225306bf705e7d6754aacd8cc6f77f6e688e9d0c0e7ed742260ba25d7f8795c", "started_at": "2026-10-24T23:04:54.979409+00:00", "timing": { "prepare_ms": 23945, "solve_ms": 3281172, "grade_ms": null }, "original_submission_valid": true, "model_provenance": "client_reported", "tokens": { "input": 30119936, "cached_input": 29752812, "fresh_input": 367124, "output": 227116, "reasoning_output": null, "total": 30347052, "coverage": "final_result_model_usage" }, "tools": { "mcp_calls": 4, "unica_calls": 4, "failed_calls": 0 }, "process": { "status": "completed", "exit_code": 0, "stop_confirmed": true } }, "verification": "repository_owner", "download": "community-downloads/demo-20261024T230428Z-a2980e--owner-2026-10-26T190154240368-0000/solution.zip", "source_context": "community-downloads/demo-20261024T230428Z-a2980e--owner-2026-10-26T190154240368-0000/source-context.json", "regrade_required": [ { "id": "grader_changed", "files": [ "calibrate.py", "calibration_periodicity.py", "calibration_query.py", "common.py", "ou.py", "penalties.py", "queries.py", "replay_calibration.py", "rules/1c-specialist-platform/rules.json", "smoke_check.py", "tasks/1c-platform-official-sample/checks.json" ] } ], "grader_revision_sha256": "4a12b62d2c10085e1fc710f377f84903abdf2fb787dda19628d944da990a86b2", "archive_sha256": "adb944365c3cdb1083a087e77aa5b006ecaef4b219bb753484956cbbc3f65363", "owner_verification": { "kind": "repository_owner", "repository": "zeegin/1c-agent-exam-benchmark", "operator": { "name": "Ingvar Vilkman", "github": "zeegin" }, "started_at": "2026-10-26T18:59:07.718052+00:00", "server": { "name": "Owner Windows stand", "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "hardware": { "cpu": "AMD Ryzen 7 5800X 8-Core Processor ", "logical_cpus": 4, "ram_bytes": 17109000192 }, "isolation": "dedicated-host" }, "platform_version": "8.3.27.2342", "grader": { "profile": "technical-v8", "commit": "5b6a28372b253e81e22b83f8559df897297e28ff", "working_tree_dirty": true, "fingerprint": { "assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "calibrate.py": "1c844971b4977fdcc3b30aebe8aad40fbd45e6828955b8deb043ac8573d61731", "calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "claude.py": "eedabc75fca0faa434f40a1624b71419ec7dc22e2854a0886cf84b4911db8372", "codescan.py": "6d8375210cef1fd768fc2d98d630d880b2993a9724f01ae25f33b4ea5aa9631d", "codex.py": "904e75503cd35f16cbb052f66806b3879fe25bfc9f99e33b93c889d862c46324", "common.py": "7696116dd1a796666518b4c5d2aa3cafa04ee974593d3636333cbe5385bd6ccb", "docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "examiner.py": "8cdffcdd52f043c905f896697403380af95bf485dd4a5edca24f7956e7795ffe", "forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "harness.py": "3cbb90fd3187e700b5df32e5daafb20313d49bb5721c826e3033cbc6aa6e3825", "interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "penalties.py": "b82704e7f47d3dfdf6e501452d7e0abca1f9da63307093d2e257e32358be0489", "platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "pr.py": "2b6bfea0634703469605ce114f9274716b485852d9a55d9185c39893b14e4726", "preflight.py": "448c3120ab64b625abae3891be686c7a214ce4211f7cf651fd90e12c0b298433", "process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "querytypes.py": "b645f489a2abc27762b4a9bbf4917e72f7b46dc053a74c0dca4a8fc46491b3ef", "replay_calibration.py": "3b6f3a289cc8a7f5e458f62bfa2c6cc534cc9076ba3f22d1e4bd8a5f9e175317", "runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "smoke_check.py": "bd6266367e6b769a95258eb383239b89a22deae406d64f6e142c77396f4639ba", "stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "submission.py": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tasks/1c-platform-official-sample/checks.json": "17a6fcc0c14410829650623eb1443ce99796e000cdfd19905ac0287988b73a00", "tasks/1c-platform-official-sample/private/official-assessment-mapping.json": "303587c0dabe77c1eeebb2017fe85539e3370b17c9090435e6e0325a66bd0644", "tasks/1c-platform-official-sample/private/owner-scoring-policy.json": "d26d534bb838ab1b5facb7bc033ca8ec40912133baadcdbad83b27fc577905f5", "starters/carcass-8.3.25.1445/starter.json": "0f7a7060885ba99a19402bfc6e63cc8fe979b0f491b040d3a01d5d21b304b3a6", "rules/1c-specialist-platform/rules.json": "7ec895a7751ef17f4a50cc80b5f7fa986e1e04360ab0b4ce9aa29115195df03c", "rules/1c-specialist-platform/examiner.json": "1247486ddd412d600db88d9c1db4ba501fc1994afd1dc2ebe85402fcc332f4c8", "rules/1c-specialist-platform/chistov.json": "800da27601a3f1c7ec1df64482fd4ad035e559ba0b390a274ed5031128487d3d", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" }, "sha256": "4a12b62d2c10085e1fc710f377f84903abdf2fb787dda19628d944da990a86b2" }, "identity_verified_at": "2026-10-26T18:44:22.364471+00:00", "identity_session_sha256": "950670ab9a82059c65525d0d6e5b8a00f0dc292581edea3eb087c4ecadeaab09", "completed_at": "2026-10-26T19:01:54.240368+00:00" } }, { "id": "demo-20261024T230428Z-a2980e", "run_id": "demo-20261024T230428Z-a2980e", "result": { "run_id": "demo-20261024T230428Z-a2980e", "created_at": "2026-10-25T00:09:38.317949+00:00", "model": "claude-opus-5-5", "harness": "unica-0.14.0-rc.1", "solve_seconds": 3281, "platform": "8.3.27.1688", "counts": { "pass": 62, "fail": 3 }, "rules": [ { "id": "BU01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU16", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU17", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU02", "verdict": "pass", "coverage": "partial", "reason": null }, { "id": "BU10", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU12", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU06", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU07", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU08", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU09", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU11", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU14", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU15", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU13", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU15", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU16", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU17", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU02", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU18", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU14", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU06", "verdict": "pass", "coverage": "no_violation_found", "reason": null }, { "id": "OU07", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU08", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU09", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU10", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU11", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU12", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU13", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU19", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU20", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU21", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR02", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR04", "verdict": "fail", "coverage": "selected_fixture", "reason": null }, { "id": "PR05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR06", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR07", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR08", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR09", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR10", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR11", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR12", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR13", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR14", "verdict": "pass", "coverage": "no_violation_found", "reason": null }, { "id": "PR15", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR16", "verdict": "fail", "coverage": "selected_fixture", "reason": null }, { "id": "PR17", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR18", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR19", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F02", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F05", "verdict": "fail", "coverage": "selected_fixture", "reason": null }, { "id": "G01", "verdict": "pass", "coverage": "static_sources", "reason": null }, { "id": "G02", "verdict": "pass", "coverage": "static_sources", "reason": null }, { "id": "G03", "verdict": "pass", "coverage": "static_sources", "reason": null } ], "charges": [ { "id": "F1C-GEN01", "points": "0.5", "reason": "не выполнено требование: PR04 — pr_tariff E1/A tariff 2025-03: 76800, expected 38400.00" }, { "id": "F1C-GEN01", "points": "0.5", "reason": "не выполнено требование: PR16 — a tariff row 10.03-03.04 was accepted; pr_tariff E1/A tariff 2025-03: 76800, expected 38400.00" }, { "id": "F1C-GEN01", "points": "0.5", "reason": "не выполнено требование: F05 — typed ['C1', 'C2'], written True, stored [('BENCH_Валюта', ''), ('BENCH_Срок', '')]" }, { "id": "F1C-GEN12", "points": "0.25", "reason": "текст запроса не разбирается платформой: DataProcessors/ЗаполнениеГрафика/Ext/ObjectModule.bsl:20 — Поле не найдено \"Подразделения.ЭтоГруппа\"" }, { "id": "F1C-GEN15", "points": "0.5", "reason": "CommonModules/РасчетЗарплаты/Ext/Module.bsl:237 — РегистрРасчета.ОсновныеНачисления: отбор по ВидРасчета, ПериодДействияКонец, ПериодДействияНачало, Подразделение, Сотрудник, индексы таблицы начинаются с ПериодДействия, ПериодРегистрации, Регистратор" }, { "id": "F1C-GEN15", "points": "0.5", "reason": "Reports/ВедомостьПоПодразделению/Ext/ManagerModule.bsl:17 — РегистрНакопления.ОстаткиНоменклатуры.ОстаткиИОбороты: отбор по Подразделение, Свойство, индексы таблицы начинаются с Номенклатура" }, { "id": "F1C-GEN23", "points": "1.0", "reason": "основная таблица регистра расчёта соединяется с его же «Данными графика»: CommonModules/РасчетЗарплаты/Ext/Module.bsl:194 ОсновныеНачисления" }, { "id": "F1C-GEN25", "points": "1.0", "reason": "результат запроса выгружается в таблицу значений Пары только для одного перебора: CommonModules/БухгалтерскийУчетСервер/Ext/Module.bsl:24" }, { "id": "F1C-GEN25", "points": "1.0", "reason": "результат запроса выгружается в таблицу значений Остатки только для одного перебора: Documents/РасходнаяНакладная/Ext/ObjectModule.bsl:137" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "проводимые документы в режиме «Записывать модифицированные»: НачислениеЗарплаты, Операция, ПриходнаяНакладная, РасходнаяНакладная, Сборка" }, { "id": "F1C-PR14", "points": "0.5", "reason": "после расчёта набор с периодом действия перезаписывается целиком, с пересчётом фактического периода действия (нужно Записать(, Истина)): CommonModules/РасчетЗарплаты/Ext/Module.bsl:14 Набор.Записать(); CommonModules/РасчетЗарплаты/Ext/Module.bsl:16 Набор.Записать(); CommonModules/РасчетЗарплаты/Ext/Module.bsl:18 Набор.Записать(); CommonModules/РасчетЗарплаты/Ext/Module.bsl:269 Набор.Записать(); CommonModules/РасчетЗарплаты/Ext/Module.bsl:271 Набор.Записать()" }, { "id": "F1C-BU07", "points": "1.0", "reason": "признаки учёта субконто не заведены: сумма ведётся по всем субконто, в том числе по складам, а себестоимость — средняя по номенклатуре всей компании (Т3.13)" }, { "id": "F1C-GEN20", "points": "2.0", "reason": "данные базы читаются в цикле по записям: CommonModules/ОперативныйУчетСервер/Ext/Module.bsl:100; CommonModules/ОперативныйУчетСервер/Ext/Module.bsl:102; CommonModules/ОперативныйУчетСервер/Ext/Module.bsl:102" }, { "id": "F1C-GEN01", "points": "0.5", "reason": "разыменование поля составного типа без ВЫРАЗИТЬ: CommonModules/ОперативныйУчетСервер/Ext/Module.bsl: Остатки.Партия.МоментВремени" } ], "score_upper_bound": "-5.75", "score": null, "grade": "unsatisfactory", "deductions": "10.75", "not_assessed": 14, "gates": { "starter_origin": "passed", "load": "loaded", "clients": "compiles", "demo_data": "present" }, "infrastructure_errors": false, "comparison_eligible": false, "binding_compatibility": null, "evaluation_sha256": "853b4f356194cfbe1bc1fe758ac6e30e33334957684d758ecc21ef2e74069f2e", "downloads": [] }, "measurement": { "operator": { "name": "Vasiliy", "github": "Gh0sTspp" }, "environment": { "captured_at": "2026-10-24T23:04:30.225789+00:00", "capture_timing": "before_run", "hardware": { "cpu": "Intel(R) Core(TM) i7-5820K CPU @ 3.30GHz", "logical_cpus": 12, "ram_bytes": 34189709312 }, "os": { "system": "Windows", "release": "10", "version": "10.0.19045", "architecture": "AMD64" }, "python": "3.13.12", "platform_version": "8.3.27.1688", "isolation": "dedicated-host", "network_profile": "open-book_shell", "unsafe_action_protection_observed_in_user_config": true, "git_revision": "be55d44b20d37140792f68a45a1eda6a29c677f7", "implementation_files": { "exam_bench/__init__.py": "ad5bf6f05dc6765f40b78bd186870ca2c49be113cfa33f8aa76f4926f2cb2c1e", "exam_bench/assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "exam_bench/bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "exam_bench/calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "exam_bench/calibrate.py": "78b5185cb0888c0c0ac3de95ffc3a80154a6de9ae66fc461f79d012e5a58e1db", "exam_bench/calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "exam_bench/calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "exam_bench/calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "exam_bench/calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "exam_bench/calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "exam_bench/claude.py": "e66c95345f969feb97738b568a8973d2c04b7f9dabf3424a2bb32ad52896c4e5", "exam_bench/cli.py": "1a37ce645633d761f7897dffc9c45e6b8b9600cd7bd233b1cbf78f49d26b099a", "exam_bench/codescan.py": "751e38001b6e65727a31e28172a0623f0bf34bc092a958037c286aa991a197ed", "exam_bench/codex.py": "c3f89d72af11f312d851c73a1610d92e79acadf336be9ccedd1f94ede3b3ccb0", "exam_bench/common.py": "8682603b519063e655eae3574a02a49efee63bde21f582ccee20ddd623fca96d", "exam_bench/docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "exam_bench/examiner.py": "d7294fdd23ed1732216cafebf0a8cf2c24cce4259859aeb7149f62b7607d087d", "exam_bench/finalize.py": "4034f1c63896a940afdb1a83d541cf47fc75c8b5061e3f839047109c04beb620", "exam_bench/forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "exam_bench/gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "exam_bench/grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "exam_bench/harness.py": "3040f6daaf1dc6e6583219f4d925151f8ba7851b2d5417d7f14645892b485ddf", "exam_bench/interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "exam_bench/interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "exam_bench/isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "exam_bench/ledger.py": "7e851523580e22d8490e75f9b6026c07f2c355007e0d11d0b252671f56bef654", "exam_bench/locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "exam_bench/materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "exam_bench/mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "exam_bench/observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "exam_bench/ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "exam_bench/penalties.py": "0d79e2e46102657dca00609b6abbfc0bf7d11fad41429564f876c82bc6b33269", "exam_bench/platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "exam_bench/portable.py": "cad56968ff407983608f5bdbc9ce7234128d7a4580b096ecea8e0e7b4edb9070", "exam_bench/portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "exam_bench/pr.py": "6a3a20caf0e10c0cc94410511a72d62c9fcda785f3abab1be2ad616d4ee16836", "exam_bench/preflight.py": "5619be0131d8641925f3ce2a3c8e5234d42aa5635d95676138ca81536d95cd29", "exam_bench/process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "exam_bench/queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "exam_bench/queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "exam_bench/replay_calibration.py": "e2d79cb508f2d5e3846d6dad36c3898d41dec1c573c1a1b7d8a2ec43e33c8c08", "exam_bench/report.py": "5e4c0757e1c7f189953f9a5302593ab726551835856baed25efd93dad6e8bfcd", "exam_bench/runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "exam_bench/smoke_check.py": "f36922a0027429ead0b414048dcc14bbe67f2f0e79a70d03dffbe1447d253545", "exam_bench/stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "exam_bench/submission.py": "3c5f703fcd90a1747884624e98b5caa1804dd422153106b96dcbb2810ee00544", "exam_bench/telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "exam_bench/windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "exam_bench/workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tools/build_public_site.py": "9682ed696f5ac9e9a82b65a45c0dece556ec7e49eeb20dcd616882cc534a8258", "tools/build_result_site.py": "3294e1d2ec1486058e208735264d61e349a68a4ae2fa2ec7a723c70e3263b496", "tools/check_native_harnesses.py": "4f5f0ed27651f78758eaef077b3b114361781f6b95ec40cb46c3fea689210473", "tools/check_native_toolkit.py": "0272794617121f2932828e5e4e9ae20095183c443666cf3ba466b44fbe875095", "tools/community_results.py": "9db56a44697d94f326efcbd7a3ae1aecdb569d43bba6c47e80ce525dc045f1f7", "tools/community_service.py": "c374480dbd88d656c0b9054fa04a8e1c6698c69e2f9cf475e82498a2dff61d84", "tools/community_setup.py": "5d7d126ed7d4dd48e1d79f57b99647a92ffcc8c9f80d90915e458888cdd76bf7", "tools/compare_harness_runs.py": "f274df5f3f804cb02504491aec946943833e12fbce6e62d281e12beb8508fc4e", "tools/create_run_plan.py": "871cd81b1eda231c0fba8805f63d2668926be9fc641559e6ddf320e2f47cd37a", "tools/demo_runner.py": "bf5cf11165b7a37bdbbf4bb7b24505bbbd74cd39cab24c4af70f111fc27ef466", "tools/installers.py": "9a2742780936b17500869e7c89202c1a2549e37d53a42ad9a50a0abbf78bbe09", "tools/machine_bundle.py": "8aa8346f99f537e81ceca6fb6ab9530e844954bab8eff87bf33d3602f81f8a30", "tools/prepare_native_harnesses.py": "7718ed341fcc7cc9e17f7bb9dd6a9f6fbfd6435411433f5acc9b12f63a8c699c", "tools/prepare_official_statement.py": "6b7028c78e90e798d6ef1a93b76520cc61a308c354fb9b87f7fad18b99800fad", "tools/prepare_open_exam_requirements.py": "544f4e378b9be5f166186f8788f8d454afdac2deb99d91d98421e39d01ba6d03", "tools/probe_harness.py": "1ed8ef93420d1484cbbfd151b7efc31b9a201ceb942dd05e3103efa22ffa7f27", "tools/probe_native_mcp.py": "9918d324129cba898993e07f8f8b6dbcbaf369398ebf28d464f9f1f00abdb254", "tools/readiness.py": "0b71ab667e6b2d9979fb3e5a769ebb8a453edec80a71090fb0b21b45af7986ce", "tools/recheck_community.py": "f0843d7d677f90da31e22bde0b1c86584dd46c022f1532d43d042619e426b230", "tools/regrade_runs.py": "011775afb06d3aac67a4aa81117a368c75896b0fcbe1e6f27ccc6237612fbf59", "tools/render_statement_text.py": "dabc0716a3612c288c671bc20e17fd4986691d732768e1e957d6dddddbea92a3", "tools/replay_calibration.py": "801f5004926c438c21ed3668fe2a4ddf45312b3e75320165a3839aae034eee9b", "tools/run_exam_campaign.py": "2c450d57a1cd0a2682838f5ec7c0a4ffb3aed0f1730d34c408e912d59cab6efd", "tools/serve_result_site.py": "86badfac863cd4ad1fc894a14110c75b28470513f0133eeae9d2799b8b4df3a9", "tools/start_demo.py": "c597e6cad28d245b3191654bb3e2801fa9dd2364e2acb25561923613717b615f", "tools/supplemental_acceptance.py": "c88fc39de1be1fdcacdd819e2ad329f60367b2df1d5deda80b37324bda3f2a01", "tools/sync_sources.py": "b51e889b0f41f9f63bfb19a09fb96d3777693d6b1d76fe0132bdd2a15e155898", "tools/validate_community_pr.py": "796b896dfade07b4529af2088a4b9b9d23484148b3bc0732b3fb837b75c9844b", "tools/verify_official_assessment_mapping.py": "daeb448a016940d5b6b1285979a56e5b9014bd91db40acb131445e4a83a23059", "tools/verify_task_package.py": "9e1e6105f6b5e4e78b36aa57f00117a9fbc8948ab53983c32ab56da88d23ccc4", "profiles/agents.json": "af9c492c08d13b3044aa6b6952589ed6a0a07d5258d8ff72bb18185b3eaebdc5", "profiles/ai-exam-execution-policy.json": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "profiles/bsl-analyzer-0.3.2-macos.json": "83537abdbf38c41ce665e4d0f24128bb51b62e971e0e0f368695f1326a7d2ffb", "profiles/bsl-analyzer-0.3.2-portable.json": "d6ba732e6778e256df34d6bc548593128820a70430c35b279796843606ee40a8", "profiles/bsl-ls-1.1.0-rc.6-macos.json": "245fc10747197e6911b2b4c77cdb15e6fa4eb7bc7c3758b63e768c5adf1df180", "profiles/bsl-ls-1.1.0-rc.6-portable.json": "9f10660881f2ec84794f7d584556b8f75c7e14b3555464af0ed0e60c4c892d86", "profiles/code-index-1.9.0-macos.json": "63a919523ce62ecec274f4c139bc7ad49a75dd4c339568b822cbc695b4e30408", "profiles/code-index-1.9.0-portable.json": "81106cee8f424ffd8a9dc46ecd8e4f57598fc1d49661a83c77b1f0507993fbdc", "profiles/codex-probe-plan.json": "166e41aad5fb3b27d9050bc6de952c6cba363cc6e804d4080568cc71a2a4d289", "profiles/machine.linux.example.json": "408304fd0581098d5d8110dc67dfeab353bc4d4030e32d37e6acf98d2b1aedfd", "profiles/machine.macos.example.json": "52e9f9d17797cb520b9d8955d6806fd550b899bed4da241ebf096dcb6a21a942", "profiles/machine.windows.example.json": "63accac9a2f81d47d03447efbabffd4760aee325193f02f46b9b29a28d50d2d8", "profiles/mcp-toolkit-1.9.0-macos.json": "1d3f9cde5ffa20589a840d01fdae03aa0fc2f412c929f064f203919c4129625b", "profiles/mcp-toolkit-1.9.0-portable.json": "8e370eebe773eef0e08045ee9c6d5be1451f769f65be0710834b262a4336e054", "profiles/none-macos.json": "b1401d9c48159aed3559006c7f6ace6ef4571224d5cf0bb76d1a823505a10056", "profiles/none-portable.json": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "profiles/rlm-tools-bsl-1.43.0-macos.json": "9354421052640ab60bc3e6aa98ff2e7ba9ca2318b0f4026c137487449242cbd2", "profiles/rlm-tools-bsl-1.43.0-portable.json": "2599e5645e0a7d4e44cb2934bc2b272cae79a9bf7ea74a23cd48aacea64bc424", "profiles/rlm-tools-bsl-1.43.0-posix-requirements.txt": "4fdf9a1bd994bf0272e65d231daf76cf19b0a34dad0ae6b50ec4f11a2ce4c330", "profiles/rlm-tools-bsl-1.43.0-windows-requirements.txt": "3730cb46c81cda5181ecd4485e98b11933104632358bc86f8c0eb1a612a8954f", "profiles/shirokov-skills-macos.json": "84f3e89091676884a802035c707e912762a1179425fb8e3faff25be736873cdb", "profiles/shirokov-skills-portable.json": "2b0a461e06602f1456410e70f02ceaa5ac32c6549c486660bcb5ace0c2f87b15", "profiles/shirokov-skills-windows-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/unica-0.12.3-macos.json": "2c39fbb591cf2c2c6e056373823615485397ea83651b7926c6f25a5fe6a0aae6", "profiles/unica-0.13.0-macos.json": "b76b5c8a4dd33f571c4a90993f1a2da5f7223b4f0f8e1042c282e21a66121052", "profiles/unica-0.14.0-rc.1-portable.json": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "rules/1c-specialist-platform/chistov.json": "77e04942f8c947b10759e7cc1eb31af05847d1711a772fbe6f23d525766757a9", "rules/1c-specialist-platform/decisions.json": "f622107423ce3c188c063318d7ab4f7718ceb38e443130677d8987f386641c09", "rules/1c-specialist-platform/examiner.json": "30353aa2a1b6545496b070d9066e9ffba0c3779e5b53ef70a4fd2cee375b18c0", "rules/1c-specialist-platform/ledger.json": "f167c10db2b5799dd9a1ea6a37cd2d7d186810dadf5ea2f50f26ae723c676882", "rules/1c-specialist-platform/rules.json": "1d320a4f8e1bf4701496388931f492315549bd3dce574b17285dd1d7f8652007", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" } } }, "conditions": { "client": "claude", "model": "claude-opus-5-5", "client_version": "2.1.310", "reasoning_effort": "medium", "harness": "unica-0.14.0-rc.1", "billing_channel": "subscription", "solve_timeout_seconds": 7200, "time_series": null, "delegation": "native_disabled", "network_profile": "open-book_shell", "deadline_disclosed": true, "statement_sha256": "8a6ccb3e673826d1f8220fda53eb310e3ec18c136d87ce8f4cebb2a08614e7e5", "starter_dt_sha256": "f40d084818b0d1cfe503fc7653a6a13f1a8e47fcd1688dad6245b12744eb4638", "profile_sha256": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "execution_policy_sha256": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "calibration_sha256": "4225306bf705e7d6754aacd8cc6f77f6e688e9d0c0e7ed742260ba25d7f8795c", "started_at": "2026-10-24T23:04:54.979409+00:00", "timing": { "prepare_ms": 23945, "solve_ms": 3281172, "grade_ms": null }, "original_submission_valid": true, "model_provenance": "client_reported", "tokens": { "input": 30119936, "cached_input": 29752812, "fresh_input": 367124, "output": 227116, "reasoning_output": null, "total": 30347052, "coverage": "final_result_model_usage" }, "tools": { "mcp_calls": 4, "unica_calls": 4, "failed_calls": 0 }, "process": { "status": "completed", "exit_code": 0, "stop_confirmed": true } }, "verification": "contributor_reported", "download": "community-downloads/demo-20261024T230428Z-a2980e/solution.zip", "source_context": "community-downloads/demo-20261024T230428Z-a2980e/source-context.json", "regrade_required": [ { "id": "grader_changed", "files": [ "assessment.py", "bp.py", "calcwrite.py", "calibrate.py", "calibration_periodicity.py", "calibration_query.py", "claude.py", "codescan.py", "codex.py", "common.py", "docx_text.py", "examiner.py", "harness.py", "interpretations.py", "locking.py", "materials.py", "mcp_toolkit.py", "ou.py", "penalties.py", "portable_harnesses.py", "pr.py", "preflight.py", "queries.py", "queryschema.py", "querytypes.py", "replay_calibration.py", "rules/1c-specialist-platform/chistov.json", "rules/1c-specialist-platform/examiner.json", "rules/1c-specialist-platform/rules.json", "rules/1c-specialist-platform/standards.json", "smoke_check.py", "starters/carcass-8.3.25.1445/starter.json", "stdio_harnesses.py", "submission.py", "tasks/1c-platform-official-sample/checks.json", "tasks/1c-platform-official-sample/private/official-assessment-mapping.json", "tasks/1c-platform-official-sample/private/owner-scoring-policy.json", "telemetry.py" ] } ], "grader_revision_sha256": "7f7f614bf86fb49d15df562c90b39d63e194f5648003ac39f0ad734d6a306689", "archive_sha256": "66368e9a4e2fb9c16cc2e396ef2f72341708916968535251817517800f262b0f" } ] }, { "id": "demo-20261025T113419Z-de9981--owner-2026-10-26T223317840149-0000", "run_id": "demo-20261025T031725Z-2076a5", "result": { "run_id": "demo-20261025T031725Z-2076a5", "created_at": "2026-10-26T22:33:17.840149+00:00", "model": "gpt-6.1-sol", "harness": "none", "solve_seconds": 4332, "platform": "8.3.27.1644", "counts": { "pass": 62, "inconclusive": 2, "fail": 1 }, "rules": [ { "id": "BU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU01.selected_fixture" }, { "id": "BU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU04.selected_fixture" }, { "id": "BU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU05.selected_fixture" }, { "id": "BU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU16.selected_fixture" }, { "id": "BU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU17.selected_fixture" }, { "id": "BU02", "verdict": "pass", "reason": null, "coverage": "partial", "assertion_id": "BU02.posting_cost_and_balance" }, { "id": "BU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU10.selected_fixture" }, { "id": "BU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU12.selected_fixture" }, { "id": "BU03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU03.selected_fixture" }, { "id": "BU06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU06.selected_fixture" }, { "id": "BU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU07.selected_fixture" }, { "id": "BU08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU08.selected_fixture" }, { "id": "BU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU09.selected_fixture" }, { "id": "BU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU11.selected_fixture" }, { "id": "BU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU14.selected_fixture" }, { "id": "BU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU15.selected_fixture" }, { "id": "BU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU13.selected_fixture" }, { "id": "OU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU15.selected_fixture" }, { "id": "OU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU16.selected_fixture" }, { "id": "OU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU17.selected_fixture" }, { "id": "OU02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU02.selected_fixture" }, { "id": "OU18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU18.selected_fixture" }, { "id": "OU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU14.selected_fixture" }, { "id": "OU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU01.selected_fixture" }, { "id": "OU03", "verdict": "pass", "reason": "История и годовая периодичность регистра подтверждены.", "coverage": "history_and_periodicity", "assertion_id": "OU03.selected_fixture" }, { "id": "OU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU05.selected_fixture" }, { "id": "OU06", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "OU06.selected_fixture" }, { "id": "OU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU07.selected_fixture" }, { "id": "OU08", "verdict": "pass", "reason": "История и дневная периодичность подтверждены; ограничение одной версии в неделю отдельно не проверяется.", "coverage": "history_and_periodicity", "assertion_id": "OU08.selected_fixture" }, { "id": "OU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU09.selected_fixture" }, { "id": "OU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU10.selected_fixture" }, { "id": "OU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU11.selected_fixture" }, { "id": "OU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU12.selected_fixture" }, { "id": "OU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU13.selected_fixture" }, { "id": "OU04", "verdict": "inconclusive", "reason": "Required observations unavailable: characteristic values could not be written: {'value_P1': '{ОбщийМодуль.BenchmarkObserver.Модуль(108)}: Ошибка при установке значения атрибута контекста (Владелец): Справочник не имеет владельца'", "coverage": "selected_fixture", "assertion_id": "OU04.selected_fixture" }, { "id": "OU19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU19.selected_fixture" }, { "id": "OU20", "verdict": "inconclusive", "reason": "Required observations unavailable: characteristic values could not be written: {'value_P1': '{ОбщийМодуль.BenchmarkObserver.Модуль(108)}: Ошибка при установке значения атрибута контекста (Владелец): Справочник не имеет владельца'", "coverage": "selected_fixture", "assertion_id": "OU20.selected_fixture" }, { "id": "OU21", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU21.selected_fixture" }, { "id": "PR01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR01.selected_fixture" }, { "id": "PR02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR02.selected_fixture" }, { "id": "PR03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR03.selected_fixture" }, { "id": "PR04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR04.selected_fixture" }, { "id": "PR05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR05.selected_fixture" }, { "id": "PR06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR06.selected_fixture" }, { "id": "PR07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR07.selected_fixture" }, { "id": "PR08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR08.selected_fixture" }, { "id": "PR09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR09.selected_fixture" }, { "id": "PR10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR10.selected_fixture" }, { "id": "PR11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR11.selected_fixture" }, { "id": "PR12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR12.selected_fixture" }, { "id": "PR13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR13.selected_fixture" }, { "id": "PR14", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "PR14.selected_fixture" }, { "id": "PR15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR15.selected_fixture" }, { "id": "PR16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR16.selected_fixture" }, { "id": "PR17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR17.selected_fixture" }, { "id": "PR18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR18.selected_fixture" }, { "id": "PR19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR19.selected_fixture" }, { "id": "F01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F01.selected_fixture" }, { "id": "F02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F02.selected_fixture" }, { "id": "F03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F03.selected_fixture" }, { "id": "F04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F04.selected_fixture" }, { "id": "F05", "verdict": "fail", "reason": "typed ['C1', 'C2'], written True, stored [('BENCH_Валюта', ''), ('BENCH_Срок', '')]", "coverage": "selected_fixture", "assertion_id": "F05.selected_fixture" }, { "id": "G01", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G01.static_sources" }, { "id": "G02", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G02.static_sources" }, { "id": "G03", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G03.static_sources" } ], "charges": [ { "id": "F1C-GEN01", "points": "0.5", "reason": "не выполнено требование: F05 — typed ['C1', 'C2'], written True, stored [('BENCH_Валюта', ''), ('BENCH_Срок', '')]" } ], "score_upper_bound": "4.5", "score": null, "grade": null, "deductions": "0.5", "not_assessed": 18, "gates": { "starter_origin": "passed", "load": "loaded", "clients": "compiles", "demo_data": "present" }, "infrastructure_errors": false, "comparison_eligible": false, "binding_compatibility": null }, "measurement": { "operator": { "name": "Вячеслав", "github": "sksibak" }, "environment": { "captured_at": "2026-10-25T03:17:28.597378+00:00", "capture_timing": "before_run", "hardware": { "cpu": "AMD Ryzen 5 4600H with Radeon Graphics ", "logical_cpus": 12, "ram_bytes": 16505962496 }, "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "python": "3.12.14", "platform_version": "8.3.27.1644", "isolation": "dedicated-host", "network_profile": "open-book_shell", "unsafe_action_protection_observed_in_user_config": true, "git_revision": "af85e791b303dbbf0b0b7af924d2489c3e57cfa8", "implementation_files": { "exam_bench/__init__.py": "ad5bf6f05dc6765f40b78bd186870ca2c49be113cfa33f8aa76f4926f2cb2c1e", "exam_bench/assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "exam_bench/bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "exam_bench/calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "exam_bench/calibrate.py": "78b5185cb0888c0c0ac3de95ffc3a80154a6de9ae66fc461f79d012e5a58e1db", "exam_bench/calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "exam_bench/calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "exam_bench/calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "exam_bench/calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "exam_bench/calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "exam_bench/claude.py": "bc1b8550de7573aaed5e39c6e9c0309e0d8175284a75490d61ec27439ed911ad", "exam_bench/cli.py": "1a37ce645633d761f7897dffc9c45e6b8b9600cd7bd233b1cbf78f49d26b099a", "exam_bench/codescan.py": "751e38001b6e65727a31e28172a0623f0bf34bc092a958037c286aa991a197ed", "exam_bench/codex.py": "c3f89d72af11f312d851c73a1610d92e79acadf336be9ccedd1f94ede3b3ccb0", "exam_bench/common.py": "8682603b519063e655eae3574a02a49efee63bde21f582ccee20ddd623fca96d", "exam_bench/docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "exam_bench/examiner.py": "d7294fdd23ed1732216cafebf0a8cf2c24cce4259859aeb7149f62b7607d087d", "exam_bench/finalize.py": "4034f1c63896a940afdb1a83d541cf47fc75c8b5061e3f839047109c04beb620", "exam_bench/forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "exam_bench/gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "exam_bench/grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "exam_bench/harness.py": "3040f6daaf1dc6e6583219f4d925151f8ba7851b2d5417d7f14645892b485ddf", "exam_bench/interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "exam_bench/interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "exam_bench/isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "exam_bench/ledger.py": "7e851523580e22d8490e75f9b6026c07f2c355007e0d11d0b252671f56bef654", "exam_bench/locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "exam_bench/materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "exam_bench/mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "exam_bench/observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "exam_bench/ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "exam_bench/penalties.py": "0d79e2e46102657dca00609b6abbfc0bf7d11fad41429564f876c82bc6b33269", "exam_bench/platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "exam_bench/portable.py": "cad56968ff407983608f5bdbc9ce7234128d7a4580b096ecea8e0e7b4edb9070", "exam_bench/portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "exam_bench/pr.py": "6a3a20caf0e10c0cc94410511a72d62c9fcda785f3abab1be2ad616d4ee16836", "exam_bench/preflight.py": "5619be0131d8641925f3ce2a3c8e5234d42aa5635d95676138ca81536d95cd29", "exam_bench/process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "exam_bench/queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "exam_bench/queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "exam_bench/replay_calibration.py": "c150457b0b23ce4e6814eb8deb4d48f6bc4a2e39d8f84a9dc7644fb99a026c2d", "exam_bench/report.py": "5e4c0757e1c7f189953f9a5302593ab726551835856baed25efd93dad6e8bfcd", "exam_bench/runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "exam_bench/smoke_check.py": "f36922a0027429ead0b414048dcc14bbe67f2f0e79a70d03dffbe1447d253545", "exam_bench/stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "exam_bench/submission.py": "d6f9d20704181c51714f1138affe4965d860ae21475ab7bb49aa5c5cefebb9f5", "exam_bench/telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "exam_bench/windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "exam_bench/workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tools/build_public_site.py": "9682ed696f5ac9e9a82b65a45c0dece556ec7e49eeb20dcd616882cc534a8258", "tools/build_result_site.py": "3294e1d2ec1486058e208735264d61e349a68a4ae2fa2ec7a723c70e3263b496", "tools/check_native_harnesses.py": "4f5f0ed27651f78758eaef077b3b114361781f6b95ec40cb46c3fea689210473", "tools/check_native_toolkit.py": "0272794617121f2932828e5e4e9ae20095183c443666cf3ba466b44fbe875095", "tools/community_results.py": "9db56a44697d94f326efcbd7a3ae1aecdb569d43bba6c47e80ce525dc045f1f7", "tools/community_service.py": "c374480dbd88d656c0b9054fa04a8e1c6698c69e2f9cf475e82498a2dff61d84", "tools/community_setup.py": "5d7d126ed7d4dd48e1d79f57b99647a92ffcc8c9f80d90915e458888cdd76bf7", "tools/compare_harness_runs.py": "f274df5f3f804cb02504491aec946943833e12fbce6e62d281e12beb8508fc4e", "tools/create_run_plan.py": "871cd81b1eda231c0fba8805f63d2668926be9fc641559e6ddf320e2f47cd37a", "tools/demo_runner.py": "230e6e49068f2bab3a0db64e6da5889e8f1834158fed8c5ec334b7694695a87b", "tools/installers.py": "9a2742780936b17500869e7c89202c1a2549e37d53a42ad9a50a0abbf78bbe09", "tools/machine_bundle.py": "8aa8346f99f537e81ceca6fb6ab9530e844954bab8eff87bf33d3602f81f8a30", "tools/prepare_native_harnesses.py": "aaa75ecf4022883984fa50c42d14d8e1a9fde2eeda03dab03b852bbc5efb2502", "tools/prepare_official_statement.py": "6b7028c78e90e798d6ef1a93b76520cc61a308c354fb9b87f7fad18b99800fad", "tools/prepare_open_exam_requirements.py": "544f4e378b9be5f166186f8788f8d454afdac2deb99d91d98421e39d01ba6d03", "tools/probe_harness.py": "1ed8ef93420d1484cbbfd151b7efc31b9a201ceb942dd05e3103efa22ffa7f27", "tools/probe_native_mcp.py": "9918d324129cba898993e07f8f8b6dbcbaf369398ebf28d464f9f1f00abdb254", "tools/readiness.py": "d34dd3f38334f51cc4574c79194cf0b80769b062a52382989a57d01c46b9aba4", "tools/recheck_community.py": "f0843d7d677f90da31e22bde0b1c86584dd46c022f1532d43d042619e426b230", "tools/regrade_runs.py": "011775afb06d3aac67a4aa81117a368c75896b0fcbe1e6f27ccc6237612fbf59", "tools/render_statement_text.py": "dabc0716a3612c288c671bc20e17fd4986691d732768e1e957d6dddddbea92a3", "tools/replay_calibration.py": "801f5004926c438c21ed3668fe2a4ddf45312b3e75320165a3839aae034eee9b", "tools/run_exam_campaign.py": "2c450d57a1cd0a2682838f5ec7c0a4ffb3aed0f1730d34c408e912d59cab6efd", "tools/serve_result_site.py": "86badfac863cd4ad1fc894a14110c75b28470513f0133eeae9d2799b8b4df3a9", "tools/start_demo.py": "c597e6cad28d245b3191654bb3e2801fa9dd2364e2acb25561923613717b615f", "tools/supplemental_acceptance.py": "c88fc39de1be1fdcacdd819e2ad329f60367b2df1d5deda80b37324bda3f2a01", "tools/sync_sources.py": "b51e889b0f41f9f63bfb19a09fb96d3777693d6b1d76fe0132bdd2a15e155898", "tools/validate_community_pr.py": "796b896dfade07b4529af2088a4b9b9d23484148b3bc0732b3fb837b75c9844b", "tools/verify_official_assessment_mapping.py": "daeb448a016940d5b6b1285979a56e5b9014bd91db40acb131445e4a83a23059", "tools/verify_task_package.py": "9e1e6105f6b5e4e78b36aa57f00117a9fbc8948ab53983c32ab56da88d23ccc4", "profiles/agents.json": "af9c492c08d13b3044aa6b6952589ed6a0a07d5258d8ff72bb18185b3eaebdc5", "profiles/ai-exam-execution-policy.json": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "profiles/bsl-analyzer-0.3.2-macos.json": "83537abdbf38c41ce665e4d0f24128bb51b62e971e0e0f368695f1326a7d2ffb", "profiles/bsl-analyzer-0.3.2-portable.json": "d6ba732e6778e256df34d6bc548593128820a70430c35b279796843606ee40a8", "profiles/bsl-ls-1.1.0-rc.6-macos.json": "245fc10747197e6911b2b4c77cdb15e6fa4eb7bc7c3758b63e768c5adf1df180", "profiles/bsl-ls-1.1.0-rc.6-portable.json": "9f10660881f2ec84794f7d584556b8f75c7e14b3555464af0ed0e60c4c892d86", "profiles/code-index-1.9.0-macos.json": "63a919523ce62ecec274f4c139bc7ad49a75dd4c339568b822cbc695b4e30408", "profiles/code-index-1.9.0-portable.json": "81106cee8f424ffd8a9dc46ecd8e4f57598fc1d49661a83c77b1f0507993fbdc", "profiles/codex-probe-plan.json": "166e41aad5fb3b27d9050bc6de952c6cba363cc6e804d4080568cc71a2a4d289", "profiles/machine.linux.example.json": "408304fd0581098d5d8110dc67dfeab353bc4d4030e32d37e6acf98d2b1aedfd", "profiles/machine.macos.example.json": "52e9f9d17797cb520b9d8955d6806fd550b899bed4da241ebf096dcb6a21a942", "profiles/machine.windows.example.json": "63accac9a2f81d47d03447efbabffd4760aee325193f02f46b9b29a28d50d2d8", "profiles/mcp-toolkit-1.9.0-macos.json": "1d3f9cde5ffa20589a840d01fdae03aa0fc2f412c929f064f203919c4129625b", "profiles/mcp-toolkit-1.9.0-portable.json": "8e370eebe773eef0e08045ee9c6d5be1451f769f65be0710834b262a4336e054", "profiles/none-macos.json": "b1401d9c48159aed3559006c7f6ace6ef4571224d5cf0bb76d1a823505a10056", "profiles/none-portable.json": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "profiles/rlm-tools-bsl-1.43.0-macos.json": "9354421052640ab60bc3e6aa98ff2e7ba9ca2318b0f4026c137487449242cbd2", "profiles/rlm-tools-bsl-1.43.0-portable.json": "2599e5645e0a7d4e44cb2934bc2b272cae79a9bf7ea74a23cd48aacea64bc424", "profiles/rlm-tools-bsl-1.43.0-posix-requirements.txt": "4fdf9a1bd994bf0272e65d231daf76cf19b0a34dad0ae6b50ec4f11a2ce4c330", "profiles/rlm-tools-bsl-1.43.0-windows-requirements.txt": "3730cb46c81cda5181ecd4485e98b11933104632358bc86f8c0eb1a612a8954f", "profiles/shirokov-skills-macos.json": "84f3e89091676884a802035c707e912762a1179425fb8e3faff25be736873cdb", "profiles/shirokov-skills-portable.json": "2b0a461e06602f1456410e70f02ceaa5ac32c6549c486660bcb5ace0c2f87b15", "profiles/shirokov-skills-windows-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/unica-0.12.3-macos.json": "2c39fbb591cf2c2c6e056373823615485397ea83651b7926c6f25a5fe6a0aae6", "profiles/unica-0.13.0-macos.json": "b76b5c8a4dd33f571c4a90993f1a2da5f7223b4f0f8e1042c282e21a66121052", "profiles/unica-0.14.0-rc.1-portable.json": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "rules/1c-specialist-platform/chistov.json": "77e04942f8c947b10759e7cc1eb31af05847d1711a772fbe6f23d525766757a9", "rules/1c-specialist-platform/decisions.json": "f622107423ce3c188c063318d7ab4f7718ceb38e443130677d8987f386641c09", "rules/1c-specialist-platform/examiner.json": "30353aa2a1b6545496b070d9066e9ffba0c3779e5b53ef70a4fd2cee375b18c0", "rules/1c-specialist-platform/ledger.json": "f167c10db2b5799dd9a1ea6a37cd2d7d186810dadf5ea2f50f26ae723c676882", "rules/1c-specialist-platform/rules.json": "1d320a4f8e1bf4701496388931f492315549bd3dce574b17285dd1d7f8652007", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" } } }, "conditions": { "client": "codex", "model": "gpt-6.1-sol", "client_version": "0.163.0-alpha.11.2", "reasoning_effort": "medium", "harness": "none", "billing_channel": "subscription", "solve_timeout_seconds": 18000, "time_series": "exam", "delegation": "native_disabled", "network_profile": "open-book_shell", "deadline_disclosed": true, "statement_sha256": "8a6ccb3e673826d1f8220fda53eb310e3ec18c136d87ce8f4cebb2a08614e7e5", "starter_dt_sha256": "f40d084818b0d1cfe503fc7653a6a13f1a8e47fcd1688dad6245b12744eb4638", "profile_sha256": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "execution_policy_sha256": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "calibration_sha256": "e8981744a194aa56f954d2965aa66cd53cd4f899f09fa7b5abda6f6b27a5ed65", "started_at": "2026-10-25T03:17:39.538679+00:00", "timing": { "prepare_ms": 10344, "solve_ms": 4332015, "grade_ms": null }, "original_submission_valid": true, "model_provenance": "requested_only", "tokens": { "input": 20696020, "cached_input": 20405120, "fresh_input": 290900, "output": 150829, "reasoning_output": 59665, "total": 20846849, "coverage": "reported_completed_root_turns" }, "tools": { "mcp_calls": 0, "unica_calls": 0, "failed_calls": 0 }, "process": { "status": "completed", "exit_code": 0, "stop_confirmed": true } }, "verification": "repository_owner", "download": "community-downloads/demo-20261025T113419Z-de9981--owner-2026-10-26T223317840149-0000/solution.zip", "source_context": "community-downloads/demo-20261025T113419Z-de9981--owner-2026-10-26T223317840149-0000/source-context.json", "regrade_required": [], "grader_revision_sha256": "9aee1ffe0e1d04f9158fbbbeed3a403a5f0550ad8a590d7a6394977590760e1a", "archive_sha256": "ddd48edc586cee4bd37a9c74be192931d5551df11ec513c4d01ea2ab4bfce334", "owner_verification": { "kind": "repository_owner", "repository": "zeegin/1c-agent-exam-benchmark", "operator": { "name": "Ingvar Vilkman", "github": "zeegin" }, "started_at": "2026-10-26T22:33:17.685124+00:00", "server": { "name": "Owner Windows stand", "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "hardware": { "cpu": "AMD Ryzen 7 5800X 8-Core Processor ", "logical_cpus": 4, "ram_bytes": 17109000192 }, "isolation": "dedicated-host" }, "platform_version": "8.3.27.2342", "grader": { "profile": "technical-v8", "commit": "e15c8ea80263c0b38baa3a1fc19611983270e8a7", "working_tree_dirty": false, "fingerprint": { "assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "calibrate.py": "aac127e03744907fd52ef149b88aa6d88a54a2b7497d56084484ee1b99e0da99", "calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "calibration_periodicity.py": "0b1953d7781e236467897cd2ed66705b75d9719353a2de60b36f2bbdfe799108", "calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "calibration_query.py": "3555b103cde8ea0519955cf52358d09223f5ab183a9df00533bdb48c89237a8c", "claude.py": "5bae98af6e2021e2718afa3a71ed04bee812deaae31a43d4e7324814139ccc82", "codescan.py": "6d8375210cef1fd768fc2d98d630d880b2993a9724f01ae25f33b4ea5aa9631d", "codex.py": "904e75503cd35f16cbb052f66806b3879fe25bfc9f99e33b93c889d862c46324", "common.py": "739b39e2bb9bdd4a571fc69df5843190cddcad094ef7e68964061bc1266b20dc", "docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "examiner.py": "8cdffcdd52f043c905f896697403380af95bf485dd4a5edca24f7956e7795ffe", "forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "harness.py": "3cbb90fd3187e700b5df32e5daafb20313d49bb5721c826e3033cbc6aa6e3825", "interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "ou.py": "f62784b54a3f85576a078a2ff1908c9395f3159e55f6bb5b1a3c564392241abe", "penalties.py": "ae388cb8953ecca1f2370a7c4cb1db3b6cc8318fc2a7563a4db15f9f5b057429", "platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "pr.py": "2b6bfea0634703469605ce114f9274716b485852d9a55d9185c39893b14e4726", "preflight.py": "448c3120ab64b625abae3891be686c7a214ce4211f7cf651fd90e12c0b298433", "process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "queries.py": "1ef57e292db3e8967a733948371ecc542f743b811890d4fc509df17303b9c4ac", "queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "querytypes.py": "b645f489a2abc27762b4a9bbf4917e72f7b46dc053a74c0dca4a8fc46491b3ef", "replay_calibration.py": "e0e3d5ca6416934715b9735aa516046b8d19ad4ae690220eeacd96b198a5f86c", "runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "smoke_check.py": "7837e980986bcb54dc8bc1dfb5d0003deef11e05f6e11df3910fa509e1f74c8d", "stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "submission.py": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tasks/1c-platform-official-sample/checks.json": "7447a9b42d3e348d29d07f001cfb6bd269acd953b7117eba7cca2ce9f5a9a60d", "tasks/1c-platform-official-sample/private/official-assessment-mapping.json": "303587c0dabe77c1eeebb2017fe85539e3370b17c9090435e6e0325a66bd0644", "tasks/1c-platform-official-sample/private/owner-scoring-policy.json": "d26d534bb838ab1b5facb7bc033ca8ec40912133baadcdbad83b27fc577905f5", "starters/carcass-8.3.25.1445/starter.json": "0f7a7060885ba99a19402bfc6e63cc8fe979b0f491b040d3a01d5d21b304b3a6", "rules/1c-specialist-platform/rules.json": "ea75e34ace5de11ba3de403c63cd2c026db81d1d991f8531e4a779d4ce9788e7", "rules/1c-specialist-platform/examiner.json": "1247486ddd412d600db88d9c1db4ba501fc1994afd1dc2ebe85402fcc332f4c8", "rules/1c-specialist-platform/chistov.json": "800da27601a3f1c7ec1df64482fd4ad035e559ba0b390a274ed5031128487d3d", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" }, "sha256": "9aee1ffe0e1d04f9158fbbbeed3a403a5f0550ad8a590d7a6394977590760e1a" }, "method": "saved_platform_observations", "outcome": "complete", "completed_at": "2026-10-26T22:33:17.840149+00:00" }, "previous_evaluations": [ { "id": "demo-20261025T113419Z-de9981--owner-2026-10-26T214355535165-0000", "run_id": "demo-20261025T031725Z-2076a5", "result": { "run_id": "demo-20261025T031725Z-2076a5", "created_at": "2026-10-26T21:43:55.535165+00:00", "model": "gpt-6.1-sol", "harness": "none", "solve_seconds": 4332, "platform": "8.3.27.1644", "counts": { "pass": 62, "inconclusive": 2, "fail": 1 }, "rules": [ { "id": "BU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU01.selected_fixture" }, { "id": "BU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU04.selected_fixture" }, { "id": "BU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU05.selected_fixture" }, { "id": "BU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU16.selected_fixture" }, { "id": "BU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU17.selected_fixture" }, { "id": "BU02", "verdict": "pass", "reason": null, "coverage": "partial", "assertion_id": "BU02.posting_cost_and_balance" }, { "id": "BU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU10.selected_fixture" }, { "id": "BU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU12.selected_fixture" }, { "id": "BU03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU03.selected_fixture" }, { "id": "BU06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU06.selected_fixture" }, { "id": "BU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU07.selected_fixture" }, { "id": "BU08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU08.selected_fixture" }, { "id": "BU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU09.selected_fixture" }, { "id": "BU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU11.selected_fixture" }, { "id": "BU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU14.selected_fixture" }, { "id": "BU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU15.selected_fixture" }, { "id": "BU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU13.selected_fixture" }, { "id": "OU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU15.selected_fixture" }, { "id": "OU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU16.selected_fixture" }, { "id": "OU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU17.selected_fixture" }, { "id": "OU02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU02.selected_fixture" }, { "id": "OU18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU18.selected_fixture" }, { "id": "OU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU14.selected_fixture" }, { "id": "OU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU01.selected_fixture" }, { "id": "OU03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU03.selected_fixture" }, { "id": "OU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU05.selected_fixture" }, { "id": "OU06", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "OU06.selected_fixture" }, { "id": "OU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU07.selected_fixture" }, { "id": "OU08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU08.selected_fixture" }, { "id": "OU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU09.selected_fixture" }, { "id": "OU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU10.selected_fixture" }, { "id": "OU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU11.selected_fixture" }, { "id": "OU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU12.selected_fixture" }, { "id": "OU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU13.selected_fixture" }, { "id": "OU04", "verdict": "inconclusive", "reason": "Required observations unavailable: characteristic values could not be written: {'value_P1': '{ОбщийМодуль.BenchmarkObserver.Модуль(108)}: Ошибка при установке значения атрибута контекста (Владелец): Справочник не имеет владельца'", "coverage": "selected_fixture", "assertion_id": "OU04.selected_fixture" }, { "id": "OU19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU19.selected_fixture" }, { "id": "OU20", "verdict": "inconclusive", "reason": "Required observations unavailable: characteristic values could not be written: {'value_P1': '{ОбщийМодуль.BenchmarkObserver.Модуль(108)}: Ошибка при установке значения атрибута контекста (Владелец): Справочник не имеет владельца'", "coverage": "selected_fixture", "assertion_id": "OU20.selected_fixture" }, { "id": "OU21", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU21.selected_fixture" }, { "id": "PR01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR01.selected_fixture" }, { "id": "PR02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR02.selected_fixture" }, { "id": "PR03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR03.selected_fixture" }, { "id": "PR04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR04.selected_fixture" }, { "id": "PR05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR05.selected_fixture" }, { "id": "PR06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR06.selected_fixture" }, { "id": "PR07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR07.selected_fixture" }, { "id": "PR08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR08.selected_fixture" }, { "id": "PR09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR09.selected_fixture" }, { "id": "PR10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR10.selected_fixture" }, { "id": "PR11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR11.selected_fixture" }, { "id": "PR12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR12.selected_fixture" }, { "id": "PR13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR13.selected_fixture" }, { "id": "PR14", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "PR14.selected_fixture" }, { "id": "PR15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR15.selected_fixture" }, { "id": "PR16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR16.selected_fixture" }, { "id": "PR17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR17.selected_fixture" }, { "id": "PR18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR18.selected_fixture" }, { "id": "PR19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR19.selected_fixture" }, { "id": "F01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F01.selected_fixture" }, { "id": "F02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F02.selected_fixture" }, { "id": "F03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F03.selected_fixture" }, { "id": "F04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F04.selected_fixture" }, { "id": "F05", "verdict": "fail", "reason": "typed ['C1', 'C2'], written True, stored [('BENCH_Валюта', ''), ('BENCH_Срок', '')]", "coverage": "selected_fixture", "assertion_id": "F05.selected_fixture" }, { "id": "G01", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G01.static_sources" }, { "id": "G02", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G02.static_sources" }, { "id": "G03", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G03.static_sources" } ], "charges": [ { "id": "F1C-GEN01", "points": "0.5", "reason": "не выполнено требование: F05 — typed ['C1', 'C2'], written True, stored [('BENCH_Валюта', ''), ('BENCH_Срок', '')]" } ], "score_upper_bound": "4.5", "score": null, "grade": null, "deductions": "0.5", "not_assessed": 18, "gates": { "starter_origin": "passed", "load": "loaded", "clients": "compiles", "demo_data": "present" }, "infrastructure_errors": false, "comparison_eligible": false, "binding_compatibility": null }, "measurement": { "operator": { "name": "Вячеслав", "github": "sksibak" }, "environment": { "captured_at": "2026-10-25T03:17:28.597378+00:00", "capture_timing": "before_run", "hardware": { "cpu": "AMD Ryzen 5 4600H with Radeon Graphics ", "logical_cpus": 12, "ram_bytes": 16505962496 }, "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "python": "3.12.14", "platform_version": "8.3.27.1644", "isolation": "dedicated-host", "network_profile": "open-book_shell", "unsafe_action_protection_observed_in_user_config": true, "git_revision": "af85e791b303dbbf0b0b7af924d2489c3e57cfa8", "implementation_files": { "exam_bench/__init__.py": "ad5bf6f05dc6765f40b78bd186870ca2c49be113cfa33f8aa76f4926f2cb2c1e", "exam_bench/assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "exam_bench/bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "exam_bench/calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "exam_bench/calibrate.py": "78b5185cb0888c0c0ac3de95ffc3a80154a6de9ae66fc461f79d012e5a58e1db", "exam_bench/calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "exam_bench/calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "exam_bench/calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "exam_bench/calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "exam_bench/calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "exam_bench/claude.py": "bc1b8550de7573aaed5e39c6e9c0309e0d8175284a75490d61ec27439ed911ad", "exam_bench/cli.py": "1a37ce645633d761f7897dffc9c45e6b8b9600cd7bd233b1cbf78f49d26b099a", "exam_bench/codescan.py": "751e38001b6e65727a31e28172a0623f0bf34bc092a958037c286aa991a197ed", "exam_bench/codex.py": "c3f89d72af11f312d851c73a1610d92e79acadf336be9ccedd1f94ede3b3ccb0", "exam_bench/common.py": "8682603b519063e655eae3574a02a49efee63bde21f582ccee20ddd623fca96d", "exam_bench/docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "exam_bench/examiner.py": "d7294fdd23ed1732216cafebf0a8cf2c24cce4259859aeb7149f62b7607d087d", "exam_bench/finalize.py": "4034f1c63896a940afdb1a83d541cf47fc75c8b5061e3f839047109c04beb620", "exam_bench/forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "exam_bench/gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "exam_bench/grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "exam_bench/harness.py": "3040f6daaf1dc6e6583219f4d925151f8ba7851b2d5417d7f14645892b485ddf", "exam_bench/interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "exam_bench/interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "exam_bench/isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "exam_bench/ledger.py": "7e851523580e22d8490e75f9b6026c07f2c355007e0d11d0b252671f56bef654", "exam_bench/locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "exam_bench/materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "exam_bench/mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "exam_bench/observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "exam_bench/ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "exam_bench/penalties.py": "0d79e2e46102657dca00609b6abbfc0bf7d11fad41429564f876c82bc6b33269", "exam_bench/platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "exam_bench/portable.py": "cad56968ff407983608f5bdbc9ce7234128d7a4580b096ecea8e0e7b4edb9070", "exam_bench/portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "exam_bench/pr.py": "6a3a20caf0e10c0cc94410511a72d62c9fcda785f3abab1be2ad616d4ee16836", "exam_bench/preflight.py": "5619be0131d8641925f3ce2a3c8e5234d42aa5635d95676138ca81536d95cd29", "exam_bench/process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "exam_bench/queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "exam_bench/queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "exam_bench/replay_calibration.py": "c150457b0b23ce4e6814eb8deb4d48f6bc4a2e39d8f84a9dc7644fb99a026c2d", "exam_bench/report.py": "5e4c0757e1c7f189953f9a5302593ab726551835856baed25efd93dad6e8bfcd", "exam_bench/runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "exam_bench/smoke_check.py": "f36922a0027429ead0b414048dcc14bbe67f2f0e79a70d03dffbe1447d253545", "exam_bench/stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "exam_bench/submission.py": "d6f9d20704181c51714f1138affe4965d860ae21475ab7bb49aa5c5cefebb9f5", "exam_bench/telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "exam_bench/windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "exam_bench/workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tools/build_public_site.py": "9682ed696f5ac9e9a82b65a45c0dece556ec7e49eeb20dcd616882cc534a8258", "tools/build_result_site.py": "3294e1d2ec1486058e208735264d61e349a68a4ae2fa2ec7a723c70e3263b496", "tools/check_native_harnesses.py": "4f5f0ed27651f78758eaef077b3b114361781f6b95ec40cb46c3fea689210473", "tools/check_native_toolkit.py": "0272794617121f2932828e5e4e9ae20095183c443666cf3ba466b44fbe875095", "tools/community_results.py": "9db56a44697d94f326efcbd7a3ae1aecdb569d43bba6c47e80ce525dc045f1f7", "tools/community_service.py": "c374480dbd88d656c0b9054fa04a8e1c6698c69e2f9cf475e82498a2dff61d84", "tools/community_setup.py": "5d7d126ed7d4dd48e1d79f57b99647a92ffcc8c9f80d90915e458888cdd76bf7", "tools/compare_harness_runs.py": "f274df5f3f804cb02504491aec946943833e12fbce6e62d281e12beb8508fc4e", "tools/create_run_plan.py": "871cd81b1eda231c0fba8805f63d2668926be9fc641559e6ddf320e2f47cd37a", "tools/demo_runner.py": "230e6e49068f2bab3a0db64e6da5889e8f1834158fed8c5ec334b7694695a87b", "tools/installers.py": "9a2742780936b17500869e7c89202c1a2549e37d53a42ad9a50a0abbf78bbe09", "tools/machine_bundle.py": "8aa8346f99f537e81ceca6fb6ab9530e844954bab8eff87bf33d3602f81f8a30", "tools/prepare_native_harnesses.py": "aaa75ecf4022883984fa50c42d14d8e1a9fde2eeda03dab03b852bbc5efb2502", "tools/prepare_official_statement.py": "6b7028c78e90e798d6ef1a93b76520cc61a308c354fb9b87f7fad18b99800fad", "tools/prepare_open_exam_requirements.py": "544f4e378b9be5f166186f8788f8d454afdac2deb99d91d98421e39d01ba6d03", "tools/probe_harness.py": "1ed8ef93420d1484cbbfd151b7efc31b9a201ceb942dd05e3103efa22ffa7f27", "tools/probe_native_mcp.py": "9918d324129cba898993e07f8f8b6dbcbaf369398ebf28d464f9f1f00abdb254", "tools/readiness.py": "d34dd3f38334f51cc4574c79194cf0b80769b062a52382989a57d01c46b9aba4", "tools/recheck_community.py": "f0843d7d677f90da31e22bde0b1c86584dd46c022f1532d43d042619e426b230", "tools/regrade_runs.py": "011775afb06d3aac67a4aa81117a368c75896b0fcbe1e6f27ccc6237612fbf59", "tools/render_statement_text.py": "dabc0716a3612c288c671bc20e17fd4986691d732768e1e957d6dddddbea92a3", "tools/replay_calibration.py": "801f5004926c438c21ed3668fe2a4ddf45312b3e75320165a3839aae034eee9b", "tools/run_exam_campaign.py": "2c450d57a1cd0a2682838f5ec7c0a4ffb3aed0f1730d34c408e912d59cab6efd", "tools/serve_result_site.py": "86badfac863cd4ad1fc894a14110c75b28470513f0133eeae9d2799b8b4df3a9", "tools/start_demo.py": "c597e6cad28d245b3191654bb3e2801fa9dd2364e2acb25561923613717b615f", "tools/supplemental_acceptance.py": "c88fc39de1be1fdcacdd819e2ad329f60367b2df1d5deda80b37324bda3f2a01", "tools/sync_sources.py": "b51e889b0f41f9f63bfb19a09fb96d3777693d6b1d76fe0132bdd2a15e155898", "tools/validate_community_pr.py": "796b896dfade07b4529af2088a4b9b9d23484148b3bc0732b3fb837b75c9844b", "tools/verify_official_assessment_mapping.py": "daeb448a016940d5b6b1285979a56e5b9014bd91db40acb131445e4a83a23059", "tools/verify_task_package.py": "9e1e6105f6b5e4e78b36aa57f00117a9fbc8948ab53983c32ab56da88d23ccc4", "profiles/agents.json": "af9c492c08d13b3044aa6b6952589ed6a0a07d5258d8ff72bb18185b3eaebdc5", "profiles/ai-exam-execution-policy.json": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "profiles/bsl-analyzer-0.3.2-macos.json": "83537abdbf38c41ce665e4d0f24128bb51b62e971e0e0f368695f1326a7d2ffb", "profiles/bsl-analyzer-0.3.2-portable.json": "d6ba732e6778e256df34d6bc548593128820a70430c35b279796843606ee40a8", "profiles/bsl-ls-1.1.0-rc.6-macos.json": "245fc10747197e6911b2b4c77cdb15e6fa4eb7bc7c3758b63e768c5adf1df180", "profiles/bsl-ls-1.1.0-rc.6-portable.json": "9f10660881f2ec84794f7d584556b8f75c7e14b3555464af0ed0e60c4c892d86", "profiles/code-index-1.9.0-macos.json": "63a919523ce62ecec274f4c139bc7ad49a75dd4c339568b822cbc695b4e30408", "profiles/code-index-1.9.0-portable.json": "81106cee8f424ffd8a9dc46ecd8e4f57598fc1d49661a83c77b1f0507993fbdc", "profiles/codex-probe-plan.json": "166e41aad5fb3b27d9050bc6de952c6cba363cc6e804d4080568cc71a2a4d289", "profiles/machine.linux.example.json": "408304fd0581098d5d8110dc67dfeab353bc4d4030e32d37e6acf98d2b1aedfd", "profiles/machine.macos.example.json": "52e9f9d17797cb520b9d8955d6806fd550b899bed4da241ebf096dcb6a21a942", "profiles/machine.windows.example.json": "63accac9a2f81d47d03447efbabffd4760aee325193f02f46b9b29a28d50d2d8", "profiles/mcp-toolkit-1.9.0-macos.json": "1d3f9cde5ffa20589a840d01fdae03aa0fc2f412c929f064f203919c4129625b", "profiles/mcp-toolkit-1.9.0-portable.json": "8e370eebe773eef0e08045ee9c6d5be1451f769f65be0710834b262a4336e054", "profiles/none-macos.json": "b1401d9c48159aed3559006c7f6ace6ef4571224d5cf0bb76d1a823505a10056", "profiles/none-portable.json": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "profiles/rlm-tools-bsl-1.43.0-macos.json": "9354421052640ab60bc3e6aa98ff2e7ba9ca2318b0f4026c137487449242cbd2", "profiles/rlm-tools-bsl-1.43.0-portable.json": "2599e5645e0a7d4e44cb2934bc2b272cae79a9bf7ea74a23cd48aacea64bc424", "profiles/rlm-tools-bsl-1.43.0-posix-requirements.txt": "4fdf9a1bd994bf0272e65d231daf76cf19b0a34dad0ae6b50ec4f11a2ce4c330", "profiles/rlm-tools-bsl-1.43.0-windows-requirements.txt": "3730cb46c81cda5181ecd4485e98b11933104632358bc86f8c0eb1a612a8954f", "profiles/shirokov-skills-macos.json": "84f3e89091676884a802035c707e912762a1179425fb8e3faff25be736873cdb", "profiles/shirokov-skills-portable.json": "2b0a461e06602f1456410e70f02ceaa5ac32c6549c486660bcb5ace0c2f87b15", "profiles/shirokov-skills-windows-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/unica-0.12.3-macos.json": "2c39fbb591cf2c2c6e056373823615485397ea83651b7926c6f25a5fe6a0aae6", "profiles/unica-0.13.0-macos.json": "b76b5c8a4dd33f571c4a90993f1a2da5f7223b4f0f8e1042c282e21a66121052", "profiles/unica-0.14.0-rc.1-portable.json": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "rules/1c-specialist-platform/chistov.json": "77e04942f8c947b10759e7cc1eb31af05847d1711a772fbe6f23d525766757a9", "rules/1c-specialist-platform/decisions.json": "f622107423ce3c188c063318d7ab4f7718ceb38e443130677d8987f386641c09", "rules/1c-specialist-platform/examiner.json": "30353aa2a1b6545496b070d9066e9ffba0c3779e5b53ef70a4fd2cee375b18c0", "rules/1c-specialist-platform/ledger.json": "f167c10db2b5799dd9a1ea6a37cd2d7d186810dadf5ea2f50f26ae723c676882", "rules/1c-specialist-platform/rules.json": "1d320a4f8e1bf4701496388931f492315549bd3dce574b17285dd1d7f8652007", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" } } }, "conditions": { "client": "codex", "model": "gpt-6.1-sol", "client_version": "0.163.0-alpha.11.2", "reasoning_effort": "medium", "harness": "none", "billing_channel": "subscription", "solve_timeout_seconds": 18000, "time_series": "exam", "delegation": "native_disabled", "network_profile": "open-book_shell", "deadline_disclosed": true, "statement_sha256": "8a6ccb3e673826d1f8220fda53eb310e3ec18c136d87ce8f4cebb2a08614e7e5", "starter_dt_sha256": "f40d084818b0d1cfe503fc7653a6a13f1a8e47fcd1688dad6245b12744eb4638", "profile_sha256": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "execution_policy_sha256": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "calibration_sha256": "e8981744a194aa56f954d2965aa66cd53cd4f899f09fa7b5abda6f6b27a5ed65", "started_at": "2026-10-25T03:17:39.538679+00:00", "timing": { "prepare_ms": 10344, "solve_ms": 4332015, "grade_ms": null }, "original_submission_valid": true, "model_provenance": "requested_only", "tokens": { "input": 20696020, "cached_input": 20405120, "fresh_input": 290900, "output": 150829, "reasoning_output": 59665, "total": 20846849, "coverage": "reported_completed_root_turns" }, "tools": { "mcp_calls": 0, "unica_calls": 0, "failed_calls": 0 }, "process": { "status": "completed", "exit_code": 0, "stop_confirmed": true } }, "verification": "repository_owner", "download": "community-downloads/demo-20261025T113419Z-de9981--owner-2026-10-26T214355535165-0000/solution.zip", "source_context": "community-downloads/demo-20261025T113419Z-de9981--owner-2026-10-26T214355535165-0000/source-context.json", "regrade_required": [ { "id": "grader_changed", "files": [ "calibrate.py", "calibration_periodicity.py", "common.py", "ou.py", "replay_calibration.py", "smoke_check.py", "tasks/1c-platform-official-sample/checks.json" ] } ], "grader_revision_sha256": "349d87e0c7f531acbe35dd2b39c35722d8a877fedde97575b49e8466ab763c1d", "archive_sha256": "c95733deeb80440bd9acb65aca63f11762f891bf9f503455d42b35b9348a98fd", "owner_verification": { "kind": "repository_owner", "repository": "zeegin/1c-agent-exam-benchmark", "operator": { "name": "Ingvar Vilkman", "github": "zeegin" }, "started_at": "2026-10-26T21:43:55.373367+00:00", "server": { "name": "Owner Windows stand", "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "hardware": { "cpu": "AMD Ryzen 7 5800X 8-Core Processor ", "logical_cpus": 4, "ram_bytes": 17109000192 }, "isolation": "dedicated-host" }, "platform_version": "8.3.27.2342", "grader": { "profile": "technical-v8", "commit": "e8fd8ced03a85b549c5472fbbda29225749f54d1", "working_tree_dirty": false, "fingerprint": { "assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "calibrate.py": "3162d431f3cab5e7976aa39f665d6286dce45499cf362d85109b7123fa8403a2", "calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "calibration_query.py": "3555b103cde8ea0519955cf52358d09223f5ab183a9df00533bdb48c89237a8c", "claude.py": "eedabc75fca0faa434f40a1624b71419ec7dc22e2854a0886cf84b4911db8372", "codescan.py": "6d8375210cef1fd768fc2d98d630d880b2993a9724f01ae25f33b4ea5aa9631d", "codex.py": "904e75503cd35f16cbb052f66806b3879fe25bfc9f99e33b93c889d862c46324", "common.py": "52825cf5c29f3536d6e046a89e789d5ef9c83aacd7f2f5a07f4f53e77b5229cc", "docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "examiner.py": "8cdffcdd52f043c905f896697403380af95bf485dd4a5edca24f7956e7795ffe", "forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "harness.py": "3cbb90fd3187e700b5df32e5daafb20313d49bb5721c826e3033cbc6aa6e3825", "interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "penalties.py": "ae388cb8953ecca1f2370a7c4cb1db3b6cc8318fc2a7563a4db15f9f5b057429", "platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "pr.py": "2b6bfea0634703469605ce114f9274716b485852d9a55d9185c39893b14e4726", "preflight.py": "448c3120ab64b625abae3891be686c7a214ce4211f7cf651fd90e12c0b298433", "process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "queries.py": "1ef57e292db3e8967a733948371ecc542f743b811890d4fc509df17303b9c4ac", "queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "querytypes.py": "b645f489a2abc27762b4a9bbf4917e72f7b46dc053a74c0dca4a8fc46491b3ef", "replay_calibration.py": "0a4d9b84a9908944c5a945878eb6f5eeda5a4e42ffff4f55c04a680742803d80", "runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "smoke_check.py": "66caf1a01f7aa18432293abe3567ac228ac837a660b08c3dc7bb093f7bd51628", "stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "submission.py": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tasks/1c-platform-official-sample/checks.json": "17a6fcc0c14410829650623eb1443ce99796e000cdfd19905ac0287988b73a00", "tasks/1c-platform-official-sample/private/official-assessment-mapping.json": "303587c0dabe77c1eeebb2017fe85539e3370b17c9090435e6e0325a66bd0644", "tasks/1c-platform-official-sample/private/owner-scoring-policy.json": "d26d534bb838ab1b5facb7bc033ca8ec40912133baadcdbad83b27fc577905f5", "starters/carcass-8.3.25.1445/starter.json": "0f7a7060885ba99a19402bfc6e63cc8fe979b0f491b040d3a01d5d21b304b3a6", "rules/1c-specialist-platform/rules.json": "ea75e34ace5de11ba3de403c63cd2c026db81d1d991f8531e4a779d4ce9788e7", "rules/1c-specialist-platform/examiner.json": "1247486ddd412d600db88d9c1db4ba501fc1994afd1dc2ebe85402fcc332f4c8", "rules/1c-specialist-platform/chistov.json": "800da27601a3f1c7ec1df64482fd4ad035e559ba0b390a274ed5031128487d3d", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" }, "sha256": "349d87e0c7f531acbe35dd2b39c35722d8a877fedde97575b49e8466ab763c1d" }, "method": "saved_platform_observations", "outcome": "complete", "completed_at": "2026-10-26T21:43:55.535165+00:00" } }, { "id": "demo-20261025T113419Z-de9981--owner-2026-10-26T190442981999-0000", "run_id": "demo-20261025T031725Z-2076a5", "result": { "run_id": "demo-20261025T031725Z-2076a5", "created_at": "2026-10-26T19:04:42.981999+00:00", "model": "gpt-6.1-sol", "harness": "none", "solve_seconds": 4332, "platform": "8.3.27.1644", "counts": { "pass": 62, "inconclusive": 2, "fail": 1 }, "rules": [ { "id": "BU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU01.selected_fixture" }, { "id": "BU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU04.selected_fixture" }, { "id": "BU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU05.selected_fixture" }, { "id": "BU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU16.selected_fixture" }, { "id": "BU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU17.selected_fixture" }, { "id": "BU02", "verdict": "pass", "reason": null, "coverage": "partial", "assertion_id": "BU02.posting_cost_and_balance" }, { "id": "BU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU10.selected_fixture" }, { "id": "BU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU12.selected_fixture" }, { "id": "BU03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU03.selected_fixture" }, { "id": "BU06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU06.selected_fixture" }, { "id": "BU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU07.selected_fixture" }, { "id": "BU08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU08.selected_fixture" }, { "id": "BU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU09.selected_fixture" }, { "id": "BU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU11.selected_fixture" }, { "id": "BU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU14.selected_fixture" }, { "id": "BU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU15.selected_fixture" }, { "id": "BU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU13.selected_fixture" }, { "id": "OU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU15.selected_fixture" }, { "id": "OU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU16.selected_fixture" }, { "id": "OU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU17.selected_fixture" }, { "id": "OU02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU02.selected_fixture" }, { "id": "OU18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU18.selected_fixture" }, { "id": "OU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU14.selected_fixture" }, { "id": "OU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU01.selected_fixture" }, { "id": "OU03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU03.selected_fixture" }, { "id": "OU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU05.selected_fixture" }, { "id": "OU06", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "OU06.selected_fixture" }, { "id": "OU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU07.selected_fixture" }, { "id": "OU08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU08.selected_fixture" }, { "id": "OU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU09.selected_fixture" }, { "id": "OU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU10.selected_fixture" }, { "id": "OU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU11.selected_fixture" }, { "id": "OU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU12.selected_fixture" }, { "id": "OU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU13.selected_fixture" }, { "id": "OU04", "verdict": "inconclusive", "reason": "Required observations unavailable: characteristic values could not be written: {'value_P1': '{ОбщийМодуль.BenchmarkObserver.Модуль(108)}: Ошибка при установке значения атрибута контекста (Владелец): Справочник не имеет владельца'", "coverage": "selected_fixture", "assertion_id": "OU04.selected_fixture" }, { "id": "OU19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU19.selected_fixture" }, { "id": "OU20", "verdict": "inconclusive", "reason": "Required observations unavailable: characteristic values could not be written: {'value_P1': '{ОбщийМодуль.BenchmarkObserver.Модуль(108)}: Ошибка при установке значения атрибута контекста (Владелец): Справочник не имеет владельца'", "coverage": "selected_fixture", "assertion_id": "OU20.selected_fixture" }, { "id": "OU21", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU21.selected_fixture" }, { "id": "PR01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR01.selected_fixture" }, { "id": "PR02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR02.selected_fixture" }, { "id": "PR03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR03.selected_fixture" }, { "id": "PR04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR04.selected_fixture" }, { "id": "PR05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR05.selected_fixture" }, { "id": "PR06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR06.selected_fixture" }, { "id": "PR07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR07.selected_fixture" }, { "id": "PR08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR08.selected_fixture" }, { "id": "PR09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR09.selected_fixture" }, { "id": "PR10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR10.selected_fixture" }, { "id": "PR11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR11.selected_fixture" }, { "id": "PR12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR12.selected_fixture" }, { "id": "PR13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR13.selected_fixture" }, { "id": "PR14", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "PR14.selected_fixture" }, { "id": "PR15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR15.selected_fixture" }, { "id": "PR16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR16.selected_fixture" }, { "id": "PR17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR17.selected_fixture" }, { "id": "PR18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR18.selected_fixture" }, { "id": "PR19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR19.selected_fixture" }, { "id": "F01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F01.selected_fixture" }, { "id": "F02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F02.selected_fixture" }, { "id": "F03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F03.selected_fixture" }, { "id": "F04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F04.selected_fixture" }, { "id": "F05", "verdict": "fail", "reason": "typed ['C1', 'C2'], written True, stored [('BENCH_Валюта', ''), ('BENCH_Срок', '')]", "coverage": "selected_fixture", "assertion_id": "F05.selected_fixture" }, { "id": "G01", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G01.static_sources" }, { "id": "G02", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G02.static_sources" }, { "id": "G03", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G03.static_sources" } ], "charges": [ { "id": "F1C-GEN01", "points": "0.5", "reason": "не выполнено требование: F05 — typed ['C1', 'C2'], written True, stored [('BENCH_Валюта', ''), ('BENCH_Срок', '')]" }, { "id": "F1C-GEN12", "points": "0.25", "reason": "текст запроса не разбирается платформой: CommonModules/РасчетыСервер/Ext/Module.bsl:48 — Поле не найдено \"Сотрудник\"" } ], "score_upper_bound": "4.25", "score": null, "grade": null, "deductions": "0.75", "not_assessed": 17, "gates": { "starter_origin": "passed", "load": "loaded", "clients": "compiles", "demo_data": "present" }, "infrastructure_errors": false, "comparison_eligible": false, "binding_compatibility": null }, "measurement": { "operator": { "name": "Вячеслав", "github": "sksibak" }, "environment": { "captured_at": "2026-10-25T03:17:28.597378+00:00", "capture_timing": "before_run", "hardware": { "cpu": "AMD Ryzen 5 4600H with Radeon Graphics ", "logical_cpus": 12, "ram_bytes": 16505962496 }, "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "python": "3.12.14", "platform_version": "8.3.27.1644", "isolation": "dedicated-host", "network_profile": "open-book_shell", "unsafe_action_protection_observed_in_user_config": true, "git_revision": "af85e791b303dbbf0b0b7af924d2489c3e57cfa8", "implementation_files": { "exam_bench/__init__.py": "ad5bf6f05dc6765f40b78bd186870ca2c49be113cfa33f8aa76f4926f2cb2c1e", "exam_bench/assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "exam_bench/bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "exam_bench/calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "exam_bench/calibrate.py": "78b5185cb0888c0c0ac3de95ffc3a80154a6de9ae66fc461f79d012e5a58e1db", "exam_bench/calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "exam_bench/calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "exam_bench/calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "exam_bench/calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "exam_bench/calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "exam_bench/claude.py": "bc1b8550de7573aaed5e39c6e9c0309e0d8175284a75490d61ec27439ed911ad", "exam_bench/cli.py": "1a37ce645633d761f7897dffc9c45e6b8b9600cd7bd233b1cbf78f49d26b099a", "exam_bench/codescan.py": "751e38001b6e65727a31e28172a0623f0bf34bc092a958037c286aa991a197ed", "exam_bench/codex.py": "c3f89d72af11f312d851c73a1610d92e79acadf336be9ccedd1f94ede3b3ccb0", "exam_bench/common.py": "8682603b519063e655eae3574a02a49efee63bde21f582ccee20ddd623fca96d", "exam_bench/docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "exam_bench/examiner.py": "d7294fdd23ed1732216cafebf0a8cf2c24cce4259859aeb7149f62b7607d087d", "exam_bench/finalize.py": "4034f1c63896a940afdb1a83d541cf47fc75c8b5061e3f839047109c04beb620", "exam_bench/forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "exam_bench/gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "exam_bench/grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "exam_bench/harness.py": "3040f6daaf1dc6e6583219f4d925151f8ba7851b2d5417d7f14645892b485ddf", "exam_bench/interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "exam_bench/interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "exam_bench/isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "exam_bench/ledger.py": "7e851523580e22d8490e75f9b6026c07f2c355007e0d11d0b252671f56bef654", "exam_bench/locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "exam_bench/materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "exam_bench/mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "exam_bench/observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "exam_bench/ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "exam_bench/penalties.py": "0d79e2e46102657dca00609b6abbfc0bf7d11fad41429564f876c82bc6b33269", "exam_bench/platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "exam_bench/portable.py": "cad56968ff407983608f5bdbc9ce7234128d7a4580b096ecea8e0e7b4edb9070", "exam_bench/portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "exam_bench/pr.py": "6a3a20caf0e10c0cc94410511a72d62c9fcda785f3abab1be2ad616d4ee16836", "exam_bench/preflight.py": "5619be0131d8641925f3ce2a3c8e5234d42aa5635d95676138ca81536d95cd29", "exam_bench/process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "exam_bench/queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "exam_bench/queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "exam_bench/replay_calibration.py": "c150457b0b23ce4e6814eb8deb4d48f6bc4a2e39d8f84a9dc7644fb99a026c2d", "exam_bench/report.py": "5e4c0757e1c7f189953f9a5302593ab726551835856baed25efd93dad6e8bfcd", "exam_bench/runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "exam_bench/smoke_check.py": "f36922a0027429ead0b414048dcc14bbe67f2f0e79a70d03dffbe1447d253545", "exam_bench/stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "exam_bench/submission.py": "d6f9d20704181c51714f1138affe4965d860ae21475ab7bb49aa5c5cefebb9f5", "exam_bench/telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "exam_bench/windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "exam_bench/workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tools/build_public_site.py": "9682ed696f5ac9e9a82b65a45c0dece556ec7e49eeb20dcd616882cc534a8258", "tools/build_result_site.py": "3294e1d2ec1486058e208735264d61e349a68a4ae2fa2ec7a723c70e3263b496", "tools/check_native_harnesses.py": "4f5f0ed27651f78758eaef077b3b114361781f6b95ec40cb46c3fea689210473", "tools/check_native_toolkit.py": "0272794617121f2932828e5e4e9ae20095183c443666cf3ba466b44fbe875095", "tools/community_results.py": "9db56a44697d94f326efcbd7a3ae1aecdb569d43bba6c47e80ce525dc045f1f7", "tools/community_service.py": "c374480dbd88d656c0b9054fa04a8e1c6698c69e2f9cf475e82498a2dff61d84", "tools/community_setup.py": "5d7d126ed7d4dd48e1d79f57b99647a92ffcc8c9f80d90915e458888cdd76bf7", "tools/compare_harness_runs.py": "f274df5f3f804cb02504491aec946943833e12fbce6e62d281e12beb8508fc4e", "tools/create_run_plan.py": "871cd81b1eda231c0fba8805f63d2668926be9fc641559e6ddf320e2f47cd37a", "tools/demo_runner.py": "230e6e49068f2bab3a0db64e6da5889e8f1834158fed8c5ec334b7694695a87b", "tools/installers.py": "9a2742780936b17500869e7c89202c1a2549e37d53a42ad9a50a0abbf78bbe09", "tools/machine_bundle.py": "8aa8346f99f537e81ceca6fb6ab9530e844954bab8eff87bf33d3602f81f8a30", "tools/prepare_native_harnesses.py": "aaa75ecf4022883984fa50c42d14d8e1a9fde2eeda03dab03b852bbc5efb2502", "tools/prepare_official_statement.py": "6b7028c78e90e798d6ef1a93b76520cc61a308c354fb9b87f7fad18b99800fad", "tools/prepare_open_exam_requirements.py": "544f4e378b9be5f166186f8788f8d454afdac2deb99d91d98421e39d01ba6d03", "tools/probe_harness.py": "1ed8ef93420d1484cbbfd151b7efc31b9a201ceb942dd05e3103efa22ffa7f27", "tools/probe_native_mcp.py": "9918d324129cba898993e07f8f8b6dbcbaf369398ebf28d464f9f1f00abdb254", "tools/readiness.py": "d34dd3f38334f51cc4574c79194cf0b80769b062a52382989a57d01c46b9aba4", "tools/recheck_community.py": "f0843d7d677f90da31e22bde0b1c86584dd46c022f1532d43d042619e426b230", "tools/regrade_runs.py": "011775afb06d3aac67a4aa81117a368c75896b0fcbe1e6f27ccc6237612fbf59", "tools/render_statement_text.py": "dabc0716a3612c288c671bc20e17fd4986691d732768e1e957d6dddddbea92a3", "tools/replay_calibration.py": "801f5004926c438c21ed3668fe2a4ddf45312b3e75320165a3839aae034eee9b", "tools/run_exam_campaign.py": "2c450d57a1cd0a2682838f5ec7c0a4ffb3aed0f1730d34c408e912d59cab6efd", "tools/serve_result_site.py": "86badfac863cd4ad1fc894a14110c75b28470513f0133eeae9d2799b8b4df3a9", "tools/start_demo.py": "c597e6cad28d245b3191654bb3e2801fa9dd2364e2acb25561923613717b615f", "tools/supplemental_acceptance.py": "c88fc39de1be1fdcacdd819e2ad329f60367b2df1d5deda80b37324bda3f2a01", "tools/sync_sources.py": "b51e889b0f41f9f63bfb19a09fb96d3777693d6b1d76fe0132bdd2a15e155898", "tools/validate_community_pr.py": "796b896dfade07b4529af2088a4b9b9d23484148b3bc0732b3fb837b75c9844b", "tools/verify_official_assessment_mapping.py": "daeb448a016940d5b6b1285979a56e5b9014bd91db40acb131445e4a83a23059", "tools/verify_task_package.py": "9e1e6105f6b5e4e78b36aa57f00117a9fbc8948ab53983c32ab56da88d23ccc4", "profiles/agents.json": "af9c492c08d13b3044aa6b6952589ed6a0a07d5258d8ff72bb18185b3eaebdc5", "profiles/ai-exam-execution-policy.json": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "profiles/bsl-analyzer-0.3.2-macos.json": "83537abdbf38c41ce665e4d0f24128bb51b62e971e0e0f368695f1326a7d2ffb", "profiles/bsl-analyzer-0.3.2-portable.json": "d6ba732e6778e256df34d6bc548593128820a70430c35b279796843606ee40a8", "profiles/bsl-ls-1.1.0-rc.6-macos.json": "245fc10747197e6911b2b4c77cdb15e6fa4eb7bc7c3758b63e768c5adf1df180", "profiles/bsl-ls-1.1.0-rc.6-portable.json": "9f10660881f2ec84794f7d584556b8f75c7e14b3555464af0ed0e60c4c892d86", "profiles/code-index-1.9.0-macos.json": "63a919523ce62ecec274f4c139bc7ad49a75dd4c339568b822cbc695b4e30408", "profiles/code-index-1.9.0-portable.json": "81106cee8f424ffd8a9dc46ecd8e4f57598fc1d49661a83c77b1f0507993fbdc", "profiles/codex-probe-plan.json": "166e41aad5fb3b27d9050bc6de952c6cba363cc6e804d4080568cc71a2a4d289", "profiles/machine.linux.example.json": "408304fd0581098d5d8110dc67dfeab353bc4d4030e32d37e6acf98d2b1aedfd", "profiles/machine.macos.example.json": "52e9f9d17797cb520b9d8955d6806fd550b899bed4da241ebf096dcb6a21a942", "profiles/machine.windows.example.json": "63accac9a2f81d47d03447efbabffd4760aee325193f02f46b9b29a28d50d2d8", "profiles/mcp-toolkit-1.9.0-macos.json": "1d3f9cde5ffa20589a840d01fdae03aa0fc2f412c929f064f203919c4129625b", "profiles/mcp-toolkit-1.9.0-portable.json": "8e370eebe773eef0e08045ee9c6d5be1451f769f65be0710834b262a4336e054", "profiles/none-macos.json": "b1401d9c48159aed3559006c7f6ace6ef4571224d5cf0bb76d1a823505a10056", "profiles/none-portable.json": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "profiles/rlm-tools-bsl-1.43.0-macos.json": "9354421052640ab60bc3e6aa98ff2e7ba9ca2318b0f4026c137487449242cbd2", "profiles/rlm-tools-bsl-1.43.0-portable.json": "2599e5645e0a7d4e44cb2934bc2b272cae79a9bf7ea74a23cd48aacea64bc424", "profiles/rlm-tools-bsl-1.43.0-posix-requirements.txt": "4fdf9a1bd994bf0272e65d231daf76cf19b0a34dad0ae6b50ec4f11a2ce4c330", "profiles/rlm-tools-bsl-1.43.0-windows-requirements.txt": "3730cb46c81cda5181ecd4485e98b11933104632358bc86f8c0eb1a612a8954f", "profiles/shirokov-skills-macos.json": "84f3e89091676884a802035c707e912762a1179425fb8e3faff25be736873cdb", "profiles/shirokov-skills-portable.json": "2b0a461e06602f1456410e70f02ceaa5ac32c6549c486660bcb5ace0c2f87b15", "profiles/shirokov-skills-windows-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/unica-0.12.3-macos.json": "2c39fbb591cf2c2c6e056373823615485397ea83651b7926c6f25a5fe6a0aae6", "profiles/unica-0.13.0-macos.json": "b76b5c8a4dd33f571c4a90993f1a2da5f7223b4f0f8e1042c282e21a66121052", "profiles/unica-0.14.0-rc.1-portable.json": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "rules/1c-specialist-platform/chistov.json": "77e04942f8c947b10759e7cc1eb31af05847d1711a772fbe6f23d525766757a9", "rules/1c-specialist-platform/decisions.json": "f622107423ce3c188c063318d7ab4f7718ceb38e443130677d8987f386641c09", "rules/1c-specialist-platform/examiner.json": "30353aa2a1b6545496b070d9066e9ffba0c3779e5b53ef70a4fd2cee375b18c0", "rules/1c-specialist-platform/ledger.json": "f167c10db2b5799dd9a1ea6a37cd2d7d186810dadf5ea2f50f26ae723c676882", "rules/1c-specialist-platform/rules.json": "1d320a4f8e1bf4701496388931f492315549bd3dce574b17285dd1d7f8652007", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" } } }, "conditions": { "client": "codex", "model": "gpt-6.1-sol", "client_version": "0.163.0-alpha.11.2", "reasoning_effort": "medium", "harness": "none", "billing_channel": "subscription", "solve_timeout_seconds": 18000, "time_series": "exam", "delegation": "native_disabled", "network_profile": "open-book_shell", "deadline_disclosed": true, "statement_sha256": "8a6ccb3e673826d1f8220fda53eb310e3ec18c136d87ce8f4cebb2a08614e7e5", "starter_dt_sha256": "f40d084818b0d1cfe503fc7653a6a13f1a8e47fcd1688dad6245b12744eb4638", "profile_sha256": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "execution_policy_sha256": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "calibration_sha256": "e8981744a194aa56f954d2965aa66cd53cd4f899f09fa7b5abda6f6b27a5ed65", "started_at": "2026-10-25T03:17:39.538679+00:00", "timing": { "prepare_ms": 10344, "solve_ms": 4332015, "grade_ms": null }, "original_submission_valid": true, "model_provenance": "requested_only", "tokens": { "input": 20696020, "cached_input": 20405120, "fresh_input": 290900, "output": 150829, "reasoning_output": 59665, "total": 20846849, "coverage": "reported_completed_root_turns" }, "tools": { "mcp_calls": 0, "unica_calls": 0, "failed_calls": 0 }, "process": { "status": "completed", "exit_code": 0, "stop_confirmed": true } }, "verification": "repository_owner", "download": "community-downloads/demo-20261025T113419Z-de9981--owner-2026-10-26T190442981999-0000/solution.zip", "source_context": "community-downloads/demo-20261025T113419Z-de9981--owner-2026-10-26T190442981999-0000/source-context.json", "regrade_required": [ { "id": "grader_changed", "files": [ "calibrate.py", "calibration_periodicity.py", "calibration_query.py", "common.py", "ou.py", "penalties.py", "queries.py", "replay_calibration.py", "rules/1c-specialist-platform/rules.json", "smoke_check.py", "tasks/1c-platform-official-sample/checks.json" ] } ], "grader_revision_sha256": "4a12b62d2c10085e1fc710f377f84903abdf2fb787dda19628d944da990a86b2", "archive_sha256": "ae6fa99ddf2fd7ffbf5018a9697376bf4c3c8274a5d9806ab5cfa1558ba07e3a", "owner_verification": { "kind": "repository_owner", "repository": "zeegin/1c-agent-exam-benchmark", "operator": { "name": "Ingvar Vilkman", "github": "zeegin" }, "started_at": "2026-10-26T19:01:54.443328+00:00", "server": { "name": "Owner Windows stand", "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "hardware": { "cpu": "AMD Ryzen 7 5800X 8-Core Processor ", "logical_cpus": 4, "ram_bytes": 17109000192 }, "isolation": "dedicated-host" }, "platform_version": "8.3.27.2342", "grader": { "profile": "technical-v8", "commit": "5b6a28372b253e81e22b83f8559df897297e28ff", "working_tree_dirty": true, "fingerprint": { "assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "calibrate.py": "1c844971b4977fdcc3b30aebe8aad40fbd45e6828955b8deb043ac8573d61731", "calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "claude.py": "eedabc75fca0faa434f40a1624b71419ec7dc22e2854a0886cf84b4911db8372", "codescan.py": "6d8375210cef1fd768fc2d98d630d880b2993a9724f01ae25f33b4ea5aa9631d", "codex.py": "904e75503cd35f16cbb052f66806b3879fe25bfc9f99e33b93c889d862c46324", "common.py": "7696116dd1a796666518b4c5d2aa3cafa04ee974593d3636333cbe5385bd6ccb", "docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "examiner.py": "8cdffcdd52f043c905f896697403380af95bf485dd4a5edca24f7956e7795ffe", "forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "harness.py": "3cbb90fd3187e700b5df32e5daafb20313d49bb5721c826e3033cbc6aa6e3825", "interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "penalties.py": "b82704e7f47d3dfdf6e501452d7e0abca1f9da63307093d2e257e32358be0489", "platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "pr.py": "2b6bfea0634703469605ce114f9274716b485852d9a55d9185c39893b14e4726", "preflight.py": "448c3120ab64b625abae3891be686c7a214ce4211f7cf651fd90e12c0b298433", "process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "querytypes.py": "b645f489a2abc27762b4a9bbf4917e72f7b46dc053a74c0dca4a8fc46491b3ef", "replay_calibration.py": "3b6f3a289cc8a7f5e458f62bfa2c6cc534cc9076ba3f22d1e4bd8a5f9e175317", "runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "smoke_check.py": "bd6266367e6b769a95258eb383239b89a22deae406d64f6e142c77396f4639ba", "stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "submission.py": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tasks/1c-platform-official-sample/checks.json": "17a6fcc0c14410829650623eb1443ce99796e000cdfd19905ac0287988b73a00", "tasks/1c-platform-official-sample/private/official-assessment-mapping.json": "303587c0dabe77c1eeebb2017fe85539e3370b17c9090435e6e0325a66bd0644", "tasks/1c-platform-official-sample/private/owner-scoring-policy.json": "d26d534bb838ab1b5facb7bc033ca8ec40912133baadcdbad83b27fc577905f5", "starters/carcass-8.3.25.1445/starter.json": "0f7a7060885ba99a19402bfc6e63cc8fe979b0f491b040d3a01d5d21b304b3a6", "rules/1c-specialist-platform/rules.json": "7ec895a7751ef17f4a50cc80b5f7fa986e1e04360ab0b4ce9aa29115195df03c", "rules/1c-specialist-platform/examiner.json": "1247486ddd412d600db88d9c1db4ba501fc1994afd1dc2ebe85402fcc332f4c8", "rules/1c-specialist-platform/chistov.json": "800da27601a3f1c7ec1df64482fd4ad035e559ba0b390a274ed5031128487d3d", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" }, "sha256": "4a12b62d2c10085e1fc710f377f84903abdf2fb787dda19628d944da990a86b2" }, "identity_verified_at": "2026-10-26T18:44:22.364471+00:00", "identity_session_sha256": "950670ab9a82059c65525d0d6e5b8a00f0dc292581edea3eb087c4ecadeaab09", "completed_at": "2026-10-26T19:04:42.981999+00:00" } }, { "id": "demo-20261025T113419Z-de9981", "run_id": "demo-20261025T031725Z-2076a5", "result": { "run_id": "demo-20261025T031725Z-2076a5", "created_at": "2026-10-25T11:38:15.265796+00:00", "model": "gpt-6.1-sol", "harness": "none", "solve_seconds": 4332, "platform": "8.3.27.1644", "counts": { "pass": 62, "inconclusive": 2, "fail": 1 }, "rules": [ { "id": "BU01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU16", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU17", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU02", "verdict": "pass", "coverage": "partial", "reason": null }, { "id": "BU10", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU12", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU06", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU07", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU08", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU09", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU11", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU14", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU15", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU13", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU15", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU16", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU17", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU02", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU18", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU14", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU06", "verdict": "pass", "coverage": "no_violation_found", "reason": null }, { "id": "OU07", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU08", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU09", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU10", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU11", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU12", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU13", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU04", "verdict": "inconclusive", "coverage": "selected_fixture", "reason": null }, { "id": "OU19", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU20", "verdict": "inconclusive", "coverage": "selected_fixture", "reason": null }, { "id": "OU21", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR02", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR06", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR07", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR08", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR09", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR10", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR11", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR12", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR13", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR14", "verdict": "pass", "coverage": "no_violation_found", "reason": null }, { "id": "PR15", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR16", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR17", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR18", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR19", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F02", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F05", "verdict": "fail", "coverage": "selected_fixture", "reason": null }, { "id": "G01", "verdict": "pass", "coverage": "static_sources", "reason": null }, { "id": "G02", "verdict": "pass", "coverage": "static_sources", "reason": null }, { "id": "G03", "verdict": "pass", "coverage": "static_sources", "reason": null } ], "charges": [ { "id": "F1C-GEN01", "points": "0.5", "reason": "не выполнено требование: F05 — typed ['C1', 'C2'], written True, stored [('BENCH_Валюта', ''), ('BENCH_Срок', '')]" }, { "id": "F1C-GEN12", "points": "0.25", "reason": "текст запроса не разбирается платформой: CommonModules/РасчетыСервер/Ext/Module.bsl:48 — Поле не найдено \"Сотрудник\"" }, { "id": "F1C-GEN20", "points": "2.0", "reason": "данные базы читаются в цикле по записям: CommonModules/УчетСервер/Ext/Module.bsl:131; CommonModules/УчетСервер/Ext/Module.bsl:133; CommonModules/УчетСервер/Ext/Module.bsl:143 и ещё 1" } ], "score_upper_bound": "2.25", "score": null, "grade": null, "deductions": "2.75", "not_assessed": 16, "gates": { "starter_origin": "passed", "load": "loaded", "clients": "compiles", "demo_data": "present" }, "infrastructure_errors": false, "comparison_eligible": false, "binding_compatibility": null, "evaluation_sha256": "ff51b035f138c261676ca0542e207e2a950b404e9f8a79df35e662708289d075", "downloads": [] }, "measurement": { "operator": { "name": "Вячеслав", "github": "sksibak" }, "environment": { "captured_at": "2026-10-25T03:17:28.597378+00:00", "capture_timing": "before_run", "hardware": { "cpu": "AMD Ryzen 5 4600H with Radeon Graphics ", "logical_cpus": 12, "ram_bytes": 16505962496 }, "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "python": "3.12.14", "platform_version": "8.3.27.1644", "isolation": "dedicated-host", "network_profile": "open-book_shell", "unsafe_action_protection_observed_in_user_config": true, "git_revision": "af85e791b303dbbf0b0b7af924d2489c3e57cfa8", "implementation_files": { "exam_bench/__init__.py": "ad5bf6f05dc6765f40b78bd186870ca2c49be113cfa33f8aa76f4926f2cb2c1e", "exam_bench/assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "exam_bench/bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "exam_bench/calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "exam_bench/calibrate.py": "78b5185cb0888c0c0ac3de95ffc3a80154a6de9ae66fc461f79d012e5a58e1db", "exam_bench/calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "exam_bench/calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "exam_bench/calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "exam_bench/calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "exam_bench/calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "exam_bench/claude.py": "bc1b8550de7573aaed5e39c6e9c0309e0d8175284a75490d61ec27439ed911ad", "exam_bench/cli.py": "1a37ce645633d761f7897dffc9c45e6b8b9600cd7bd233b1cbf78f49d26b099a", "exam_bench/codescan.py": "751e38001b6e65727a31e28172a0623f0bf34bc092a958037c286aa991a197ed", "exam_bench/codex.py": "c3f89d72af11f312d851c73a1610d92e79acadf336be9ccedd1f94ede3b3ccb0", "exam_bench/common.py": "8682603b519063e655eae3574a02a49efee63bde21f582ccee20ddd623fca96d", "exam_bench/docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "exam_bench/examiner.py": "d7294fdd23ed1732216cafebf0a8cf2c24cce4259859aeb7149f62b7607d087d", "exam_bench/finalize.py": "4034f1c63896a940afdb1a83d541cf47fc75c8b5061e3f839047109c04beb620", "exam_bench/forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "exam_bench/gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "exam_bench/grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "exam_bench/harness.py": "3040f6daaf1dc6e6583219f4d925151f8ba7851b2d5417d7f14645892b485ddf", "exam_bench/interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "exam_bench/interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "exam_bench/isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "exam_bench/ledger.py": "7e851523580e22d8490e75f9b6026c07f2c355007e0d11d0b252671f56bef654", "exam_bench/locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "exam_bench/materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "exam_bench/mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "exam_bench/observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "exam_bench/ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "exam_bench/penalties.py": "0d79e2e46102657dca00609b6abbfc0bf7d11fad41429564f876c82bc6b33269", "exam_bench/platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "exam_bench/portable.py": "cad56968ff407983608f5bdbc9ce7234128d7a4580b096ecea8e0e7b4edb9070", "exam_bench/portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "exam_bench/pr.py": "6a3a20caf0e10c0cc94410511a72d62c9fcda785f3abab1be2ad616d4ee16836", "exam_bench/preflight.py": "5619be0131d8641925f3ce2a3c8e5234d42aa5635d95676138ca81536d95cd29", "exam_bench/process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "exam_bench/queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "exam_bench/queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "exam_bench/replay_calibration.py": "c150457b0b23ce4e6814eb8deb4d48f6bc4a2e39d8f84a9dc7644fb99a026c2d", "exam_bench/report.py": "5e4c0757e1c7f189953f9a5302593ab726551835856baed25efd93dad6e8bfcd", "exam_bench/runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "exam_bench/smoke_check.py": "f36922a0027429ead0b414048dcc14bbe67f2f0e79a70d03dffbe1447d253545", "exam_bench/stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "exam_bench/submission.py": "d6f9d20704181c51714f1138affe4965d860ae21475ab7bb49aa5c5cefebb9f5", "exam_bench/telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "exam_bench/windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "exam_bench/workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tools/build_public_site.py": "9682ed696f5ac9e9a82b65a45c0dece556ec7e49eeb20dcd616882cc534a8258", "tools/build_result_site.py": "3294e1d2ec1486058e208735264d61e349a68a4ae2fa2ec7a723c70e3263b496", "tools/check_native_harnesses.py": "4f5f0ed27651f78758eaef077b3b114361781f6b95ec40cb46c3fea689210473", "tools/check_native_toolkit.py": "0272794617121f2932828e5e4e9ae20095183c443666cf3ba466b44fbe875095", "tools/community_results.py": "9db56a44697d94f326efcbd7a3ae1aecdb569d43bba6c47e80ce525dc045f1f7", "tools/community_service.py": "c374480dbd88d656c0b9054fa04a8e1c6698c69e2f9cf475e82498a2dff61d84", "tools/community_setup.py": "5d7d126ed7d4dd48e1d79f57b99647a92ffcc8c9f80d90915e458888cdd76bf7", "tools/compare_harness_runs.py": "f274df5f3f804cb02504491aec946943833e12fbce6e62d281e12beb8508fc4e", "tools/create_run_plan.py": "871cd81b1eda231c0fba8805f63d2668926be9fc641559e6ddf320e2f47cd37a", "tools/demo_runner.py": "230e6e49068f2bab3a0db64e6da5889e8f1834158fed8c5ec334b7694695a87b", "tools/installers.py": "9a2742780936b17500869e7c89202c1a2549e37d53a42ad9a50a0abbf78bbe09", "tools/machine_bundle.py": "8aa8346f99f537e81ceca6fb6ab9530e844954bab8eff87bf33d3602f81f8a30", "tools/prepare_native_harnesses.py": "aaa75ecf4022883984fa50c42d14d8e1a9fde2eeda03dab03b852bbc5efb2502", "tools/prepare_official_statement.py": "6b7028c78e90e798d6ef1a93b76520cc61a308c354fb9b87f7fad18b99800fad", "tools/prepare_open_exam_requirements.py": "544f4e378b9be5f166186f8788f8d454afdac2deb99d91d98421e39d01ba6d03", "tools/probe_harness.py": "1ed8ef93420d1484cbbfd151b7efc31b9a201ceb942dd05e3103efa22ffa7f27", "tools/probe_native_mcp.py": "9918d324129cba898993e07f8f8b6dbcbaf369398ebf28d464f9f1f00abdb254", "tools/readiness.py": "d34dd3f38334f51cc4574c79194cf0b80769b062a52382989a57d01c46b9aba4", "tools/recheck_community.py": "f0843d7d677f90da31e22bde0b1c86584dd46c022f1532d43d042619e426b230", "tools/regrade_runs.py": "011775afb06d3aac67a4aa81117a368c75896b0fcbe1e6f27ccc6237612fbf59", "tools/render_statement_text.py": "dabc0716a3612c288c671bc20e17fd4986691d732768e1e957d6dddddbea92a3", "tools/replay_calibration.py": "801f5004926c438c21ed3668fe2a4ddf45312b3e75320165a3839aae034eee9b", "tools/run_exam_campaign.py": "2c450d57a1cd0a2682838f5ec7c0a4ffb3aed0f1730d34c408e912d59cab6efd", "tools/serve_result_site.py": "86badfac863cd4ad1fc894a14110c75b28470513f0133eeae9d2799b8b4df3a9", "tools/start_demo.py": "c597e6cad28d245b3191654bb3e2801fa9dd2364e2acb25561923613717b615f", "tools/supplemental_acceptance.py": "c88fc39de1be1fdcacdd819e2ad329f60367b2df1d5deda80b37324bda3f2a01", "tools/sync_sources.py": "b51e889b0f41f9f63bfb19a09fb96d3777693d6b1d76fe0132bdd2a15e155898", "tools/validate_community_pr.py": "796b896dfade07b4529af2088a4b9b9d23484148b3bc0732b3fb837b75c9844b", "tools/verify_official_assessment_mapping.py": "daeb448a016940d5b6b1285979a56e5b9014bd91db40acb131445e4a83a23059", "tools/verify_task_package.py": "9e1e6105f6b5e4e78b36aa57f00117a9fbc8948ab53983c32ab56da88d23ccc4", "profiles/agents.json": "af9c492c08d13b3044aa6b6952589ed6a0a07d5258d8ff72bb18185b3eaebdc5", "profiles/ai-exam-execution-policy.json": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "profiles/bsl-analyzer-0.3.2-macos.json": "83537abdbf38c41ce665e4d0f24128bb51b62e971e0e0f368695f1326a7d2ffb", "profiles/bsl-analyzer-0.3.2-portable.json": "d6ba732e6778e256df34d6bc548593128820a70430c35b279796843606ee40a8", "profiles/bsl-ls-1.1.0-rc.6-macos.json": "245fc10747197e6911b2b4c77cdb15e6fa4eb7bc7c3758b63e768c5adf1df180", "profiles/bsl-ls-1.1.0-rc.6-portable.json": "9f10660881f2ec84794f7d584556b8f75c7e14b3555464af0ed0e60c4c892d86", "profiles/code-index-1.9.0-macos.json": "63a919523ce62ecec274f4c139bc7ad49a75dd4c339568b822cbc695b4e30408", "profiles/code-index-1.9.0-portable.json": "81106cee8f424ffd8a9dc46ecd8e4f57598fc1d49661a83c77b1f0507993fbdc", "profiles/codex-probe-plan.json": "166e41aad5fb3b27d9050bc6de952c6cba363cc6e804d4080568cc71a2a4d289", "profiles/machine.linux.example.json": "408304fd0581098d5d8110dc67dfeab353bc4d4030e32d37e6acf98d2b1aedfd", "profiles/machine.macos.example.json": "52e9f9d17797cb520b9d8955d6806fd550b899bed4da241ebf096dcb6a21a942", "profiles/machine.windows.example.json": "63accac9a2f81d47d03447efbabffd4760aee325193f02f46b9b29a28d50d2d8", "profiles/mcp-toolkit-1.9.0-macos.json": "1d3f9cde5ffa20589a840d01fdae03aa0fc2f412c929f064f203919c4129625b", "profiles/mcp-toolkit-1.9.0-portable.json": "8e370eebe773eef0e08045ee9c6d5be1451f769f65be0710834b262a4336e054", "profiles/none-macos.json": "b1401d9c48159aed3559006c7f6ace6ef4571224d5cf0bb76d1a823505a10056", "profiles/none-portable.json": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "profiles/rlm-tools-bsl-1.43.0-macos.json": "9354421052640ab60bc3e6aa98ff2e7ba9ca2318b0f4026c137487449242cbd2", "profiles/rlm-tools-bsl-1.43.0-portable.json": "2599e5645e0a7d4e44cb2934bc2b272cae79a9bf7ea74a23cd48aacea64bc424", "profiles/rlm-tools-bsl-1.43.0-posix-requirements.txt": "4fdf9a1bd994bf0272e65d231daf76cf19b0a34dad0ae6b50ec4f11a2ce4c330", "profiles/rlm-tools-bsl-1.43.0-windows-requirements.txt": "3730cb46c81cda5181ecd4485e98b11933104632358bc86f8c0eb1a612a8954f", "profiles/shirokov-skills-macos.json": "84f3e89091676884a802035c707e912762a1179425fb8e3faff25be736873cdb", "profiles/shirokov-skills-portable.json": "2b0a461e06602f1456410e70f02ceaa5ac32c6549c486660bcb5ace0c2f87b15", "profiles/shirokov-skills-windows-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/unica-0.12.3-macos.json": "2c39fbb591cf2c2c6e056373823615485397ea83651b7926c6f25a5fe6a0aae6", "profiles/unica-0.13.0-macos.json": "b76b5c8a4dd33f571c4a90993f1a2da5f7223b4f0f8e1042c282e21a66121052", "profiles/unica-0.14.0-rc.1-portable.json": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "rules/1c-specialist-platform/chistov.json": "77e04942f8c947b10759e7cc1eb31af05847d1711a772fbe6f23d525766757a9", "rules/1c-specialist-platform/decisions.json": "f622107423ce3c188c063318d7ab4f7718ceb38e443130677d8987f386641c09", "rules/1c-specialist-platform/examiner.json": "30353aa2a1b6545496b070d9066e9ffba0c3779e5b53ef70a4fd2cee375b18c0", "rules/1c-specialist-platform/ledger.json": "f167c10db2b5799dd9a1ea6a37cd2d7d186810dadf5ea2f50f26ae723c676882", "rules/1c-specialist-platform/rules.json": "1d320a4f8e1bf4701496388931f492315549bd3dce574b17285dd1d7f8652007", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" } } }, "conditions": { "client": "codex", "model": "gpt-6.1-sol", "client_version": "0.163.0-alpha.11.2", "reasoning_effort": "medium", "harness": "none", "billing_channel": "subscription", "solve_timeout_seconds": 18000, "time_series": "exam", "delegation": "native_disabled", "network_profile": "open-book_shell", "deadline_disclosed": true, "statement_sha256": "8a6ccb3e673826d1f8220fda53eb310e3ec18c136d87ce8f4cebb2a08614e7e5", "starter_dt_sha256": "f40d084818b0d1cfe503fc7653a6a13f1a8e47fcd1688dad6245b12744eb4638", "profile_sha256": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "execution_policy_sha256": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "calibration_sha256": "e8981744a194aa56f954d2965aa66cd53cd4f899f09fa7b5abda6f6b27a5ed65", "started_at": "2026-10-25T03:17:39.538679+00:00", "timing": { "prepare_ms": 10344, "solve_ms": 4332015, "grade_ms": null }, "original_submission_valid": true, "model_provenance": "requested_only", "tokens": { "input": 20696020, "cached_input": 20405120, "fresh_input": 290900, "output": 150829, "reasoning_output": 59665, "total": 20846849, "coverage": "reported_completed_root_turns" }, "tools": { "mcp_calls": 0, "unica_calls": 0, "failed_calls": 0 }, "process": { "status": "completed", "exit_code": 0, "stop_confirmed": true } }, "verification": "contributor_reported", "download": "community-downloads/demo-20261025T113419Z-de9981/solution.zip", "source_context": "community-downloads/demo-20261025T113419Z-de9981/source-context.json", "regrade_required": [ { "id": "grader_changed", "files": [ "assessment.py", "bp.py", "calcwrite.py", "calibrate.py", "calibration_periodicity.py", "calibration_query.py", "claude.py", "codescan.py", "codex.py", "common.py", "docx_text.py", "examiner.py", "harness.py", "interpretations.py", "locking.py", "materials.py", "mcp_toolkit.py", "ou.py", "penalties.py", "portable_harnesses.py", "pr.py", "preflight.py", "queries.py", "queryschema.py", "querytypes.py", "replay_calibration.py", "rules/1c-specialist-platform/chistov.json", "rules/1c-specialist-platform/examiner.json", "rules/1c-specialist-platform/rules.json", "rules/1c-specialist-platform/standards.json", "smoke_check.py", "starters/carcass-8.3.25.1445/starter.json", "stdio_harnesses.py", "tasks/1c-platform-official-sample/checks.json", "tasks/1c-platform-official-sample/private/official-assessment-mapping.json", "tasks/1c-platform-official-sample/private/owner-scoring-policy.json", "telemetry.py" ] } ], "grader_revision_sha256": "855d4f66db31ec9f50ebfc18f596c0d1d157e53e2830c51f853c1338f628e49c", "archive_sha256": "79cc891bd07bccb0b7c0e4e3deae80432b0860a17c1556b2f6a16fd6ffc4a4d4" }, { "id": "demo-20261025T031725Z-2076a5", "run_id": "demo-20261025T031725Z-2076a5", "result": { "run_id": "demo-20261025T031725Z-2076a5", "created_at": "2026-10-25T04:33:39.517381+00:00", "model": "gpt-6.1-sol", "harness": "none", "solve_seconds": 4332, "platform": "8.3.27.1644", "counts": { "pass": 62, "inconclusive": 2, "fail": 1 }, "rules": [ { "id": "BU01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU16", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU17", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU02", "verdict": "pass", "coverage": "partial", "reason": null }, { "id": "BU10", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU12", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU06", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU07", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU08", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU09", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU11", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU14", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU15", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU13", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU15", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU16", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU17", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU02", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU18", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU14", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU06", "verdict": "pass", "coverage": "no_violation_found", "reason": null }, { "id": "OU07", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU08", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU09", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU10", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU11", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU12", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU13", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU04", "verdict": "inconclusive", "coverage": "selected_fixture", "reason": null }, { "id": "OU19", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU20", "verdict": "inconclusive", "coverage": "selected_fixture", "reason": null }, { "id": "OU21", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR02", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR06", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR07", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR08", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR09", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR10", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR11", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR12", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR13", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR14", "verdict": "pass", "coverage": "no_violation_found", "reason": null }, { "id": "PR15", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR16", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR17", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR18", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR19", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F02", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F05", "verdict": "fail", "coverage": "selected_fixture", "reason": null }, { "id": "G01", "verdict": "pass", "coverage": "static_sources", "reason": null }, { "id": "G02", "verdict": "pass", "coverage": "static_sources", "reason": null }, { "id": "G03", "verdict": "pass", "coverage": "static_sources", "reason": null } ], "charges": [ { "id": "F1C-GEN01", "points": "0.5", "reason": "не выполнено требование: F05 — typed ['C1', 'C2'], written True, stored [('BENCH_Валюта', ''), ('BENCH_Срок', '')]" }, { "id": "F1C-GEN12", "points": "0.25", "reason": "текст запроса не разбирается платформой: CommonModules/РасчетыСервер/Ext/Module.bsl:48 — Поле не найдено \"Сотрудник\"" }, { "id": "F1C-GEN20", "points": "2.0", "reason": "данные базы читаются в цикле по записям: CommonModules/УчетСервер/Ext/Module.bsl:131; CommonModules/УчетСервер/Ext/Module.bsl:133; CommonModules/УчетСервер/Ext/Module.bsl:143 и ещё 1" } ], "score_upper_bound": "2.25", "score": null, "grade": null, "deductions": "2.75", "not_assessed": 16, "gates": { "starter_origin": "passed", "load": "loaded", "clients": "compiles", "demo_data": "present" }, "infrastructure_errors": false, "comparison_eligible": false, "binding_compatibility": null, "evaluation_sha256": "77024244f8469fc72d576864a158ef157ceb86fd1e5aac0a4efe719bcc0b6176", "downloads": [] }, "measurement": { "operator": { "name": "Вячеслав", "github": "sksibak" }, "environment": { "captured_at": "2026-10-25T03:17:28.597378+00:00", "capture_timing": "before_run", "hardware": { "cpu": "AMD Ryzen 5 4600H with Radeon Graphics ", "logical_cpus": 12, "ram_bytes": 16505962496 }, "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "python": "3.12.14", "platform_version": "8.3.27.1644", "isolation": "dedicated-host", "network_profile": "open-book_shell", "unsafe_action_protection_observed_in_user_config": true, "git_revision": "af85e791b303dbbf0b0b7af924d2489c3e57cfa8", "implementation_files": { "exam_bench/__init__.py": "ad5bf6f05dc6765f40b78bd186870ca2c49be113cfa33f8aa76f4926f2cb2c1e", "exam_bench/assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "exam_bench/bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "exam_bench/calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "exam_bench/calibrate.py": "78b5185cb0888c0c0ac3de95ffc3a80154a6de9ae66fc461f79d012e5a58e1db", "exam_bench/calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "exam_bench/calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "exam_bench/calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "exam_bench/calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "exam_bench/calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "exam_bench/claude.py": "bc1b8550de7573aaed5e39c6e9c0309e0d8175284a75490d61ec27439ed911ad", "exam_bench/cli.py": "1a37ce645633d761f7897dffc9c45e6b8b9600cd7bd233b1cbf78f49d26b099a", "exam_bench/codescan.py": "751e38001b6e65727a31e28172a0623f0bf34bc092a958037c286aa991a197ed", "exam_bench/codex.py": "c3f89d72af11f312d851c73a1610d92e79acadf336be9ccedd1f94ede3b3ccb0", "exam_bench/common.py": "8682603b519063e655eae3574a02a49efee63bde21f582ccee20ddd623fca96d", "exam_bench/docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "exam_bench/examiner.py": "d7294fdd23ed1732216cafebf0a8cf2c24cce4259859aeb7149f62b7607d087d", "exam_bench/finalize.py": "4034f1c63896a940afdb1a83d541cf47fc75c8b5061e3f839047109c04beb620", "exam_bench/forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "exam_bench/gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "exam_bench/grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "exam_bench/harness.py": "3040f6daaf1dc6e6583219f4d925151f8ba7851b2d5417d7f14645892b485ddf", "exam_bench/interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "exam_bench/interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "exam_bench/isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "exam_bench/ledger.py": "7e851523580e22d8490e75f9b6026c07f2c355007e0d11d0b252671f56bef654", "exam_bench/locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "exam_bench/materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "exam_bench/mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "exam_bench/observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "exam_bench/ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "exam_bench/penalties.py": "0d79e2e46102657dca00609b6abbfc0bf7d11fad41429564f876c82bc6b33269", "exam_bench/platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "exam_bench/portable.py": "cad56968ff407983608f5bdbc9ce7234128d7a4580b096ecea8e0e7b4edb9070", "exam_bench/portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "exam_bench/pr.py": "6a3a20caf0e10c0cc94410511a72d62c9fcda785f3abab1be2ad616d4ee16836", "exam_bench/preflight.py": "5619be0131d8641925f3ce2a3c8e5234d42aa5635d95676138ca81536d95cd29", "exam_bench/process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "exam_bench/queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "exam_bench/queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "exam_bench/replay_calibration.py": "c150457b0b23ce4e6814eb8deb4d48f6bc4a2e39d8f84a9dc7644fb99a026c2d", "exam_bench/report.py": "5e4c0757e1c7f189953f9a5302593ab726551835856baed25efd93dad6e8bfcd", "exam_bench/runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "exam_bench/smoke_check.py": "f36922a0027429ead0b414048dcc14bbe67f2f0e79a70d03dffbe1447d253545", "exam_bench/stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "exam_bench/submission.py": "d6f9d20704181c51714f1138affe4965d860ae21475ab7bb49aa5c5cefebb9f5", "exam_bench/telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "exam_bench/windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "exam_bench/workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tools/build_public_site.py": "9682ed696f5ac9e9a82b65a45c0dece556ec7e49eeb20dcd616882cc534a8258", "tools/build_result_site.py": "3294e1d2ec1486058e208735264d61e349a68a4ae2fa2ec7a723c70e3263b496", "tools/check_native_harnesses.py": "4f5f0ed27651f78758eaef077b3b114361781f6b95ec40cb46c3fea689210473", "tools/check_native_toolkit.py": "0272794617121f2932828e5e4e9ae20095183c443666cf3ba466b44fbe875095", "tools/community_results.py": "9db56a44697d94f326efcbd7a3ae1aecdb569d43bba6c47e80ce525dc045f1f7", "tools/community_service.py": "c374480dbd88d656c0b9054fa04a8e1c6698c69e2f9cf475e82498a2dff61d84", "tools/community_setup.py": "5d7d126ed7d4dd48e1d79f57b99647a92ffcc8c9f80d90915e458888cdd76bf7", "tools/compare_harness_runs.py": "f274df5f3f804cb02504491aec946943833e12fbce6e62d281e12beb8508fc4e", "tools/create_run_plan.py": "871cd81b1eda231c0fba8805f63d2668926be9fc641559e6ddf320e2f47cd37a", "tools/demo_runner.py": "230e6e49068f2bab3a0db64e6da5889e8f1834158fed8c5ec334b7694695a87b", "tools/installers.py": "9a2742780936b17500869e7c89202c1a2549e37d53a42ad9a50a0abbf78bbe09", "tools/machine_bundle.py": "8aa8346f99f537e81ceca6fb6ab9530e844954bab8eff87bf33d3602f81f8a30", "tools/prepare_native_harnesses.py": "aaa75ecf4022883984fa50c42d14d8e1a9fde2eeda03dab03b852bbc5efb2502", "tools/prepare_official_statement.py": "6b7028c78e90e798d6ef1a93b76520cc61a308c354fb9b87f7fad18b99800fad", "tools/prepare_open_exam_requirements.py": "544f4e378b9be5f166186f8788f8d454afdac2deb99d91d98421e39d01ba6d03", "tools/probe_harness.py": "1ed8ef93420d1484cbbfd151b7efc31b9a201ceb942dd05e3103efa22ffa7f27", "tools/probe_native_mcp.py": "9918d324129cba898993e07f8f8b6dbcbaf369398ebf28d464f9f1f00abdb254", "tools/readiness.py": "d34dd3f38334f51cc4574c79194cf0b80769b062a52382989a57d01c46b9aba4", "tools/recheck_community.py": "f0843d7d677f90da31e22bde0b1c86584dd46c022f1532d43d042619e426b230", "tools/regrade_runs.py": "011775afb06d3aac67a4aa81117a368c75896b0fcbe1e6f27ccc6237612fbf59", "tools/render_statement_text.py": "dabc0716a3612c288c671bc20e17fd4986691d732768e1e957d6dddddbea92a3", "tools/replay_calibration.py": "801f5004926c438c21ed3668fe2a4ddf45312b3e75320165a3839aae034eee9b", "tools/run_exam_campaign.py": "2c450d57a1cd0a2682838f5ec7c0a4ffb3aed0f1730d34c408e912d59cab6efd", "tools/serve_result_site.py": "86badfac863cd4ad1fc894a14110c75b28470513f0133eeae9d2799b8b4df3a9", "tools/start_demo.py": "c597e6cad28d245b3191654bb3e2801fa9dd2364e2acb25561923613717b615f", "tools/supplemental_acceptance.py": "c88fc39de1be1fdcacdd819e2ad329f60367b2df1d5deda80b37324bda3f2a01", "tools/sync_sources.py": "b51e889b0f41f9f63bfb19a09fb96d3777693d6b1d76fe0132bdd2a15e155898", "tools/validate_community_pr.py": "796b896dfade07b4529af2088a4b9b9d23484148b3bc0732b3fb837b75c9844b", "tools/verify_official_assessment_mapping.py": "daeb448a016940d5b6b1285979a56e5b9014bd91db40acb131445e4a83a23059", "tools/verify_task_package.py": "9e1e6105f6b5e4e78b36aa57f00117a9fbc8948ab53983c32ab56da88d23ccc4", "profiles/agents.json": "af9c492c08d13b3044aa6b6952589ed6a0a07d5258d8ff72bb18185b3eaebdc5", "profiles/ai-exam-execution-policy.json": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "profiles/bsl-analyzer-0.3.2-macos.json": "83537abdbf38c41ce665e4d0f24128bb51b62e971e0e0f368695f1326a7d2ffb", "profiles/bsl-analyzer-0.3.2-portable.json": "d6ba732e6778e256df34d6bc548593128820a70430c35b279796843606ee40a8", "profiles/bsl-ls-1.1.0-rc.6-macos.json": "245fc10747197e6911b2b4c77cdb15e6fa4eb7bc7c3758b63e768c5adf1df180", "profiles/bsl-ls-1.1.0-rc.6-portable.json": "9f10660881f2ec84794f7d584556b8f75c7e14b3555464af0ed0e60c4c892d86", "profiles/code-index-1.9.0-macos.json": "63a919523ce62ecec274f4c139bc7ad49a75dd4c339568b822cbc695b4e30408", "profiles/code-index-1.9.0-portable.json": "81106cee8f424ffd8a9dc46ecd8e4f57598fc1d49661a83c77b1f0507993fbdc", "profiles/codex-probe-plan.json": "166e41aad5fb3b27d9050bc6de952c6cba363cc6e804d4080568cc71a2a4d289", "profiles/machine.linux.example.json": "408304fd0581098d5d8110dc67dfeab353bc4d4030e32d37e6acf98d2b1aedfd", "profiles/machine.macos.example.json": "52e9f9d17797cb520b9d8955d6806fd550b899bed4da241ebf096dcb6a21a942", "profiles/machine.windows.example.json": "63accac9a2f81d47d03447efbabffd4760aee325193f02f46b9b29a28d50d2d8", "profiles/mcp-toolkit-1.9.0-macos.json": "1d3f9cde5ffa20589a840d01fdae03aa0fc2f412c929f064f203919c4129625b", "profiles/mcp-toolkit-1.9.0-portable.json": "8e370eebe773eef0e08045ee9c6d5be1451f769f65be0710834b262a4336e054", "profiles/none-macos.json": "b1401d9c48159aed3559006c7f6ace6ef4571224d5cf0bb76d1a823505a10056", "profiles/none-portable.json": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "profiles/rlm-tools-bsl-1.43.0-macos.json": "9354421052640ab60bc3e6aa98ff2e7ba9ca2318b0f4026c137487449242cbd2", "profiles/rlm-tools-bsl-1.43.0-portable.json": "2599e5645e0a7d4e44cb2934bc2b272cae79a9bf7ea74a23cd48aacea64bc424", "profiles/rlm-tools-bsl-1.43.0-posix-requirements.txt": "4fdf9a1bd994bf0272e65d231daf76cf19b0a34dad0ae6b50ec4f11a2ce4c330", "profiles/rlm-tools-bsl-1.43.0-windows-requirements.txt": "3730cb46c81cda5181ecd4485e98b11933104632358bc86f8c0eb1a612a8954f", "profiles/shirokov-skills-macos.json": "84f3e89091676884a802035c707e912762a1179425fb8e3faff25be736873cdb", "profiles/shirokov-skills-portable.json": "2b0a461e06602f1456410e70f02ceaa5ac32c6549c486660bcb5ace0c2f87b15", "profiles/shirokov-skills-windows-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/unica-0.12.3-macos.json": "2c39fbb591cf2c2c6e056373823615485397ea83651b7926c6f25a5fe6a0aae6", "profiles/unica-0.13.0-macos.json": "b76b5c8a4dd33f571c4a90993f1a2da5f7223b4f0f8e1042c282e21a66121052", "profiles/unica-0.14.0-rc.1-portable.json": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "rules/1c-specialist-platform/chistov.json": "77e04942f8c947b10759e7cc1eb31af05847d1711a772fbe6f23d525766757a9", "rules/1c-specialist-platform/decisions.json": "f622107423ce3c188c063318d7ab4f7718ceb38e443130677d8987f386641c09", "rules/1c-specialist-platform/examiner.json": "30353aa2a1b6545496b070d9066e9ffba0c3779e5b53ef70a4fd2cee375b18c0", "rules/1c-specialist-platform/ledger.json": "f167c10db2b5799dd9a1ea6a37cd2d7d186810dadf5ea2f50f26ae723c676882", "rules/1c-specialist-platform/rules.json": "1d320a4f8e1bf4701496388931f492315549bd3dce574b17285dd1d7f8652007", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" } } }, "conditions": { "client": "codex", "model": "gpt-6.1-sol", "client_version": "0.163.0-alpha.11.2", "reasoning_effort": "medium", "harness": "none", "billing_channel": "subscription", "solve_timeout_seconds": 18000, "time_series": "exam", "delegation": "native_disabled", "network_profile": "open-book_shell", "deadline_disclosed": true, "statement_sha256": "8a6ccb3e673826d1f8220fda53eb310e3ec18c136d87ce8f4cebb2a08614e7e5", "starter_dt_sha256": "f40d084818b0d1cfe503fc7653a6a13f1a8e47fcd1688dad6245b12744eb4638", "profile_sha256": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "execution_policy_sha256": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "calibration_sha256": "e8981744a194aa56f954d2965aa66cd53cd4f899f09fa7b5abda6f6b27a5ed65", "started_at": "2026-10-25T03:17:39.538679+00:00", "timing": { "prepare_ms": 10344, "solve_ms": 4332015, "grade_ms": null }, "original_submission_valid": true, "model_provenance": "requested_only", "tokens": { "input": 20696020, "cached_input": 20405120, "fresh_input": 290900, "output": 150829, "reasoning_output": 59665, "total": 20846849, "coverage": "reported_completed_root_turns" }, "tools": { "mcp_calls": 0, "unica_calls": 0, "failed_calls": 0 }, "process": { "status": "completed", "exit_code": 0, "stop_confirmed": true } }, "verification": "contributor_reported", "download": "community-downloads/demo-20261025T031725Z-2076a5/solution.zip", "source_context": "community-downloads/demo-20261025T031725Z-2076a5/source-context.json", "regrade_required": [ { "id": "grader_changed", "files": [ "assessment.py", "bp.py", "calcwrite.py", "calibrate.py", "calibration_periodicity.py", "calibration_query.py", "claude.py", "codescan.py", "codex.py", "common.py", "docx_text.py", "examiner.py", "harness.py", "interpretations.py", "locking.py", "materials.py", "mcp_toolkit.py", "ou.py", "penalties.py", "portable_harnesses.py", "pr.py", "preflight.py", "queries.py", "queryschema.py", "querytypes.py", "replay_calibration.py", "rules/1c-specialist-platform/chistov.json", "rules/1c-specialist-platform/examiner.json", "rules/1c-specialist-platform/rules.json", "rules/1c-specialist-platform/standards.json", "smoke_check.py", "starters/carcass-8.3.25.1445/starter.json", "stdio_harnesses.py", "submission.py", "tasks/1c-platform-official-sample/checks.json", "tasks/1c-platform-official-sample/private/official-assessment-mapping.json", "tasks/1c-platform-official-sample/private/owner-scoring-policy.json", "telemetry.py" ] } ], "grader_revision_sha256": "13710d802a08278385c484500f48f1678e0b002e5c7a3d8c00e14c1e75b1fbe9", "archive_sha256": "440d4f228f443437a0a1f3a8545d5f27c496c5d8943ffc0bbf3a61efd44c8620" } ] }, { "id": "demo-20261025T113819Z-9d209c--owner-2026-10-26T223322513267-0000", "run_id": "demo-20261025T043533Z-b8847b", "result": { "run_id": "demo-20261025T043533Z-b8847b", "created_at": "2026-10-26T22:33:22.513267+00:00", "model": "gpt-6.1-sol", "harness": "unica-0.14.0-rc.1", "solve_seconds": 1750, "platform": "8.3.27.1644", "counts": { "pass": 64, "fail": 1 }, "rules": [ { "id": "BU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU01.selected_fixture" }, { "id": "BU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU04.selected_fixture" }, { "id": "BU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU05.selected_fixture" }, { "id": "BU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU16.selected_fixture" }, { "id": "BU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU17.selected_fixture" }, { "id": "BU02", "verdict": "pass", "reason": null, "coverage": "partial", "assertion_id": "BU02.posting_cost_and_balance" }, { "id": "BU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU10.selected_fixture" }, { "id": "BU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU12.selected_fixture" }, { "id": "BU03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU03.selected_fixture" }, { "id": "BU06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU06.selected_fixture" }, { "id": "BU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU07.selected_fixture" }, { "id": "BU08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU08.selected_fixture" }, { "id": "BU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU09.selected_fixture" }, { "id": "BU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU11.selected_fixture" }, { "id": "BU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU14.selected_fixture" }, { "id": "BU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU15.selected_fixture" }, { "id": "BU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU13.selected_fixture" }, { "id": "OU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU15.selected_fixture" }, { "id": "OU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU16.selected_fixture" }, { "id": "OU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU17.selected_fixture" }, { "id": "OU02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU02.selected_fixture" }, { "id": "OU18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU18.selected_fixture" }, { "id": "OU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU14.selected_fixture" }, { "id": "OU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU01.selected_fixture" }, { "id": "OU03", "verdict": "pass", "reason": "История и годовая периодичность регистра подтверждены.", "coverage": "history_and_periodicity", "assertion_id": "OU03.selected_fixture" }, { "id": "OU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU05.selected_fixture" }, { "id": "OU06", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "OU06.selected_fixture" }, { "id": "OU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU07.selected_fixture" }, { "id": "OU08", "verdict": "pass", "reason": "История и дневная периодичность подтверждены; ограничение одной версии в неделю отдельно не проверяется.", "coverage": "history_and_periodicity", "assertion_id": "OU08.selected_fixture" }, { "id": "OU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU09.selected_fixture" }, { "id": "OU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU10.selected_fixture" }, { "id": "OU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU11.selected_fixture" }, { "id": "OU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU12.selected_fixture" }, { "id": "OU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU13.selected_fixture" }, { "id": "OU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU04.selected_fixture" }, { "id": "OU19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU19.selected_fixture" }, { "id": "OU20", "verdict": "fail", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU20.selected_fixture" }, { "id": "OU21", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU21.selected_fixture" }, { "id": "PR01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR01.selected_fixture" }, { "id": "PR02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR02.selected_fixture" }, { "id": "PR03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR03.selected_fixture" }, { "id": "PR04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR04.selected_fixture" }, { "id": "PR05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR05.selected_fixture" }, { "id": "PR06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR06.selected_fixture" }, { "id": "PR07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR07.selected_fixture" }, { "id": "PR08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR08.selected_fixture" }, { "id": "PR09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR09.selected_fixture" }, { "id": "PR10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR10.selected_fixture" }, { "id": "PR11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR11.selected_fixture" }, { "id": "PR12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR12.selected_fixture" }, { "id": "PR13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR13.selected_fixture" }, { "id": "PR14", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "PR14.selected_fixture" }, { "id": "PR15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR15.selected_fixture" }, { "id": "PR16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR16.selected_fixture" }, { "id": "PR17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR17.selected_fixture" }, { "id": "PR18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR18.selected_fixture" }, { "id": "PR19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR19.selected_fixture" }, { "id": "F01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F01.selected_fixture" }, { "id": "F02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F02.selected_fixture" }, { "id": "F03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F03.selected_fixture" }, { "id": "F04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F04.selected_fixture" }, { "id": "F05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F05.selected_fixture" }, { "id": "G01", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G01.static_sources" }, { "id": "G02", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G02.static_sources" }, { "id": "G03", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G03.static_sources" } ], "charges": [ { "id": "F1C-GEN03", "points": "0.5", "reason": "отчёт не соответствует заданию: OU20" }, { "id": "F1C-GEN15", "points": "0.5", "reason": "CommonModules/УчетСервер/Ext/Module.bsl:41 — РегистрНакопления.ОстаткиНоменклатуры.Остатки: отбор по Подразделение, индексы таблицы начинаются с Номенклатура" }, { "id": "F1C-PR09", "points": "0.5", "reason": "CommonModules/УчетСервер/Ext/Module.bsl:349 — РегистрРасчета.Начисления.БазаНачисления: база получается без отбора по регистратору — по всем записям регистра" }, { "id": "F1C-PR09", "points": "0.5", "reason": "CommonModules/УчетСервер/Ext/Module.bsl:370 — РегистрРасчета.Начисления.БазаНачисления: база получается без отбора по регистратору — по всем записям регистра" }, { "id": "F1C-GEN15", "points": "0.5", "reason": "Reports/Ведомость/Ext/ManagerModule.bsl:2 — РегистрНакопления.ОстаткиНоменклатуры.ОстаткиИОбороты: отбор по Подразделение, индексы таблицы начинаются с Номенклатура" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "проводимые документы в режиме «Записывать модифицированные»: Операция, Сборка" }, { "id": "F1C-BU06", "points": "1.5", "reason": "ресурс Количество без признака учёта — количество ведётся на всех счетах" }, { "id": "F1C-BU05", "points": "0.5", "reason": "аналитика счетов вынесена в измерения регистра бухгалтерии и есть у всех счетов: Номенклатура (Номенклатура), Склад (Склады)" }, { "id": "F1C-PR08", "points": "2.0", "reason": "база берётся из основной таблицы регистра расчёта, БазаНачисления нигде не используется: Documents/НачислениеЗарплаты/Ext/ObjectModule.bsl:6" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "оперативное проведение разрешено у документов с движениями по регистрам расчёта: НачислениеЗарплаты" }, { "id": "F1C-GEN21", "points": "2.0", "reason": "данные графика без отбора по регистратору: CommonModules/УчетСервер/Ext/Module.bsl:316" } ], "score_upper_bound": "-5.5", "score": null, "grade": "unsatisfactory", "deductions": "10.5", "not_assessed": 16, "gates": { "starter_origin": "passed", "load": "loaded", "clients": "compiles", "demo_data": "present" }, "infrastructure_errors": false, "comparison_eligible": false, "binding_compatibility": null }, "measurement": { "operator": { "name": "Вячеслав", "github": "sksibak" }, "environment": { "captured_at": "2026-10-25T04:35:35.871356+00:00", "capture_timing": "before_run", "hardware": { "cpu": "AMD Ryzen 5 4600H with Radeon Graphics ", "logical_cpus": 12, "ram_bytes": 16505962496 }, "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "python": "3.12.14", "platform_version": "8.3.27.1644", "isolation": "dedicated-host", "network_profile": "open-book_shell", "unsafe_action_protection_observed_in_user_config": true, "git_revision": "af85e791b303dbbf0b0b7af924d2489c3e57cfa8", "implementation_files": { "exam_bench/__init__.py": "ad5bf6f05dc6765f40b78bd186870ca2c49be113cfa33f8aa76f4926f2cb2c1e", "exam_bench/assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "exam_bench/bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "exam_bench/calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "exam_bench/calibrate.py": "78b5185cb0888c0c0ac3de95ffc3a80154a6de9ae66fc461f79d012e5a58e1db", "exam_bench/calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "exam_bench/calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "exam_bench/calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "exam_bench/calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "exam_bench/calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "exam_bench/claude.py": "bc1b8550de7573aaed5e39c6e9c0309e0d8175284a75490d61ec27439ed911ad", "exam_bench/cli.py": "1a37ce645633d761f7897dffc9c45e6b8b9600cd7bd233b1cbf78f49d26b099a", "exam_bench/codescan.py": "751e38001b6e65727a31e28172a0623f0bf34bc092a958037c286aa991a197ed", "exam_bench/codex.py": "c3f89d72af11f312d851c73a1610d92e79acadf336be9ccedd1f94ede3b3ccb0", "exam_bench/common.py": "8682603b519063e655eae3574a02a49efee63bde21f582ccee20ddd623fca96d", "exam_bench/docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "exam_bench/examiner.py": "d7294fdd23ed1732216cafebf0a8cf2c24cce4259859aeb7149f62b7607d087d", "exam_bench/finalize.py": "4034f1c63896a940afdb1a83d541cf47fc75c8b5061e3f839047109c04beb620", "exam_bench/forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "exam_bench/gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "exam_bench/grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "exam_bench/harness.py": "3040f6daaf1dc6e6583219f4d925151f8ba7851b2d5417d7f14645892b485ddf", "exam_bench/interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "exam_bench/interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "exam_bench/isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "exam_bench/ledger.py": "7e851523580e22d8490e75f9b6026c07f2c355007e0d11d0b252671f56bef654", "exam_bench/locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "exam_bench/materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "exam_bench/mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "exam_bench/observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "exam_bench/ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "exam_bench/penalties.py": "0d79e2e46102657dca00609b6abbfc0bf7d11fad41429564f876c82bc6b33269", "exam_bench/platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "exam_bench/portable.py": "cad56968ff407983608f5bdbc9ce7234128d7a4580b096ecea8e0e7b4edb9070", "exam_bench/portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "exam_bench/pr.py": "6a3a20caf0e10c0cc94410511a72d62c9fcda785f3abab1be2ad616d4ee16836", "exam_bench/preflight.py": "5619be0131d8641925f3ce2a3c8e5234d42aa5635d95676138ca81536d95cd29", "exam_bench/process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "exam_bench/queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "exam_bench/queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "exam_bench/replay_calibration.py": "c150457b0b23ce4e6814eb8deb4d48f6bc4a2e39d8f84a9dc7644fb99a026c2d", "exam_bench/report.py": "5e4c0757e1c7f189953f9a5302593ab726551835856baed25efd93dad6e8bfcd", "exam_bench/runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "exam_bench/smoke_check.py": "f36922a0027429ead0b414048dcc14bbe67f2f0e79a70d03dffbe1447d253545", "exam_bench/stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "exam_bench/submission.py": "d6f9d20704181c51714f1138affe4965d860ae21475ab7bb49aa5c5cefebb9f5", "exam_bench/telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "exam_bench/windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "exam_bench/workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tools/build_public_site.py": "9682ed696f5ac9e9a82b65a45c0dece556ec7e49eeb20dcd616882cc534a8258", "tools/build_result_site.py": "3294e1d2ec1486058e208735264d61e349a68a4ae2fa2ec7a723c70e3263b496", "tools/check_native_harnesses.py": "4f5f0ed27651f78758eaef077b3b114361781f6b95ec40cb46c3fea689210473", "tools/check_native_toolkit.py": "0272794617121f2932828e5e4e9ae20095183c443666cf3ba466b44fbe875095", "tools/community_results.py": "9db56a44697d94f326efcbd7a3ae1aecdb569d43bba6c47e80ce525dc045f1f7", "tools/community_service.py": "c374480dbd88d656c0b9054fa04a8e1c6698c69e2f9cf475e82498a2dff61d84", "tools/community_setup.py": "5d7d126ed7d4dd48e1d79f57b99647a92ffcc8c9f80d90915e458888cdd76bf7", "tools/compare_harness_runs.py": "f274df5f3f804cb02504491aec946943833e12fbce6e62d281e12beb8508fc4e", "tools/create_run_plan.py": "871cd81b1eda231c0fba8805f63d2668926be9fc641559e6ddf320e2f47cd37a", "tools/demo_runner.py": "230e6e49068f2bab3a0db64e6da5889e8f1834158fed8c5ec334b7694695a87b", "tools/installers.py": "9a2742780936b17500869e7c89202c1a2549e37d53a42ad9a50a0abbf78bbe09", "tools/machine_bundle.py": "8aa8346f99f537e81ceca6fb6ab9530e844954bab8eff87bf33d3602f81f8a30", "tools/prepare_native_harnesses.py": "aaa75ecf4022883984fa50c42d14d8e1a9fde2eeda03dab03b852bbc5efb2502", "tools/prepare_official_statement.py": "6b7028c78e90e798d6ef1a93b76520cc61a308c354fb9b87f7fad18b99800fad", "tools/prepare_open_exam_requirements.py": "544f4e378b9be5f166186f8788f8d454afdac2deb99d91d98421e39d01ba6d03", "tools/probe_harness.py": "1ed8ef93420d1484cbbfd151b7efc31b9a201ceb942dd05e3103efa22ffa7f27", "tools/probe_native_mcp.py": "9918d324129cba898993e07f8f8b6dbcbaf369398ebf28d464f9f1f00abdb254", "tools/readiness.py": "d34dd3f38334f51cc4574c79194cf0b80769b062a52382989a57d01c46b9aba4", "tools/recheck_community.py": "f0843d7d677f90da31e22bde0b1c86584dd46c022f1532d43d042619e426b230", "tools/regrade_runs.py": "011775afb06d3aac67a4aa81117a368c75896b0fcbe1e6f27ccc6237612fbf59", "tools/render_statement_text.py": "dabc0716a3612c288c671bc20e17fd4986691d732768e1e957d6dddddbea92a3", "tools/replay_calibration.py": "801f5004926c438c21ed3668fe2a4ddf45312b3e75320165a3839aae034eee9b", "tools/run_exam_campaign.py": "2c450d57a1cd0a2682838f5ec7c0a4ffb3aed0f1730d34c408e912d59cab6efd", "tools/serve_result_site.py": "86badfac863cd4ad1fc894a14110c75b28470513f0133eeae9d2799b8b4df3a9", "tools/start_demo.py": "c597e6cad28d245b3191654bb3e2801fa9dd2364e2acb25561923613717b615f", "tools/supplemental_acceptance.py": "c88fc39de1be1fdcacdd819e2ad329f60367b2df1d5deda80b37324bda3f2a01", "tools/sync_sources.py": "b51e889b0f41f9f63bfb19a09fb96d3777693d6b1d76fe0132bdd2a15e155898", "tools/validate_community_pr.py": "796b896dfade07b4529af2088a4b9b9d23484148b3bc0732b3fb837b75c9844b", "tools/verify_official_assessment_mapping.py": "daeb448a016940d5b6b1285979a56e5b9014bd91db40acb131445e4a83a23059", "tools/verify_task_package.py": "9e1e6105f6b5e4e78b36aa57f00117a9fbc8948ab53983c32ab56da88d23ccc4", "profiles/agents.json": "af9c492c08d13b3044aa6b6952589ed6a0a07d5258d8ff72bb18185b3eaebdc5", "profiles/ai-exam-execution-policy.json": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "profiles/bsl-analyzer-0.3.2-macos.json": "83537abdbf38c41ce665e4d0f24128bb51b62e971e0e0f368695f1326a7d2ffb", "profiles/bsl-analyzer-0.3.2-portable.json": "d6ba732e6778e256df34d6bc548593128820a70430c35b279796843606ee40a8", "profiles/bsl-ls-1.1.0-rc.6-macos.json": "245fc10747197e6911b2b4c77cdb15e6fa4eb7bc7c3758b63e768c5adf1df180", "profiles/bsl-ls-1.1.0-rc.6-portable.json": "9f10660881f2ec84794f7d584556b8f75c7e14b3555464af0ed0e60c4c892d86", "profiles/code-index-1.9.0-macos.json": "63a919523ce62ecec274f4c139bc7ad49a75dd4c339568b822cbc695b4e30408", "profiles/code-index-1.9.0-portable.json": "81106cee8f424ffd8a9dc46ecd8e4f57598fc1d49661a83c77b1f0507993fbdc", "profiles/codex-probe-plan.json": "166e41aad5fb3b27d9050bc6de952c6cba363cc6e804d4080568cc71a2a4d289", "profiles/machine.linux.example.json": "408304fd0581098d5d8110dc67dfeab353bc4d4030e32d37e6acf98d2b1aedfd", "profiles/machine.macos.example.json": "52e9f9d17797cb520b9d8955d6806fd550b899bed4da241ebf096dcb6a21a942", "profiles/machine.windows.example.json": "63accac9a2f81d47d03447efbabffd4760aee325193f02f46b9b29a28d50d2d8", "profiles/mcp-toolkit-1.9.0-macos.json": "1d3f9cde5ffa20589a840d01fdae03aa0fc2f412c929f064f203919c4129625b", "profiles/mcp-toolkit-1.9.0-portable.json": "8e370eebe773eef0e08045ee9c6d5be1451f769f65be0710834b262a4336e054", "profiles/none-macos.json": "b1401d9c48159aed3559006c7f6ace6ef4571224d5cf0bb76d1a823505a10056", "profiles/none-portable.json": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "profiles/rlm-tools-bsl-1.43.0-macos.json": "9354421052640ab60bc3e6aa98ff2e7ba9ca2318b0f4026c137487449242cbd2", "profiles/rlm-tools-bsl-1.43.0-portable.json": "2599e5645e0a7d4e44cb2934bc2b272cae79a9bf7ea74a23cd48aacea64bc424", "profiles/rlm-tools-bsl-1.43.0-posix-requirements.txt": "4fdf9a1bd994bf0272e65d231daf76cf19b0a34dad0ae6b50ec4f11a2ce4c330", "profiles/rlm-tools-bsl-1.43.0-windows-requirements.txt": "3730cb46c81cda5181ecd4485e98b11933104632358bc86f8c0eb1a612a8954f", "profiles/shirokov-skills-macos.json": "84f3e89091676884a802035c707e912762a1179425fb8e3faff25be736873cdb", "profiles/shirokov-skills-portable.json": "2b0a461e06602f1456410e70f02ceaa5ac32c6549c486660bcb5ace0c2f87b15", "profiles/shirokov-skills-windows-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/unica-0.12.3-macos.json": "2c39fbb591cf2c2c6e056373823615485397ea83651b7926c6f25a5fe6a0aae6", "profiles/unica-0.13.0-macos.json": "b76b5c8a4dd33f571c4a90993f1a2da5f7223b4f0f8e1042c282e21a66121052", "profiles/unica-0.14.0-rc.1-portable.json": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "rules/1c-specialist-platform/chistov.json": "77e04942f8c947b10759e7cc1eb31af05847d1711a772fbe6f23d525766757a9", "rules/1c-specialist-platform/decisions.json": "f622107423ce3c188c063318d7ab4f7718ceb38e443130677d8987f386641c09", "rules/1c-specialist-platform/examiner.json": "30353aa2a1b6545496b070d9066e9ffba0c3779e5b53ef70a4fd2cee375b18c0", "rules/1c-specialist-platform/ledger.json": "f167c10db2b5799dd9a1ea6a37cd2d7d186810dadf5ea2f50f26ae723c676882", "rules/1c-specialist-platform/rules.json": "1d320a4f8e1bf4701496388931f492315549bd3dce574b17285dd1d7f8652007", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" } } }, "conditions": { "client": "codex", "model": "gpt-6.1-sol", "client_version": "0.163.0-alpha.11.2", "reasoning_effort": "medium", "harness": "unica-0.14.0-rc.1", "billing_channel": "subscription", "solve_timeout_seconds": 1800, "time_series": "fast", "delegation": "native_disabled", "network_profile": "open-book_shell", "deadline_disclosed": true, "statement_sha256": "8a6ccb3e673826d1f8220fda53eb310e3ec18c136d87ce8f4cebb2a08614e7e5", "starter_dt_sha256": "f40d084818b0d1cfe503fc7653a6a13f1a8e47fcd1688dad6245b12744eb4638", "profile_sha256": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "execution_policy_sha256": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "calibration_sha256": "e8981744a194aa56f954d2965aa66cd53cd4f899f09fa7b5abda6f6b27a5ed65", "started_at": "2026-10-25T04:35:46.776087+00:00", "timing": { "prepare_ms": 7953, "solve_ms": 1750093, "grade_ms": null }, "original_submission_valid": true, "model_provenance": "requested_only", "tokens": { "input": 15320636, "cached_input": 15152896, "fresh_input": 167740, "output": 69307, "reasoning_output": 16218, "total": 15389943, "coverage": "reported_completed_root_turns" }, "tools": { "mcp_calls": 238, "unica_calls": 238, "failed_calls": 26 }, "process": { "status": "completed", "exit_code": 0, "stop_confirmed": true } }, "verification": "repository_owner", "download": "community-downloads/demo-20261025T113819Z-9d209c--owner-2026-10-26T223322513267-0000/solution.zip", "source_context": "community-downloads/demo-20261025T113819Z-9d209c--owner-2026-10-26T223322513267-0000/source-context.json", "regrade_required": [], "grader_revision_sha256": "9aee1ffe0e1d04f9158fbbbeed3a403a5f0550ad8a590d7a6394977590760e1a", "archive_sha256": "4bb287e18642860317e2aa878df41ff367144ad34f779b14dac6b09cda626f21", "owner_verification": { "kind": "repository_owner", "repository": "zeegin/1c-agent-exam-benchmark", "operator": { "name": "Ingvar Vilkman", "github": "zeegin" }, "started_at": "2026-10-26T22:33:22.357262+00:00", "server": { "name": "Owner Windows stand", "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "hardware": { "cpu": "AMD Ryzen 7 5800X 8-Core Processor ", "logical_cpus": 4, "ram_bytes": 17109000192 }, "isolation": "dedicated-host" }, "platform_version": "8.3.27.2342", "grader": { "profile": "technical-v8", "commit": "e15c8ea80263c0b38baa3a1fc19611983270e8a7", "working_tree_dirty": false, "fingerprint": { "assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "calibrate.py": "aac127e03744907fd52ef149b88aa6d88a54a2b7497d56084484ee1b99e0da99", "calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "calibration_periodicity.py": "0b1953d7781e236467897cd2ed66705b75d9719353a2de60b36f2bbdfe799108", "calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "calibration_query.py": "3555b103cde8ea0519955cf52358d09223f5ab183a9df00533bdb48c89237a8c", "claude.py": "5bae98af6e2021e2718afa3a71ed04bee812deaae31a43d4e7324814139ccc82", "codescan.py": "6d8375210cef1fd768fc2d98d630d880b2993a9724f01ae25f33b4ea5aa9631d", "codex.py": "904e75503cd35f16cbb052f66806b3879fe25bfc9f99e33b93c889d862c46324", "common.py": "739b39e2bb9bdd4a571fc69df5843190cddcad094ef7e68964061bc1266b20dc", "docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "examiner.py": "8cdffcdd52f043c905f896697403380af95bf485dd4a5edca24f7956e7795ffe", "forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "harness.py": "3cbb90fd3187e700b5df32e5daafb20313d49bb5721c826e3033cbc6aa6e3825", "interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "ou.py": "f62784b54a3f85576a078a2ff1908c9395f3159e55f6bb5b1a3c564392241abe", "penalties.py": "ae388cb8953ecca1f2370a7c4cb1db3b6cc8318fc2a7563a4db15f9f5b057429", "platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "pr.py": "2b6bfea0634703469605ce114f9274716b485852d9a55d9185c39893b14e4726", "preflight.py": "448c3120ab64b625abae3891be686c7a214ce4211f7cf651fd90e12c0b298433", "process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "queries.py": "1ef57e292db3e8967a733948371ecc542f743b811890d4fc509df17303b9c4ac", "queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "querytypes.py": "b645f489a2abc27762b4a9bbf4917e72f7b46dc053a74c0dca4a8fc46491b3ef", "replay_calibration.py": "e0e3d5ca6416934715b9735aa516046b8d19ad4ae690220eeacd96b198a5f86c", "runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "smoke_check.py": "7837e980986bcb54dc8bc1dfb5d0003deef11e05f6e11df3910fa509e1f74c8d", "stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "submission.py": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tasks/1c-platform-official-sample/checks.json": "7447a9b42d3e348d29d07f001cfb6bd269acd953b7117eba7cca2ce9f5a9a60d", "tasks/1c-platform-official-sample/private/official-assessment-mapping.json": "303587c0dabe77c1eeebb2017fe85539e3370b17c9090435e6e0325a66bd0644", "tasks/1c-platform-official-sample/private/owner-scoring-policy.json": "d26d534bb838ab1b5facb7bc033ca8ec40912133baadcdbad83b27fc577905f5", "starters/carcass-8.3.25.1445/starter.json": "0f7a7060885ba99a19402bfc6e63cc8fe979b0f491b040d3a01d5d21b304b3a6", "rules/1c-specialist-platform/rules.json": "ea75e34ace5de11ba3de403c63cd2c026db81d1d991f8531e4a779d4ce9788e7", "rules/1c-specialist-platform/examiner.json": "1247486ddd412d600db88d9c1db4ba501fc1994afd1dc2ebe85402fcc332f4c8", "rules/1c-specialist-platform/chistov.json": "800da27601a3f1c7ec1df64482fd4ad035e559ba0b390a274ed5031128487d3d", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" }, "sha256": "9aee1ffe0e1d04f9158fbbbeed3a403a5f0550ad8a590d7a6394977590760e1a" }, "method": "saved_platform_observations", "outcome": "complete", "completed_at": "2026-10-26T22:33:22.513267+00:00" }, "previous_evaluations": [ { "id": "demo-20261025T113819Z-9d209c--owner-2026-10-26T214400531590-0000", "run_id": "demo-20261025T043533Z-b8847b", "result": { "run_id": "demo-20261025T043533Z-b8847b", "created_at": "2026-10-26T21:44:00.531590+00:00", "model": "gpt-6.1-sol", "harness": "unica-0.14.0-rc.1", "solve_seconds": 1750, "platform": "8.3.27.1644", "counts": { "pass": 64, "fail": 1 }, "rules": [ { "id": "BU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU01.selected_fixture" }, { "id": "BU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU04.selected_fixture" }, { "id": "BU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU05.selected_fixture" }, { "id": "BU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU16.selected_fixture" }, { "id": "BU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU17.selected_fixture" }, { "id": "BU02", "verdict": "pass", "reason": null, "coverage": "partial", "assertion_id": "BU02.posting_cost_and_balance" }, { "id": "BU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU10.selected_fixture" }, { "id": "BU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU12.selected_fixture" }, { "id": "BU03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU03.selected_fixture" }, { "id": "BU06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU06.selected_fixture" }, { "id": "BU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU07.selected_fixture" }, { "id": "BU08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU08.selected_fixture" }, { "id": "BU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU09.selected_fixture" }, { "id": "BU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU11.selected_fixture" }, { "id": "BU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU14.selected_fixture" }, { "id": "BU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU15.selected_fixture" }, { "id": "BU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU13.selected_fixture" }, { "id": "OU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU15.selected_fixture" }, { "id": "OU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU16.selected_fixture" }, { "id": "OU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU17.selected_fixture" }, { "id": "OU02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU02.selected_fixture" }, { "id": "OU18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU18.selected_fixture" }, { "id": "OU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU14.selected_fixture" }, { "id": "OU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU01.selected_fixture" }, { "id": "OU03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU03.selected_fixture" }, { "id": "OU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU05.selected_fixture" }, { "id": "OU06", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "OU06.selected_fixture" }, { "id": "OU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU07.selected_fixture" }, { "id": "OU08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU08.selected_fixture" }, { "id": "OU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU09.selected_fixture" }, { "id": "OU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU10.selected_fixture" }, { "id": "OU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU11.selected_fixture" }, { "id": "OU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU12.selected_fixture" }, { "id": "OU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU13.selected_fixture" }, { "id": "OU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU04.selected_fixture" }, { "id": "OU19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU19.selected_fixture" }, { "id": "OU20", "verdict": "fail", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU20.selected_fixture" }, { "id": "OU21", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU21.selected_fixture" }, { "id": "PR01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR01.selected_fixture" }, { "id": "PR02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR02.selected_fixture" }, { "id": "PR03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR03.selected_fixture" }, { "id": "PR04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR04.selected_fixture" }, { "id": "PR05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR05.selected_fixture" }, { "id": "PR06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR06.selected_fixture" }, { "id": "PR07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR07.selected_fixture" }, { "id": "PR08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR08.selected_fixture" }, { "id": "PR09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR09.selected_fixture" }, { "id": "PR10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR10.selected_fixture" }, { "id": "PR11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR11.selected_fixture" }, { "id": "PR12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR12.selected_fixture" }, { "id": "PR13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR13.selected_fixture" }, { "id": "PR14", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "PR14.selected_fixture" }, { "id": "PR15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR15.selected_fixture" }, { "id": "PR16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR16.selected_fixture" }, { "id": "PR17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR17.selected_fixture" }, { "id": "PR18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR18.selected_fixture" }, { "id": "PR19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR19.selected_fixture" }, { "id": "F01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F01.selected_fixture" }, { "id": "F02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F02.selected_fixture" }, { "id": "F03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F03.selected_fixture" }, { "id": "F04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F04.selected_fixture" }, { "id": "F05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F05.selected_fixture" }, { "id": "G01", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G01.static_sources" }, { "id": "G02", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G02.static_sources" }, { "id": "G03", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G03.static_sources" } ], "charges": [ { "id": "F1C-GEN03", "points": "0.5", "reason": "отчёт не соответствует заданию: OU20" }, { "id": "F1C-GEN15", "points": "0.5", "reason": "CommonModules/УчетСервер/Ext/Module.bsl:41 — РегистрНакопления.ОстаткиНоменклатуры.Остатки: отбор по Подразделение, индексы таблицы начинаются с Номенклатура" }, { "id": "F1C-PR09", "points": "0.5", "reason": "CommonModules/УчетСервер/Ext/Module.bsl:349 — РегистрРасчета.Начисления.БазаНачисления: база получается без отбора по регистратору — по всем записям регистра" }, { "id": "F1C-PR09", "points": "0.5", "reason": "CommonModules/УчетСервер/Ext/Module.bsl:370 — РегистрРасчета.Начисления.БазаНачисления: база получается без отбора по регистратору — по всем записям регистра" }, { "id": "F1C-GEN15", "points": "0.5", "reason": "Reports/Ведомость/Ext/ManagerModule.bsl:2 — РегистрНакопления.ОстаткиНоменклатуры.ОстаткиИОбороты: отбор по Подразделение, индексы таблицы начинаются с Номенклатура" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "проводимые документы в режиме «Записывать модифицированные»: Операция, Сборка" }, { "id": "F1C-BU06", "points": "1.5", "reason": "ресурс Количество без признака учёта — количество ведётся на всех счетах" }, { "id": "F1C-BU05", "points": "0.5", "reason": "аналитика счетов вынесена в измерения регистра бухгалтерии и есть у всех счетов: Номенклатура (Номенклатура), Склад (Склады)" }, { "id": "F1C-PR08", "points": "2.0", "reason": "база берётся из основной таблицы регистра расчёта, БазаНачисления нигде не используется: Documents/НачислениеЗарплаты/Ext/ObjectModule.bsl:6" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "оперативное проведение разрешено у документов с движениями по регистрам расчёта: НачислениеЗарплаты" }, { "id": "F1C-GEN21", "points": "2.0", "reason": "данные графика без отбора по регистратору: CommonModules/УчетСервер/Ext/Module.bsl:316" } ], "score_upper_bound": "-5.5", "score": null, "grade": "unsatisfactory", "deductions": "10.5", "not_assessed": 16, "gates": { "starter_origin": "passed", "load": "loaded", "clients": "compiles", "demo_data": "present" }, "infrastructure_errors": false, "comparison_eligible": false, "binding_compatibility": null }, "measurement": { "operator": { "name": "Вячеслав", "github": "sksibak" }, "environment": { "captured_at": "2026-10-25T04:35:35.871356+00:00", "capture_timing": "before_run", "hardware": { "cpu": "AMD Ryzen 5 4600H with Radeon Graphics ", "logical_cpus": 12, "ram_bytes": 16505962496 }, "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "python": "3.12.14", "platform_version": "8.3.27.1644", "isolation": "dedicated-host", "network_profile": "open-book_shell", "unsafe_action_protection_observed_in_user_config": true, "git_revision": "af85e791b303dbbf0b0b7af924d2489c3e57cfa8", "implementation_files": { "exam_bench/__init__.py": "ad5bf6f05dc6765f40b78bd186870ca2c49be113cfa33f8aa76f4926f2cb2c1e", "exam_bench/assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "exam_bench/bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "exam_bench/calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "exam_bench/calibrate.py": "78b5185cb0888c0c0ac3de95ffc3a80154a6de9ae66fc461f79d012e5a58e1db", "exam_bench/calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "exam_bench/calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "exam_bench/calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "exam_bench/calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "exam_bench/calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "exam_bench/claude.py": "bc1b8550de7573aaed5e39c6e9c0309e0d8175284a75490d61ec27439ed911ad", "exam_bench/cli.py": "1a37ce645633d761f7897dffc9c45e6b8b9600cd7bd233b1cbf78f49d26b099a", "exam_bench/codescan.py": "751e38001b6e65727a31e28172a0623f0bf34bc092a958037c286aa991a197ed", "exam_bench/codex.py": "c3f89d72af11f312d851c73a1610d92e79acadf336be9ccedd1f94ede3b3ccb0", "exam_bench/common.py": "8682603b519063e655eae3574a02a49efee63bde21f582ccee20ddd623fca96d", "exam_bench/docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "exam_bench/examiner.py": "d7294fdd23ed1732216cafebf0a8cf2c24cce4259859aeb7149f62b7607d087d", "exam_bench/finalize.py": "4034f1c63896a940afdb1a83d541cf47fc75c8b5061e3f839047109c04beb620", "exam_bench/forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "exam_bench/gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "exam_bench/grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "exam_bench/harness.py": "3040f6daaf1dc6e6583219f4d925151f8ba7851b2d5417d7f14645892b485ddf", "exam_bench/interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "exam_bench/interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "exam_bench/isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "exam_bench/ledger.py": "7e851523580e22d8490e75f9b6026c07f2c355007e0d11d0b252671f56bef654", "exam_bench/locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "exam_bench/materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "exam_bench/mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "exam_bench/observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "exam_bench/ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "exam_bench/penalties.py": "0d79e2e46102657dca00609b6abbfc0bf7d11fad41429564f876c82bc6b33269", "exam_bench/platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "exam_bench/portable.py": "cad56968ff407983608f5bdbc9ce7234128d7a4580b096ecea8e0e7b4edb9070", "exam_bench/portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "exam_bench/pr.py": "6a3a20caf0e10c0cc94410511a72d62c9fcda785f3abab1be2ad616d4ee16836", "exam_bench/preflight.py": "5619be0131d8641925f3ce2a3c8e5234d42aa5635d95676138ca81536d95cd29", "exam_bench/process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "exam_bench/queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "exam_bench/queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "exam_bench/replay_calibration.py": "c150457b0b23ce4e6814eb8deb4d48f6bc4a2e39d8f84a9dc7644fb99a026c2d", "exam_bench/report.py": "5e4c0757e1c7f189953f9a5302593ab726551835856baed25efd93dad6e8bfcd", "exam_bench/runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "exam_bench/smoke_check.py": "f36922a0027429ead0b414048dcc14bbe67f2f0e79a70d03dffbe1447d253545", "exam_bench/stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "exam_bench/submission.py": "d6f9d20704181c51714f1138affe4965d860ae21475ab7bb49aa5c5cefebb9f5", "exam_bench/telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "exam_bench/windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "exam_bench/workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tools/build_public_site.py": "9682ed696f5ac9e9a82b65a45c0dece556ec7e49eeb20dcd616882cc534a8258", "tools/build_result_site.py": "3294e1d2ec1486058e208735264d61e349a68a4ae2fa2ec7a723c70e3263b496", "tools/check_native_harnesses.py": "4f5f0ed27651f78758eaef077b3b114361781f6b95ec40cb46c3fea689210473", "tools/check_native_toolkit.py": "0272794617121f2932828e5e4e9ae20095183c443666cf3ba466b44fbe875095", "tools/community_results.py": "9db56a44697d94f326efcbd7a3ae1aecdb569d43bba6c47e80ce525dc045f1f7", "tools/community_service.py": "c374480dbd88d656c0b9054fa04a8e1c6698c69e2f9cf475e82498a2dff61d84", "tools/community_setup.py": "5d7d126ed7d4dd48e1d79f57b99647a92ffcc8c9f80d90915e458888cdd76bf7", "tools/compare_harness_runs.py": "f274df5f3f804cb02504491aec946943833e12fbce6e62d281e12beb8508fc4e", "tools/create_run_plan.py": "871cd81b1eda231c0fba8805f63d2668926be9fc641559e6ddf320e2f47cd37a", "tools/demo_runner.py": "230e6e49068f2bab3a0db64e6da5889e8f1834158fed8c5ec334b7694695a87b", "tools/installers.py": "9a2742780936b17500869e7c89202c1a2549e37d53a42ad9a50a0abbf78bbe09", "tools/machine_bundle.py": "8aa8346f99f537e81ceca6fb6ab9530e844954bab8eff87bf33d3602f81f8a30", "tools/prepare_native_harnesses.py": "aaa75ecf4022883984fa50c42d14d8e1a9fde2eeda03dab03b852bbc5efb2502", "tools/prepare_official_statement.py": "6b7028c78e90e798d6ef1a93b76520cc61a308c354fb9b87f7fad18b99800fad", "tools/prepare_open_exam_requirements.py": "544f4e378b9be5f166186f8788f8d454afdac2deb99d91d98421e39d01ba6d03", "tools/probe_harness.py": "1ed8ef93420d1484cbbfd151b7efc31b9a201ceb942dd05e3103efa22ffa7f27", "tools/probe_native_mcp.py": "9918d324129cba898993e07f8f8b6dbcbaf369398ebf28d464f9f1f00abdb254", "tools/readiness.py": "d34dd3f38334f51cc4574c79194cf0b80769b062a52382989a57d01c46b9aba4", "tools/recheck_community.py": "f0843d7d677f90da31e22bde0b1c86584dd46c022f1532d43d042619e426b230", "tools/regrade_runs.py": "011775afb06d3aac67a4aa81117a368c75896b0fcbe1e6f27ccc6237612fbf59", "tools/render_statement_text.py": "dabc0716a3612c288c671bc20e17fd4986691d732768e1e957d6dddddbea92a3", "tools/replay_calibration.py": "801f5004926c438c21ed3668fe2a4ddf45312b3e75320165a3839aae034eee9b", "tools/run_exam_campaign.py": "2c450d57a1cd0a2682838f5ec7c0a4ffb3aed0f1730d34c408e912d59cab6efd", "tools/serve_result_site.py": "86badfac863cd4ad1fc894a14110c75b28470513f0133eeae9d2799b8b4df3a9", "tools/start_demo.py": "c597e6cad28d245b3191654bb3e2801fa9dd2364e2acb25561923613717b615f", "tools/supplemental_acceptance.py": "c88fc39de1be1fdcacdd819e2ad329f60367b2df1d5deda80b37324bda3f2a01", "tools/sync_sources.py": "b51e889b0f41f9f63bfb19a09fb96d3777693d6b1d76fe0132bdd2a15e155898", "tools/validate_community_pr.py": "796b896dfade07b4529af2088a4b9b9d23484148b3bc0732b3fb837b75c9844b", "tools/verify_official_assessment_mapping.py": "daeb448a016940d5b6b1285979a56e5b9014bd91db40acb131445e4a83a23059", "tools/verify_task_package.py": "9e1e6105f6b5e4e78b36aa57f00117a9fbc8948ab53983c32ab56da88d23ccc4", "profiles/agents.json": "af9c492c08d13b3044aa6b6952589ed6a0a07d5258d8ff72bb18185b3eaebdc5", "profiles/ai-exam-execution-policy.json": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "profiles/bsl-analyzer-0.3.2-macos.json": "83537abdbf38c41ce665e4d0f24128bb51b62e971e0e0f368695f1326a7d2ffb", "profiles/bsl-analyzer-0.3.2-portable.json": "d6ba732e6778e256df34d6bc548593128820a70430c35b279796843606ee40a8", "profiles/bsl-ls-1.1.0-rc.6-macos.json": "245fc10747197e6911b2b4c77cdb15e6fa4eb7bc7c3758b63e768c5adf1df180", "profiles/bsl-ls-1.1.0-rc.6-portable.json": "9f10660881f2ec84794f7d584556b8f75c7e14b3555464af0ed0e60c4c892d86", "profiles/code-index-1.9.0-macos.json": "63a919523ce62ecec274f4c139bc7ad49a75dd4c339568b822cbc695b4e30408", "profiles/code-index-1.9.0-portable.json": "81106cee8f424ffd8a9dc46ecd8e4f57598fc1d49661a83c77b1f0507993fbdc", "profiles/codex-probe-plan.json": "166e41aad5fb3b27d9050bc6de952c6cba363cc6e804d4080568cc71a2a4d289", "profiles/machine.linux.example.json": "408304fd0581098d5d8110dc67dfeab353bc4d4030e32d37e6acf98d2b1aedfd", "profiles/machine.macos.example.json": "52e9f9d17797cb520b9d8955d6806fd550b899bed4da241ebf096dcb6a21a942", "profiles/machine.windows.example.json": "63accac9a2f81d47d03447efbabffd4760aee325193f02f46b9b29a28d50d2d8", "profiles/mcp-toolkit-1.9.0-macos.json": "1d3f9cde5ffa20589a840d01fdae03aa0fc2f412c929f064f203919c4129625b", "profiles/mcp-toolkit-1.9.0-portable.json": "8e370eebe773eef0e08045ee9c6d5be1451f769f65be0710834b262a4336e054", "profiles/none-macos.json": "b1401d9c48159aed3559006c7f6ace6ef4571224d5cf0bb76d1a823505a10056", "profiles/none-portable.json": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "profiles/rlm-tools-bsl-1.43.0-macos.json": "9354421052640ab60bc3e6aa98ff2e7ba9ca2318b0f4026c137487449242cbd2", "profiles/rlm-tools-bsl-1.43.0-portable.json": "2599e5645e0a7d4e44cb2934bc2b272cae79a9bf7ea74a23cd48aacea64bc424", "profiles/rlm-tools-bsl-1.43.0-posix-requirements.txt": "4fdf9a1bd994bf0272e65d231daf76cf19b0a34dad0ae6b50ec4f11a2ce4c330", "profiles/rlm-tools-bsl-1.43.0-windows-requirements.txt": "3730cb46c81cda5181ecd4485e98b11933104632358bc86f8c0eb1a612a8954f", "profiles/shirokov-skills-macos.json": "84f3e89091676884a802035c707e912762a1179425fb8e3faff25be736873cdb", "profiles/shirokov-skills-portable.json": "2b0a461e06602f1456410e70f02ceaa5ac32c6549c486660bcb5ace0c2f87b15", "profiles/shirokov-skills-windows-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/unica-0.12.3-macos.json": "2c39fbb591cf2c2c6e056373823615485397ea83651b7926c6f25a5fe6a0aae6", "profiles/unica-0.13.0-macos.json": "b76b5c8a4dd33f571c4a90993f1a2da5f7223b4f0f8e1042c282e21a66121052", "profiles/unica-0.14.0-rc.1-portable.json": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "rules/1c-specialist-platform/chistov.json": "77e04942f8c947b10759e7cc1eb31af05847d1711a772fbe6f23d525766757a9", "rules/1c-specialist-platform/decisions.json": "f622107423ce3c188c063318d7ab4f7718ceb38e443130677d8987f386641c09", "rules/1c-specialist-platform/examiner.json": "30353aa2a1b6545496b070d9066e9ffba0c3779e5b53ef70a4fd2cee375b18c0", "rules/1c-specialist-platform/ledger.json": "f167c10db2b5799dd9a1ea6a37cd2d7d186810dadf5ea2f50f26ae723c676882", "rules/1c-specialist-platform/rules.json": "1d320a4f8e1bf4701496388931f492315549bd3dce574b17285dd1d7f8652007", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" } } }, "conditions": { "client": "codex", "model": "gpt-6.1-sol", "client_version": "0.163.0-alpha.11.2", "reasoning_effort": "medium", "harness": "unica-0.14.0-rc.1", "billing_channel": "subscription", "solve_timeout_seconds": 1800, "time_series": "fast", "delegation": "native_disabled", "network_profile": "open-book_shell", "deadline_disclosed": true, "statement_sha256": "8a6ccb3e673826d1f8220fda53eb310e3ec18c136d87ce8f4cebb2a08614e7e5", "starter_dt_sha256": "f40d084818b0d1cfe503fc7653a6a13f1a8e47fcd1688dad6245b12744eb4638", "profile_sha256": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "execution_policy_sha256": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "calibration_sha256": "e8981744a194aa56f954d2965aa66cd53cd4f899f09fa7b5abda6f6b27a5ed65", "started_at": "2026-10-25T04:35:46.776087+00:00", "timing": { "prepare_ms": 7953, "solve_ms": 1750093, "grade_ms": null }, "original_submission_valid": true, "model_provenance": "requested_only", "tokens": { "input": 15320636, "cached_input": 15152896, "fresh_input": 167740, "output": 69307, "reasoning_output": 16218, "total": 15389943, "coverage": "reported_completed_root_turns" }, "tools": { "mcp_calls": 238, "unica_calls": 238, "failed_calls": 26 }, "process": { "status": "completed", "exit_code": 0, "stop_confirmed": true } }, "verification": "repository_owner", "download": "community-downloads/demo-20261025T113819Z-9d209c--owner-2026-10-26T214400531590-0000/solution.zip", "source_context": "community-downloads/demo-20261025T113819Z-9d209c--owner-2026-10-26T214400531590-0000/source-context.json", "regrade_required": [ { "id": "grader_changed", "files": [ "calibrate.py", "calibration_periodicity.py", "common.py", "ou.py", "replay_calibration.py", "smoke_check.py", "tasks/1c-platform-official-sample/checks.json" ] } ], "grader_revision_sha256": "349d87e0c7f531acbe35dd2b39c35722d8a877fedde97575b49e8466ab763c1d", "archive_sha256": "b4f2495de55223bf5e6eedff14615e7e24ad523f154f9919aaca060df6d2d9dc", "owner_verification": { "kind": "repository_owner", "repository": "zeegin/1c-agent-exam-benchmark", "operator": { "name": "Ingvar Vilkman", "github": "zeegin" }, "started_at": "2026-10-26T21:44:00.369705+00:00", "server": { "name": "Owner Windows stand", "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "hardware": { "cpu": "AMD Ryzen 7 5800X 8-Core Processor ", "logical_cpus": 4, "ram_bytes": 17109000192 }, "isolation": "dedicated-host" }, "platform_version": "8.3.27.2342", "grader": { "profile": "technical-v8", "commit": "e8fd8ced03a85b549c5472fbbda29225749f54d1", "working_tree_dirty": false, "fingerprint": { "assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "calibrate.py": "3162d431f3cab5e7976aa39f665d6286dce45499cf362d85109b7123fa8403a2", "calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "calibration_query.py": "3555b103cde8ea0519955cf52358d09223f5ab183a9df00533bdb48c89237a8c", "claude.py": "eedabc75fca0faa434f40a1624b71419ec7dc22e2854a0886cf84b4911db8372", "codescan.py": "6d8375210cef1fd768fc2d98d630d880b2993a9724f01ae25f33b4ea5aa9631d", "codex.py": "904e75503cd35f16cbb052f66806b3879fe25bfc9f99e33b93c889d862c46324", "common.py": "52825cf5c29f3536d6e046a89e789d5ef9c83aacd7f2f5a07f4f53e77b5229cc", "docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "examiner.py": "8cdffcdd52f043c905f896697403380af95bf485dd4a5edca24f7956e7795ffe", "forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "harness.py": "3cbb90fd3187e700b5df32e5daafb20313d49bb5721c826e3033cbc6aa6e3825", "interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "penalties.py": "ae388cb8953ecca1f2370a7c4cb1db3b6cc8318fc2a7563a4db15f9f5b057429", "platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "pr.py": "2b6bfea0634703469605ce114f9274716b485852d9a55d9185c39893b14e4726", "preflight.py": "448c3120ab64b625abae3891be686c7a214ce4211f7cf651fd90e12c0b298433", "process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "queries.py": "1ef57e292db3e8967a733948371ecc542f743b811890d4fc509df17303b9c4ac", "queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "querytypes.py": "b645f489a2abc27762b4a9bbf4917e72f7b46dc053a74c0dca4a8fc46491b3ef", "replay_calibration.py": "0a4d9b84a9908944c5a945878eb6f5eeda5a4e42ffff4f55c04a680742803d80", "runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "smoke_check.py": "66caf1a01f7aa18432293abe3567ac228ac837a660b08c3dc7bb093f7bd51628", "stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "submission.py": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tasks/1c-platform-official-sample/checks.json": "17a6fcc0c14410829650623eb1443ce99796e000cdfd19905ac0287988b73a00", "tasks/1c-platform-official-sample/private/official-assessment-mapping.json": "303587c0dabe77c1eeebb2017fe85539e3370b17c9090435e6e0325a66bd0644", "tasks/1c-platform-official-sample/private/owner-scoring-policy.json": "d26d534bb838ab1b5facb7bc033ca8ec40912133baadcdbad83b27fc577905f5", "starters/carcass-8.3.25.1445/starter.json": "0f7a7060885ba99a19402bfc6e63cc8fe979b0f491b040d3a01d5d21b304b3a6", "rules/1c-specialist-platform/rules.json": "ea75e34ace5de11ba3de403c63cd2c026db81d1d991f8531e4a779d4ce9788e7", "rules/1c-specialist-platform/examiner.json": "1247486ddd412d600db88d9c1db4ba501fc1994afd1dc2ebe85402fcc332f4c8", "rules/1c-specialist-platform/chistov.json": "800da27601a3f1c7ec1df64482fd4ad035e559ba0b390a274ed5031128487d3d", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" }, "sha256": "349d87e0c7f531acbe35dd2b39c35722d8a877fedde97575b49e8466ab763c1d" }, "method": "saved_platform_observations", "outcome": "complete", "completed_at": "2026-10-26T21:44:00.531590+00:00" } }, { "id": "demo-20261025T113819Z-9d209c--owner-2026-10-26T190737172161-0000", "run_id": "demo-20261025T043533Z-b8847b", "result": { "run_id": "demo-20261025T043533Z-b8847b", "created_at": "2026-10-26T19:07:37.172161+00:00", "model": "gpt-6.1-sol", "harness": "unica-0.14.0-rc.1", "solve_seconds": 1750, "platform": "8.3.27.1644", "counts": { "pass": 64, "fail": 1 }, "rules": [ { "id": "BU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU01.selected_fixture" }, { "id": "BU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU04.selected_fixture" }, { "id": "BU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU05.selected_fixture" }, { "id": "BU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU16.selected_fixture" }, { "id": "BU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU17.selected_fixture" }, { "id": "BU02", "verdict": "pass", "reason": null, "coverage": "partial", "assertion_id": "BU02.posting_cost_and_balance" }, { "id": "BU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU10.selected_fixture" }, { "id": "BU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU12.selected_fixture" }, { "id": "BU03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU03.selected_fixture" }, { "id": "BU06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU06.selected_fixture" }, { "id": "BU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU07.selected_fixture" }, { "id": "BU08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU08.selected_fixture" }, { "id": "BU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU09.selected_fixture" }, { "id": "BU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU11.selected_fixture" }, { "id": "BU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU14.selected_fixture" }, { "id": "BU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU15.selected_fixture" }, { "id": "BU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU13.selected_fixture" }, { "id": "OU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU15.selected_fixture" }, { "id": "OU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU16.selected_fixture" }, { "id": "OU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU17.selected_fixture" }, { "id": "OU02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU02.selected_fixture" }, { "id": "OU18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU18.selected_fixture" }, { "id": "OU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU14.selected_fixture" }, { "id": "OU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU01.selected_fixture" }, { "id": "OU03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU03.selected_fixture" }, { "id": "OU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU05.selected_fixture" }, { "id": "OU06", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "OU06.selected_fixture" }, { "id": "OU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU07.selected_fixture" }, { "id": "OU08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU08.selected_fixture" }, { "id": "OU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU09.selected_fixture" }, { "id": "OU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU10.selected_fixture" }, { "id": "OU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU11.selected_fixture" }, { "id": "OU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU12.selected_fixture" }, { "id": "OU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU13.selected_fixture" }, { "id": "OU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU04.selected_fixture" }, { "id": "OU19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU19.selected_fixture" }, { "id": "OU20", "verdict": "fail", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU20.selected_fixture" }, { "id": "OU21", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU21.selected_fixture" }, { "id": "PR01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR01.selected_fixture" }, { "id": "PR02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR02.selected_fixture" }, { "id": "PR03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR03.selected_fixture" }, { "id": "PR04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR04.selected_fixture" }, { "id": "PR05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR05.selected_fixture" }, { "id": "PR06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR06.selected_fixture" }, { "id": "PR07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR07.selected_fixture" }, { "id": "PR08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR08.selected_fixture" }, { "id": "PR09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR09.selected_fixture" }, { "id": "PR10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR10.selected_fixture" }, { "id": "PR11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR11.selected_fixture" }, { "id": "PR12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR12.selected_fixture" }, { "id": "PR13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR13.selected_fixture" }, { "id": "PR14", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "PR14.selected_fixture" }, { "id": "PR15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR15.selected_fixture" }, { "id": "PR16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR16.selected_fixture" }, { "id": "PR17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR17.selected_fixture" }, { "id": "PR18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR18.selected_fixture" }, { "id": "PR19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR19.selected_fixture" }, { "id": "F01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F01.selected_fixture" }, { "id": "F02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F02.selected_fixture" }, { "id": "F03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F03.selected_fixture" }, { "id": "F04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F04.selected_fixture" }, { "id": "F05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F05.selected_fixture" }, { "id": "G01", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G01.static_sources" }, { "id": "G02", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G02.static_sources" }, { "id": "G03", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G03.static_sources" } ], "charges": [ { "id": "F1C-GEN03", "points": "0.5", "reason": "отчёт не соответствует заданию: OU20" }, { "id": "F1C-GEN15", "points": "0.5", "reason": "CommonModules/УчетСервер/Ext/Module.bsl:41 — РегистрНакопления.ОстаткиНоменклатуры.Остатки: отбор по Подразделение, индексы таблицы начинаются с Номенклатура" }, { "id": "F1C-PR09", "points": "0.5", "reason": "CommonModules/УчетСервер/Ext/Module.bsl:349 — РегистрРасчета.Начисления.БазаНачисления: база получается без отбора по регистратору — по всем записям регистра" }, { "id": "F1C-PR09", "points": "0.5", "reason": "CommonModules/УчетСервер/Ext/Module.bsl:370 — РегистрРасчета.Начисления.БазаНачисления: база получается без отбора по регистратору — по всем записям регистра" }, { "id": "F1C-GEN15", "points": "0.5", "reason": "Reports/Ведомость/Ext/ManagerModule.bsl:2 — РегистрНакопления.ОстаткиНоменклатуры.ОстаткиИОбороты: отбор по Подразделение, индексы таблицы начинаются с Номенклатура" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "проводимые документы в режиме «Записывать модифицированные»: Операция, Сборка" }, { "id": "F1C-BU06", "points": "1.5", "reason": "ресурс Количество без признака учёта — количество ведётся на всех счетах" }, { "id": "F1C-BU05", "points": "0.5", "reason": "аналитика счетов вынесена в измерения регистра бухгалтерии и есть у всех счетов: Номенклатура (Номенклатура), Склад (Склады)" }, { "id": "F1C-PR08", "points": "2.0", "reason": "база берётся из основной таблицы регистра расчёта, БазаНачисления нигде не используется: Documents/НачислениеЗарплаты/Ext/ObjectModule.bsl:6" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "оперативное проведение разрешено у документов с движениями по регистрам расчёта: НачислениеЗарплаты" }, { "id": "F1C-GEN21", "points": "2.0", "reason": "данные графика без отбора по регистратору: CommonModules/УчетСервер/Ext/Module.bsl:316" } ], "score_upper_bound": "-5.5", "score": null, "grade": "unsatisfactory", "deductions": "10.5", "not_assessed": 16, "gates": { "starter_origin": "passed", "load": "loaded", "clients": "compiles", "demo_data": "present" }, "infrastructure_errors": false, "comparison_eligible": false, "binding_compatibility": null }, "measurement": { "operator": { "name": "Вячеслав", "github": "sksibak" }, "environment": { "captured_at": "2026-10-25T04:35:35.871356+00:00", "capture_timing": "before_run", "hardware": { "cpu": "AMD Ryzen 5 4600H with Radeon Graphics ", "logical_cpus": 12, "ram_bytes": 16505962496 }, "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "python": "3.12.14", "platform_version": "8.3.27.1644", "isolation": "dedicated-host", "network_profile": "open-book_shell", "unsafe_action_protection_observed_in_user_config": true, "git_revision": "af85e791b303dbbf0b0b7af924d2489c3e57cfa8", "implementation_files": { "exam_bench/__init__.py": "ad5bf6f05dc6765f40b78bd186870ca2c49be113cfa33f8aa76f4926f2cb2c1e", "exam_bench/assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "exam_bench/bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "exam_bench/calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "exam_bench/calibrate.py": "78b5185cb0888c0c0ac3de95ffc3a80154a6de9ae66fc461f79d012e5a58e1db", "exam_bench/calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "exam_bench/calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "exam_bench/calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "exam_bench/calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "exam_bench/calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "exam_bench/claude.py": "bc1b8550de7573aaed5e39c6e9c0309e0d8175284a75490d61ec27439ed911ad", "exam_bench/cli.py": "1a37ce645633d761f7897dffc9c45e6b8b9600cd7bd233b1cbf78f49d26b099a", "exam_bench/codescan.py": "751e38001b6e65727a31e28172a0623f0bf34bc092a958037c286aa991a197ed", "exam_bench/codex.py": "c3f89d72af11f312d851c73a1610d92e79acadf336be9ccedd1f94ede3b3ccb0", "exam_bench/common.py": "8682603b519063e655eae3574a02a49efee63bde21f582ccee20ddd623fca96d", "exam_bench/docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "exam_bench/examiner.py": "d7294fdd23ed1732216cafebf0a8cf2c24cce4259859aeb7149f62b7607d087d", "exam_bench/finalize.py": "4034f1c63896a940afdb1a83d541cf47fc75c8b5061e3f839047109c04beb620", "exam_bench/forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "exam_bench/gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "exam_bench/grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "exam_bench/harness.py": "3040f6daaf1dc6e6583219f4d925151f8ba7851b2d5417d7f14645892b485ddf", "exam_bench/interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "exam_bench/interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "exam_bench/isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "exam_bench/ledger.py": "7e851523580e22d8490e75f9b6026c07f2c355007e0d11d0b252671f56bef654", "exam_bench/locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "exam_bench/materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "exam_bench/mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "exam_bench/observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "exam_bench/ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "exam_bench/penalties.py": "0d79e2e46102657dca00609b6abbfc0bf7d11fad41429564f876c82bc6b33269", "exam_bench/platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "exam_bench/portable.py": "cad56968ff407983608f5bdbc9ce7234128d7a4580b096ecea8e0e7b4edb9070", "exam_bench/portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "exam_bench/pr.py": "6a3a20caf0e10c0cc94410511a72d62c9fcda785f3abab1be2ad616d4ee16836", "exam_bench/preflight.py": "5619be0131d8641925f3ce2a3c8e5234d42aa5635d95676138ca81536d95cd29", "exam_bench/process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "exam_bench/queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "exam_bench/queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "exam_bench/replay_calibration.py": "c150457b0b23ce4e6814eb8deb4d48f6bc4a2e39d8f84a9dc7644fb99a026c2d", "exam_bench/report.py": "5e4c0757e1c7f189953f9a5302593ab726551835856baed25efd93dad6e8bfcd", "exam_bench/runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "exam_bench/smoke_check.py": "f36922a0027429ead0b414048dcc14bbe67f2f0e79a70d03dffbe1447d253545", "exam_bench/stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "exam_bench/submission.py": "d6f9d20704181c51714f1138affe4965d860ae21475ab7bb49aa5c5cefebb9f5", "exam_bench/telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "exam_bench/windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "exam_bench/workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tools/build_public_site.py": "9682ed696f5ac9e9a82b65a45c0dece556ec7e49eeb20dcd616882cc534a8258", "tools/build_result_site.py": "3294e1d2ec1486058e208735264d61e349a68a4ae2fa2ec7a723c70e3263b496", "tools/check_native_harnesses.py": "4f5f0ed27651f78758eaef077b3b114361781f6b95ec40cb46c3fea689210473", "tools/check_native_toolkit.py": "0272794617121f2932828e5e4e9ae20095183c443666cf3ba466b44fbe875095", "tools/community_results.py": "9db56a44697d94f326efcbd7a3ae1aecdb569d43bba6c47e80ce525dc045f1f7", "tools/community_service.py": "c374480dbd88d656c0b9054fa04a8e1c6698c69e2f9cf475e82498a2dff61d84", "tools/community_setup.py": "5d7d126ed7d4dd48e1d79f57b99647a92ffcc8c9f80d90915e458888cdd76bf7", "tools/compare_harness_runs.py": "f274df5f3f804cb02504491aec946943833e12fbce6e62d281e12beb8508fc4e", "tools/create_run_plan.py": "871cd81b1eda231c0fba8805f63d2668926be9fc641559e6ddf320e2f47cd37a", "tools/demo_runner.py": "230e6e49068f2bab3a0db64e6da5889e8f1834158fed8c5ec334b7694695a87b", "tools/installers.py": "9a2742780936b17500869e7c89202c1a2549e37d53a42ad9a50a0abbf78bbe09", "tools/machine_bundle.py": "8aa8346f99f537e81ceca6fb6ab9530e844954bab8eff87bf33d3602f81f8a30", "tools/prepare_native_harnesses.py": "aaa75ecf4022883984fa50c42d14d8e1a9fde2eeda03dab03b852bbc5efb2502", "tools/prepare_official_statement.py": "6b7028c78e90e798d6ef1a93b76520cc61a308c354fb9b87f7fad18b99800fad", "tools/prepare_open_exam_requirements.py": "544f4e378b9be5f166186f8788f8d454afdac2deb99d91d98421e39d01ba6d03", "tools/probe_harness.py": "1ed8ef93420d1484cbbfd151b7efc31b9a201ceb942dd05e3103efa22ffa7f27", "tools/probe_native_mcp.py": "9918d324129cba898993e07f8f8b6dbcbaf369398ebf28d464f9f1f00abdb254", "tools/readiness.py": "d34dd3f38334f51cc4574c79194cf0b80769b062a52382989a57d01c46b9aba4", "tools/recheck_community.py": "f0843d7d677f90da31e22bde0b1c86584dd46c022f1532d43d042619e426b230", "tools/regrade_runs.py": "011775afb06d3aac67a4aa81117a368c75896b0fcbe1e6f27ccc6237612fbf59", "tools/render_statement_text.py": "dabc0716a3612c288c671bc20e17fd4986691d732768e1e957d6dddddbea92a3", "tools/replay_calibration.py": "801f5004926c438c21ed3668fe2a4ddf45312b3e75320165a3839aae034eee9b", "tools/run_exam_campaign.py": "2c450d57a1cd0a2682838f5ec7c0a4ffb3aed0f1730d34c408e912d59cab6efd", "tools/serve_result_site.py": "86badfac863cd4ad1fc894a14110c75b28470513f0133eeae9d2799b8b4df3a9", "tools/start_demo.py": "c597e6cad28d245b3191654bb3e2801fa9dd2364e2acb25561923613717b615f", "tools/supplemental_acceptance.py": "c88fc39de1be1fdcacdd819e2ad329f60367b2df1d5deda80b37324bda3f2a01", "tools/sync_sources.py": "b51e889b0f41f9f63bfb19a09fb96d3777693d6b1d76fe0132bdd2a15e155898", "tools/validate_community_pr.py": "796b896dfade07b4529af2088a4b9b9d23484148b3bc0732b3fb837b75c9844b", "tools/verify_official_assessment_mapping.py": "daeb448a016940d5b6b1285979a56e5b9014bd91db40acb131445e4a83a23059", "tools/verify_task_package.py": "9e1e6105f6b5e4e78b36aa57f00117a9fbc8948ab53983c32ab56da88d23ccc4", "profiles/agents.json": "af9c492c08d13b3044aa6b6952589ed6a0a07d5258d8ff72bb18185b3eaebdc5", "profiles/ai-exam-execution-policy.json": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "profiles/bsl-analyzer-0.3.2-macos.json": "83537abdbf38c41ce665e4d0f24128bb51b62e971e0e0f368695f1326a7d2ffb", "profiles/bsl-analyzer-0.3.2-portable.json": "d6ba732e6778e256df34d6bc548593128820a70430c35b279796843606ee40a8", "profiles/bsl-ls-1.1.0-rc.6-macos.json": "245fc10747197e6911b2b4c77cdb15e6fa4eb7bc7c3758b63e768c5adf1df180", "profiles/bsl-ls-1.1.0-rc.6-portable.json": "9f10660881f2ec84794f7d584556b8f75c7e14b3555464af0ed0e60c4c892d86", "profiles/code-index-1.9.0-macos.json": "63a919523ce62ecec274f4c139bc7ad49a75dd4c339568b822cbc695b4e30408", "profiles/code-index-1.9.0-portable.json": "81106cee8f424ffd8a9dc46ecd8e4f57598fc1d49661a83c77b1f0507993fbdc", "profiles/codex-probe-plan.json": "166e41aad5fb3b27d9050bc6de952c6cba363cc6e804d4080568cc71a2a4d289", "profiles/machine.linux.example.json": "408304fd0581098d5d8110dc67dfeab353bc4d4030e32d37e6acf98d2b1aedfd", "profiles/machine.macos.example.json": "52e9f9d17797cb520b9d8955d6806fd550b899bed4da241ebf096dcb6a21a942", "profiles/machine.windows.example.json": "63accac9a2f81d47d03447efbabffd4760aee325193f02f46b9b29a28d50d2d8", "profiles/mcp-toolkit-1.9.0-macos.json": "1d3f9cde5ffa20589a840d01fdae03aa0fc2f412c929f064f203919c4129625b", "profiles/mcp-toolkit-1.9.0-portable.json": "8e370eebe773eef0e08045ee9c6d5be1451f769f65be0710834b262a4336e054", "profiles/none-macos.json": "b1401d9c48159aed3559006c7f6ace6ef4571224d5cf0bb76d1a823505a10056", "profiles/none-portable.json": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "profiles/rlm-tools-bsl-1.43.0-macos.json": "9354421052640ab60bc3e6aa98ff2e7ba9ca2318b0f4026c137487449242cbd2", "profiles/rlm-tools-bsl-1.43.0-portable.json": "2599e5645e0a7d4e44cb2934bc2b272cae79a9bf7ea74a23cd48aacea64bc424", "profiles/rlm-tools-bsl-1.43.0-posix-requirements.txt": "4fdf9a1bd994bf0272e65d231daf76cf19b0a34dad0ae6b50ec4f11a2ce4c330", "profiles/rlm-tools-bsl-1.43.0-windows-requirements.txt": "3730cb46c81cda5181ecd4485e98b11933104632358bc86f8c0eb1a612a8954f", "profiles/shirokov-skills-macos.json": "84f3e89091676884a802035c707e912762a1179425fb8e3faff25be736873cdb", "profiles/shirokov-skills-portable.json": "2b0a461e06602f1456410e70f02ceaa5ac32c6549c486660bcb5ace0c2f87b15", "profiles/shirokov-skills-windows-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/unica-0.12.3-macos.json": "2c39fbb591cf2c2c6e056373823615485397ea83651b7926c6f25a5fe6a0aae6", "profiles/unica-0.13.0-macos.json": "b76b5c8a4dd33f571c4a90993f1a2da5f7223b4f0f8e1042c282e21a66121052", "profiles/unica-0.14.0-rc.1-portable.json": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "rules/1c-specialist-platform/chistov.json": "77e04942f8c947b10759e7cc1eb31af05847d1711a772fbe6f23d525766757a9", "rules/1c-specialist-platform/decisions.json": "f622107423ce3c188c063318d7ab4f7718ceb38e443130677d8987f386641c09", "rules/1c-specialist-platform/examiner.json": "30353aa2a1b6545496b070d9066e9ffba0c3779e5b53ef70a4fd2cee375b18c0", "rules/1c-specialist-platform/ledger.json": "f167c10db2b5799dd9a1ea6a37cd2d7d186810dadf5ea2f50f26ae723c676882", "rules/1c-specialist-platform/rules.json": "1d320a4f8e1bf4701496388931f492315549bd3dce574b17285dd1d7f8652007", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" } } }, "conditions": { "client": "codex", "model": "gpt-6.1-sol", "client_version": "0.163.0-alpha.11.2", "reasoning_effort": "medium", "harness": "unica-0.14.0-rc.1", "billing_channel": "subscription", "solve_timeout_seconds": 1800, "time_series": "fast", "delegation": "native_disabled", "network_profile": "open-book_shell", "deadline_disclosed": true, "statement_sha256": "8a6ccb3e673826d1f8220fda53eb310e3ec18c136d87ce8f4cebb2a08614e7e5", "starter_dt_sha256": "f40d084818b0d1cfe503fc7653a6a13f1a8e47fcd1688dad6245b12744eb4638", "profile_sha256": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "execution_policy_sha256": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "calibration_sha256": "e8981744a194aa56f954d2965aa66cd53cd4f899f09fa7b5abda6f6b27a5ed65", "started_at": "2026-10-25T04:35:46.776087+00:00", "timing": { "prepare_ms": 7953, "solve_ms": 1750093, "grade_ms": null }, "original_submission_valid": true, "model_provenance": "requested_only", "tokens": { "input": 15320636, "cached_input": 15152896, "fresh_input": 167740, "output": 69307, "reasoning_output": 16218, "total": 15389943, "coverage": "reported_completed_root_turns" }, "tools": { "mcp_calls": 238, "unica_calls": 238, "failed_calls": 26 }, "process": { "status": "completed", "exit_code": 0, "stop_confirmed": true } }, "verification": "repository_owner", "download": "community-downloads/demo-20261025T113819Z-9d209c--owner-2026-10-26T190737172161-0000/solution.zip", "source_context": "community-downloads/demo-20261025T113819Z-9d209c--owner-2026-10-26T190737172161-0000/source-context.json", "regrade_required": [ { "id": "grader_changed", "files": [ "calibrate.py", "calibration_periodicity.py", "calibration_query.py", "common.py", "ou.py", "penalties.py", "queries.py", "replay_calibration.py", "rules/1c-specialist-platform/rules.json", "smoke_check.py", "tasks/1c-platform-official-sample/checks.json" ] } ], "grader_revision_sha256": "4a12b62d2c10085e1fc710f377f84903abdf2fb787dda19628d944da990a86b2", "archive_sha256": "707089b9c6830ad1c62646d5b976a166298b358c36459e4da340686138623da1", "owner_verification": { "kind": "repository_owner", "repository": "zeegin/1c-agent-exam-benchmark", "operator": { "name": "Ingvar Vilkman", "github": "zeegin" }, "started_at": "2026-10-26T19:04:43.180546+00:00", "server": { "name": "Owner Windows stand", "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "hardware": { "cpu": "AMD Ryzen 7 5800X 8-Core Processor ", "logical_cpus": 4, "ram_bytes": 17109000192 }, "isolation": "dedicated-host" }, "platform_version": "8.3.27.2342", "grader": { "profile": "technical-v8", "commit": "5b6a28372b253e81e22b83f8559df897297e28ff", "working_tree_dirty": true, "fingerprint": { "assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "calibrate.py": "1c844971b4977fdcc3b30aebe8aad40fbd45e6828955b8deb043ac8573d61731", "calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "claude.py": "eedabc75fca0faa434f40a1624b71419ec7dc22e2854a0886cf84b4911db8372", "codescan.py": "6d8375210cef1fd768fc2d98d630d880b2993a9724f01ae25f33b4ea5aa9631d", "codex.py": "904e75503cd35f16cbb052f66806b3879fe25bfc9f99e33b93c889d862c46324", "common.py": "7696116dd1a796666518b4c5d2aa3cafa04ee974593d3636333cbe5385bd6ccb", "docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "examiner.py": "8cdffcdd52f043c905f896697403380af95bf485dd4a5edca24f7956e7795ffe", "forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "harness.py": "3cbb90fd3187e700b5df32e5daafb20313d49bb5721c826e3033cbc6aa6e3825", "interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "penalties.py": "b82704e7f47d3dfdf6e501452d7e0abca1f9da63307093d2e257e32358be0489", "platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "pr.py": "2b6bfea0634703469605ce114f9274716b485852d9a55d9185c39893b14e4726", "preflight.py": "448c3120ab64b625abae3891be686c7a214ce4211f7cf651fd90e12c0b298433", "process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "querytypes.py": "b645f489a2abc27762b4a9bbf4917e72f7b46dc053a74c0dca4a8fc46491b3ef", "replay_calibration.py": "3b6f3a289cc8a7f5e458f62bfa2c6cc534cc9076ba3f22d1e4bd8a5f9e175317", "runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "smoke_check.py": "bd6266367e6b769a95258eb383239b89a22deae406d64f6e142c77396f4639ba", "stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "submission.py": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tasks/1c-platform-official-sample/checks.json": "17a6fcc0c14410829650623eb1443ce99796e000cdfd19905ac0287988b73a00", "tasks/1c-platform-official-sample/private/official-assessment-mapping.json": "303587c0dabe77c1eeebb2017fe85539e3370b17c9090435e6e0325a66bd0644", "tasks/1c-platform-official-sample/private/owner-scoring-policy.json": "d26d534bb838ab1b5facb7bc033ca8ec40912133baadcdbad83b27fc577905f5", "starters/carcass-8.3.25.1445/starter.json": "0f7a7060885ba99a19402bfc6e63cc8fe979b0f491b040d3a01d5d21b304b3a6", "rules/1c-specialist-platform/rules.json": "7ec895a7751ef17f4a50cc80b5f7fa986e1e04360ab0b4ce9aa29115195df03c", "rules/1c-specialist-platform/examiner.json": "1247486ddd412d600db88d9c1db4ba501fc1994afd1dc2ebe85402fcc332f4c8", "rules/1c-specialist-platform/chistov.json": "800da27601a3f1c7ec1df64482fd4ad035e559ba0b390a274ed5031128487d3d", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" }, "sha256": "4a12b62d2c10085e1fc710f377f84903abdf2fb787dda19628d944da990a86b2" }, "identity_verified_at": "2026-10-26T18:44:22.364471+00:00", "identity_session_sha256": "950670ab9a82059c65525d0d6e5b8a00f0dc292581edea3eb087c4ecadeaab09", "completed_at": "2026-10-26T19:07:37.172161+00:00" } }, { "id": "demo-20261025T113819Z-9d209c", "run_id": "demo-20261025T043533Z-b8847b", "result": { "run_id": "demo-20261025T043533Z-b8847b", "created_at": "2026-10-25T11:42:09.981630+00:00", "model": "gpt-6.1-sol", "harness": "unica-0.14.0-rc.1", "solve_seconds": 1750, "platform": "8.3.27.1644", "counts": { "pass": 64, "fail": 1 }, "rules": [ { "id": "BU01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU16", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU17", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU02", "verdict": "pass", "coverage": "partial", "reason": null }, { "id": "BU10", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU12", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU06", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU07", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU08", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU09", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU11", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU14", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU15", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU13", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU15", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU16", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU17", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU02", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU18", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU14", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU06", "verdict": "pass", "coverage": "no_violation_found", "reason": null }, { "id": "OU07", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU08", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU09", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU10", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU11", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU12", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU13", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU19", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU20", "verdict": "fail", "coverage": "selected_fixture", "reason": "Ведомость не прошла проверку группировки по значениям характеристик." }, { "id": "OU21", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR02", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR06", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR07", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR08", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR09", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR10", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR11", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR12", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR13", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR14", "verdict": "pass", "coverage": "no_violation_found", "reason": null }, { "id": "PR15", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR16", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR17", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR18", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR19", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F02", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "G01", "verdict": "pass", "coverage": "static_sources", "reason": null }, { "id": "G02", "verdict": "pass", "coverage": "static_sources", "reason": null }, { "id": "G03", "verdict": "pass", "coverage": "static_sources", "reason": null } ], "charges": [ { "id": "F1C-GEN03", "points": "0.5", "reason": "Ведомость не прошла проверку группировки по значениям характеристик." }, { "id": "F1C-GEN15", "points": "0.5", "reason": "CommonModules/УчетСервер/Ext/Module.bsl:41 — РегистрНакопления.ОстаткиНоменклатуры.Остатки: отбор по Подразделение, индексы таблицы начинаются с Номенклатура" }, { "id": "F1C-PR09", "points": "0.5", "reason": "CommonModules/УчетСервер/Ext/Module.bsl:349 — РегистрРасчета.Начисления.БазаНачисления: база получается без отбора по регистратору — по всем записям регистра" }, { "id": "F1C-PR09", "points": "0.5", "reason": "CommonModules/УчетСервер/Ext/Module.bsl:370 — РегистрРасчета.Начисления.БазаНачисления: база получается без отбора по регистратору — по всем записям регистра" }, { "id": "F1C-GEN15", "points": "0.5", "reason": "Reports/Ведомость/Ext/ManagerModule.bsl:2 — РегистрНакопления.ОстаткиНоменклатуры.ОстаткиИОбороты: отбор по Подразделение, индексы таблицы начинаются с Номенклатура" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "проводимые документы в режиме «Записывать модифицированные»: Операция, Сборка" }, { "id": "F1C-BU06", "points": "1.5", "reason": "ресурс Количество без признака учёта — количество ведётся на всех счетах" }, { "id": "F1C-BU05", "points": "0.5", "reason": "аналитика счетов вынесена в измерения регистра бухгалтерии и есть у всех счетов: Номенклатура (Номенклатура), Склад (Склады)" }, { "id": "F1C-PR08", "points": "2.0", "reason": "база берётся из основной таблицы регистра расчёта, БазаНачисления нигде не используется: Documents/НачислениеЗарплаты/Ext/ObjectModule.bsl:6" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "оперативное проведение разрешено у документов с движениями по регистрам расчёта: НачислениеЗарплаты" }, { "id": "F1C-GEN21", "points": "2.0", "reason": "данные графика без отбора по регистратору: CommonModules/УчетСервер/Ext/Module.bsl:316" } ], "score_upper_bound": "-5.5", "score": null, "grade": "unsatisfactory", "deductions": "10.5", "not_assessed": 16, "gates": { "starter_origin": "passed", "load": "loaded", "clients": "compiles", "demo_data": "present" }, "infrastructure_errors": false, "comparison_eligible": false, "binding_compatibility": null, "evaluation_sha256": "22fec963a39848e945ce687d0b2001f21c18c9b2be22ea97af76ced95d1c9157", "downloads": [] }, "measurement": { "operator": { "name": "Вячеслав", "github": "sksibak" }, "environment": { "captured_at": "2026-10-25T04:35:35.871356+00:00", "capture_timing": "before_run", "hardware": { "cpu": "AMD Ryzen 5 4600H with Radeon Graphics ", "logical_cpus": 12, "ram_bytes": 16505962496 }, "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "python": "3.12.14", "platform_version": "8.3.27.1644", "isolation": "dedicated-host", "network_profile": "open-book_shell", "unsafe_action_protection_observed_in_user_config": true, "git_revision": "af85e791b303dbbf0b0b7af924d2489c3e57cfa8", "implementation_files": { "exam_bench/__init__.py": "ad5bf6f05dc6765f40b78bd186870ca2c49be113cfa33f8aa76f4926f2cb2c1e", "exam_bench/assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "exam_bench/bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "exam_bench/calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "exam_bench/calibrate.py": "78b5185cb0888c0c0ac3de95ffc3a80154a6de9ae66fc461f79d012e5a58e1db", "exam_bench/calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "exam_bench/calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "exam_bench/calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "exam_bench/calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "exam_bench/calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "exam_bench/claude.py": "bc1b8550de7573aaed5e39c6e9c0309e0d8175284a75490d61ec27439ed911ad", "exam_bench/cli.py": "1a37ce645633d761f7897dffc9c45e6b8b9600cd7bd233b1cbf78f49d26b099a", "exam_bench/codescan.py": "751e38001b6e65727a31e28172a0623f0bf34bc092a958037c286aa991a197ed", "exam_bench/codex.py": "c3f89d72af11f312d851c73a1610d92e79acadf336be9ccedd1f94ede3b3ccb0", "exam_bench/common.py": "8682603b519063e655eae3574a02a49efee63bde21f582ccee20ddd623fca96d", "exam_bench/docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "exam_bench/examiner.py": "d7294fdd23ed1732216cafebf0a8cf2c24cce4259859aeb7149f62b7607d087d", "exam_bench/finalize.py": "4034f1c63896a940afdb1a83d541cf47fc75c8b5061e3f839047109c04beb620", "exam_bench/forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "exam_bench/gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "exam_bench/grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "exam_bench/harness.py": "3040f6daaf1dc6e6583219f4d925151f8ba7851b2d5417d7f14645892b485ddf", "exam_bench/interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "exam_bench/interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "exam_bench/isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "exam_bench/ledger.py": "7e851523580e22d8490e75f9b6026c07f2c355007e0d11d0b252671f56bef654", "exam_bench/locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "exam_bench/materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "exam_bench/mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "exam_bench/observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "exam_bench/ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "exam_bench/penalties.py": "0d79e2e46102657dca00609b6abbfc0bf7d11fad41429564f876c82bc6b33269", "exam_bench/platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "exam_bench/portable.py": "cad56968ff407983608f5bdbc9ce7234128d7a4580b096ecea8e0e7b4edb9070", "exam_bench/portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "exam_bench/pr.py": "6a3a20caf0e10c0cc94410511a72d62c9fcda785f3abab1be2ad616d4ee16836", "exam_bench/preflight.py": "5619be0131d8641925f3ce2a3c8e5234d42aa5635d95676138ca81536d95cd29", "exam_bench/process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "exam_bench/queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "exam_bench/queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "exam_bench/replay_calibration.py": "c150457b0b23ce4e6814eb8deb4d48f6bc4a2e39d8f84a9dc7644fb99a026c2d", "exam_bench/report.py": "5e4c0757e1c7f189953f9a5302593ab726551835856baed25efd93dad6e8bfcd", "exam_bench/runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "exam_bench/smoke_check.py": "f36922a0027429ead0b414048dcc14bbe67f2f0e79a70d03dffbe1447d253545", "exam_bench/stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "exam_bench/submission.py": "d6f9d20704181c51714f1138affe4965d860ae21475ab7bb49aa5c5cefebb9f5", "exam_bench/telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "exam_bench/windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "exam_bench/workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tools/build_public_site.py": "9682ed696f5ac9e9a82b65a45c0dece556ec7e49eeb20dcd616882cc534a8258", "tools/build_result_site.py": "3294e1d2ec1486058e208735264d61e349a68a4ae2fa2ec7a723c70e3263b496", "tools/check_native_harnesses.py": "4f5f0ed27651f78758eaef077b3b114361781f6b95ec40cb46c3fea689210473", "tools/check_native_toolkit.py": "0272794617121f2932828e5e4e9ae20095183c443666cf3ba466b44fbe875095", "tools/community_results.py": "9db56a44697d94f326efcbd7a3ae1aecdb569d43bba6c47e80ce525dc045f1f7", "tools/community_service.py": "c374480dbd88d656c0b9054fa04a8e1c6698c69e2f9cf475e82498a2dff61d84", "tools/community_setup.py": "5d7d126ed7d4dd48e1d79f57b99647a92ffcc8c9f80d90915e458888cdd76bf7", "tools/compare_harness_runs.py": "f274df5f3f804cb02504491aec946943833e12fbce6e62d281e12beb8508fc4e", "tools/create_run_plan.py": "871cd81b1eda231c0fba8805f63d2668926be9fc641559e6ddf320e2f47cd37a", "tools/demo_runner.py": "230e6e49068f2bab3a0db64e6da5889e8f1834158fed8c5ec334b7694695a87b", "tools/installers.py": "9a2742780936b17500869e7c89202c1a2549e37d53a42ad9a50a0abbf78bbe09", "tools/machine_bundle.py": "8aa8346f99f537e81ceca6fb6ab9530e844954bab8eff87bf33d3602f81f8a30", "tools/prepare_native_harnesses.py": "aaa75ecf4022883984fa50c42d14d8e1a9fde2eeda03dab03b852bbc5efb2502", "tools/prepare_official_statement.py": "6b7028c78e90e798d6ef1a93b76520cc61a308c354fb9b87f7fad18b99800fad", "tools/prepare_open_exam_requirements.py": "544f4e378b9be5f166186f8788f8d454afdac2deb99d91d98421e39d01ba6d03", "tools/probe_harness.py": "1ed8ef93420d1484cbbfd151b7efc31b9a201ceb942dd05e3103efa22ffa7f27", "tools/probe_native_mcp.py": "9918d324129cba898993e07f8f8b6dbcbaf369398ebf28d464f9f1f00abdb254", "tools/readiness.py": "d34dd3f38334f51cc4574c79194cf0b80769b062a52382989a57d01c46b9aba4", "tools/recheck_community.py": "f0843d7d677f90da31e22bde0b1c86584dd46c022f1532d43d042619e426b230", "tools/regrade_runs.py": "011775afb06d3aac67a4aa81117a368c75896b0fcbe1e6f27ccc6237612fbf59", "tools/render_statement_text.py": "dabc0716a3612c288c671bc20e17fd4986691d732768e1e957d6dddddbea92a3", "tools/replay_calibration.py": "801f5004926c438c21ed3668fe2a4ddf45312b3e75320165a3839aae034eee9b", "tools/run_exam_campaign.py": "2c450d57a1cd0a2682838f5ec7c0a4ffb3aed0f1730d34c408e912d59cab6efd", "tools/serve_result_site.py": "86badfac863cd4ad1fc894a14110c75b28470513f0133eeae9d2799b8b4df3a9", "tools/start_demo.py": "c597e6cad28d245b3191654bb3e2801fa9dd2364e2acb25561923613717b615f", "tools/supplemental_acceptance.py": "c88fc39de1be1fdcacdd819e2ad329f60367b2df1d5deda80b37324bda3f2a01", "tools/sync_sources.py": "b51e889b0f41f9f63bfb19a09fb96d3777693d6b1d76fe0132bdd2a15e155898", "tools/validate_community_pr.py": "796b896dfade07b4529af2088a4b9b9d23484148b3bc0732b3fb837b75c9844b", "tools/verify_official_assessment_mapping.py": "daeb448a016940d5b6b1285979a56e5b9014bd91db40acb131445e4a83a23059", "tools/verify_task_package.py": "9e1e6105f6b5e4e78b36aa57f00117a9fbc8948ab53983c32ab56da88d23ccc4", "profiles/agents.json": "af9c492c08d13b3044aa6b6952589ed6a0a07d5258d8ff72bb18185b3eaebdc5", "profiles/ai-exam-execution-policy.json": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "profiles/bsl-analyzer-0.3.2-macos.json": "83537abdbf38c41ce665e4d0f24128bb51b62e971e0e0f368695f1326a7d2ffb", "profiles/bsl-analyzer-0.3.2-portable.json": "d6ba732e6778e256df34d6bc548593128820a70430c35b279796843606ee40a8", "profiles/bsl-ls-1.1.0-rc.6-macos.json": "245fc10747197e6911b2b4c77cdb15e6fa4eb7bc7c3758b63e768c5adf1df180", "profiles/bsl-ls-1.1.0-rc.6-portable.json": "9f10660881f2ec84794f7d584556b8f75c7e14b3555464af0ed0e60c4c892d86", "profiles/code-index-1.9.0-macos.json": "63a919523ce62ecec274f4c139bc7ad49a75dd4c339568b822cbc695b4e30408", "profiles/code-index-1.9.0-portable.json": "81106cee8f424ffd8a9dc46ecd8e4f57598fc1d49661a83c77b1f0507993fbdc", "profiles/codex-probe-plan.json": "166e41aad5fb3b27d9050bc6de952c6cba363cc6e804d4080568cc71a2a4d289", "profiles/machine.linux.example.json": "408304fd0581098d5d8110dc67dfeab353bc4d4030e32d37e6acf98d2b1aedfd", "profiles/machine.macos.example.json": "52e9f9d17797cb520b9d8955d6806fd550b899bed4da241ebf096dcb6a21a942", "profiles/machine.windows.example.json": "63accac9a2f81d47d03447efbabffd4760aee325193f02f46b9b29a28d50d2d8", "profiles/mcp-toolkit-1.9.0-macos.json": "1d3f9cde5ffa20589a840d01fdae03aa0fc2f412c929f064f203919c4129625b", "profiles/mcp-toolkit-1.9.0-portable.json": "8e370eebe773eef0e08045ee9c6d5be1451f769f65be0710834b262a4336e054", "profiles/none-macos.json": "b1401d9c48159aed3559006c7f6ace6ef4571224d5cf0bb76d1a823505a10056", "profiles/none-portable.json": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "profiles/rlm-tools-bsl-1.43.0-macos.json": "9354421052640ab60bc3e6aa98ff2e7ba9ca2318b0f4026c137487449242cbd2", "profiles/rlm-tools-bsl-1.43.0-portable.json": "2599e5645e0a7d4e44cb2934bc2b272cae79a9bf7ea74a23cd48aacea64bc424", "profiles/rlm-tools-bsl-1.43.0-posix-requirements.txt": "4fdf9a1bd994bf0272e65d231daf76cf19b0a34dad0ae6b50ec4f11a2ce4c330", "profiles/rlm-tools-bsl-1.43.0-windows-requirements.txt": "3730cb46c81cda5181ecd4485e98b11933104632358bc86f8c0eb1a612a8954f", "profiles/shirokov-skills-macos.json": "84f3e89091676884a802035c707e912762a1179425fb8e3faff25be736873cdb", "profiles/shirokov-skills-portable.json": "2b0a461e06602f1456410e70f02ceaa5ac32c6549c486660bcb5ace0c2f87b15", "profiles/shirokov-skills-windows-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/unica-0.12.3-macos.json": "2c39fbb591cf2c2c6e056373823615485397ea83651b7926c6f25a5fe6a0aae6", "profiles/unica-0.13.0-macos.json": "b76b5c8a4dd33f571c4a90993f1a2da5f7223b4f0f8e1042c282e21a66121052", "profiles/unica-0.14.0-rc.1-portable.json": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "rules/1c-specialist-platform/chistov.json": "77e04942f8c947b10759e7cc1eb31af05847d1711a772fbe6f23d525766757a9", "rules/1c-specialist-platform/decisions.json": "f622107423ce3c188c063318d7ab4f7718ceb38e443130677d8987f386641c09", "rules/1c-specialist-platform/examiner.json": "30353aa2a1b6545496b070d9066e9ffba0c3779e5b53ef70a4fd2cee375b18c0", "rules/1c-specialist-platform/ledger.json": "f167c10db2b5799dd9a1ea6a37cd2d7d186810dadf5ea2f50f26ae723c676882", "rules/1c-specialist-platform/rules.json": "1d320a4f8e1bf4701496388931f492315549bd3dce574b17285dd1d7f8652007", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" } } }, "conditions": { "client": "codex", "model": "gpt-6.1-sol", "client_version": "0.163.0-alpha.11.2", "reasoning_effort": "medium", "harness": "unica-0.14.0-rc.1", "billing_channel": "subscription", "solve_timeout_seconds": 1800, "time_series": "fast", "delegation": "native_disabled", "network_profile": "open-book_shell", "deadline_disclosed": true, "statement_sha256": "8a6ccb3e673826d1f8220fda53eb310e3ec18c136d87ce8f4cebb2a08614e7e5", "starter_dt_sha256": "f40d084818b0d1cfe503fc7653a6a13f1a8e47fcd1688dad6245b12744eb4638", "profile_sha256": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "execution_policy_sha256": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "calibration_sha256": "e8981744a194aa56f954d2965aa66cd53cd4f899f09fa7b5abda6f6b27a5ed65", "started_at": "2026-10-25T04:35:46.776087+00:00", "timing": { "prepare_ms": 7953, "solve_ms": 1750093, "grade_ms": null }, "original_submission_valid": true, "model_provenance": "requested_only", "tokens": { "input": 15320636, "cached_input": 15152896, "fresh_input": 167740, "output": 69307, "reasoning_output": 16218, "total": 15389943, "coverage": "reported_completed_root_turns" }, "tools": { "mcp_calls": 238, "unica_calls": 238, "failed_calls": 26 }, "process": { "status": "completed", "exit_code": 0, "stop_confirmed": true } }, "verification": "contributor_reported", "download": "community-downloads/demo-20261025T113819Z-9d209c/solution.zip", "source_context": "community-downloads/demo-20261025T113819Z-9d209c/source-context.json", "regrade_required": [ { "id": "grader_changed", "files": [ "assessment.py", "bp.py", "calcwrite.py", "calibrate.py", "calibration_periodicity.py", "calibration_query.py", "claude.py", "codescan.py", "codex.py", "common.py", "docx_text.py", "examiner.py", "harness.py", "interpretations.py", "locking.py", "materials.py", "mcp_toolkit.py", "ou.py", "penalties.py", "portable_harnesses.py", "pr.py", "preflight.py", "queries.py", "queryschema.py", "querytypes.py", "replay_calibration.py", "rules/1c-specialist-platform/chistov.json", "rules/1c-specialist-platform/examiner.json", "rules/1c-specialist-platform/rules.json", "rules/1c-specialist-platform/standards.json", "smoke_check.py", "starters/carcass-8.3.25.1445/starter.json", "stdio_harnesses.py", "tasks/1c-platform-official-sample/checks.json", "tasks/1c-platform-official-sample/private/official-assessment-mapping.json", "tasks/1c-platform-official-sample/private/owner-scoring-policy.json", "telemetry.py" ] } ], "grader_revision_sha256": "855d4f66db31ec9f50ebfc18f596c0d1d157e53e2830c51f853c1338f628e49c", "archive_sha256": "0c99ac46b6b76b0dfd76e9db126fc7fd5240ecfa0cf45e9ee8e917b8870ecab4" }, { "id": "demo-20261025T043533Z-b8847b", "run_id": "demo-20261025T043533Z-b8847b", "result": { "run_id": "demo-20261025T043533Z-b8847b", "created_at": "2026-10-25T05:08:26.616972+00:00", "model": "gpt-6.1-sol", "harness": "unica-0.14.0-rc.1", "solve_seconds": 1750, "platform": "8.3.27.1644", "counts": { "pass": 64, "fail": 1 }, "rules": [ { "id": "BU01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU16", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU17", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU02", "verdict": "pass", "coverage": "partial", "reason": null }, { "id": "BU10", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU12", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU06", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU07", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU08", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU09", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU11", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU14", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU15", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU13", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU15", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU16", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU17", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU02", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU18", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU14", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU06", "verdict": "pass", "coverage": "no_violation_found", "reason": null }, { "id": "OU07", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU08", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU09", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU10", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU11", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU12", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU13", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU19", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU20", "verdict": "fail", "coverage": "selected_fixture", "reason": "Ведомость не прошла проверку группировки по значениям характеристик." }, { "id": "OU21", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR02", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR06", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR07", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR08", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR09", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR10", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR11", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR12", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR13", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR14", "verdict": "pass", "coverage": "no_violation_found", "reason": null }, { "id": "PR15", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR16", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR17", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR18", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR19", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F02", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "G01", "verdict": "pass", "coverage": "static_sources", "reason": null }, { "id": "G02", "verdict": "pass", "coverage": "static_sources", "reason": null }, { "id": "G03", "verdict": "pass", "coverage": "static_sources", "reason": null } ], "charges": [ { "id": "F1C-GEN03", "points": "0.5", "reason": "Ведомость не прошла проверку группировки по значениям характеристик." }, { "id": "F1C-GEN15", "points": "0.5", "reason": "CommonModules/УчетСервер/Ext/Module.bsl:41 — РегистрНакопления.ОстаткиНоменклатуры.Остатки: отбор по Подразделение, индексы таблицы начинаются с Номенклатура" }, { "id": "F1C-PR09", "points": "0.5", "reason": "CommonModules/УчетСервер/Ext/Module.bsl:349 — РегистрРасчета.Начисления.БазаНачисления: база получается без отбора по регистратору — по всем записям регистра" }, { "id": "F1C-PR09", "points": "0.5", "reason": "CommonModules/УчетСервер/Ext/Module.bsl:370 — РегистрРасчета.Начисления.БазаНачисления: база получается без отбора по регистратору — по всем записям регистра" }, { "id": "F1C-GEN15", "points": "0.5", "reason": "Reports/Ведомость/Ext/ManagerModule.bsl:2 — РегистрНакопления.ОстаткиНоменклатуры.ОстаткиИОбороты: отбор по Подразделение, индексы таблицы начинаются с Номенклатура" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "проводимые документы в режиме «Записывать модифицированные»: Операция, Сборка" }, { "id": "F1C-BU06", "points": "1.5", "reason": "ресурс Количество без признака учёта — количество ведётся на всех счетах" }, { "id": "F1C-BU05", "points": "0.5", "reason": "аналитика счетов вынесена в измерения регистра бухгалтерии и есть у всех счетов: Номенклатура (Номенклатура), Склад (Склады)" }, { "id": "F1C-PR08", "points": "2.0", "reason": "база берётся из основной таблицы регистра расчёта, БазаНачисления нигде не используется: Documents/НачислениеЗарплаты/Ext/ObjectModule.bsl:6" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "оперативное проведение разрешено у документов с движениями по регистрам расчёта: НачислениеЗарплаты" }, { "id": "F1C-GEN21", "points": "2.0", "reason": "данные графика без отбора по регистратору: CommonModules/УчетСервер/Ext/Module.bsl:316" } ], "score_upper_bound": "-5.5", "score": null, "grade": "unsatisfactory", "deductions": "10.5", "not_assessed": 16, "gates": { "starter_origin": "passed", "load": "loaded", "clients": "compiles", "demo_data": "present" }, "infrastructure_errors": false, "comparison_eligible": false, "binding_compatibility": null, "evaluation_sha256": "c369f48d79d0a1df1ee1a8742ff279e510ab50cdc483c20541b2d6989dff5c4f", "downloads": [] }, "measurement": { "operator": { "name": "Вячеслав", "github": "sksibak" }, "environment": { "captured_at": "2026-10-25T04:35:35.871356+00:00", "capture_timing": "before_run", "hardware": { "cpu": "AMD Ryzen 5 4600H with Radeon Graphics ", "logical_cpus": 12, "ram_bytes": 16505962496 }, "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "python": "3.12.14", "platform_version": "8.3.27.1644", "isolation": "dedicated-host", "network_profile": "open-book_shell", "unsafe_action_protection_observed_in_user_config": true, "git_revision": "af85e791b303dbbf0b0b7af924d2489c3e57cfa8", "implementation_files": { "exam_bench/__init__.py": "ad5bf6f05dc6765f40b78bd186870ca2c49be113cfa33f8aa76f4926f2cb2c1e", "exam_bench/assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "exam_bench/bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "exam_bench/calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "exam_bench/calibrate.py": "78b5185cb0888c0c0ac3de95ffc3a80154a6de9ae66fc461f79d012e5a58e1db", "exam_bench/calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "exam_bench/calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "exam_bench/calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "exam_bench/calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "exam_bench/calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "exam_bench/claude.py": "bc1b8550de7573aaed5e39c6e9c0309e0d8175284a75490d61ec27439ed911ad", "exam_bench/cli.py": "1a37ce645633d761f7897dffc9c45e6b8b9600cd7bd233b1cbf78f49d26b099a", "exam_bench/codescan.py": "751e38001b6e65727a31e28172a0623f0bf34bc092a958037c286aa991a197ed", "exam_bench/codex.py": "c3f89d72af11f312d851c73a1610d92e79acadf336be9ccedd1f94ede3b3ccb0", "exam_bench/common.py": "8682603b519063e655eae3574a02a49efee63bde21f582ccee20ddd623fca96d", "exam_bench/docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "exam_bench/examiner.py": "d7294fdd23ed1732216cafebf0a8cf2c24cce4259859aeb7149f62b7607d087d", "exam_bench/finalize.py": "4034f1c63896a940afdb1a83d541cf47fc75c8b5061e3f839047109c04beb620", "exam_bench/forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "exam_bench/gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "exam_bench/grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "exam_bench/harness.py": "3040f6daaf1dc6e6583219f4d925151f8ba7851b2d5417d7f14645892b485ddf", "exam_bench/interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "exam_bench/interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "exam_bench/isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "exam_bench/ledger.py": "7e851523580e22d8490e75f9b6026c07f2c355007e0d11d0b252671f56bef654", "exam_bench/locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "exam_bench/materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "exam_bench/mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "exam_bench/observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "exam_bench/ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "exam_bench/penalties.py": "0d79e2e46102657dca00609b6abbfc0bf7d11fad41429564f876c82bc6b33269", "exam_bench/platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "exam_bench/portable.py": "cad56968ff407983608f5bdbc9ce7234128d7a4580b096ecea8e0e7b4edb9070", "exam_bench/portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "exam_bench/pr.py": "6a3a20caf0e10c0cc94410511a72d62c9fcda785f3abab1be2ad616d4ee16836", "exam_bench/preflight.py": "5619be0131d8641925f3ce2a3c8e5234d42aa5635d95676138ca81536d95cd29", "exam_bench/process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "exam_bench/queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "exam_bench/queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "exam_bench/replay_calibration.py": "c150457b0b23ce4e6814eb8deb4d48f6bc4a2e39d8f84a9dc7644fb99a026c2d", "exam_bench/report.py": "5e4c0757e1c7f189953f9a5302593ab726551835856baed25efd93dad6e8bfcd", "exam_bench/runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "exam_bench/smoke_check.py": "f36922a0027429ead0b414048dcc14bbe67f2f0e79a70d03dffbe1447d253545", "exam_bench/stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "exam_bench/submission.py": "d6f9d20704181c51714f1138affe4965d860ae21475ab7bb49aa5c5cefebb9f5", "exam_bench/telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "exam_bench/windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "exam_bench/workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tools/build_public_site.py": "9682ed696f5ac9e9a82b65a45c0dece556ec7e49eeb20dcd616882cc534a8258", "tools/build_result_site.py": "3294e1d2ec1486058e208735264d61e349a68a4ae2fa2ec7a723c70e3263b496", "tools/check_native_harnesses.py": "4f5f0ed27651f78758eaef077b3b114361781f6b95ec40cb46c3fea689210473", "tools/check_native_toolkit.py": "0272794617121f2932828e5e4e9ae20095183c443666cf3ba466b44fbe875095", "tools/community_results.py": "9db56a44697d94f326efcbd7a3ae1aecdb569d43bba6c47e80ce525dc045f1f7", "tools/community_service.py": "c374480dbd88d656c0b9054fa04a8e1c6698c69e2f9cf475e82498a2dff61d84", "tools/community_setup.py": "5d7d126ed7d4dd48e1d79f57b99647a92ffcc8c9f80d90915e458888cdd76bf7", "tools/compare_harness_runs.py": "f274df5f3f804cb02504491aec946943833e12fbce6e62d281e12beb8508fc4e", "tools/create_run_plan.py": "871cd81b1eda231c0fba8805f63d2668926be9fc641559e6ddf320e2f47cd37a", "tools/demo_runner.py": "230e6e49068f2bab3a0db64e6da5889e8f1834158fed8c5ec334b7694695a87b", "tools/installers.py": "9a2742780936b17500869e7c89202c1a2549e37d53a42ad9a50a0abbf78bbe09", "tools/machine_bundle.py": "8aa8346f99f537e81ceca6fb6ab9530e844954bab8eff87bf33d3602f81f8a30", "tools/prepare_native_harnesses.py": "aaa75ecf4022883984fa50c42d14d8e1a9fde2eeda03dab03b852bbc5efb2502", "tools/prepare_official_statement.py": "6b7028c78e90e798d6ef1a93b76520cc61a308c354fb9b87f7fad18b99800fad", "tools/prepare_open_exam_requirements.py": "544f4e378b9be5f166186f8788f8d454afdac2deb99d91d98421e39d01ba6d03", "tools/probe_harness.py": "1ed8ef93420d1484cbbfd151b7efc31b9a201ceb942dd05e3103efa22ffa7f27", "tools/probe_native_mcp.py": "9918d324129cba898993e07f8f8b6dbcbaf369398ebf28d464f9f1f00abdb254", "tools/readiness.py": "d34dd3f38334f51cc4574c79194cf0b80769b062a52382989a57d01c46b9aba4", "tools/recheck_community.py": "f0843d7d677f90da31e22bde0b1c86584dd46c022f1532d43d042619e426b230", "tools/regrade_runs.py": "011775afb06d3aac67a4aa81117a368c75896b0fcbe1e6f27ccc6237612fbf59", "tools/render_statement_text.py": "dabc0716a3612c288c671bc20e17fd4986691d732768e1e957d6dddddbea92a3", "tools/replay_calibration.py": "801f5004926c438c21ed3668fe2a4ddf45312b3e75320165a3839aae034eee9b", "tools/run_exam_campaign.py": "2c450d57a1cd0a2682838f5ec7c0a4ffb3aed0f1730d34c408e912d59cab6efd", "tools/serve_result_site.py": "86badfac863cd4ad1fc894a14110c75b28470513f0133eeae9d2799b8b4df3a9", "tools/start_demo.py": "c597e6cad28d245b3191654bb3e2801fa9dd2364e2acb25561923613717b615f", "tools/supplemental_acceptance.py": "c88fc39de1be1fdcacdd819e2ad329f60367b2df1d5deda80b37324bda3f2a01", "tools/sync_sources.py": "b51e889b0f41f9f63bfb19a09fb96d3777693d6b1d76fe0132bdd2a15e155898", "tools/validate_community_pr.py": "796b896dfade07b4529af2088a4b9b9d23484148b3bc0732b3fb837b75c9844b", "tools/verify_official_assessment_mapping.py": "daeb448a016940d5b6b1285979a56e5b9014bd91db40acb131445e4a83a23059", "tools/verify_task_package.py": "9e1e6105f6b5e4e78b36aa57f00117a9fbc8948ab53983c32ab56da88d23ccc4", "profiles/agents.json": "af9c492c08d13b3044aa6b6952589ed6a0a07d5258d8ff72bb18185b3eaebdc5", "profiles/ai-exam-execution-policy.json": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "profiles/bsl-analyzer-0.3.2-macos.json": "83537abdbf38c41ce665e4d0f24128bb51b62e971e0e0f368695f1326a7d2ffb", "profiles/bsl-analyzer-0.3.2-portable.json": "d6ba732e6778e256df34d6bc548593128820a70430c35b279796843606ee40a8", "profiles/bsl-ls-1.1.0-rc.6-macos.json": "245fc10747197e6911b2b4c77cdb15e6fa4eb7bc7c3758b63e768c5adf1df180", "profiles/bsl-ls-1.1.0-rc.6-portable.json": "9f10660881f2ec84794f7d584556b8f75c7e14b3555464af0ed0e60c4c892d86", "profiles/code-index-1.9.0-macos.json": "63a919523ce62ecec274f4c139bc7ad49a75dd4c339568b822cbc695b4e30408", "profiles/code-index-1.9.0-portable.json": "81106cee8f424ffd8a9dc46ecd8e4f57598fc1d49661a83c77b1f0507993fbdc", "profiles/codex-probe-plan.json": "166e41aad5fb3b27d9050bc6de952c6cba363cc6e804d4080568cc71a2a4d289", "profiles/machine.linux.example.json": "408304fd0581098d5d8110dc67dfeab353bc4d4030e32d37e6acf98d2b1aedfd", "profiles/machine.macos.example.json": "52e9f9d17797cb520b9d8955d6806fd550b899bed4da241ebf096dcb6a21a942", "profiles/machine.windows.example.json": "63accac9a2f81d47d03447efbabffd4760aee325193f02f46b9b29a28d50d2d8", "profiles/mcp-toolkit-1.9.0-macos.json": "1d3f9cde5ffa20589a840d01fdae03aa0fc2f412c929f064f203919c4129625b", "profiles/mcp-toolkit-1.9.0-portable.json": "8e370eebe773eef0e08045ee9c6d5be1451f769f65be0710834b262a4336e054", "profiles/none-macos.json": "b1401d9c48159aed3559006c7f6ace6ef4571224d5cf0bb76d1a823505a10056", "profiles/none-portable.json": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "profiles/rlm-tools-bsl-1.43.0-macos.json": "9354421052640ab60bc3e6aa98ff2e7ba9ca2318b0f4026c137487449242cbd2", "profiles/rlm-tools-bsl-1.43.0-portable.json": "2599e5645e0a7d4e44cb2934bc2b272cae79a9bf7ea74a23cd48aacea64bc424", "profiles/rlm-tools-bsl-1.43.0-posix-requirements.txt": "4fdf9a1bd994bf0272e65d231daf76cf19b0a34dad0ae6b50ec4f11a2ce4c330", "profiles/rlm-tools-bsl-1.43.0-windows-requirements.txt": "3730cb46c81cda5181ecd4485e98b11933104632358bc86f8c0eb1a612a8954f", "profiles/shirokov-skills-macos.json": "84f3e89091676884a802035c707e912762a1179425fb8e3faff25be736873cdb", "profiles/shirokov-skills-portable.json": "2b0a461e06602f1456410e70f02ceaa5ac32c6549c486660bcb5ace0c2f87b15", "profiles/shirokov-skills-windows-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/unica-0.12.3-macos.json": "2c39fbb591cf2c2c6e056373823615485397ea83651b7926c6f25a5fe6a0aae6", "profiles/unica-0.13.0-macos.json": "b76b5c8a4dd33f571c4a90993f1a2da5f7223b4f0f8e1042c282e21a66121052", "profiles/unica-0.14.0-rc.1-portable.json": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "rules/1c-specialist-platform/chistov.json": "77e04942f8c947b10759e7cc1eb31af05847d1711a772fbe6f23d525766757a9", "rules/1c-specialist-platform/decisions.json": "f622107423ce3c188c063318d7ab4f7718ceb38e443130677d8987f386641c09", "rules/1c-specialist-platform/examiner.json": "30353aa2a1b6545496b070d9066e9ffba0c3779e5b53ef70a4fd2cee375b18c0", "rules/1c-specialist-platform/ledger.json": "f167c10db2b5799dd9a1ea6a37cd2d7d186810dadf5ea2f50f26ae723c676882", "rules/1c-specialist-platform/rules.json": "1d320a4f8e1bf4701496388931f492315549bd3dce574b17285dd1d7f8652007", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" } } }, "conditions": { "client": "codex", "model": "gpt-6.1-sol", "client_version": "0.163.0-alpha.11.2", "reasoning_effort": "medium", "harness": "unica-0.14.0-rc.1", "billing_channel": "subscription", "solve_timeout_seconds": 1800, "time_series": "fast", "delegation": "native_disabled", "network_profile": "open-book_shell", "deadline_disclosed": true, "statement_sha256": "8a6ccb3e673826d1f8220fda53eb310e3ec18c136d87ce8f4cebb2a08614e7e5", "starter_dt_sha256": "f40d084818b0d1cfe503fc7653a6a13f1a8e47fcd1688dad6245b12744eb4638", "profile_sha256": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "execution_policy_sha256": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "calibration_sha256": "e8981744a194aa56f954d2965aa66cd53cd4f899f09fa7b5abda6f6b27a5ed65", "started_at": "2026-10-25T04:35:46.776087+00:00", "timing": { "prepare_ms": 7953, "solve_ms": 1750093, "grade_ms": null }, "original_submission_valid": true, "model_provenance": "requested_only", "tokens": { "input": 15320636, "cached_input": 15152896, "fresh_input": 167740, "output": 69307, "reasoning_output": 16218, "total": 15389943, "coverage": "reported_completed_root_turns" }, "tools": { "mcp_calls": 238, "unica_calls": 238, "failed_calls": 26 }, "process": { "status": "completed", "exit_code": 0, "stop_confirmed": true } }, "verification": "contributor_reported", "download": "community-downloads/demo-20261025T043533Z-b8847b/solution.zip", "source_context": "community-downloads/demo-20261025T043533Z-b8847b/source-context.json", "regrade_required": [ { "id": "grader_changed", "files": [ "assessment.py", "bp.py", "calcwrite.py", "calibrate.py", "calibration_periodicity.py", "calibration_query.py", "claude.py", "codescan.py", "codex.py", "common.py", "docx_text.py", "examiner.py", "harness.py", "interpretations.py", "locking.py", "materials.py", "mcp_toolkit.py", "ou.py", "penalties.py", "portable_harnesses.py", "pr.py", "preflight.py", "queries.py", "queryschema.py", "querytypes.py", "replay_calibration.py", "rules/1c-specialist-platform/chistov.json", "rules/1c-specialist-platform/examiner.json", "rules/1c-specialist-platform/rules.json", "rules/1c-specialist-platform/standards.json", "smoke_check.py", "starters/carcass-8.3.25.1445/starter.json", "stdio_harnesses.py", "submission.py", "tasks/1c-platform-official-sample/checks.json", "tasks/1c-platform-official-sample/private/official-assessment-mapping.json", "tasks/1c-platform-official-sample/private/owner-scoring-policy.json", "telemetry.py" ] } ], "grader_revision_sha256": "13710d802a08278385c484500f48f1678e0b002e5c7a3d8c00e14c1e75b1fbe9", "archive_sha256": "1f823db228ecc0a62f5f636d290ee7498ad552c14916f78f429b392bcf866c3a" } ] }, { "id": "demo-20261025T114214Z-de8c5f", "run_id": "demo-20261025T052655Z-9c0f1c", "result": { "run_id": "demo-20261025T052655Z-9c0f1c", "created_at": "2026-10-25T11:46:14.029458+00:00", "model": "gpt-6.1-sol", "harness": "unica-0.14.0-rc.1", "solve_seconds": 3524, "platform": "8.3.27.1644", "counts": { "pass": 55, "inconclusive": 10 }, "rules": [ { "id": "BU01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU16", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU17", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU02", "verdict": "pass", "coverage": "partial", "reason": null }, { "id": "BU10", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU12", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU06", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU07", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU08", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU09", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU11", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU14", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU15", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU13", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU15", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU16", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU17", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU02", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU18", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU14", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU01", "verdict": "inconclusive", "coverage": "selected_fixture", "reason": null }, { "id": "OU03", "verdict": "inconclusive", "coverage": "selected_fixture", "reason": null }, { "id": "OU05", "verdict": "inconclusive", "coverage": "selected_fixture", "reason": null }, { "id": "OU06", "verdict": "pass", "coverage": "no_violation_found", "reason": null }, { "id": "OU07", "verdict": "inconclusive", "coverage": "selected_fixture", "reason": null }, { "id": "OU08", "verdict": "inconclusive", "coverage": "selected_fixture", "reason": null }, { "id": "OU09", "verdict": "inconclusive", "coverage": "selected_fixture", "reason": null }, { "id": "OU10", "verdict": "inconclusive", "coverage": "selected_fixture", "reason": null }, { "id": "OU11", "verdict": "inconclusive", "coverage": "selected_fixture", "reason": null }, { "id": "OU12", "verdict": "inconclusive", "coverage": "selected_fixture", "reason": null }, { "id": "OU13", "verdict": "inconclusive", "coverage": "selected_fixture", "reason": null }, { "id": "OU04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU19", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU20", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU21", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR02", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR06", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR07", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR08", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR09", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR10", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR11", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR12", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR13", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR14", "verdict": "pass", "coverage": "no_violation_found", "reason": null }, { "id": "PR15", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR16", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR17", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR18", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR19", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F02", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "G01", "verdict": "pass", "coverage": "static_sources", "reason": null }, { "id": "G02", "verdict": "pass", "coverage": "static_sources", "reason": null }, { "id": "G03", "verdict": "pass", "coverage": "static_sources", "reason": null } ], "charges": [ { "id": "F1C-GEN15", "points": "0.5", "reason": "Reports/Ведомость/Ext/ManagerModule.bsl:8 — РегистрНакопления.ОстаткиНоменклатуры.ОстаткиИОбороты: отбор по Подразделение, Свойство, индексы таблицы начинаются с Номенклатура" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "проводимые документы в режиме «Записывать модифицированные»: Операция, Сборка" }, { "id": "F1C-GEN21", "points": "2.0", "reason": "параметры виртуальной таблицы не заданы или заменены условием ГДЕ: CommonModules/УчетСервер/Ext/Module.bsl:96 РегистрНакопления.ОстаткиНоменклатуры.Остатки(,; CommonModules/УчетСервер/Ext/Module.bsl:296 РегистрБухгалтерии.Управленческий.Остатки(,; CommonModules/УчетСервер/Ext/Module.bsl:339 РегистрБухгалтерии.Управленческий.Остатки(," }, { "id": "F1C-GEN28", "points": "1.0", "reason": "оперативное проведение разрешено у документов с движениями по регистрам расчёта: НачислениеЗарплаты" }, { "id": "F1C-GEN22", "points": "1.0", "reason": "значения графика выбираются без ЕСТЬNULL: CommonModules/РасчетЗарплаты/Ext/Module.bsl:69 ДниПериодДействия, ДниФактическийПериодДействия, ЗначениеФактическийПериодДействия" } ], "score_upper_bound": "-0.5", "score": null, "grade": "unsatisfactory", "deductions": "5.5", "not_assessed": 17, "gates": { "starter_origin": "passed", "load": "loaded", "clients": "compiles", "demo_data": "present" }, "infrastructure_errors": true, "comparison_eligible": false, "binding_compatibility": null, "evaluation_sha256": "b1449a5a4b0a114958d92efaa7d7587ba628b6a9953644911a88a996b14778e6", "downloads": [] }, "measurement": { "operator": { "name": "Вячеслав", "github": "sksibak" }, "environment": { "captured_at": "2026-10-25T05:26:58.072855+00:00", "capture_timing": "before_run", "hardware": { "cpu": "AMD Ryzen 5 4600H with Radeon Graphics ", "logical_cpus": 12, "ram_bytes": 16505962496 }, "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "python": "3.12.14", "platform_version": "8.3.27.1644", "isolation": "dedicated-host", "network_profile": "open-book_shell", "unsafe_action_protection_observed_in_user_config": true, "git_revision": "af85e791b303dbbf0b0b7af924d2489c3e57cfa8", "implementation_files": { "exam_bench/__init__.py": "ad5bf6f05dc6765f40b78bd186870ca2c49be113cfa33f8aa76f4926f2cb2c1e", "exam_bench/assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "exam_bench/bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "exam_bench/calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "exam_bench/calibrate.py": "78b5185cb0888c0c0ac3de95ffc3a80154a6de9ae66fc461f79d012e5a58e1db", "exam_bench/calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "exam_bench/calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "exam_bench/calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "exam_bench/calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "exam_bench/calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "exam_bench/claude.py": "bc1b8550de7573aaed5e39c6e9c0309e0d8175284a75490d61ec27439ed911ad", "exam_bench/cli.py": "1a37ce645633d761f7897dffc9c45e6b8b9600cd7bd233b1cbf78f49d26b099a", "exam_bench/codescan.py": "751e38001b6e65727a31e28172a0623f0bf34bc092a958037c286aa991a197ed", "exam_bench/codex.py": "c3f89d72af11f312d851c73a1610d92e79acadf336be9ccedd1f94ede3b3ccb0", "exam_bench/common.py": "8682603b519063e655eae3574a02a49efee63bde21f582ccee20ddd623fca96d", "exam_bench/docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "exam_bench/examiner.py": "d7294fdd23ed1732216cafebf0a8cf2c24cce4259859aeb7149f62b7607d087d", "exam_bench/finalize.py": "4034f1c63896a940afdb1a83d541cf47fc75c8b5061e3f839047109c04beb620", "exam_bench/forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "exam_bench/gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "exam_bench/grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "exam_bench/harness.py": "3040f6daaf1dc6e6583219f4d925151f8ba7851b2d5417d7f14645892b485ddf", "exam_bench/interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "exam_bench/interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "exam_bench/isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "exam_bench/ledger.py": "7e851523580e22d8490e75f9b6026c07f2c355007e0d11d0b252671f56bef654", "exam_bench/locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "exam_bench/materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "exam_bench/mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "exam_bench/observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "exam_bench/ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "exam_bench/penalties.py": "0d79e2e46102657dca00609b6abbfc0bf7d11fad41429564f876c82bc6b33269", "exam_bench/platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "exam_bench/portable.py": "cad56968ff407983608f5bdbc9ce7234128d7a4580b096ecea8e0e7b4edb9070", "exam_bench/portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "exam_bench/pr.py": "6a3a20caf0e10c0cc94410511a72d62c9fcda785f3abab1be2ad616d4ee16836", "exam_bench/preflight.py": "5619be0131d8641925f3ce2a3c8e5234d42aa5635d95676138ca81536d95cd29", "exam_bench/process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "exam_bench/queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "exam_bench/queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "exam_bench/replay_calibration.py": "c150457b0b23ce4e6814eb8deb4d48f6bc4a2e39d8f84a9dc7644fb99a026c2d", "exam_bench/report.py": "5e4c0757e1c7f189953f9a5302593ab726551835856baed25efd93dad6e8bfcd", "exam_bench/runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "exam_bench/smoke_check.py": "f36922a0027429ead0b414048dcc14bbe67f2f0e79a70d03dffbe1447d253545", "exam_bench/stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "exam_bench/submission.py": "d6f9d20704181c51714f1138affe4965d860ae21475ab7bb49aa5c5cefebb9f5", "exam_bench/telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "exam_bench/windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "exam_bench/workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tools/build_public_site.py": "9682ed696f5ac9e9a82b65a45c0dece556ec7e49eeb20dcd616882cc534a8258", "tools/build_result_site.py": "3294e1d2ec1486058e208735264d61e349a68a4ae2fa2ec7a723c70e3263b496", "tools/check_native_harnesses.py": "4f5f0ed27651f78758eaef077b3b114361781f6b95ec40cb46c3fea689210473", "tools/check_native_toolkit.py": "0272794617121f2932828e5e4e9ae20095183c443666cf3ba466b44fbe875095", "tools/community_results.py": "9db56a44697d94f326efcbd7a3ae1aecdb569d43bba6c47e80ce525dc045f1f7", "tools/community_service.py": "c374480dbd88d656c0b9054fa04a8e1c6698c69e2f9cf475e82498a2dff61d84", "tools/community_setup.py": "5d7d126ed7d4dd48e1d79f57b99647a92ffcc8c9f80d90915e458888cdd76bf7", "tools/compare_harness_runs.py": "f274df5f3f804cb02504491aec946943833e12fbce6e62d281e12beb8508fc4e", "tools/create_run_plan.py": "871cd81b1eda231c0fba8805f63d2668926be9fc641559e6ddf320e2f47cd37a", "tools/demo_runner.py": "230e6e49068f2bab3a0db64e6da5889e8f1834158fed8c5ec334b7694695a87b", "tools/installers.py": "9a2742780936b17500869e7c89202c1a2549e37d53a42ad9a50a0abbf78bbe09", "tools/machine_bundle.py": "8aa8346f99f537e81ceca6fb6ab9530e844954bab8eff87bf33d3602f81f8a30", "tools/prepare_native_harnesses.py": "aaa75ecf4022883984fa50c42d14d8e1a9fde2eeda03dab03b852bbc5efb2502", "tools/prepare_official_statement.py": "6b7028c78e90e798d6ef1a93b76520cc61a308c354fb9b87f7fad18b99800fad", "tools/prepare_open_exam_requirements.py": "544f4e378b9be5f166186f8788f8d454afdac2deb99d91d98421e39d01ba6d03", "tools/probe_harness.py": "1ed8ef93420d1484cbbfd151b7efc31b9a201ceb942dd05e3103efa22ffa7f27", "tools/probe_native_mcp.py": "9918d324129cba898993e07f8f8b6dbcbaf369398ebf28d464f9f1f00abdb254", "tools/readiness.py": "d34dd3f38334f51cc4574c79194cf0b80769b062a52382989a57d01c46b9aba4", "tools/recheck_community.py": "f0843d7d677f90da31e22bde0b1c86584dd46c022f1532d43d042619e426b230", "tools/regrade_runs.py": "011775afb06d3aac67a4aa81117a368c75896b0fcbe1e6f27ccc6237612fbf59", "tools/render_statement_text.py": "dabc0716a3612c288c671bc20e17fd4986691d732768e1e957d6dddddbea92a3", "tools/replay_calibration.py": "801f5004926c438c21ed3668fe2a4ddf45312b3e75320165a3839aae034eee9b", "tools/run_exam_campaign.py": "2c450d57a1cd0a2682838f5ec7c0a4ffb3aed0f1730d34c408e912d59cab6efd", "tools/serve_result_site.py": "86badfac863cd4ad1fc894a14110c75b28470513f0133eeae9d2799b8b4df3a9", "tools/start_demo.py": "c597e6cad28d245b3191654bb3e2801fa9dd2364e2acb25561923613717b615f", "tools/supplemental_acceptance.py": "c88fc39de1be1fdcacdd819e2ad329f60367b2df1d5deda80b37324bda3f2a01", "tools/sync_sources.py": "b51e889b0f41f9f63bfb19a09fb96d3777693d6b1d76fe0132bdd2a15e155898", "tools/validate_community_pr.py": "796b896dfade07b4529af2088a4b9b9d23484148b3bc0732b3fb837b75c9844b", "tools/verify_official_assessment_mapping.py": "daeb448a016940d5b6b1285979a56e5b9014bd91db40acb131445e4a83a23059", "tools/verify_task_package.py": "9e1e6105f6b5e4e78b36aa57f00117a9fbc8948ab53983c32ab56da88d23ccc4", "profiles/agents.json": "af9c492c08d13b3044aa6b6952589ed6a0a07d5258d8ff72bb18185b3eaebdc5", "profiles/ai-exam-execution-policy.json": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "profiles/bsl-analyzer-0.3.2-macos.json": "83537abdbf38c41ce665e4d0f24128bb51b62e971e0e0f368695f1326a7d2ffb", "profiles/bsl-analyzer-0.3.2-portable.json": "d6ba732e6778e256df34d6bc548593128820a70430c35b279796843606ee40a8", "profiles/bsl-ls-1.1.0-rc.6-macos.json": "245fc10747197e6911b2b4c77cdb15e6fa4eb7bc7c3758b63e768c5adf1df180", "profiles/bsl-ls-1.1.0-rc.6-portable.json": "9f10660881f2ec84794f7d584556b8f75c7e14b3555464af0ed0e60c4c892d86", "profiles/code-index-1.9.0-macos.json": "63a919523ce62ecec274f4c139bc7ad49a75dd4c339568b822cbc695b4e30408", "profiles/code-index-1.9.0-portable.json": "81106cee8f424ffd8a9dc46ecd8e4f57598fc1d49661a83c77b1f0507993fbdc", "profiles/codex-probe-plan.json": "166e41aad5fb3b27d9050bc6de952c6cba363cc6e804d4080568cc71a2a4d289", "profiles/machine.linux.example.json": "408304fd0581098d5d8110dc67dfeab353bc4d4030e32d37e6acf98d2b1aedfd", "profiles/machine.macos.example.json": "52e9f9d17797cb520b9d8955d6806fd550b899bed4da241ebf096dcb6a21a942", "profiles/machine.windows.example.json": "63accac9a2f81d47d03447efbabffd4760aee325193f02f46b9b29a28d50d2d8", "profiles/mcp-toolkit-1.9.0-macos.json": "1d3f9cde5ffa20589a840d01fdae03aa0fc2f412c929f064f203919c4129625b", "profiles/mcp-toolkit-1.9.0-portable.json": "8e370eebe773eef0e08045ee9c6d5be1451f769f65be0710834b262a4336e054", "profiles/none-macos.json": "b1401d9c48159aed3559006c7f6ace6ef4571224d5cf0bb76d1a823505a10056", "profiles/none-portable.json": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "profiles/rlm-tools-bsl-1.43.0-macos.json": "9354421052640ab60bc3e6aa98ff2e7ba9ca2318b0f4026c137487449242cbd2", "profiles/rlm-tools-bsl-1.43.0-portable.json": "2599e5645e0a7d4e44cb2934bc2b272cae79a9bf7ea74a23cd48aacea64bc424", "profiles/rlm-tools-bsl-1.43.0-posix-requirements.txt": "4fdf9a1bd994bf0272e65d231daf76cf19b0a34dad0ae6b50ec4f11a2ce4c330", "profiles/rlm-tools-bsl-1.43.0-windows-requirements.txt": "3730cb46c81cda5181ecd4485e98b11933104632358bc86f8c0eb1a612a8954f", "profiles/shirokov-skills-macos.json": "84f3e89091676884a802035c707e912762a1179425fb8e3faff25be736873cdb", "profiles/shirokov-skills-portable.json": "2b0a461e06602f1456410e70f02ceaa5ac32c6549c486660bcb5ace0c2f87b15", "profiles/shirokov-skills-windows-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/unica-0.12.3-macos.json": "2c39fbb591cf2c2c6e056373823615485397ea83651b7926c6f25a5fe6a0aae6", "profiles/unica-0.13.0-macos.json": "b76b5c8a4dd33f571c4a90993f1a2da5f7223b4f0f8e1042c282e21a66121052", "profiles/unica-0.14.0-rc.1-portable.json": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "rules/1c-specialist-platform/chistov.json": "77e04942f8c947b10759e7cc1eb31af05847d1711a772fbe6f23d525766757a9", "rules/1c-specialist-platform/decisions.json": "f622107423ce3c188c063318d7ab4f7718ceb38e443130677d8987f386641c09", "rules/1c-specialist-platform/examiner.json": "30353aa2a1b6545496b070d9066e9ffba0c3779e5b53ef70a4fd2cee375b18c0", "rules/1c-specialist-platform/ledger.json": "f167c10db2b5799dd9a1ea6a37cd2d7d186810dadf5ea2f50f26ae723c676882", "rules/1c-specialist-platform/rules.json": "1d320a4f8e1bf4701496388931f492315549bd3dce574b17285dd1d7f8652007", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" } } }, "conditions": { "client": "codex", "model": "gpt-6.1-sol", "client_version": "0.163.0-alpha.11.2", "reasoning_effort": "medium", "harness": "unica-0.14.0-rc.1", "billing_channel": "subscription", "solve_timeout_seconds": 3600, "time_series": null, "delegation": "native_disabled", "network_profile": "open-book_shell", "deadline_disclosed": true, "statement_sha256": "8a6ccb3e673826d1f8220fda53eb310e3ec18c136d87ce8f4cebb2a08614e7e5", "starter_dt_sha256": "f40d084818b0d1cfe503fc7653a6a13f1a8e47fcd1688dad6245b12744eb4638", "profile_sha256": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "execution_policy_sha256": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "calibration_sha256": "e8981744a194aa56f954d2965aa66cd53cd4f899f09fa7b5abda6f6b27a5ed65", "started_at": "2026-10-25T05:27:08.909870+00:00", "timing": { "prepare_ms": 7875, "solve_ms": 3523906, "grade_ms": null }, "original_submission_valid": true, "model_provenance": "requested_only", "tokens": { "input": 27733372, "cached_input": 27369344, "fresh_input": 364028, "output": 128032, "reasoning_output": 45106, "total": 27861404, "coverage": "reported_completed_root_turns" }, "tools": { "mcp_calls": 545, "unica_calls": 545, "failed_calls": 35 }, "process": { "status": "completed", "exit_code": 0, "stop_confirmed": true } }, "verification": "contributor_reported", "download": "community-downloads/demo-20261025T114214Z-de8c5f/solution.zip", "source_context": "community-downloads/demo-20261025T114214Z-de8c5f/source-context.json", "regrade_required": [ { "id": "grader_changed", "files": [ "assessment.py", "bp.py", "calcwrite.py", "calibrate.py", "calibration_periodicity.py", "calibration_query.py", "claude.py", "codescan.py", "codex.py", "common.py", "docx_text.py", "examiner.py", "harness.py", "interpretations.py", "locking.py", "materials.py", "mcp_toolkit.py", "ou.py", "penalties.py", "portable_harnesses.py", "pr.py", "preflight.py", "queries.py", "queryschema.py", "querytypes.py", "replay_calibration.py", "rules/1c-specialist-platform/chistov.json", "rules/1c-specialist-platform/examiner.json", "rules/1c-specialist-platform/rules.json", "rules/1c-specialist-platform/standards.json", "smoke_check.py", "starters/carcass-8.3.25.1445/starter.json", "stdio_harnesses.py", "tasks/1c-platform-official-sample/checks.json", "tasks/1c-platform-official-sample/private/official-assessment-mapping.json", "tasks/1c-platform-official-sample/private/owner-scoring-policy.json", "telemetry.py" ] } ], "grader_revision_sha256": "855d4f66db31ec9f50ebfc18f596c0d1d157e53e2830c51f853c1338f628e49c", "archive_sha256": "461a42e54cf51738a3539fff8aefcaff884a88af5f8f2b2ca3c87ff69e4ffd7c", "previous_evaluations": [ { "id": "demo-20261025T052655Z-9c0f1c", "run_id": "demo-20261025T052655Z-9c0f1c", "result": { "run_id": "demo-20261025T052655Z-9c0f1c", "created_at": "2026-10-25T06:29:24.405754+00:00", "model": "gpt-6.1-sol", "harness": "unica-0.14.0-rc.1", "solve_seconds": 3524, "platform": "8.3.27.1644", "counts": { "pass": 55, "inconclusive": 10 }, "rules": [ { "id": "BU01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU16", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU17", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU02", "verdict": "pass", "coverage": "partial", "reason": null }, { "id": "BU10", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU12", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU06", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU07", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU08", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU09", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU11", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU14", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU15", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU13", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU15", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU16", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU17", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU02", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU18", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU14", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU01", "verdict": "inconclusive", "coverage": "selected_fixture", "reason": null }, { "id": "OU03", "verdict": "inconclusive", "coverage": "selected_fixture", "reason": null }, { "id": "OU05", "verdict": "inconclusive", "coverage": "selected_fixture", "reason": null }, { "id": "OU06", "verdict": "pass", "coverage": "no_violation_found", "reason": null }, { "id": "OU07", "verdict": "inconclusive", "coverage": "selected_fixture", "reason": null }, { "id": "OU08", "verdict": "inconclusive", "coverage": "selected_fixture", "reason": null }, { "id": "OU09", "verdict": "inconclusive", "coverage": "selected_fixture", "reason": null }, { "id": "OU10", "verdict": "inconclusive", "coverage": "selected_fixture", "reason": null }, { "id": "OU11", "verdict": "inconclusive", "coverage": "selected_fixture", "reason": null }, { "id": "OU12", "verdict": "inconclusive", "coverage": "selected_fixture", "reason": null }, { "id": "OU13", "verdict": "inconclusive", "coverage": "selected_fixture", "reason": null }, { "id": "OU04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU19", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU20", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU21", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR02", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR06", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR07", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR08", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR09", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR10", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR11", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR12", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR13", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR14", "verdict": "pass", "coverage": "no_violation_found", "reason": null }, { "id": "PR15", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR16", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR17", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR18", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR19", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F02", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "G01", "verdict": "pass", "coverage": "static_sources", "reason": null }, { "id": "G02", "verdict": "pass", "coverage": "static_sources", "reason": null }, { "id": "G03", "verdict": "pass", "coverage": "static_sources", "reason": null } ], "charges": [ { "id": "F1C-GEN15", "points": "0.5", "reason": "Reports/Ведомость/Ext/ManagerModule.bsl:8 — РегистрНакопления.ОстаткиНоменклатуры.ОстаткиИОбороты: отбор по Подразделение, Свойство, индексы таблицы начинаются с Номенклатура" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "проводимые документы в режиме «Записывать модифицированные»: Операция, Сборка" }, { "id": "F1C-GEN21", "points": "2.0", "reason": "параметры виртуальной таблицы не заданы или заменены условием ГДЕ: CommonModules/УчетСервер/Ext/Module.bsl:96 РегистрНакопления.ОстаткиНоменклатуры.Остатки(,; CommonModules/УчетСервер/Ext/Module.bsl:296 РегистрБухгалтерии.Управленческий.Остатки(,; CommonModules/УчетСервер/Ext/Module.bsl:339 РегистрБухгалтерии.Управленческий.Остатки(," }, { "id": "F1C-GEN28", "points": "1.0", "reason": "оперативное проведение разрешено у документов с движениями по регистрам расчёта: НачислениеЗарплаты" }, { "id": "F1C-GEN22", "points": "1.0", "reason": "значения графика выбираются без ЕСТЬNULL: CommonModules/РасчетЗарплаты/Ext/Module.bsl:69 ДниПериодДействия, ДниФактическийПериодДействия, ЗначениеФактическийПериодДействия" } ], "score_upper_bound": "-0.5", "score": null, "grade": "unsatisfactory", "deductions": "5.5", "not_assessed": 17, "gates": { "starter_origin": "passed", "load": "loaded", "clients": "compiles", "demo_data": "present" }, "infrastructure_errors": true, "comparison_eligible": false, "binding_compatibility": null, "evaluation_sha256": "c5a765bc8a9b77b448d33ac79193b3059a55c4353f8448eb8f63de7216c65053", "downloads": [] }, "measurement": { "operator": { "name": "Вячеслав", "github": "sksibak" }, "environment": { "captured_at": "2026-10-25T05:26:58.072855+00:00", "capture_timing": "before_run", "hardware": { "cpu": "AMD Ryzen 5 4600H with Radeon Graphics ", "logical_cpus": 12, "ram_bytes": 16505962496 }, "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "python": "3.12.14", "platform_version": "8.3.27.1644", "isolation": "dedicated-host", "network_profile": "open-book_shell", "unsafe_action_protection_observed_in_user_config": true, "git_revision": "af85e791b303dbbf0b0b7af924d2489c3e57cfa8", "implementation_files": { "exam_bench/__init__.py": "ad5bf6f05dc6765f40b78bd186870ca2c49be113cfa33f8aa76f4926f2cb2c1e", "exam_bench/assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "exam_bench/bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "exam_bench/calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "exam_bench/calibrate.py": "78b5185cb0888c0c0ac3de95ffc3a80154a6de9ae66fc461f79d012e5a58e1db", "exam_bench/calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "exam_bench/calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "exam_bench/calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "exam_bench/calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "exam_bench/calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "exam_bench/claude.py": "bc1b8550de7573aaed5e39c6e9c0309e0d8175284a75490d61ec27439ed911ad", "exam_bench/cli.py": "1a37ce645633d761f7897dffc9c45e6b8b9600cd7bd233b1cbf78f49d26b099a", "exam_bench/codescan.py": "751e38001b6e65727a31e28172a0623f0bf34bc092a958037c286aa991a197ed", "exam_bench/codex.py": "c3f89d72af11f312d851c73a1610d92e79acadf336be9ccedd1f94ede3b3ccb0", "exam_bench/common.py": "8682603b519063e655eae3574a02a49efee63bde21f582ccee20ddd623fca96d", "exam_bench/docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "exam_bench/examiner.py": "d7294fdd23ed1732216cafebf0a8cf2c24cce4259859aeb7149f62b7607d087d", "exam_bench/finalize.py": "4034f1c63896a940afdb1a83d541cf47fc75c8b5061e3f839047109c04beb620", "exam_bench/forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "exam_bench/gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "exam_bench/grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "exam_bench/harness.py": "3040f6daaf1dc6e6583219f4d925151f8ba7851b2d5417d7f14645892b485ddf", "exam_bench/interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "exam_bench/interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "exam_bench/isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "exam_bench/ledger.py": "7e851523580e22d8490e75f9b6026c07f2c355007e0d11d0b252671f56bef654", "exam_bench/locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "exam_bench/materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "exam_bench/mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "exam_bench/observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "exam_bench/ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "exam_bench/penalties.py": "0d79e2e46102657dca00609b6abbfc0bf7d11fad41429564f876c82bc6b33269", "exam_bench/platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "exam_bench/portable.py": "cad56968ff407983608f5bdbc9ce7234128d7a4580b096ecea8e0e7b4edb9070", "exam_bench/portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "exam_bench/pr.py": "6a3a20caf0e10c0cc94410511a72d62c9fcda785f3abab1be2ad616d4ee16836", "exam_bench/preflight.py": "5619be0131d8641925f3ce2a3c8e5234d42aa5635d95676138ca81536d95cd29", "exam_bench/process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "exam_bench/queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "exam_bench/queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "exam_bench/replay_calibration.py": "c150457b0b23ce4e6814eb8deb4d48f6bc4a2e39d8f84a9dc7644fb99a026c2d", "exam_bench/report.py": "5e4c0757e1c7f189953f9a5302593ab726551835856baed25efd93dad6e8bfcd", "exam_bench/runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "exam_bench/smoke_check.py": "f36922a0027429ead0b414048dcc14bbe67f2f0e79a70d03dffbe1447d253545", "exam_bench/stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "exam_bench/submission.py": "d6f9d20704181c51714f1138affe4965d860ae21475ab7bb49aa5c5cefebb9f5", "exam_bench/telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "exam_bench/windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "exam_bench/workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tools/build_public_site.py": "9682ed696f5ac9e9a82b65a45c0dece556ec7e49eeb20dcd616882cc534a8258", "tools/build_result_site.py": "3294e1d2ec1486058e208735264d61e349a68a4ae2fa2ec7a723c70e3263b496", "tools/check_native_harnesses.py": "4f5f0ed27651f78758eaef077b3b114361781f6b95ec40cb46c3fea689210473", "tools/check_native_toolkit.py": "0272794617121f2932828e5e4e9ae20095183c443666cf3ba466b44fbe875095", "tools/community_results.py": "9db56a44697d94f326efcbd7a3ae1aecdb569d43bba6c47e80ce525dc045f1f7", "tools/community_service.py": "c374480dbd88d656c0b9054fa04a8e1c6698c69e2f9cf475e82498a2dff61d84", "tools/community_setup.py": "5d7d126ed7d4dd48e1d79f57b99647a92ffcc8c9f80d90915e458888cdd76bf7", "tools/compare_harness_runs.py": "f274df5f3f804cb02504491aec946943833e12fbce6e62d281e12beb8508fc4e", "tools/create_run_plan.py": "871cd81b1eda231c0fba8805f63d2668926be9fc641559e6ddf320e2f47cd37a", "tools/demo_runner.py": "230e6e49068f2bab3a0db64e6da5889e8f1834158fed8c5ec334b7694695a87b", "tools/installers.py": "9a2742780936b17500869e7c89202c1a2549e37d53a42ad9a50a0abbf78bbe09", "tools/machine_bundle.py": "8aa8346f99f537e81ceca6fb6ab9530e844954bab8eff87bf33d3602f81f8a30", "tools/prepare_native_harnesses.py": "aaa75ecf4022883984fa50c42d14d8e1a9fde2eeda03dab03b852bbc5efb2502", "tools/prepare_official_statement.py": "6b7028c78e90e798d6ef1a93b76520cc61a308c354fb9b87f7fad18b99800fad", "tools/prepare_open_exam_requirements.py": "544f4e378b9be5f166186f8788f8d454afdac2deb99d91d98421e39d01ba6d03", "tools/probe_harness.py": "1ed8ef93420d1484cbbfd151b7efc31b9a201ceb942dd05e3103efa22ffa7f27", "tools/probe_native_mcp.py": "9918d324129cba898993e07f8f8b6dbcbaf369398ebf28d464f9f1f00abdb254", "tools/readiness.py": "d34dd3f38334f51cc4574c79194cf0b80769b062a52382989a57d01c46b9aba4", "tools/recheck_community.py": "f0843d7d677f90da31e22bde0b1c86584dd46c022f1532d43d042619e426b230", "tools/regrade_runs.py": "011775afb06d3aac67a4aa81117a368c75896b0fcbe1e6f27ccc6237612fbf59", "tools/render_statement_text.py": "dabc0716a3612c288c671bc20e17fd4986691d732768e1e957d6dddddbea92a3", "tools/replay_calibration.py": "801f5004926c438c21ed3668fe2a4ddf45312b3e75320165a3839aae034eee9b", "tools/run_exam_campaign.py": "2c450d57a1cd0a2682838f5ec7c0a4ffb3aed0f1730d34c408e912d59cab6efd", "tools/serve_result_site.py": "86badfac863cd4ad1fc894a14110c75b28470513f0133eeae9d2799b8b4df3a9", "tools/start_demo.py": "c597e6cad28d245b3191654bb3e2801fa9dd2364e2acb25561923613717b615f", "tools/supplemental_acceptance.py": "c88fc39de1be1fdcacdd819e2ad329f60367b2df1d5deda80b37324bda3f2a01", "tools/sync_sources.py": "b51e889b0f41f9f63bfb19a09fb96d3777693d6b1d76fe0132bdd2a15e155898", "tools/validate_community_pr.py": "796b896dfade07b4529af2088a4b9b9d23484148b3bc0732b3fb837b75c9844b", "tools/verify_official_assessment_mapping.py": "daeb448a016940d5b6b1285979a56e5b9014bd91db40acb131445e4a83a23059", "tools/verify_task_package.py": "9e1e6105f6b5e4e78b36aa57f00117a9fbc8948ab53983c32ab56da88d23ccc4", "profiles/agents.json": "af9c492c08d13b3044aa6b6952589ed6a0a07d5258d8ff72bb18185b3eaebdc5", "profiles/ai-exam-execution-policy.json": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "profiles/bsl-analyzer-0.3.2-macos.json": "83537abdbf38c41ce665e4d0f24128bb51b62e971e0e0f368695f1326a7d2ffb", "profiles/bsl-analyzer-0.3.2-portable.json": "d6ba732e6778e256df34d6bc548593128820a70430c35b279796843606ee40a8", "profiles/bsl-ls-1.1.0-rc.6-macos.json": "245fc10747197e6911b2b4c77cdb15e6fa4eb7bc7c3758b63e768c5adf1df180", "profiles/bsl-ls-1.1.0-rc.6-portable.json": "9f10660881f2ec84794f7d584556b8f75c7e14b3555464af0ed0e60c4c892d86", "profiles/code-index-1.9.0-macos.json": "63a919523ce62ecec274f4c139bc7ad49a75dd4c339568b822cbc695b4e30408", "profiles/code-index-1.9.0-portable.json": "81106cee8f424ffd8a9dc46ecd8e4f57598fc1d49661a83c77b1f0507993fbdc", "profiles/codex-probe-plan.json": "166e41aad5fb3b27d9050bc6de952c6cba363cc6e804d4080568cc71a2a4d289", "profiles/machine.linux.example.json": "408304fd0581098d5d8110dc67dfeab353bc4d4030e32d37e6acf98d2b1aedfd", "profiles/machine.macos.example.json": "52e9f9d17797cb520b9d8955d6806fd550b899bed4da241ebf096dcb6a21a942", "profiles/machine.windows.example.json": "63accac9a2f81d47d03447efbabffd4760aee325193f02f46b9b29a28d50d2d8", "profiles/mcp-toolkit-1.9.0-macos.json": "1d3f9cde5ffa20589a840d01fdae03aa0fc2f412c929f064f203919c4129625b", "profiles/mcp-toolkit-1.9.0-portable.json": "8e370eebe773eef0e08045ee9c6d5be1451f769f65be0710834b262a4336e054", "profiles/none-macos.json": "b1401d9c48159aed3559006c7f6ace6ef4571224d5cf0bb76d1a823505a10056", "profiles/none-portable.json": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "profiles/rlm-tools-bsl-1.43.0-macos.json": "9354421052640ab60bc3e6aa98ff2e7ba9ca2318b0f4026c137487449242cbd2", "profiles/rlm-tools-bsl-1.43.0-portable.json": "2599e5645e0a7d4e44cb2934bc2b272cae79a9bf7ea74a23cd48aacea64bc424", "profiles/rlm-tools-bsl-1.43.0-posix-requirements.txt": "4fdf9a1bd994bf0272e65d231daf76cf19b0a34dad0ae6b50ec4f11a2ce4c330", "profiles/rlm-tools-bsl-1.43.0-windows-requirements.txt": "3730cb46c81cda5181ecd4485e98b11933104632358bc86f8c0eb1a612a8954f", "profiles/shirokov-skills-macos.json": "84f3e89091676884a802035c707e912762a1179425fb8e3faff25be736873cdb", "profiles/shirokov-skills-portable.json": "2b0a461e06602f1456410e70f02ceaa5ac32c6549c486660bcb5ace0c2f87b15", "profiles/shirokov-skills-windows-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/unica-0.12.3-macos.json": "2c39fbb591cf2c2c6e056373823615485397ea83651b7926c6f25a5fe6a0aae6", "profiles/unica-0.13.0-macos.json": "b76b5c8a4dd33f571c4a90993f1a2da5f7223b4f0f8e1042c282e21a66121052", "profiles/unica-0.14.0-rc.1-portable.json": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "rules/1c-specialist-platform/chistov.json": "77e04942f8c947b10759e7cc1eb31af05847d1711a772fbe6f23d525766757a9", "rules/1c-specialist-platform/decisions.json": "f622107423ce3c188c063318d7ab4f7718ceb38e443130677d8987f386641c09", "rules/1c-specialist-platform/examiner.json": "30353aa2a1b6545496b070d9066e9ffba0c3779e5b53ef70a4fd2cee375b18c0", "rules/1c-specialist-platform/ledger.json": "f167c10db2b5799dd9a1ea6a37cd2d7d186810dadf5ea2f50f26ae723c676882", "rules/1c-specialist-platform/rules.json": "1d320a4f8e1bf4701496388931f492315549bd3dce574b17285dd1d7f8652007", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" } } }, "conditions": { "client": "codex", "model": "gpt-6.1-sol", "client_version": "0.163.0-alpha.11.2", "reasoning_effort": "medium", "harness": "unica-0.14.0-rc.1", "billing_channel": "subscription", "solve_timeout_seconds": 3600, "time_series": null, "delegation": "native_disabled", "network_profile": "open-book_shell", "deadline_disclosed": true, "statement_sha256": "8a6ccb3e673826d1f8220fda53eb310e3ec18c136d87ce8f4cebb2a08614e7e5", "starter_dt_sha256": "f40d084818b0d1cfe503fc7653a6a13f1a8e47fcd1688dad6245b12744eb4638", "profile_sha256": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "execution_policy_sha256": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "calibration_sha256": "e8981744a194aa56f954d2965aa66cd53cd4f899f09fa7b5abda6f6b27a5ed65", "started_at": "2026-10-25T05:27:08.909870+00:00", "timing": { "prepare_ms": 7875, "solve_ms": 3523906, "grade_ms": null }, "original_submission_valid": true, "model_provenance": "requested_only", "tokens": { "input": 27733372, "cached_input": 27369344, "fresh_input": 364028, "output": 128032, "reasoning_output": 45106, "total": 27861404, "coverage": "reported_completed_root_turns" }, "tools": { "mcp_calls": 545, "unica_calls": 545, "failed_calls": 35 }, "process": { "status": "completed", "exit_code": 0, "stop_confirmed": true } }, "verification": "contributor_reported", "download": "community-downloads/demo-20261025T052655Z-9c0f1c/solution.zip", "source_context": "community-downloads/demo-20261025T052655Z-9c0f1c/source-context.json", "regrade_required": [ { "id": "grader_changed", "files": [ "assessment.py", "bp.py", "calcwrite.py", "calibrate.py", "calibration_periodicity.py", "calibration_query.py", "claude.py", "codescan.py", "codex.py", "common.py", "docx_text.py", "examiner.py", "harness.py", "interpretations.py", "locking.py", "materials.py", "mcp_toolkit.py", "ou.py", "penalties.py", "portable_harnesses.py", "pr.py", "preflight.py", "queries.py", "queryschema.py", "querytypes.py", "replay_calibration.py", "rules/1c-specialist-platform/chistov.json", "rules/1c-specialist-platform/examiner.json", "rules/1c-specialist-platform/rules.json", "rules/1c-specialist-platform/standards.json", "smoke_check.py", "starters/carcass-8.3.25.1445/starter.json", "stdio_harnesses.py", "submission.py", "tasks/1c-platform-official-sample/checks.json", "tasks/1c-platform-official-sample/private/official-assessment-mapping.json", "tasks/1c-platform-official-sample/private/owner-scoring-policy.json", "telemetry.py" ] } ], "grader_revision_sha256": "13710d802a08278385c484500f48f1678e0b002e5c7a3d8c00e14c1e75b1fbe9", "archive_sha256": "bb8dcd908ab350f189a86458d72e13db710deb510dd885cfc985cfca3292efd4" } ] }, { "id": "demo-20261025T063054Z-b9676e--owner-2026-10-26T223250308491-0000", "run_id": "demo-20261025T063054Z-b9676e", "result": { "run_id": "demo-20261025T063054Z-b9676e", "created_at": "2026-10-26T22:32:50.308491+00:00", "model": "gpt-6.1-sol", "harness": "unica-0.14.0-rc.1", "solve_seconds": 7031, "platform": "8.3.27.1644", "counts": { "pass": 52, "fail": 3, "inconclusive": 10 }, "rules": [ { "id": "BU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU01.selected_fixture" }, { "id": "BU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU04.selected_fixture" }, { "id": "BU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU05.selected_fixture" }, { "id": "BU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU16.selected_fixture" }, { "id": "BU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU17.selected_fixture" }, { "id": "BU02", "verdict": "pass", "reason": null, "coverage": "partial", "assertion_id": "BU02.posting_cost_and_balance" }, { "id": "BU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU10.selected_fixture" }, { "id": "BU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU12.selected_fixture" }, { "id": "BU03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU03.selected_fixture" }, { "id": "BU06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU06.selected_fixture" }, { "id": "BU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU07.selected_fixture" }, { "id": "BU08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU08.selected_fixture" }, { "id": "BU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU09.selected_fixture" }, { "id": "BU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU11.selected_fixture" }, { "id": "BU14", "verdict": "fail", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU14.selected_fixture" }, { "id": "BU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU15.selected_fixture" }, { "id": "BU13", "verdict": "fail", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU13.selected_fixture" }, { "id": "OU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU15.selected_fixture" }, { "id": "OU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU16.selected_fixture" }, { "id": "OU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU17.selected_fixture" }, { "id": "OU02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU02.selected_fixture" }, { "id": "OU18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU18.selected_fixture" }, { "id": "OU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU14.selected_fixture" }, { "id": "OU01", "verdict": "inconclusive", "reason": "Required observations unavailable: 'ou_assembly'", "coverage": "selected_fixture", "assertion_id": "OU01.selected_fixture" }, { "id": "OU03", "verdict": "inconclusive", "reason": "Недостаточно данных: история не подтверждена: 'ou_history'", "coverage": "history_and_periodicity", "assertion_id": "OU03.selected_fixture" }, { "id": "OU05", "verdict": "inconclusive", "reason": "Required observations unavailable: 'ou_assembly'", "coverage": "selected_fixture", "assertion_id": "OU05.selected_fixture" }, { "id": "OU06", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "OU06.selected_fixture" }, { "id": "OU07", "verdict": "inconclusive", "reason": "Required observations unavailable: 'ou_assembly'", "coverage": "selected_fixture", "assertion_id": "OU07.selected_fixture" }, { "id": "OU08", "verdict": "inconclusive", "reason": "Недостаточно данных: история не подтверждена: 'ou_history'", "coverage": "history_and_periodicity", "assertion_id": "OU08.selected_fixture" }, { "id": "OU09", "verdict": "inconclusive", "reason": "Required observations unavailable: 'ou_assembly'", "coverage": "selected_fixture", "assertion_id": "OU09.selected_fixture" }, { "id": "OU10", "verdict": "inconclusive", "reason": "Required observations unavailable: 'ou_assembly'", "coverage": "selected_fixture", "assertion_id": "OU10.selected_fixture" }, { "id": "OU11", "verdict": "inconclusive", "reason": "Required observations unavailable: 'ou_assembly'", "coverage": "selected_fixture", "assertion_id": "OU11.selected_fixture" }, { "id": "OU12", "verdict": "inconclusive", "reason": "Required observations unavailable: 'ou_history'", "coverage": "selected_fixture", "assertion_id": "OU12.selected_fixture" }, { "id": "OU13", "verdict": "inconclusive", "reason": "Required observations unavailable: 'ou_assembly'", "coverage": "selected_fixture", "assertion_id": "OU13.selected_fixture" }, { "id": "OU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU04.selected_fixture" }, { "id": "OU19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU19.selected_fixture" }, { "id": "OU20", "verdict": "fail", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU20.selected_fixture" }, { "id": "OU21", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU21.selected_fixture" }, { "id": "PR01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR01.selected_fixture" }, { "id": "PR02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR02.selected_fixture" }, { "id": "PR03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR03.selected_fixture" }, { "id": "PR04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR04.selected_fixture" }, { "id": "PR05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR05.selected_fixture" }, { "id": "PR06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR06.selected_fixture" }, { "id": "PR07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR07.selected_fixture" }, { "id": "PR08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR08.selected_fixture" }, { "id": "PR09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR09.selected_fixture" }, { "id": "PR10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR10.selected_fixture" }, { "id": "PR11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR11.selected_fixture" }, { "id": "PR12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR12.selected_fixture" }, { "id": "PR13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR13.selected_fixture" }, { "id": "PR14", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "PR14.selected_fixture" }, { "id": "PR15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR15.selected_fixture" }, { "id": "PR16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR16.selected_fixture" }, { "id": "PR17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR17.selected_fixture" }, { "id": "PR18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR18.selected_fixture" }, { "id": "PR19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR19.selected_fixture" }, { "id": "F01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F01.selected_fixture" }, { "id": "F02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F02.selected_fixture" }, { "id": "F03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F03.selected_fixture" }, { "id": "F04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F04.selected_fixture" }, { "id": "F05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F05.selected_fixture" }, { "id": "G01", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G01.static_sources" }, { "id": "G02", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G02.static_sources" }, { "id": "G03", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G03.static_sources" } ], "charges": [ { "id": "F1C-GEN03", "points": "0.5", "reason": "отчёт не соответствует заданию: OU20" }, { "id": "F1C-GEN01", "points": "0.5", "reason": "не выполнено требование: BU13" }, { "id": "F1C-GEN01", "points": "0.5", "reason": "не выполнено требование: BU14" }, { "id": "F1C-GEN15", "points": "0.5", "reason": "Reports/ВедомостьПоПодразделению/Ext/ManagerModule.bsl:3 — РегистрНакопления.ОстаткиНоменклатуры.ОстаткиИОбороты: отбор по Подразделение, индексы таблицы начинаются с Номенклатура" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "проводимые документы в режиме «Записывать модифицированные»: Операция, Сборка" }, { "id": "F1C-PR14", "points": "0.5", "reason": "после расчёта набор с периодом действия перезаписывается целиком, с пересчётом фактического периода действия (нужно Записать(, Истина)): CommonModules/РасчетЗарплаты/Ext/Module.bsl:145 Набор.Записать(); CommonModules/РасчетЗарплаты/Ext/Module.bsl:190 Набор.Записать(); CommonModules/РасчетЗарплаты/Ext/Module.bsl:193 Набор.Записать(); CommonModules/РасчетЗарплаты/Ext/Module.bsl:304 Набор.Записать()" }, { "id": "F1C-BU06", "points": "1.5", "reason": "признак учёта ТоварныйУчет плана счетов не указан ни у одного ресурса регистра — не действует" }, { "id": "F1C-BU05", "points": "0.5", "reason": "аналитика счетов вынесена в измерения регистра бухгалтерии и есть у всех счетов: Номенклатура (Номенклатура), Склад (Склады)" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "оперативное проведение разрешено у документов с движениями по регистрам расчёта: НачислениеЗарплаты" }, { "id": "F1C-GEN21", "points": "2.0", "reason": "данные графика без отбора по регистратору: CommonModules/РасчетЗарплаты/Ext/Module.bsl:235" }, { "id": "F1C-GEN22", "points": "1.0", "reason": "значения графика выбираются без ЕСТЬNULL: CommonModules/РасчетЗарплаты/Ext/Module.bsl:235 ДниФактическийПериодДействия" } ], "score_upper_bound": "-4.5", "score": null, "grade": "unsatisfactory", "deductions": "9.5", "not_assessed": 18, "gates": { "starter_origin": "passed", "load": "loaded", "clients": "compiles", "demo_data": "present" }, "infrastructure_errors": true, "comparison_eligible": false, "binding_compatibility": null }, "measurement": { "operator": { "name": "Вячеслав", "github": "sksibak" }, "environment": { "captured_at": "2026-10-25T06:30:56.582237+00:00", "capture_timing": "before_run", "hardware": { "cpu": "AMD Ryzen 5 4600H with Radeon Graphics ", "logical_cpus": 12, "ram_bytes": 16505962496 }, "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "python": "3.12.14", "platform_version": "8.3.27.1644", "isolation": "dedicated-host", "network_profile": "open-book_shell", "unsafe_action_protection_observed_in_user_config": true, "git_revision": "af85e791b303dbbf0b0b7af924d2489c3e57cfa8", "implementation_files": { "exam_bench/__init__.py": "ad5bf6f05dc6765f40b78bd186870ca2c49be113cfa33f8aa76f4926f2cb2c1e", "exam_bench/assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "exam_bench/bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "exam_bench/calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "exam_bench/calibrate.py": "78b5185cb0888c0c0ac3de95ffc3a80154a6de9ae66fc461f79d012e5a58e1db", "exam_bench/calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "exam_bench/calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "exam_bench/calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "exam_bench/calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "exam_bench/calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "exam_bench/claude.py": "bc1b8550de7573aaed5e39c6e9c0309e0d8175284a75490d61ec27439ed911ad", "exam_bench/cli.py": "1a37ce645633d761f7897dffc9c45e6b8b9600cd7bd233b1cbf78f49d26b099a", "exam_bench/codescan.py": "751e38001b6e65727a31e28172a0623f0bf34bc092a958037c286aa991a197ed", "exam_bench/codex.py": "c3f89d72af11f312d851c73a1610d92e79acadf336be9ccedd1f94ede3b3ccb0", "exam_bench/common.py": "8682603b519063e655eae3574a02a49efee63bde21f582ccee20ddd623fca96d", "exam_bench/docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "exam_bench/examiner.py": "d7294fdd23ed1732216cafebf0a8cf2c24cce4259859aeb7149f62b7607d087d", "exam_bench/finalize.py": "4034f1c63896a940afdb1a83d541cf47fc75c8b5061e3f839047109c04beb620", "exam_bench/forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "exam_bench/gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "exam_bench/grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "exam_bench/harness.py": "3040f6daaf1dc6e6583219f4d925151f8ba7851b2d5417d7f14645892b485ddf", "exam_bench/interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "exam_bench/interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "exam_bench/isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "exam_bench/ledger.py": "7e851523580e22d8490e75f9b6026c07f2c355007e0d11d0b252671f56bef654", "exam_bench/locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "exam_bench/materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "exam_bench/mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "exam_bench/observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "exam_bench/ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "exam_bench/penalties.py": "0d79e2e46102657dca00609b6abbfc0bf7d11fad41429564f876c82bc6b33269", "exam_bench/platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "exam_bench/portable.py": "cad56968ff407983608f5bdbc9ce7234128d7a4580b096ecea8e0e7b4edb9070", "exam_bench/portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "exam_bench/pr.py": "6a3a20caf0e10c0cc94410511a72d62c9fcda785f3abab1be2ad616d4ee16836", "exam_bench/preflight.py": "5619be0131d8641925f3ce2a3c8e5234d42aa5635d95676138ca81536d95cd29", "exam_bench/process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "exam_bench/queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "exam_bench/queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "exam_bench/replay_calibration.py": "c150457b0b23ce4e6814eb8deb4d48f6bc4a2e39d8f84a9dc7644fb99a026c2d", "exam_bench/report.py": "5e4c0757e1c7f189953f9a5302593ab726551835856baed25efd93dad6e8bfcd", "exam_bench/runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "exam_bench/smoke_check.py": "f36922a0027429ead0b414048dcc14bbe67f2f0e79a70d03dffbe1447d253545", "exam_bench/stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "exam_bench/submission.py": "d6f9d20704181c51714f1138affe4965d860ae21475ab7bb49aa5c5cefebb9f5", "exam_bench/telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "exam_bench/windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "exam_bench/workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tools/build_public_site.py": "9682ed696f5ac9e9a82b65a45c0dece556ec7e49eeb20dcd616882cc534a8258", "tools/build_result_site.py": "3294e1d2ec1486058e208735264d61e349a68a4ae2fa2ec7a723c70e3263b496", "tools/check_native_harnesses.py": "4f5f0ed27651f78758eaef077b3b114361781f6b95ec40cb46c3fea689210473", "tools/check_native_toolkit.py": "0272794617121f2932828e5e4e9ae20095183c443666cf3ba466b44fbe875095", "tools/community_results.py": "9db56a44697d94f326efcbd7a3ae1aecdb569d43bba6c47e80ce525dc045f1f7", "tools/community_service.py": "c374480dbd88d656c0b9054fa04a8e1c6698c69e2f9cf475e82498a2dff61d84", "tools/community_setup.py": "5d7d126ed7d4dd48e1d79f57b99647a92ffcc8c9f80d90915e458888cdd76bf7", "tools/compare_harness_runs.py": "f274df5f3f804cb02504491aec946943833e12fbce6e62d281e12beb8508fc4e", "tools/create_run_plan.py": "871cd81b1eda231c0fba8805f63d2668926be9fc641559e6ddf320e2f47cd37a", "tools/demo_runner.py": "230e6e49068f2bab3a0db64e6da5889e8f1834158fed8c5ec334b7694695a87b", "tools/installers.py": "9a2742780936b17500869e7c89202c1a2549e37d53a42ad9a50a0abbf78bbe09", "tools/machine_bundle.py": "8aa8346f99f537e81ceca6fb6ab9530e844954bab8eff87bf33d3602f81f8a30", "tools/prepare_native_harnesses.py": "aaa75ecf4022883984fa50c42d14d8e1a9fde2eeda03dab03b852bbc5efb2502", "tools/prepare_official_statement.py": "6b7028c78e90e798d6ef1a93b76520cc61a308c354fb9b87f7fad18b99800fad", "tools/prepare_open_exam_requirements.py": "544f4e378b9be5f166186f8788f8d454afdac2deb99d91d98421e39d01ba6d03", "tools/probe_harness.py": "1ed8ef93420d1484cbbfd151b7efc31b9a201ceb942dd05e3103efa22ffa7f27", "tools/probe_native_mcp.py": "9918d324129cba898993e07f8f8b6dbcbaf369398ebf28d464f9f1f00abdb254", "tools/readiness.py": "d34dd3f38334f51cc4574c79194cf0b80769b062a52382989a57d01c46b9aba4", "tools/recheck_community.py": "f0843d7d677f90da31e22bde0b1c86584dd46c022f1532d43d042619e426b230", "tools/regrade_runs.py": "011775afb06d3aac67a4aa81117a368c75896b0fcbe1e6f27ccc6237612fbf59", "tools/render_statement_text.py": "dabc0716a3612c288c671bc20e17fd4986691d732768e1e957d6dddddbea92a3", "tools/replay_calibration.py": "801f5004926c438c21ed3668fe2a4ddf45312b3e75320165a3839aae034eee9b", "tools/run_exam_campaign.py": "2c450d57a1cd0a2682838f5ec7c0a4ffb3aed0f1730d34c408e912d59cab6efd", "tools/serve_result_site.py": "86badfac863cd4ad1fc894a14110c75b28470513f0133eeae9d2799b8b4df3a9", "tools/start_demo.py": "c597e6cad28d245b3191654bb3e2801fa9dd2364e2acb25561923613717b615f", "tools/supplemental_acceptance.py": "c88fc39de1be1fdcacdd819e2ad329f60367b2df1d5deda80b37324bda3f2a01", "tools/sync_sources.py": "b51e889b0f41f9f63bfb19a09fb96d3777693d6b1d76fe0132bdd2a15e155898", "tools/validate_community_pr.py": "796b896dfade07b4529af2088a4b9b9d23484148b3bc0732b3fb837b75c9844b", "tools/verify_official_assessment_mapping.py": "daeb448a016940d5b6b1285979a56e5b9014bd91db40acb131445e4a83a23059", "tools/verify_task_package.py": "9e1e6105f6b5e4e78b36aa57f00117a9fbc8948ab53983c32ab56da88d23ccc4", "profiles/agents.json": "af9c492c08d13b3044aa6b6952589ed6a0a07d5258d8ff72bb18185b3eaebdc5", "profiles/ai-exam-execution-policy.json": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "profiles/bsl-analyzer-0.3.2-macos.json": "83537abdbf38c41ce665e4d0f24128bb51b62e971e0e0f368695f1326a7d2ffb", "profiles/bsl-analyzer-0.3.2-portable.json": "d6ba732e6778e256df34d6bc548593128820a70430c35b279796843606ee40a8", "profiles/bsl-ls-1.1.0-rc.6-macos.json": "245fc10747197e6911b2b4c77cdb15e6fa4eb7bc7c3758b63e768c5adf1df180", "profiles/bsl-ls-1.1.0-rc.6-portable.json": "9f10660881f2ec84794f7d584556b8f75c7e14b3555464af0ed0e60c4c892d86", "profiles/code-index-1.9.0-macos.json": "63a919523ce62ecec274f4c139bc7ad49a75dd4c339568b822cbc695b4e30408", "profiles/code-index-1.9.0-portable.json": "81106cee8f424ffd8a9dc46ecd8e4f57598fc1d49661a83c77b1f0507993fbdc", "profiles/codex-probe-plan.json": "166e41aad5fb3b27d9050bc6de952c6cba363cc6e804d4080568cc71a2a4d289", "profiles/machine.linux.example.json": "408304fd0581098d5d8110dc67dfeab353bc4d4030e32d37e6acf98d2b1aedfd", "profiles/machine.macos.example.json": "52e9f9d17797cb520b9d8955d6806fd550b899bed4da241ebf096dcb6a21a942", "profiles/machine.windows.example.json": "63accac9a2f81d47d03447efbabffd4760aee325193f02f46b9b29a28d50d2d8", "profiles/mcp-toolkit-1.9.0-macos.json": "1d3f9cde5ffa20589a840d01fdae03aa0fc2f412c929f064f203919c4129625b", "profiles/mcp-toolkit-1.9.0-portable.json": "8e370eebe773eef0e08045ee9c6d5be1451f769f65be0710834b262a4336e054", "profiles/none-macos.json": "b1401d9c48159aed3559006c7f6ace6ef4571224d5cf0bb76d1a823505a10056", "profiles/none-portable.json": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "profiles/rlm-tools-bsl-1.43.0-macos.json": "9354421052640ab60bc3e6aa98ff2e7ba9ca2318b0f4026c137487449242cbd2", "profiles/rlm-tools-bsl-1.43.0-portable.json": "2599e5645e0a7d4e44cb2934bc2b272cae79a9bf7ea74a23cd48aacea64bc424", "profiles/rlm-tools-bsl-1.43.0-posix-requirements.txt": "4fdf9a1bd994bf0272e65d231daf76cf19b0a34dad0ae6b50ec4f11a2ce4c330", "profiles/rlm-tools-bsl-1.43.0-windows-requirements.txt": "3730cb46c81cda5181ecd4485e98b11933104632358bc86f8c0eb1a612a8954f", "profiles/shirokov-skills-macos.json": "84f3e89091676884a802035c707e912762a1179425fb8e3faff25be736873cdb", "profiles/shirokov-skills-portable.json": "2b0a461e06602f1456410e70f02ceaa5ac32c6549c486660bcb5ace0c2f87b15", "profiles/shirokov-skills-windows-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/unica-0.12.3-macos.json": "2c39fbb591cf2c2c6e056373823615485397ea83651b7926c6f25a5fe6a0aae6", "profiles/unica-0.13.0-macos.json": "b76b5c8a4dd33f571c4a90993f1a2da5f7223b4f0f8e1042c282e21a66121052", "profiles/unica-0.14.0-rc.1-portable.json": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "rules/1c-specialist-platform/chistov.json": "77e04942f8c947b10759e7cc1eb31af05847d1711a772fbe6f23d525766757a9", "rules/1c-specialist-platform/decisions.json": "f622107423ce3c188c063318d7ab4f7718ceb38e443130677d8987f386641c09", "rules/1c-specialist-platform/examiner.json": "30353aa2a1b6545496b070d9066e9ffba0c3779e5b53ef70a4fd2cee375b18c0", "rules/1c-specialist-platform/ledger.json": "f167c10db2b5799dd9a1ea6a37cd2d7d186810dadf5ea2f50f26ae723c676882", "rules/1c-specialist-platform/rules.json": "1d320a4f8e1bf4701496388931f492315549bd3dce574b17285dd1d7f8652007", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" } } }, "conditions": { "client": "codex", "model": "gpt-6.1-sol", "client_version": "0.163.0-alpha.11.2", "reasoning_effort": "medium", "harness": "unica-0.14.0-rc.1", "billing_channel": "subscription", "solve_timeout_seconds": 7200, "time_series": null, "delegation": "native_disabled", "network_profile": "open-book_shell", "deadline_disclosed": true, "statement_sha256": "8a6ccb3e673826d1f8220fda53eb310e3ec18c136d87ce8f4cebb2a08614e7e5", "starter_dt_sha256": "f40d084818b0d1cfe503fc7653a6a13f1a8e47fcd1688dad6245b12744eb4638", "profile_sha256": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "execution_policy_sha256": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "calibration_sha256": "e8981744a194aa56f954d2965aa66cd53cd4f899f09fa7b5abda6f6b27a5ed65", "started_at": "2026-10-25T06:31:06.187531+00:00", "timing": { "prepare_ms": 9000, "solve_ms": 7031109, "grade_ms": null }, "original_submission_valid": true, "model_provenance": "requested_only", "tokens": { "input": 38707601, "cached_input": 37712256, "fresh_input": 995345, "output": 186873, "reasoning_output": 91034, "total": 38894474, "coverage": "reported_completed_root_turns" }, "tools": { "mcp_calls": 688, "unica_calls": 688, "failed_calls": 21 }, "process": { "status": "completed", "exit_code": 0, "stop_confirmed": true } }, "verification": "repository_owner_incomplete", "download": "community-downloads/demo-20261025T063054Z-b9676e--owner-2026-10-26T223250308491-0000/solution.zip", "source_context": "community-downloads/demo-20261025T063054Z-b9676e--owner-2026-10-26T223250308491-0000/source-context.json", "regrade_required": [], "grader_revision_sha256": "9aee1ffe0e1d04f9158fbbbeed3a403a5f0550ad8a590d7a6394977590760e1a", "archive_sha256": "9c143e8e6c009d055fac4e9814a133cd41e1509b1643ba3d5d5d77ab6b03abea", "owner_verification": { "kind": "repository_owner", "repository": "zeegin/1c-agent-exam-benchmark", "operator": { "name": "Ingvar Vilkman", "github": "zeegin" }, "started_at": "2026-10-26T22:32:50.153305+00:00", "server": { "name": "Owner Windows stand", "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "hardware": { "cpu": "AMD Ryzen 7 5800X 8-Core Processor ", "logical_cpus": 4, "ram_bytes": 17109000192 }, "isolation": "dedicated-host" }, "platform_version": "8.3.27.2342", "grader": { "profile": "technical-v8", "commit": "e15c8ea80263c0b38baa3a1fc19611983270e8a7", "working_tree_dirty": false, "fingerprint": { "assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "calibrate.py": "aac127e03744907fd52ef149b88aa6d88a54a2b7497d56084484ee1b99e0da99", "calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "calibration_periodicity.py": "0b1953d7781e236467897cd2ed66705b75d9719353a2de60b36f2bbdfe799108", "calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "calibration_query.py": "3555b103cde8ea0519955cf52358d09223f5ab183a9df00533bdb48c89237a8c", "claude.py": "5bae98af6e2021e2718afa3a71ed04bee812deaae31a43d4e7324814139ccc82", "codescan.py": "6d8375210cef1fd768fc2d98d630d880b2993a9724f01ae25f33b4ea5aa9631d", "codex.py": "904e75503cd35f16cbb052f66806b3879fe25bfc9f99e33b93c889d862c46324", "common.py": "739b39e2bb9bdd4a571fc69df5843190cddcad094ef7e68964061bc1266b20dc", "docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "examiner.py": "8cdffcdd52f043c905f896697403380af95bf485dd4a5edca24f7956e7795ffe", "forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "harness.py": "3cbb90fd3187e700b5df32e5daafb20313d49bb5721c826e3033cbc6aa6e3825", "interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "ou.py": "f62784b54a3f85576a078a2ff1908c9395f3159e55f6bb5b1a3c564392241abe", "penalties.py": "ae388cb8953ecca1f2370a7c4cb1db3b6cc8318fc2a7563a4db15f9f5b057429", "platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "pr.py": "2b6bfea0634703469605ce114f9274716b485852d9a55d9185c39893b14e4726", "preflight.py": "448c3120ab64b625abae3891be686c7a214ce4211f7cf651fd90e12c0b298433", "process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "queries.py": "1ef57e292db3e8967a733948371ecc542f743b811890d4fc509df17303b9c4ac", "queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "querytypes.py": "b645f489a2abc27762b4a9bbf4917e72f7b46dc053a74c0dca4a8fc46491b3ef", "replay_calibration.py": "e0e3d5ca6416934715b9735aa516046b8d19ad4ae690220eeacd96b198a5f86c", "runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "smoke_check.py": "7837e980986bcb54dc8bc1dfb5d0003deef11e05f6e11df3910fa509e1f74c8d", "stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "submission.py": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tasks/1c-platform-official-sample/checks.json": "7447a9b42d3e348d29d07f001cfb6bd269acd953b7117eba7cca2ce9f5a9a60d", "tasks/1c-platform-official-sample/private/official-assessment-mapping.json": "303587c0dabe77c1eeebb2017fe85539e3370b17c9090435e6e0325a66bd0644", "tasks/1c-platform-official-sample/private/owner-scoring-policy.json": "d26d534bb838ab1b5facb7bc033ca8ec40912133baadcdbad83b27fc577905f5", "starters/carcass-8.3.25.1445/starter.json": "0f7a7060885ba99a19402bfc6e63cc8fe979b0f491b040d3a01d5d21b304b3a6", "rules/1c-specialist-platform/rules.json": "ea75e34ace5de11ba3de403c63cd2c026db81d1d991f8531e4a779d4ce9788e7", "rules/1c-specialist-platform/examiner.json": "1247486ddd412d600db88d9c1db4ba501fc1994afd1dc2ebe85402fcc332f4c8", "rules/1c-specialist-platform/chistov.json": "800da27601a3f1c7ec1df64482fd4ad035e559ba0b390a274ed5031128487d3d", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" }, "sha256": "9aee1ffe0e1d04f9158fbbbeed3a403a5f0550ad8a590d7a6394977590760e1a" }, "method": "saved_platform_observations", "outcome": "incomplete", "completed_at": "2026-10-26T22:32:50.308491+00:00" }, "previous_evaluations": [ { "id": "demo-20261025T063054Z-b9676e--owner-2026-10-26T214326254722-0000", "run_id": "demo-20261025T063054Z-b9676e", "result": { "run_id": "demo-20261025T063054Z-b9676e", "created_at": "2026-10-26T21:43:26.254722+00:00", "model": "gpt-6.1-sol", "harness": "unica-0.14.0-rc.1", "solve_seconds": 7031, "platform": "8.3.27.1644", "counts": { "pass": 52, "fail": 3, "inconclusive": 10 }, "rules": [ { "id": "BU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU01.selected_fixture" }, { "id": "BU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU04.selected_fixture" }, { "id": "BU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU05.selected_fixture" }, { "id": "BU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU16.selected_fixture" }, { "id": "BU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU17.selected_fixture" }, { "id": "BU02", "verdict": "pass", "reason": null, "coverage": "partial", "assertion_id": "BU02.posting_cost_and_balance" }, { "id": "BU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU10.selected_fixture" }, { "id": "BU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU12.selected_fixture" }, { "id": "BU03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU03.selected_fixture" }, { "id": "BU06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU06.selected_fixture" }, { "id": "BU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU07.selected_fixture" }, { "id": "BU08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU08.selected_fixture" }, { "id": "BU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU09.selected_fixture" }, { "id": "BU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU11.selected_fixture" }, { "id": "BU14", "verdict": "fail", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU14.selected_fixture" }, { "id": "BU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU15.selected_fixture" }, { "id": "BU13", "verdict": "fail", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU13.selected_fixture" }, { "id": "OU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU15.selected_fixture" }, { "id": "OU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU16.selected_fixture" }, { "id": "OU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU17.selected_fixture" }, { "id": "OU02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU02.selected_fixture" }, { "id": "OU18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU18.selected_fixture" }, { "id": "OU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU14.selected_fixture" }, { "id": "OU01", "verdict": "inconclusive", "reason": "Required observations unavailable: 'ou_assembly'", "coverage": "selected_fixture", "assertion_id": "OU01.selected_fixture" }, { "id": "OU03", "verdict": "inconclusive", "reason": "Required observations unavailable: 'ou_history'", "coverage": "selected_fixture", "assertion_id": "OU03.selected_fixture" }, { "id": "OU05", "verdict": "inconclusive", "reason": "Required observations unavailable: 'ou_assembly'", "coverage": "selected_fixture", "assertion_id": "OU05.selected_fixture" }, { "id": "OU06", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "OU06.selected_fixture" }, { "id": "OU07", "verdict": "inconclusive", "reason": "Required observations unavailable: 'ou_assembly'", "coverage": "selected_fixture", "assertion_id": "OU07.selected_fixture" }, { "id": "OU08", "verdict": "inconclusive", "reason": "Required observations unavailable: 'ou_history'", "coverage": "selected_fixture", "assertion_id": "OU08.selected_fixture" }, { "id": "OU09", "verdict": "inconclusive", "reason": "Required observations unavailable: 'ou_assembly'", "coverage": "selected_fixture", "assertion_id": "OU09.selected_fixture" }, { "id": "OU10", "verdict": "inconclusive", "reason": "Required observations unavailable: 'ou_assembly'", "coverage": "selected_fixture", "assertion_id": "OU10.selected_fixture" }, { "id": "OU11", "verdict": "inconclusive", "reason": "Required observations unavailable: 'ou_assembly'", "coverage": "selected_fixture", "assertion_id": "OU11.selected_fixture" }, { "id": "OU12", "verdict": "inconclusive", "reason": "Required observations unavailable: 'ou_history'", "coverage": "selected_fixture", "assertion_id": "OU12.selected_fixture" }, { "id": "OU13", "verdict": "inconclusive", "reason": "Required observations unavailable: 'ou_assembly'", "coverage": "selected_fixture", "assertion_id": "OU13.selected_fixture" }, { "id": "OU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU04.selected_fixture" }, { "id": "OU19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU19.selected_fixture" }, { "id": "OU20", "verdict": "fail", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU20.selected_fixture" }, { "id": "OU21", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU21.selected_fixture" }, { "id": "PR01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR01.selected_fixture" }, { "id": "PR02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR02.selected_fixture" }, { "id": "PR03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR03.selected_fixture" }, { "id": "PR04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR04.selected_fixture" }, { "id": "PR05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR05.selected_fixture" }, { "id": "PR06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR06.selected_fixture" }, { "id": "PR07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR07.selected_fixture" }, { "id": "PR08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR08.selected_fixture" }, { "id": "PR09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR09.selected_fixture" }, { "id": "PR10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR10.selected_fixture" }, { "id": "PR11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR11.selected_fixture" }, { "id": "PR12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR12.selected_fixture" }, { "id": "PR13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR13.selected_fixture" }, { "id": "PR14", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "PR14.selected_fixture" }, { "id": "PR15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR15.selected_fixture" }, { "id": "PR16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR16.selected_fixture" }, { "id": "PR17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR17.selected_fixture" }, { "id": "PR18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR18.selected_fixture" }, { "id": "PR19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR19.selected_fixture" }, { "id": "F01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F01.selected_fixture" }, { "id": "F02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F02.selected_fixture" }, { "id": "F03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F03.selected_fixture" }, { "id": "F04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F04.selected_fixture" }, { "id": "F05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F05.selected_fixture" }, { "id": "G01", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G01.static_sources" }, { "id": "G02", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G02.static_sources" }, { "id": "G03", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G03.static_sources" } ], "charges": [ { "id": "F1C-GEN03", "points": "0.5", "reason": "отчёт не соответствует заданию: OU20" }, { "id": "F1C-GEN01", "points": "0.5", "reason": "не выполнено требование: BU13" }, { "id": "F1C-GEN01", "points": "0.5", "reason": "не выполнено требование: BU14" }, { "id": "F1C-GEN15", "points": "0.5", "reason": "Reports/ВедомостьПоПодразделению/Ext/ManagerModule.bsl:3 — РегистрНакопления.ОстаткиНоменклатуры.ОстаткиИОбороты: отбор по Подразделение, индексы таблицы начинаются с Номенклатура" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "проводимые документы в режиме «Записывать модифицированные»: Операция, Сборка" }, { "id": "F1C-PR14", "points": "0.5", "reason": "после расчёта набор с периодом действия перезаписывается целиком, с пересчётом фактического периода действия (нужно Записать(, Истина)): CommonModules/РасчетЗарплаты/Ext/Module.bsl:145 Набор.Записать(); CommonModules/РасчетЗарплаты/Ext/Module.bsl:190 Набор.Записать(); CommonModules/РасчетЗарплаты/Ext/Module.bsl:193 Набор.Записать(); CommonModules/РасчетЗарплаты/Ext/Module.bsl:304 Набор.Записать()" }, { "id": "F1C-BU06", "points": "1.5", "reason": "признак учёта ТоварныйУчет плана счетов не указан ни у одного ресурса регистра — не действует" }, { "id": "F1C-BU05", "points": "0.5", "reason": "аналитика счетов вынесена в измерения регистра бухгалтерии и есть у всех счетов: Номенклатура (Номенклатура), Склад (Склады)" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "оперативное проведение разрешено у документов с движениями по регистрам расчёта: НачислениеЗарплаты" }, { "id": "F1C-GEN21", "points": "2.0", "reason": "данные графика без отбора по регистратору: CommonModules/РасчетЗарплаты/Ext/Module.bsl:235" }, { "id": "F1C-GEN22", "points": "1.0", "reason": "значения графика выбираются без ЕСТЬNULL: CommonModules/РасчетЗарплаты/Ext/Module.bsl:235 ДниФактическийПериодДействия" } ], "score_upper_bound": "-4.5", "score": null, "grade": "unsatisfactory", "deductions": "9.5", "not_assessed": 18, "gates": { "starter_origin": "passed", "load": "loaded", "clients": "compiles", "demo_data": "present" }, "infrastructure_errors": true, "comparison_eligible": false, "binding_compatibility": null }, "measurement": { "operator": { "name": "Вячеслав", "github": "sksibak" }, "environment": { "captured_at": "2026-10-25T06:30:56.582237+00:00", "capture_timing": "before_run", "hardware": { "cpu": "AMD Ryzen 5 4600H with Radeon Graphics ", "logical_cpus": 12, "ram_bytes": 16505962496 }, "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "python": "3.12.14", "platform_version": "8.3.27.1644", "isolation": "dedicated-host", "network_profile": "open-book_shell", "unsafe_action_protection_observed_in_user_config": true, "git_revision": "af85e791b303dbbf0b0b7af924d2489c3e57cfa8", "implementation_files": { "exam_bench/__init__.py": "ad5bf6f05dc6765f40b78bd186870ca2c49be113cfa33f8aa76f4926f2cb2c1e", "exam_bench/assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "exam_bench/bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "exam_bench/calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "exam_bench/calibrate.py": "78b5185cb0888c0c0ac3de95ffc3a80154a6de9ae66fc461f79d012e5a58e1db", "exam_bench/calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "exam_bench/calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "exam_bench/calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "exam_bench/calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "exam_bench/calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "exam_bench/claude.py": "bc1b8550de7573aaed5e39c6e9c0309e0d8175284a75490d61ec27439ed911ad", "exam_bench/cli.py": "1a37ce645633d761f7897dffc9c45e6b8b9600cd7bd233b1cbf78f49d26b099a", "exam_bench/codescan.py": "751e38001b6e65727a31e28172a0623f0bf34bc092a958037c286aa991a197ed", "exam_bench/codex.py": "c3f89d72af11f312d851c73a1610d92e79acadf336be9ccedd1f94ede3b3ccb0", "exam_bench/common.py": "8682603b519063e655eae3574a02a49efee63bde21f582ccee20ddd623fca96d", "exam_bench/docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "exam_bench/examiner.py": "d7294fdd23ed1732216cafebf0a8cf2c24cce4259859aeb7149f62b7607d087d", "exam_bench/finalize.py": "4034f1c63896a940afdb1a83d541cf47fc75c8b5061e3f839047109c04beb620", "exam_bench/forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "exam_bench/gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "exam_bench/grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "exam_bench/harness.py": "3040f6daaf1dc6e6583219f4d925151f8ba7851b2d5417d7f14645892b485ddf", "exam_bench/interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "exam_bench/interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "exam_bench/isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "exam_bench/ledger.py": "7e851523580e22d8490e75f9b6026c07f2c355007e0d11d0b252671f56bef654", "exam_bench/locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "exam_bench/materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "exam_bench/mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "exam_bench/observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "exam_bench/ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "exam_bench/penalties.py": "0d79e2e46102657dca00609b6abbfc0bf7d11fad41429564f876c82bc6b33269", "exam_bench/platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "exam_bench/portable.py": "cad56968ff407983608f5bdbc9ce7234128d7a4580b096ecea8e0e7b4edb9070", "exam_bench/portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "exam_bench/pr.py": "6a3a20caf0e10c0cc94410511a72d62c9fcda785f3abab1be2ad616d4ee16836", "exam_bench/preflight.py": "5619be0131d8641925f3ce2a3c8e5234d42aa5635d95676138ca81536d95cd29", "exam_bench/process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "exam_bench/queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "exam_bench/queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "exam_bench/replay_calibration.py": "c150457b0b23ce4e6814eb8deb4d48f6bc4a2e39d8f84a9dc7644fb99a026c2d", "exam_bench/report.py": "5e4c0757e1c7f189953f9a5302593ab726551835856baed25efd93dad6e8bfcd", "exam_bench/runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "exam_bench/smoke_check.py": "f36922a0027429ead0b414048dcc14bbe67f2f0e79a70d03dffbe1447d253545", "exam_bench/stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "exam_bench/submission.py": "d6f9d20704181c51714f1138affe4965d860ae21475ab7bb49aa5c5cefebb9f5", "exam_bench/telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "exam_bench/windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "exam_bench/workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tools/build_public_site.py": "9682ed696f5ac9e9a82b65a45c0dece556ec7e49eeb20dcd616882cc534a8258", "tools/build_result_site.py": "3294e1d2ec1486058e208735264d61e349a68a4ae2fa2ec7a723c70e3263b496", "tools/check_native_harnesses.py": "4f5f0ed27651f78758eaef077b3b114361781f6b95ec40cb46c3fea689210473", "tools/check_native_toolkit.py": "0272794617121f2932828e5e4e9ae20095183c443666cf3ba466b44fbe875095", "tools/community_results.py": "9db56a44697d94f326efcbd7a3ae1aecdb569d43bba6c47e80ce525dc045f1f7", "tools/community_service.py": "c374480dbd88d656c0b9054fa04a8e1c6698c69e2f9cf475e82498a2dff61d84", "tools/community_setup.py": "5d7d126ed7d4dd48e1d79f57b99647a92ffcc8c9f80d90915e458888cdd76bf7", "tools/compare_harness_runs.py": "f274df5f3f804cb02504491aec946943833e12fbce6e62d281e12beb8508fc4e", "tools/create_run_plan.py": "871cd81b1eda231c0fba8805f63d2668926be9fc641559e6ddf320e2f47cd37a", "tools/demo_runner.py": "230e6e49068f2bab3a0db64e6da5889e8f1834158fed8c5ec334b7694695a87b", "tools/installers.py": "9a2742780936b17500869e7c89202c1a2549e37d53a42ad9a50a0abbf78bbe09", "tools/machine_bundle.py": "8aa8346f99f537e81ceca6fb6ab9530e844954bab8eff87bf33d3602f81f8a30", "tools/prepare_native_harnesses.py": "aaa75ecf4022883984fa50c42d14d8e1a9fde2eeda03dab03b852bbc5efb2502", "tools/prepare_official_statement.py": "6b7028c78e90e798d6ef1a93b76520cc61a308c354fb9b87f7fad18b99800fad", "tools/prepare_open_exam_requirements.py": "544f4e378b9be5f166186f8788f8d454afdac2deb99d91d98421e39d01ba6d03", "tools/probe_harness.py": "1ed8ef93420d1484cbbfd151b7efc31b9a201ceb942dd05e3103efa22ffa7f27", "tools/probe_native_mcp.py": "9918d324129cba898993e07f8f8b6dbcbaf369398ebf28d464f9f1f00abdb254", "tools/readiness.py": "d34dd3f38334f51cc4574c79194cf0b80769b062a52382989a57d01c46b9aba4", "tools/recheck_community.py": "f0843d7d677f90da31e22bde0b1c86584dd46c022f1532d43d042619e426b230", "tools/regrade_runs.py": "011775afb06d3aac67a4aa81117a368c75896b0fcbe1e6f27ccc6237612fbf59", "tools/render_statement_text.py": "dabc0716a3612c288c671bc20e17fd4986691d732768e1e957d6dddddbea92a3", "tools/replay_calibration.py": "801f5004926c438c21ed3668fe2a4ddf45312b3e75320165a3839aae034eee9b", "tools/run_exam_campaign.py": "2c450d57a1cd0a2682838f5ec7c0a4ffb3aed0f1730d34c408e912d59cab6efd", "tools/serve_result_site.py": "86badfac863cd4ad1fc894a14110c75b28470513f0133eeae9d2799b8b4df3a9", "tools/start_demo.py": "c597e6cad28d245b3191654bb3e2801fa9dd2364e2acb25561923613717b615f", "tools/supplemental_acceptance.py": "c88fc39de1be1fdcacdd819e2ad329f60367b2df1d5deda80b37324bda3f2a01", "tools/sync_sources.py": "b51e889b0f41f9f63bfb19a09fb96d3777693d6b1d76fe0132bdd2a15e155898", "tools/validate_community_pr.py": "796b896dfade07b4529af2088a4b9b9d23484148b3bc0732b3fb837b75c9844b", "tools/verify_official_assessment_mapping.py": "daeb448a016940d5b6b1285979a56e5b9014bd91db40acb131445e4a83a23059", "tools/verify_task_package.py": "9e1e6105f6b5e4e78b36aa57f00117a9fbc8948ab53983c32ab56da88d23ccc4", "profiles/agents.json": "af9c492c08d13b3044aa6b6952589ed6a0a07d5258d8ff72bb18185b3eaebdc5", "profiles/ai-exam-execution-policy.json": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "profiles/bsl-analyzer-0.3.2-macos.json": "83537abdbf38c41ce665e4d0f24128bb51b62e971e0e0f368695f1326a7d2ffb", "profiles/bsl-analyzer-0.3.2-portable.json": "d6ba732e6778e256df34d6bc548593128820a70430c35b279796843606ee40a8", "profiles/bsl-ls-1.1.0-rc.6-macos.json": "245fc10747197e6911b2b4c77cdb15e6fa4eb7bc7c3758b63e768c5adf1df180", "profiles/bsl-ls-1.1.0-rc.6-portable.json": "9f10660881f2ec84794f7d584556b8f75c7e14b3555464af0ed0e60c4c892d86", "profiles/code-index-1.9.0-macos.json": "63a919523ce62ecec274f4c139bc7ad49a75dd4c339568b822cbc695b4e30408", "profiles/code-index-1.9.0-portable.json": "81106cee8f424ffd8a9dc46ecd8e4f57598fc1d49661a83c77b1f0507993fbdc", "profiles/codex-probe-plan.json": "166e41aad5fb3b27d9050bc6de952c6cba363cc6e804d4080568cc71a2a4d289", "profiles/machine.linux.example.json": "408304fd0581098d5d8110dc67dfeab353bc4d4030e32d37e6acf98d2b1aedfd", "profiles/machine.macos.example.json": "52e9f9d17797cb520b9d8955d6806fd550b899bed4da241ebf096dcb6a21a942", "profiles/machine.windows.example.json": "63accac9a2f81d47d03447efbabffd4760aee325193f02f46b9b29a28d50d2d8", "profiles/mcp-toolkit-1.9.0-macos.json": "1d3f9cde5ffa20589a840d01fdae03aa0fc2f412c929f064f203919c4129625b", "profiles/mcp-toolkit-1.9.0-portable.json": "8e370eebe773eef0e08045ee9c6d5be1451f769f65be0710834b262a4336e054", "profiles/none-macos.json": "b1401d9c48159aed3559006c7f6ace6ef4571224d5cf0bb76d1a823505a10056", "profiles/none-portable.json": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "profiles/rlm-tools-bsl-1.43.0-macos.json": "9354421052640ab60bc3e6aa98ff2e7ba9ca2318b0f4026c137487449242cbd2", "profiles/rlm-tools-bsl-1.43.0-portable.json": "2599e5645e0a7d4e44cb2934bc2b272cae79a9bf7ea74a23cd48aacea64bc424", "profiles/rlm-tools-bsl-1.43.0-posix-requirements.txt": "4fdf9a1bd994bf0272e65d231daf76cf19b0a34dad0ae6b50ec4f11a2ce4c330", "profiles/rlm-tools-bsl-1.43.0-windows-requirements.txt": "3730cb46c81cda5181ecd4485e98b11933104632358bc86f8c0eb1a612a8954f", "profiles/shirokov-skills-macos.json": "84f3e89091676884a802035c707e912762a1179425fb8e3faff25be736873cdb", "profiles/shirokov-skills-portable.json": "2b0a461e06602f1456410e70f02ceaa5ac32c6549c486660bcb5ace0c2f87b15", "profiles/shirokov-skills-windows-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/unica-0.12.3-macos.json": "2c39fbb591cf2c2c6e056373823615485397ea83651b7926c6f25a5fe6a0aae6", "profiles/unica-0.13.0-macos.json": "b76b5c8a4dd33f571c4a90993f1a2da5f7223b4f0f8e1042c282e21a66121052", "profiles/unica-0.14.0-rc.1-portable.json": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "rules/1c-specialist-platform/chistov.json": "77e04942f8c947b10759e7cc1eb31af05847d1711a772fbe6f23d525766757a9", "rules/1c-specialist-platform/decisions.json": "f622107423ce3c188c063318d7ab4f7718ceb38e443130677d8987f386641c09", "rules/1c-specialist-platform/examiner.json": "30353aa2a1b6545496b070d9066e9ffba0c3779e5b53ef70a4fd2cee375b18c0", "rules/1c-specialist-platform/ledger.json": "f167c10db2b5799dd9a1ea6a37cd2d7d186810dadf5ea2f50f26ae723c676882", "rules/1c-specialist-platform/rules.json": "1d320a4f8e1bf4701496388931f492315549bd3dce574b17285dd1d7f8652007", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" } } }, "conditions": { "client": "codex", "model": "gpt-6.1-sol", "client_version": "0.163.0-alpha.11.2", "reasoning_effort": "medium", "harness": "unica-0.14.0-rc.1", "billing_channel": "subscription", "solve_timeout_seconds": 7200, "time_series": null, "delegation": "native_disabled", "network_profile": "open-book_shell", "deadline_disclosed": true, "statement_sha256": "8a6ccb3e673826d1f8220fda53eb310e3ec18c136d87ce8f4cebb2a08614e7e5", "starter_dt_sha256": "f40d084818b0d1cfe503fc7653a6a13f1a8e47fcd1688dad6245b12744eb4638", "profile_sha256": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "execution_policy_sha256": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "calibration_sha256": "e8981744a194aa56f954d2965aa66cd53cd4f899f09fa7b5abda6f6b27a5ed65", "started_at": "2026-10-25T06:31:06.187531+00:00", "timing": { "prepare_ms": 9000, "solve_ms": 7031109, "grade_ms": null }, "original_submission_valid": true, "model_provenance": "requested_only", "tokens": { "input": 38707601, "cached_input": 37712256, "fresh_input": 995345, "output": 186873, "reasoning_output": 91034, "total": 38894474, "coverage": "reported_completed_root_turns" }, "tools": { "mcp_calls": 688, "unica_calls": 688, "failed_calls": 21 }, "process": { "status": "completed", "exit_code": 0, "stop_confirmed": true } }, "verification": "repository_owner_incomplete", "download": "community-downloads/demo-20261025T063054Z-b9676e--owner-2026-10-26T214326254722-0000/solution.zip", "source_context": "community-downloads/demo-20261025T063054Z-b9676e--owner-2026-10-26T214326254722-0000/source-context.json", "regrade_required": [ { "id": "grader_changed", "files": [ "calibrate.py", "calibration_periodicity.py", "common.py", "ou.py", "replay_calibration.py", "smoke_check.py", "tasks/1c-platform-official-sample/checks.json" ] } ], "grader_revision_sha256": "349d87e0c7f531acbe35dd2b39c35722d8a877fedde97575b49e8466ab763c1d", "archive_sha256": "69e3cfbc134bf0b2962ed46938bce961c4bede4b30e251ab81e2f13277d3fdfe", "owner_verification": { "kind": "repository_owner", "repository": "zeegin/1c-agent-exam-benchmark", "operator": { "name": "Ingvar Vilkman", "github": "zeegin" }, "started_at": "2026-10-26T21:43:26.096513+00:00", "server": { "name": "Owner Windows stand", "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "hardware": { "cpu": "AMD Ryzen 7 5800X 8-Core Processor ", "logical_cpus": 4, "ram_bytes": 17109000192 }, "isolation": "dedicated-host" }, "platform_version": "8.3.27.2342", "grader": { "profile": "technical-v8", "commit": "e8fd8ced03a85b549c5472fbbda29225749f54d1", "working_tree_dirty": false, "fingerprint": { "assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "calibrate.py": "3162d431f3cab5e7976aa39f665d6286dce45499cf362d85109b7123fa8403a2", "calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "calibration_query.py": "3555b103cde8ea0519955cf52358d09223f5ab183a9df00533bdb48c89237a8c", "claude.py": "eedabc75fca0faa434f40a1624b71419ec7dc22e2854a0886cf84b4911db8372", "codescan.py": "6d8375210cef1fd768fc2d98d630d880b2993a9724f01ae25f33b4ea5aa9631d", "codex.py": "904e75503cd35f16cbb052f66806b3879fe25bfc9f99e33b93c889d862c46324", "common.py": "52825cf5c29f3536d6e046a89e789d5ef9c83aacd7f2f5a07f4f53e77b5229cc", "docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "examiner.py": "8cdffcdd52f043c905f896697403380af95bf485dd4a5edca24f7956e7795ffe", "forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "harness.py": "3cbb90fd3187e700b5df32e5daafb20313d49bb5721c826e3033cbc6aa6e3825", "interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "penalties.py": "ae388cb8953ecca1f2370a7c4cb1db3b6cc8318fc2a7563a4db15f9f5b057429", "platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "pr.py": "2b6bfea0634703469605ce114f9274716b485852d9a55d9185c39893b14e4726", "preflight.py": "448c3120ab64b625abae3891be686c7a214ce4211f7cf651fd90e12c0b298433", "process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "queries.py": "1ef57e292db3e8967a733948371ecc542f743b811890d4fc509df17303b9c4ac", "queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "querytypes.py": "b645f489a2abc27762b4a9bbf4917e72f7b46dc053a74c0dca4a8fc46491b3ef", "replay_calibration.py": "0a4d9b84a9908944c5a945878eb6f5eeda5a4e42ffff4f55c04a680742803d80", "runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "smoke_check.py": "66caf1a01f7aa18432293abe3567ac228ac837a660b08c3dc7bb093f7bd51628", "stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "submission.py": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tasks/1c-platform-official-sample/checks.json": "17a6fcc0c14410829650623eb1443ce99796e000cdfd19905ac0287988b73a00", "tasks/1c-platform-official-sample/private/official-assessment-mapping.json": "303587c0dabe77c1eeebb2017fe85539e3370b17c9090435e6e0325a66bd0644", "tasks/1c-platform-official-sample/private/owner-scoring-policy.json": "d26d534bb838ab1b5facb7bc033ca8ec40912133baadcdbad83b27fc577905f5", "starters/carcass-8.3.25.1445/starter.json": "0f7a7060885ba99a19402bfc6e63cc8fe979b0f491b040d3a01d5d21b304b3a6", "rules/1c-specialist-platform/rules.json": "ea75e34ace5de11ba3de403c63cd2c026db81d1d991f8531e4a779d4ce9788e7", "rules/1c-specialist-platform/examiner.json": "1247486ddd412d600db88d9c1db4ba501fc1994afd1dc2ebe85402fcc332f4c8", "rules/1c-specialist-platform/chistov.json": "800da27601a3f1c7ec1df64482fd4ad035e559ba0b390a274ed5031128487d3d", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" }, "sha256": "349d87e0c7f531acbe35dd2b39c35722d8a877fedde97575b49e8466ab763c1d" }, "method": "saved_platform_observations", "outcome": "incomplete", "completed_at": "2026-10-26T21:43:26.254722+00:00" } }, { "id": "demo-20261025T063054Z-b9676e", "run_id": "demo-20261025T063054Z-b9676e", "result": { "run_id": "demo-20261025T063054Z-b9676e", "created_at": "2026-10-25T08:32:22.240287+00:00", "model": "gpt-6.1-sol", "harness": "unica-0.14.0-rc.1", "solve_seconds": 7031, "platform": "8.3.27.1644", "counts": { "pass": 52, "fail": 3, "inconclusive": 10 }, "rules": [ { "id": "BU01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU16", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU17", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU02", "verdict": "pass", "coverage": "partial", "reason": null }, { "id": "BU10", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU12", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU06", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU07", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU08", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU09", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU11", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU14", "verdict": "fail", "coverage": "selected_fixture", "reason": null }, { "id": "BU15", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU13", "verdict": "fail", "coverage": "selected_fixture", "reason": null }, { "id": "OU15", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU16", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU17", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU02", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU18", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU14", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU01", "verdict": "inconclusive", "coverage": "selected_fixture", "reason": null }, { "id": "OU03", "verdict": "inconclusive", "coverage": "selected_fixture", "reason": null }, { "id": "OU05", "verdict": "inconclusive", "coverage": "selected_fixture", "reason": null }, { "id": "OU06", "verdict": "pass", "coverage": "no_violation_found", "reason": null }, { "id": "OU07", "verdict": "inconclusive", "coverage": "selected_fixture", "reason": null }, { "id": "OU08", "verdict": "inconclusive", "coverage": "selected_fixture", "reason": null }, { "id": "OU09", "verdict": "inconclusive", "coverage": "selected_fixture", "reason": null }, { "id": "OU10", "verdict": "inconclusive", "coverage": "selected_fixture", "reason": null }, { "id": "OU11", "verdict": "inconclusive", "coverage": "selected_fixture", "reason": null }, { "id": "OU12", "verdict": "inconclusive", "coverage": "selected_fixture", "reason": null }, { "id": "OU13", "verdict": "inconclusive", "coverage": "selected_fixture", "reason": null }, { "id": "OU04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU19", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU20", "verdict": "fail", "coverage": "selected_fixture", "reason": "Ведомость не прошла проверку группировки по значениям характеристик." }, { "id": "OU21", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR02", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR06", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR07", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR08", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR09", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR10", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR11", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR12", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR13", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR14", "verdict": "pass", "coverage": "no_violation_found", "reason": null }, { "id": "PR15", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR16", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR17", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR18", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR19", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F02", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "G01", "verdict": "pass", "coverage": "static_sources", "reason": null }, { "id": "G02", "verdict": "pass", "coverage": "static_sources", "reason": null }, { "id": "G03", "verdict": "pass", "coverage": "static_sources", "reason": null } ], "charges": [ { "id": "F1C-GEN03", "points": "0.5", "reason": "Ведомость не прошла проверку группировки по значениям характеристик." }, { "id": "F1C-GEN01", "points": "0.5", "reason": "не выполнено требование: BU13" }, { "id": "F1C-GEN01", "points": "0.5", "reason": "не выполнено требование: BU14" }, { "id": "F1C-GEN12", "points": "0.25", "reason": "текст запроса не разбирается платформой: CommonModules/РасчетЗарплаты/Ext/Module.bsl:330 — Поле не найдено \"НомерСтроки\"" }, { "id": "F1C-GEN15", "points": "0.5", "reason": "Reports/ВедомостьПоПодразделению/Ext/ManagerModule.bsl:3 — РегистрНакопления.ОстаткиНоменклатуры.ОстаткиИОбороты: отбор по Подразделение, индексы таблицы начинаются с Номенклатура" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "проводимые документы в режиме «Записывать модифицированные»: Операция, Сборка" }, { "id": "F1C-PR14", "points": "0.5", "reason": "после расчёта набор с периодом действия перезаписывается целиком, с пересчётом фактического периода действия (нужно Записать(, Истина)): CommonModules/РасчетЗарплаты/Ext/Module.bsl:145 Набор.Записать(); CommonModules/РасчетЗарплаты/Ext/Module.bsl:190 Набор.Записать(); CommonModules/РасчетЗарплаты/Ext/Module.bsl:193 Набор.Записать(); CommonModules/РасчетЗарплаты/Ext/Module.bsl:304 Набор.Записать()" }, { "id": "F1C-BU06", "points": "1.5", "reason": "признак учёта ТоварныйУчет плана счетов не указан ни у одного ресурса регистра — не действует" }, { "id": "F1C-BU05", "points": "0.5", "reason": "аналитика счетов вынесена в измерения регистра бухгалтерии и есть у всех счетов: Номенклатура (Номенклатура), Склад (Склады)" }, { "id": "F1C-GEN20", "points": "2.0", "reason": "данные базы читаются в цикле по записям: CommonModules/РасчетЗарплаты/Ext/Module.bsl:139; CommonModules/Учет/Ext/Module.bsl:217; CommonModules/Учет/Ext/Module.bsl:359 и ещё 3" }, { "id": "F1C-GEN21", "points": "2.0", "reason": "параметры виртуальной таблицы не заданы или заменены условием ГДЕ: CommonModules/Учет/Ext/Module.bsl:384 РегистрНакопления.ОстаткиНоменклатуры.Остатки(,; CommonModules/Учет/Ext/Module.bsl:398 РегистрБухгалтерии.Управленческий.Остатки(," }, { "id": "F1C-GEN28", "points": "1.0", "reason": "оперативное проведение разрешено у документов с движениями по регистрам расчёта: НачислениеЗарплаты" }, { "id": "F1C-GEN21", "points": "2.0", "reason": "данные графика без отбора по регистратору: CommonModules/РасчетЗарплаты/Ext/Module.bsl:235" }, { "id": "F1C-GEN22", "points": "1.0", "reason": "значения графика выбираются без ЕСТЬNULL: CommonModules/РасчетЗарплаты/Ext/Module.bsl:235 ДниФактическийПериодДействия" } ], "score_upper_bound": "-8.75", "score": null, "grade": "unsatisfactory", "deductions": "13.75", "not_assessed": 16, "gates": { "starter_origin": "passed", "load": "loaded", "clients": "compiles", "demo_data": "present" }, "infrastructure_errors": true, "comparison_eligible": false, "binding_compatibility": null, "evaluation_sha256": "cb33742cb2e0083d52ef0671169e19252f4350630f6e2eb476ba67e036eeb38f", "downloads": [] }, "measurement": { "operator": { "name": "Вячеслав", "github": "sksibak" }, "environment": { "captured_at": "2026-10-25T06:30:56.582237+00:00", "capture_timing": "before_run", "hardware": { "cpu": "AMD Ryzen 5 4600H with Radeon Graphics ", "logical_cpus": 12, "ram_bytes": 16505962496 }, "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "python": "3.12.14", "platform_version": "8.3.27.1644", "isolation": "dedicated-host", "network_profile": "open-book_shell", "unsafe_action_protection_observed_in_user_config": true, "git_revision": "af85e791b303dbbf0b0b7af924d2489c3e57cfa8", "implementation_files": { "exam_bench/__init__.py": "ad5bf6f05dc6765f40b78bd186870ca2c49be113cfa33f8aa76f4926f2cb2c1e", "exam_bench/assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "exam_bench/bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "exam_bench/calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "exam_bench/calibrate.py": "78b5185cb0888c0c0ac3de95ffc3a80154a6de9ae66fc461f79d012e5a58e1db", "exam_bench/calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "exam_bench/calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "exam_bench/calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "exam_bench/calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "exam_bench/calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "exam_bench/claude.py": "bc1b8550de7573aaed5e39c6e9c0309e0d8175284a75490d61ec27439ed911ad", "exam_bench/cli.py": "1a37ce645633d761f7897dffc9c45e6b8b9600cd7bd233b1cbf78f49d26b099a", "exam_bench/codescan.py": "751e38001b6e65727a31e28172a0623f0bf34bc092a958037c286aa991a197ed", "exam_bench/codex.py": "c3f89d72af11f312d851c73a1610d92e79acadf336be9ccedd1f94ede3b3ccb0", "exam_bench/common.py": "8682603b519063e655eae3574a02a49efee63bde21f582ccee20ddd623fca96d", "exam_bench/docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "exam_bench/examiner.py": "d7294fdd23ed1732216cafebf0a8cf2c24cce4259859aeb7149f62b7607d087d", "exam_bench/finalize.py": "4034f1c63896a940afdb1a83d541cf47fc75c8b5061e3f839047109c04beb620", "exam_bench/forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "exam_bench/gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "exam_bench/grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "exam_bench/harness.py": "3040f6daaf1dc6e6583219f4d925151f8ba7851b2d5417d7f14645892b485ddf", "exam_bench/interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "exam_bench/interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "exam_bench/isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "exam_bench/ledger.py": "7e851523580e22d8490e75f9b6026c07f2c355007e0d11d0b252671f56bef654", "exam_bench/locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "exam_bench/materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "exam_bench/mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "exam_bench/observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "exam_bench/ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "exam_bench/penalties.py": "0d79e2e46102657dca00609b6abbfc0bf7d11fad41429564f876c82bc6b33269", "exam_bench/platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "exam_bench/portable.py": "cad56968ff407983608f5bdbc9ce7234128d7a4580b096ecea8e0e7b4edb9070", "exam_bench/portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "exam_bench/pr.py": "6a3a20caf0e10c0cc94410511a72d62c9fcda785f3abab1be2ad616d4ee16836", "exam_bench/preflight.py": "5619be0131d8641925f3ce2a3c8e5234d42aa5635d95676138ca81536d95cd29", "exam_bench/process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "exam_bench/queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "exam_bench/queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "exam_bench/replay_calibration.py": "c150457b0b23ce4e6814eb8deb4d48f6bc4a2e39d8f84a9dc7644fb99a026c2d", "exam_bench/report.py": "5e4c0757e1c7f189953f9a5302593ab726551835856baed25efd93dad6e8bfcd", "exam_bench/runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "exam_bench/smoke_check.py": "f36922a0027429ead0b414048dcc14bbe67f2f0e79a70d03dffbe1447d253545", "exam_bench/stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "exam_bench/submission.py": "d6f9d20704181c51714f1138affe4965d860ae21475ab7bb49aa5c5cefebb9f5", "exam_bench/telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "exam_bench/windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "exam_bench/workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tools/build_public_site.py": "9682ed696f5ac9e9a82b65a45c0dece556ec7e49eeb20dcd616882cc534a8258", "tools/build_result_site.py": "3294e1d2ec1486058e208735264d61e349a68a4ae2fa2ec7a723c70e3263b496", "tools/check_native_harnesses.py": "4f5f0ed27651f78758eaef077b3b114361781f6b95ec40cb46c3fea689210473", "tools/check_native_toolkit.py": "0272794617121f2932828e5e4e9ae20095183c443666cf3ba466b44fbe875095", "tools/community_results.py": "9db56a44697d94f326efcbd7a3ae1aecdb569d43bba6c47e80ce525dc045f1f7", "tools/community_service.py": "c374480dbd88d656c0b9054fa04a8e1c6698c69e2f9cf475e82498a2dff61d84", "tools/community_setup.py": "5d7d126ed7d4dd48e1d79f57b99647a92ffcc8c9f80d90915e458888cdd76bf7", "tools/compare_harness_runs.py": "f274df5f3f804cb02504491aec946943833e12fbce6e62d281e12beb8508fc4e", "tools/create_run_plan.py": "871cd81b1eda231c0fba8805f63d2668926be9fc641559e6ddf320e2f47cd37a", "tools/demo_runner.py": "230e6e49068f2bab3a0db64e6da5889e8f1834158fed8c5ec334b7694695a87b", "tools/installers.py": "9a2742780936b17500869e7c89202c1a2549e37d53a42ad9a50a0abbf78bbe09", "tools/machine_bundle.py": "8aa8346f99f537e81ceca6fb6ab9530e844954bab8eff87bf33d3602f81f8a30", "tools/prepare_native_harnesses.py": "aaa75ecf4022883984fa50c42d14d8e1a9fde2eeda03dab03b852bbc5efb2502", "tools/prepare_official_statement.py": "6b7028c78e90e798d6ef1a93b76520cc61a308c354fb9b87f7fad18b99800fad", "tools/prepare_open_exam_requirements.py": "544f4e378b9be5f166186f8788f8d454afdac2deb99d91d98421e39d01ba6d03", "tools/probe_harness.py": "1ed8ef93420d1484cbbfd151b7efc31b9a201ceb942dd05e3103efa22ffa7f27", "tools/probe_native_mcp.py": "9918d324129cba898993e07f8f8b6dbcbaf369398ebf28d464f9f1f00abdb254", "tools/readiness.py": "d34dd3f38334f51cc4574c79194cf0b80769b062a52382989a57d01c46b9aba4", "tools/recheck_community.py": "f0843d7d677f90da31e22bde0b1c86584dd46c022f1532d43d042619e426b230", "tools/regrade_runs.py": "011775afb06d3aac67a4aa81117a368c75896b0fcbe1e6f27ccc6237612fbf59", "tools/render_statement_text.py": "dabc0716a3612c288c671bc20e17fd4986691d732768e1e957d6dddddbea92a3", "tools/replay_calibration.py": "801f5004926c438c21ed3668fe2a4ddf45312b3e75320165a3839aae034eee9b", "tools/run_exam_campaign.py": "2c450d57a1cd0a2682838f5ec7c0a4ffb3aed0f1730d34c408e912d59cab6efd", "tools/serve_result_site.py": "86badfac863cd4ad1fc894a14110c75b28470513f0133eeae9d2799b8b4df3a9", "tools/start_demo.py": "c597e6cad28d245b3191654bb3e2801fa9dd2364e2acb25561923613717b615f", "tools/supplemental_acceptance.py": "c88fc39de1be1fdcacdd819e2ad329f60367b2df1d5deda80b37324bda3f2a01", "tools/sync_sources.py": "b51e889b0f41f9f63bfb19a09fb96d3777693d6b1d76fe0132bdd2a15e155898", "tools/validate_community_pr.py": "796b896dfade07b4529af2088a4b9b9d23484148b3bc0732b3fb837b75c9844b", "tools/verify_official_assessment_mapping.py": "daeb448a016940d5b6b1285979a56e5b9014bd91db40acb131445e4a83a23059", "tools/verify_task_package.py": "9e1e6105f6b5e4e78b36aa57f00117a9fbc8948ab53983c32ab56da88d23ccc4", "profiles/agents.json": "af9c492c08d13b3044aa6b6952589ed6a0a07d5258d8ff72bb18185b3eaebdc5", "profiles/ai-exam-execution-policy.json": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "profiles/bsl-analyzer-0.3.2-macos.json": "83537abdbf38c41ce665e4d0f24128bb51b62e971e0e0f368695f1326a7d2ffb", "profiles/bsl-analyzer-0.3.2-portable.json": "d6ba732e6778e256df34d6bc548593128820a70430c35b279796843606ee40a8", "profiles/bsl-ls-1.1.0-rc.6-macos.json": "245fc10747197e6911b2b4c77cdb15e6fa4eb7bc7c3758b63e768c5adf1df180", "profiles/bsl-ls-1.1.0-rc.6-portable.json": "9f10660881f2ec84794f7d584556b8f75c7e14b3555464af0ed0e60c4c892d86", "profiles/code-index-1.9.0-macos.json": "63a919523ce62ecec274f4c139bc7ad49a75dd4c339568b822cbc695b4e30408", "profiles/code-index-1.9.0-portable.json": "81106cee8f424ffd8a9dc46ecd8e4f57598fc1d49661a83c77b1f0507993fbdc", "profiles/codex-probe-plan.json": "166e41aad5fb3b27d9050bc6de952c6cba363cc6e804d4080568cc71a2a4d289", "profiles/machine.linux.example.json": "408304fd0581098d5d8110dc67dfeab353bc4d4030e32d37e6acf98d2b1aedfd", "profiles/machine.macos.example.json": "52e9f9d17797cb520b9d8955d6806fd550b899bed4da241ebf096dcb6a21a942", "profiles/machine.windows.example.json": "63accac9a2f81d47d03447efbabffd4760aee325193f02f46b9b29a28d50d2d8", "profiles/mcp-toolkit-1.9.0-macos.json": "1d3f9cde5ffa20589a840d01fdae03aa0fc2f412c929f064f203919c4129625b", "profiles/mcp-toolkit-1.9.0-portable.json": "8e370eebe773eef0e08045ee9c6d5be1451f769f65be0710834b262a4336e054", "profiles/none-macos.json": "b1401d9c48159aed3559006c7f6ace6ef4571224d5cf0bb76d1a823505a10056", "profiles/none-portable.json": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "profiles/rlm-tools-bsl-1.43.0-macos.json": "9354421052640ab60bc3e6aa98ff2e7ba9ca2318b0f4026c137487449242cbd2", "profiles/rlm-tools-bsl-1.43.0-portable.json": "2599e5645e0a7d4e44cb2934bc2b272cae79a9bf7ea74a23cd48aacea64bc424", "profiles/rlm-tools-bsl-1.43.0-posix-requirements.txt": "4fdf9a1bd994bf0272e65d231daf76cf19b0a34dad0ae6b50ec4f11a2ce4c330", "profiles/rlm-tools-bsl-1.43.0-windows-requirements.txt": "3730cb46c81cda5181ecd4485e98b11933104632358bc86f8c0eb1a612a8954f", "profiles/shirokov-skills-macos.json": "84f3e89091676884a802035c707e912762a1179425fb8e3faff25be736873cdb", "profiles/shirokov-skills-portable.json": "2b0a461e06602f1456410e70f02ceaa5ac32c6549c486660bcb5ace0c2f87b15", "profiles/shirokov-skills-windows-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/unica-0.12.3-macos.json": "2c39fbb591cf2c2c6e056373823615485397ea83651b7926c6f25a5fe6a0aae6", "profiles/unica-0.13.0-macos.json": "b76b5c8a4dd33f571c4a90993f1a2da5f7223b4f0f8e1042c282e21a66121052", "profiles/unica-0.14.0-rc.1-portable.json": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "rules/1c-specialist-platform/chistov.json": "77e04942f8c947b10759e7cc1eb31af05847d1711a772fbe6f23d525766757a9", "rules/1c-specialist-platform/decisions.json": "f622107423ce3c188c063318d7ab4f7718ceb38e443130677d8987f386641c09", "rules/1c-specialist-platform/examiner.json": "30353aa2a1b6545496b070d9066e9ffba0c3779e5b53ef70a4fd2cee375b18c0", "rules/1c-specialist-platform/ledger.json": "f167c10db2b5799dd9a1ea6a37cd2d7d186810dadf5ea2f50f26ae723c676882", "rules/1c-specialist-platform/rules.json": "1d320a4f8e1bf4701496388931f492315549bd3dce574b17285dd1d7f8652007", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" } } }, "conditions": { "client": "codex", "model": "gpt-6.1-sol", "client_version": "0.163.0-alpha.11.2", "reasoning_effort": "medium", "harness": "unica-0.14.0-rc.1", "billing_channel": "subscription", "solve_timeout_seconds": 7200, "time_series": null, "delegation": "native_disabled", "network_profile": "open-book_shell", "deadline_disclosed": true, "statement_sha256": "8a6ccb3e673826d1f8220fda53eb310e3ec18c136d87ce8f4cebb2a08614e7e5", "starter_dt_sha256": "f40d084818b0d1cfe503fc7653a6a13f1a8e47fcd1688dad6245b12744eb4638", "profile_sha256": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "execution_policy_sha256": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "calibration_sha256": "e8981744a194aa56f954d2965aa66cd53cd4f899f09fa7b5abda6f6b27a5ed65", "started_at": "2026-10-25T06:31:06.187531+00:00", "timing": { "prepare_ms": 9000, "solve_ms": 7031109, "grade_ms": null }, "original_submission_valid": true, "model_provenance": "requested_only", "tokens": { "input": 38707601, "cached_input": 37712256, "fresh_input": 995345, "output": 186873, "reasoning_output": 91034, "total": 38894474, "coverage": "reported_completed_root_turns" }, "tools": { "mcp_calls": 688, "unica_calls": 688, "failed_calls": 21 }, "process": { "status": "completed", "exit_code": 0, "stop_confirmed": true } }, "verification": "contributor_reported", "download": "community-downloads/demo-20261025T063054Z-b9676e/solution.zip", "source_context": "community-downloads/demo-20261025T063054Z-b9676e/source-context.json", "regrade_required": [ { "id": "grader_changed", "files": [ "assessment.py", "bp.py", "calcwrite.py", "calibrate.py", "calibration_periodicity.py", "calibration_query.py", "claude.py", "codescan.py", "codex.py", "common.py", "docx_text.py", "examiner.py", "harness.py", "interpretations.py", "locking.py", "materials.py", "mcp_toolkit.py", "ou.py", "penalties.py", "portable_harnesses.py", "pr.py", "preflight.py", "queries.py", "queryschema.py", "querytypes.py", "replay_calibration.py", "rules/1c-specialist-platform/chistov.json", "rules/1c-specialist-platform/examiner.json", "rules/1c-specialist-platform/rules.json", "rules/1c-specialist-platform/standards.json", "smoke_check.py", "starters/carcass-8.3.25.1445/starter.json", "stdio_harnesses.py", "submission.py", "tasks/1c-platform-official-sample/checks.json", "tasks/1c-platform-official-sample/private/official-assessment-mapping.json", "tasks/1c-platform-official-sample/private/owner-scoring-policy.json", "telemetry.py" ] } ], "grader_revision_sha256": "13710d802a08278385c484500f48f1678e0b002e5c7a3d8c00e14c1e75b1fbe9", "archive_sha256": "775db3aaa8aa0e9c162dd1ec73fc3819311f389ff5757f781eb7593d10c635d8" } ] }, { "id": "demo-20261025T145428Z-209efd--owner-2026-10-26T223328100393-0000", "run_id": "demo-20261025T145428Z-209efd", "result": { "run_id": "demo-20261025T145428Z-209efd", "created_at": "2026-10-26T22:33:28.100393+00:00", "model": "grok-4.7-high", "harness": "none", "solve_seconds": 5395, "platform": "8.3.27.2342", "counts": { "pass": 59, "fail": 4, "inconclusive": 2 }, "rules": [ { "id": "BU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU01.selected_fixture" }, { "id": "BU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU04.selected_fixture" }, { "id": "BU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU05.selected_fixture" }, { "id": "BU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU16.selected_fixture" }, { "id": "BU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU17.selected_fixture" }, { "id": "BU02", "verdict": "pass", "reason": null, "coverage": "partial", "assertion_id": "BU02.posting_cost_and_balance" }, { "id": "BU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU10.selected_fixture" }, { "id": "BU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU12.selected_fixture" }, { "id": "BU03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU03.selected_fixture" }, { "id": "BU06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU06.selected_fixture" }, { "id": "BU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU07.selected_fixture" }, { "id": "BU08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU08.selected_fixture" }, { "id": "BU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU09.selected_fixture" }, { "id": "BU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU11.selected_fixture" }, { "id": "BU14", "verdict": "fail", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU14.selected_fixture" }, { "id": "BU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU15.selected_fixture" }, { "id": "BU13", "verdict": "fail", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU13.selected_fixture" }, { "id": "OU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU15.selected_fixture" }, { "id": "OU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU16.selected_fixture" }, { "id": "OU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU17.selected_fixture" }, { "id": "OU02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU02.selected_fixture" }, { "id": "OU18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU18.selected_fixture" }, { "id": "OU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU14.selected_fixture" }, { "id": "OU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU01.selected_fixture" }, { "id": "OU03", "verdict": "pass", "reason": "История и годовая периодичность регистра подтверждены.", "coverage": "history_and_periodicity", "assertion_id": "OU03.selected_fixture" }, { "id": "OU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU05.selected_fixture" }, { "id": "OU06", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "OU06.selected_fixture" }, { "id": "OU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU07.selected_fixture" }, { "id": "OU08", "verdict": "pass", "reason": "История и дневная периодичность подтверждены; ограничение одной версии в неделю отдельно не проверяется.", "coverage": "history_and_periodicity", "assertion_id": "OU08.selected_fixture" }, { "id": "OU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU09.selected_fixture" }, { "id": "OU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU10.selected_fixture" }, { "id": "OU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU11.selected_fixture" }, { "id": "OU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU12.selected_fixture" }, { "id": "OU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU13.selected_fixture" }, { "id": "OU04", "verdict": "inconclusive", "reason": "Required observations unavailable: characteristic values could not be written: {'value_P1': '{ОбщийМодуль.BenchmarkObserver.Модуль(108)}: Ошибка при установке значения атрибута контекста (Владелец): Справочник не имеет владельца'", "coverage": "selected_fixture", "assertion_id": "OU04.selected_fixture" }, { "id": "OU19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU19.selected_fixture" }, { "id": "OU20", "verdict": "inconclusive", "reason": "Required observations unavailable: characteristic values could not be written: {'value_P1': '{ОбщийМодуль.BenchmarkObserver.Модуль(108)}: Ошибка при установке значения атрибута контекста (Владелец): Справочник не имеет владельца'", "coverage": "selected_fixture", "assertion_id": "OU20.selected_fixture" }, { "id": "OU21", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU21.selected_fixture" }, { "id": "PR01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR01.selected_fixture" }, { "id": "PR02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR02.selected_fixture" }, { "id": "PR03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR03.selected_fixture" }, { "id": "PR04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR04.selected_fixture" }, { "id": "PR05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR05.selected_fixture" }, { "id": "PR06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR06.selected_fixture" }, { "id": "PR07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR07.selected_fixture" }, { "id": "PR08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR08.selected_fixture" }, { "id": "PR09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR09.selected_fixture" }, { "id": "PR10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR10.selected_fixture" }, { "id": "PR11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR11.selected_fixture" }, { "id": "PR12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR12.selected_fixture" }, { "id": "PR13", "verdict": "fail", "reason": "pr_backdate E4/B tariff 2025-01: 2160, expected 1680.00; pr_backdate E4/B tariff 2025-02: 1920, expected 1680.00", "coverage": "selected_fixture", "assertion_id": "PR13.selected_fixture" }, { "id": "PR14", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "PR14.selected_fixture" }, { "id": "PR15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR15.selected_fixture" }, { "id": "PR16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR16.selected_fixture" }, { "id": "PR17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR17.selected_fixture" }, { "id": "PR18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR18.selected_fixture" }, { "id": "PR19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR19.selected_fixture" }, { "id": "F01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F01.selected_fixture" }, { "id": "F02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F02.selected_fixture" }, { "id": "F03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F03.selected_fixture" }, { "id": "F04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F04.selected_fixture" }, { "id": "F05", "verdict": "fail", "reason": "typed ['C1', 'C2'], written True, stored [('BENCH_Валюта', ''), ('BENCH_Срок', '')]", "coverage": "selected_fixture", "assertion_id": "F05.selected_fixture" }, { "id": "G01", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G01.static_sources" }, { "id": "G02", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G02.static_sources" }, { "id": "G03", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G03.static_sources" } ], "charges": [ { "id": "F1C-GEN01", "points": "0.5", "reason": "не выполнено требование: BU13" }, { "id": "F1C-GEN01", "points": "0.5", "reason": "не выполнено требование: BU14" }, { "id": "F1C-GEN01", "points": "0.5", "reason": "не выполнено требование: PR13 — pr_backdate E4/B tariff 2025-01: 2160, expected 1680.00; pr_backdate E4/B tariff 2025-02: 1920, expected 1680.00" }, { "id": "F1C-GEN01", "points": "0.5", "reason": "не выполнено требование: F05 — typed ['C1', 'C2'], written True, stored [('BENCH_Валюта', ''), ('BENCH_Срок', '')]" }, { "id": "F1C-GEN12", "points": "0.25", "reason": "текст запроса не разбирается платформой: DataProcessors/ЗаполнениеГрафика/Ext/ObjectModule.bsl:5 — Поле не найдено \"Подразделения.ЭтоГруппа\"" }, { "id": "F1C-GEN15", "points": "0.5", "reason": "Reports/ПремииСотрудников/Ext/ManagerModule.bsl:9 — РегистрРасчета.Начисления: отбор по ВидРасчета, ПериодДействияНачало, индексы таблицы начинаются с ПериодДействия, ПериодРегистрации, Подразделение, Регистратор, Сотрудник" }, { "id": "F1C-PR14", "points": "0.5", "reason": "после расчёта набор с периодом действия перезаписывается целиком, с пересчётом фактического периода действия (нужно Записать(, Истина)): CommonModules/РасчетЗарплаты/Ext/Module.bsl:29 Набор.Записать(); CommonModules/РасчетЗарплаты/Ext/Module.bsl:31 Набор.Записать(); CommonModules/РасчетЗарплаты/Ext/Module.bsl:33 Набор.Записать(); CommonModules/РасчетЗарплаты/Ext/Module.bsl:35 Набор.Записать(); CommonModules/РасчетЗарплаты/Ext/Module.bsl:37 Набор.Записать(); CommonModules/РасчетЗарплаты/Ext/Module.bsl:39 Набор.Записать()" }, { "id": "F1C-BU06", "points": "1.5", "reason": "ресурс Количество балансовый" }, { "id": "F1C-BU07", "points": "1.0", "reason": "признак учёта субконто Суммовой, Количественный, ТолькоОбороты заведён в плане счетов, но не указан ни у одного ресурса регистра — не действует" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "оперативное проведение разрешено у документов с движениями по регистрам расчёта: НачислениеЗарплаты" }, { "id": "F1C-GEN21", "points": "2.0", "reason": "данные графика без отбора по регистратору: CommonModules/РасчетЗарплаты/Ext/Module.bsl:450" }, { "id": "F1C-GEN01", "points": "0.5", "reason": "разыменование поля составного типа без ВЫРАЗИТЬ: CommonModules/УчетЗапасов/Ext/Module.bsl: Остатки.Партия.Дата" } ], "score_upper_bound": "-4.25", "score": null, "grade": "unsatisfactory", "deductions": "9.25", "not_assessed": 16, "gates": { "starter_origin": "passed", "load": "loaded", "clients": "compiles", "demo_data": "present" }, "infrastructure_errors": false, "comparison_eligible": false, "binding_compatibility": null }, "measurement": { "operator": { "name": "Виктор Мурашкин", "github": "VictorMurashkin" }, "environment": { "captured_at": "2026-10-25T14:54:30.054169+00:00", "capture_timing": "before_run", "hardware": { "cpu": "12th Gen Intel(R) Core(TM) i5-12600KF", "logical_cpus": 16, "ram_bytes": 68500021248 }, "os": { "system": "Windows", "release": "11", "version": "10.0.26100", "architecture": "AMD64" }, "python": "3.14.6", "platform_version": "8.3.27.2342", "isolation": "dedicated-host", "network_profile": "open-book_shell", "unsafe_action_protection_observed_in_user_config": true, "git_revision": "2d3566285b9fb7c93d60e4d903679c17d8dc71b8", "implementation_files": { "exam_bench/__init__.py": "ad5bf6f05dc6765f40b78bd186870ca2c49be113cfa33f8aa76f4926f2cb2c1e", "exam_bench/assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "exam_bench/bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "exam_bench/calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "exam_bench/calibrate.py": "78b5185cb0888c0c0ac3de95ffc3a80154a6de9ae66fc461f79d012e5a58e1db", "exam_bench/calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "exam_bench/calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "exam_bench/calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "exam_bench/calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "exam_bench/calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "exam_bench/claude.py": "9c68ca50de1301f20ca2109df21943caa7ac0c6da17bf0a5fbd305d2c244d9e5", "exam_bench/cli.py": "a1a83be1f53924705576ed06b2a2c20868067fd0c5d3da839192e7b13c37540b", "exam_bench/codescan.py": "751e38001b6e65727a31e28172a0623f0bf34bc092a958037c286aa991a197ed", "exam_bench/codex.py": "904e75503cd35f16cbb052f66806b3879fe25bfc9f99e33b93c889d862c46324", "exam_bench/common.py": "8682603b519063e655eae3574a02a49efee63bde21f582ccee20ddd623fca96d", "exam_bench/cursor.py": "88d903f344eedddb2303166ec10827714e4acde90bdc94eefd3ace46ef685671", "exam_bench/cursor_bsl.py": "753f02ebed60e5b8bbefba0933adbdf28477ef916353d70e3c68c817ce6c42e0", "exam_bench/cursor_harnesses.py": "d4bc375cdf5462cf99df079f2ea20148912f9e366e04225ad4abf73f9cafddf9", "exam_bench/docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "exam_bench/examiner.py": "d7294fdd23ed1732216cafebf0a8cf2c24cce4259859aeb7149f62b7607d087d", "exam_bench/finalize.py": "4034f1c63896a940afdb1a83d541cf47fc75c8b5061e3f839047109c04beb620", "exam_bench/forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "exam_bench/gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "exam_bench/grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "exam_bench/harness.py": "3040f6daaf1dc6e6583219f4d925151f8ba7851b2d5417d7f14645892b485ddf", "exam_bench/interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "exam_bench/interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "exam_bench/isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "exam_bench/ledger.py": "7e851523580e22d8490e75f9b6026c07f2c355007e0d11d0b252671f56bef654", "exam_bench/locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "exam_bench/materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "exam_bench/mcp_toolkit.py": "f4c3ea8d9ce542645960a0234ddb61712a047793c58d4e2a0691fc9a45961383", "exam_bench/observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "exam_bench/ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "exam_bench/penalties.py": "0d79e2e46102657dca00609b6abbfc0bf7d11fad41429564f876c82bc6b33269", "exam_bench/platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "exam_bench/portable.py": "cad56968ff407983608f5bdbc9ce7234128d7a4580b096ecea8e0e7b4edb9070", "exam_bench/portable_harnesses.py": "686c46a4231067625b3a20f0b22639d14bcaeb26fab3493e06f92b53dfead05a", "exam_bench/pr.py": "6a3a20caf0e10c0cc94410511a72d62c9fcda785f3abab1be2ad616d4ee16836", "exam_bench/preflight.py": "fbce47aa201c1f5acdbc80b241655dce443df35f9d14d3260c2325f875d6f6e4", "exam_bench/process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "exam_bench/queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "exam_bench/queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "exam_bench/replay_calibration.py": "e2d79cb508f2d5e3846d6dad36c3898d41dec1c573c1a1b7d8a2ec43e33c8c08", "exam_bench/report.py": "5e4c0757e1c7f189953f9a5302593ab726551835856baed25efd93dad6e8bfcd", "exam_bench/runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "exam_bench/smoke_check.py": "f36922a0027429ead0b414048dcc14bbe67f2f0e79a70d03dffbe1447d253545", "exam_bench/stdio_harnesses.py": "0bbfd791fb244a934c6cda3a4e63fbe9ce515e4af64729bb923ce86645057288", "exam_bench/submission.py": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "exam_bench/telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "exam_bench/windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "exam_bench/workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tools/build_public_site.py": "9682ed696f5ac9e9a82b65a45c0dece556ec7e49eeb20dcd616882cc534a8258", "tools/build_result_site.py": "38fc65d8dc01d51249e1c92c174d6ef42b8a0400a63a621d66bb4de9aaccce47", "tools/check_native_harnesses.py": "1fdde7b8eeb76f94341592ddbf1cac61306a65779d7b871ecabd053ab70c1e80", "tools/check_native_toolkit.py": "0272794617121f2932828e5e4e9ae20095183c443666cf3ba466b44fbe875095", "tools/community_results.py": "3f4c0067088353ec5bba8ea32decba5e205c3f7993cc305d07693b54c7039a23", "tools/community_service.py": "c374480dbd88d656c0b9054fa04a8e1c6698c69e2f9cf475e82498a2dff61d84", "tools/community_setup.py": "5d7d126ed7d4dd48e1d79f57b99647a92ffcc8c9f80d90915e458888cdd76bf7", "tools/compare_harness_runs.py": "f274df5f3f804cb02504491aec946943833e12fbce6e62d281e12beb8508fc4e", "tools/create_run_plan.py": "694f1b376f5b78de23705b8df3ec943def516eda93f96e7afaa3942729a1240c", "tools/demo_runner.py": "0f4267b97f5aaa25d60087be8fbe16f2ff6d7cc28de1ba4822d5d1302fb19163", "tools/installers.py": "9a2742780936b17500869e7c89202c1a2549e37d53a42ad9a50a0abbf78bbe09", "tools/machine_bundle.py": "8aa8346f99f537e81ceca6fb6ab9530e844954bab8eff87bf33d3602f81f8a30", "tools/prepare_native_harnesses.py": "fba3fd78b1fdd400196e086c5f463aec5ecefe41e81cd6875d87c76a3126a877", "tools/prepare_official_statement.py": "6b7028c78e90e798d6ef1a93b76520cc61a308c354fb9b87f7fad18b99800fad", "tools/prepare_open_exam_requirements.py": "544f4e378b9be5f166186f8788f8d454afdac2deb99d91d98421e39d01ba6d03", "tools/probe_cursor_harnesses.py": "19952ea409c934ed89cf2589dbb7dcf8d52fad5e01ca256c7df552578d28addc", "tools/probe_harness.py": "1ed8ef93420d1484cbbfd151b7efc31b9a201ceb942dd05e3103efa22ffa7f27", "tools/probe_http_mcp.py": "2667e191fb831b1cbc9cbbbbefdfad16241e17d620a1a42a43405ab0b8139ac4", "tools/probe_native_mcp.py": "9918d324129cba898993e07f8f8b6dbcbaf369398ebf28d464f9f1f00abdb254", "tools/readiness.py": "3c5404be17a7a0a2f72d7cef5714f7d1d6bde7da0d8eb698da4cc65d0b0dd3f3", "tools/recheck_community.py": "f0843d7d677f90da31e22bde0b1c86584dd46c022f1532d43d042619e426b230", "tools/regrade_runs.py": "011775afb06d3aac67a4aa81117a368c75896b0fcbe1e6f27ccc6237612fbf59", "tools/render_statement_text.py": "dabc0716a3612c288c671bc20e17fd4986691d732768e1e957d6dddddbea92a3", "tools/replay_calibration.py": "801f5004926c438c21ed3668fe2a4ddf45312b3e75320165a3839aae034eee9b", "tools/run_exam_campaign.py": "2c450d57a1cd0a2682838f5ec7c0a4ffb3aed0f1730d34c408e912d59cab6efd", "tools/serve_result_site.py": "86badfac863cd4ad1fc894a14110c75b28470513f0133eeae9d2799b8b4df3a9", "tools/start_demo.py": "c597e6cad28d245b3191654bb3e2801fa9dd2364e2acb25561923613717b615f", "tools/supplemental_acceptance.py": "7327277143d80a531e4c254ac74a9fc0e0d5c76572d53b8469e0a580eda17d65", "tools/sync_sources.py": "b51e889b0f41f9f63bfb19a09fb96d3777693d6b1d76fe0132bdd2a15e155898", "tools/validate_community_pr.py": "796b896dfade07b4529af2088a4b9b9d23484148b3bc0732b3fb837b75c9844b", "tools/verify_official_assessment_mapping.py": "daeb448a016940d5b6b1285979a56e5b9014bd91db40acb131445e4a83a23059", "tools/verify_task_package.py": "9e1e6105f6b5e4e78b36aa57f00117a9fbc8948ab53983c32ab56da88d23ccc4", "profiles/1c-ai-rules-2026-10-23-requirements.txt": "fd7ada214e0977776eb350794bb492d97824d96810eb7b158e46cf5cd72c8e65", "profiles/agents.json": "af9c492c08d13b3044aa6b6952589ed6a0a07d5258d8ff72bb18185b3eaebdc5", "profiles/ai-exam-execution-policy.json": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "profiles/bsl-analyzer-0.3.2-macos.json": "83537abdbf38c41ce665e4d0f24128bb51b62e971e0e0f368695f1326a7d2ffb", "profiles/bsl-analyzer-0.3.2-portable.json": "d6ba732e6778e256df34d6bc548593128820a70430c35b279796843606ee40a8", "profiles/bsl-ls-1.1.0-rc.6-macos.json": "245fc10747197e6911b2b4c77cdb15e6fa4eb7bc7c3758b63e768c5adf1df180", "profiles/bsl-ls-1.1.0-rc.6-portable.json": "9f10660881f2ec84794f7d584556b8f75c7e14b3555464af0ed0e60c4c892d86", "profiles/claude-code-skills-1c-1.12.0-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/code-index-1.9.0-macos.json": "63a919523ce62ecec274f4c139bc7ad49a75dd4c339568b822cbc695b4e30408", "profiles/code-index-1.9.0-portable.json": "81106cee8f424ffd8a9dc46ecd8e4f57598fc1d49661a83c77b1f0507993fbdc", "profiles/codex-probe-plan.json": "166e41aad5fb3b27d9050bc6de952c6cba363cc6e804d4080568cc71a2a4d289", "profiles/machine.linux.example.json": "408304fd0581098d5d8110dc67dfeab353bc4d4030e32d37e6acf98d2b1aedfd", "profiles/machine.macos.example.json": "52e9f9d17797cb520b9d8955d6806fd550b899bed4da241ebf096dcb6a21a942", "profiles/machine.windows.example.json": "63accac9a2f81d47d03447efbabffd4760aee325193f02f46b9b29a28d50d2d8", "profiles/mcp-toolkit-1.9.0-macos.json": "1d3f9cde5ffa20589a840d01fdae03aa0fc2f412c929f064f203919c4129625b", "profiles/mcp-toolkit-1.9.0-portable.json": "8e370eebe773eef0e08045ee9c6d5be1451f769f65be0710834b262a4336e054", "profiles/none-macos.json": "b1401d9c48159aed3559006c7f6ace6ef4571224d5cf0bb76d1a823505a10056", "profiles/none-portable.json": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "profiles/rlm-tools-bsl-1.43.0-macos.json": "9354421052640ab60bc3e6aa98ff2e7ba9ca2318b0f4026c137487449242cbd2", "profiles/rlm-tools-bsl-1.43.0-portable.json": "2599e5645e0a7d4e44cb2934bc2b272cae79a9bf7ea74a23cd48aacea64bc424", "profiles/rlm-tools-bsl-1.43.0-posix-requirements.txt": "4fdf9a1bd994bf0272e65d231daf76cf19b0a34dad0ae6b50ec4f11a2ce4c330", "profiles/rlm-tools-bsl-1.43.0-windows-requirements.txt": "3730cb46c81cda5181ecd4485e98b11933104632358bc86f8c0eb1a612a8954f", "profiles/shirokov-skills-macos.json": "84f3e89091676884a802035c707e912762a1179425fb8e3faff25be736873cdb", "profiles/shirokov-skills-portable.json": "2b0a461e06602f1456410e70f02ceaa5ac32c6549c486660bcb5ace0c2f87b15", "profiles/shirokov-skills-windows-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/unica-0.12.3-macos.json": "2c39fbb591cf2c2c6e056373823615485397ea83651b7926c6f25a5fe6a0aae6", "profiles/unica-0.13.0-macos.json": "b76b5c8a4dd33f571c4a90993f1a2da5f7223b4f0f8e1042c282e21a66121052", "profiles/unica-0.14.0-rc.1-portable.json": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "rules/1c-specialist-platform/chistov.json": "7a42ef723a1f5f03f02c387cd3ca95725f7364c2e11ebdfc988a02919ab22c37", "rules/1c-specialist-platform/decisions.json": "f622107423ce3c188c063318d7ab4f7718ceb38e443130677d8987f386641c09", "rules/1c-specialist-platform/examiner.json": "30353aa2a1b6545496b070d9066e9ffba0c3779e5b53ef70a4fd2cee375b18c0", "rules/1c-specialist-platform/ledger.json": "f167c10db2b5799dd9a1ea6a37cd2d7d186810dadf5ea2f50f26ae723c676882", "rules/1c-specialist-platform/rules.json": "1d320a4f8e1bf4701496388931f492315549bd3dce574b17285dd1d7f8652007", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" } } }, "conditions": { "client": "cursor", "model": "grok-4.7-high", "client_version": "2026.10.22-27dcf5f", "reasoning_effort": null, "harness": "none", "billing_channel": "subscription", "solve_timeout_seconds": 18000, "time_series": "exam", "delegation": "requested_disabled_unverified", "network_profile": "open-book_shell", "deadline_disclosed": true, "statement_sha256": "8a6ccb3e673826d1f8220fda53eb310e3ec18c136d87ce8f4cebb2a08614e7e5", "starter_dt_sha256": "f40d084818b0d1cfe503fc7653a6a13f1a8e47fcd1688dad6245b12744eb4638", "profile_sha256": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "execution_policy_sha256": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "calibration_sha256": "201d0591454d3b4cea9a26fde9088181f106b37b26f26392edb010457480b5c8", "started_at": "2026-10-25T14:54:48.106383+00:00", "timing": { "prepare_ms": 16331, "solve_ms": 5394921, "grade_ms": null }, "original_submission_valid": true, "model_provenance": "client_reported", "tokens": { "input": 36819638, "cached_input": 36221440, "fresh_input": 598198, "output": 347182, "reasoning_output": null, "total": 37166820, "coverage": "client_final_result" }, "tools": { "mcp_calls": 0, "unica_calls": 0, "failed_calls": 0 }, "process": { "status": "completed", "exit_code": 0, "stop_confirmed": true } }, "verification": "repository_owner", "download": "community-downloads/demo-20261025T145428Z-209efd--owner-2026-10-26T223328100393-0000/solution.zip", "source_context": "community-downloads/demo-20261025T145428Z-209efd--owner-2026-10-26T223328100393-0000/source-context.json", "regrade_required": [], "grader_revision_sha256": "9aee1ffe0e1d04f9158fbbbeed3a403a5f0550ad8a590d7a6394977590760e1a", "archive_sha256": "c822dca37164ac1590e2eb3646d8cfd2185e5356c78161712a2d23a207feacdb", "owner_verification": { "kind": "repository_owner", "repository": "zeegin/1c-agent-exam-benchmark", "operator": { "name": "Ingvar Vilkman", "github": "zeegin" }, "started_at": "2026-10-26T22:33:27.945490+00:00", "server": { "name": "Owner Windows stand", "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "hardware": { "cpu": "AMD Ryzen 7 5800X 8-Core Processor ", "logical_cpus": 4, "ram_bytes": 17109000192 }, "isolation": "dedicated-host" }, "platform_version": "8.3.27.2342", "grader": { "profile": "technical-v8", "commit": "e15c8ea80263c0b38baa3a1fc19611983270e8a7", "working_tree_dirty": false, "fingerprint": { "assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "calibrate.py": "aac127e03744907fd52ef149b88aa6d88a54a2b7497d56084484ee1b99e0da99", "calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "calibration_periodicity.py": "0b1953d7781e236467897cd2ed66705b75d9719353a2de60b36f2bbdfe799108", "calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "calibration_query.py": "3555b103cde8ea0519955cf52358d09223f5ab183a9df00533bdb48c89237a8c", "claude.py": "5bae98af6e2021e2718afa3a71ed04bee812deaae31a43d4e7324814139ccc82", "codescan.py": "6d8375210cef1fd768fc2d98d630d880b2993a9724f01ae25f33b4ea5aa9631d", "codex.py": "904e75503cd35f16cbb052f66806b3879fe25bfc9f99e33b93c889d862c46324", "common.py": "739b39e2bb9bdd4a571fc69df5843190cddcad094ef7e68964061bc1266b20dc", "docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "examiner.py": "8cdffcdd52f043c905f896697403380af95bf485dd4a5edca24f7956e7795ffe", "forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "harness.py": "3cbb90fd3187e700b5df32e5daafb20313d49bb5721c826e3033cbc6aa6e3825", "interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "ou.py": "f62784b54a3f85576a078a2ff1908c9395f3159e55f6bb5b1a3c564392241abe", "penalties.py": "ae388cb8953ecca1f2370a7c4cb1db3b6cc8318fc2a7563a4db15f9f5b057429", "platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "pr.py": "2b6bfea0634703469605ce114f9274716b485852d9a55d9185c39893b14e4726", "preflight.py": "448c3120ab64b625abae3891be686c7a214ce4211f7cf651fd90e12c0b298433", "process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "queries.py": "1ef57e292db3e8967a733948371ecc542f743b811890d4fc509df17303b9c4ac", "queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "querytypes.py": "b645f489a2abc27762b4a9bbf4917e72f7b46dc053a74c0dca4a8fc46491b3ef", "replay_calibration.py": "e0e3d5ca6416934715b9735aa516046b8d19ad4ae690220eeacd96b198a5f86c", "runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "smoke_check.py": "7837e980986bcb54dc8bc1dfb5d0003deef11e05f6e11df3910fa509e1f74c8d", "stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "submission.py": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tasks/1c-platform-official-sample/checks.json": "7447a9b42d3e348d29d07f001cfb6bd269acd953b7117eba7cca2ce9f5a9a60d", "tasks/1c-platform-official-sample/private/official-assessment-mapping.json": "303587c0dabe77c1eeebb2017fe85539e3370b17c9090435e6e0325a66bd0644", "tasks/1c-platform-official-sample/private/owner-scoring-policy.json": "d26d534bb838ab1b5facb7bc033ca8ec40912133baadcdbad83b27fc577905f5", "starters/carcass-8.3.25.1445/starter.json": "0f7a7060885ba99a19402bfc6e63cc8fe979b0f491b040d3a01d5d21b304b3a6", "rules/1c-specialist-platform/rules.json": "ea75e34ace5de11ba3de403c63cd2c026db81d1d991f8531e4a779d4ce9788e7", "rules/1c-specialist-platform/examiner.json": "1247486ddd412d600db88d9c1db4ba501fc1994afd1dc2ebe85402fcc332f4c8", "rules/1c-specialist-platform/chistov.json": "800da27601a3f1c7ec1df64482fd4ad035e559ba0b390a274ed5031128487d3d", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" }, "sha256": "9aee1ffe0e1d04f9158fbbbeed3a403a5f0550ad8a590d7a6394977590760e1a" }, "method": "saved_platform_observations", "outcome": "complete", "completed_at": "2026-10-26T22:33:28.100393+00:00" }, "previous_evaluations": [ { "id": "demo-20261025T145428Z-209efd--owner-2026-10-26T214406769623-0000", "run_id": "demo-20261025T145428Z-209efd", "result": { "run_id": "demo-20261025T145428Z-209efd", "created_at": "2026-10-26T21:44:06.769623+00:00", "model": "grok-4.7-high", "harness": "none", "solve_seconds": 5395, "platform": "8.3.27.2342", "counts": { "pass": 59, "fail": 4, "inconclusive": 2 }, "rules": [ { "id": "BU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU01.selected_fixture" }, { "id": "BU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU04.selected_fixture" }, { "id": "BU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU05.selected_fixture" }, { "id": "BU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU16.selected_fixture" }, { "id": "BU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU17.selected_fixture" }, { "id": "BU02", "verdict": "pass", "reason": null, "coverage": "partial", "assertion_id": "BU02.posting_cost_and_balance" }, { "id": "BU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU10.selected_fixture" }, { "id": "BU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU12.selected_fixture" }, { "id": "BU03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU03.selected_fixture" }, { "id": "BU06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU06.selected_fixture" }, { "id": "BU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU07.selected_fixture" }, { "id": "BU08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU08.selected_fixture" }, { "id": "BU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU09.selected_fixture" }, { "id": "BU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU11.selected_fixture" }, { "id": "BU14", "verdict": "fail", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU14.selected_fixture" }, { "id": "BU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU15.selected_fixture" }, { "id": "BU13", "verdict": "fail", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU13.selected_fixture" }, { "id": "OU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU15.selected_fixture" }, { "id": "OU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU16.selected_fixture" }, { "id": "OU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU17.selected_fixture" }, { "id": "OU02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU02.selected_fixture" }, { "id": "OU18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU18.selected_fixture" }, { "id": "OU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU14.selected_fixture" }, { "id": "OU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU01.selected_fixture" }, { "id": "OU03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU03.selected_fixture" }, { "id": "OU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU05.selected_fixture" }, { "id": "OU06", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "OU06.selected_fixture" }, { "id": "OU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU07.selected_fixture" }, { "id": "OU08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU08.selected_fixture" }, { "id": "OU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU09.selected_fixture" }, { "id": "OU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU10.selected_fixture" }, { "id": "OU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU11.selected_fixture" }, { "id": "OU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU12.selected_fixture" }, { "id": "OU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU13.selected_fixture" }, { "id": "OU04", "verdict": "inconclusive", "reason": "Required observations unavailable: characteristic values could not be written: {'value_P1': '{ОбщийМодуль.BenchmarkObserver.Модуль(108)}: Ошибка при установке значения атрибута контекста (Владелец): Справочник не имеет владельца'", "coverage": "selected_fixture", "assertion_id": "OU04.selected_fixture" }, { "id": "OU19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU19.selected_fixture" }, { "id": "OU20", "verdict": "inconclusive", "reason": "Required observations unavailable: characteristic values could not be written: {'value_P1': '{ОбщийМодуль.BenchmarkObserver.Модуль(108)}: Ошибка при установке значения атрибута контекста (Владелец): Справочник не имеет владельца'", "coverage": "selected_fixture", "assertion_id": "OU20.selected_fixture" }, { "id": "OU21", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU21.selected_fixture" }, { "id": "PR01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR01.selected_fixture" }, { "id": "PR02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR02.selected_fixture" }, { "id": "PR03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR03.selected_fixture" }, { "id": "PR04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR04.selected_fixture" }, { "id": "PR05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR05.selected_fixture" }, { "id": "PR06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR06.selected_fixture" }, { "id": "PR07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR07.selected_fixture" }, { "id": "PR08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR08.selected_fixture" }, { "id": "PR09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR09.selected_fixture" }, { "id": "PR10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR10.selected_fixture" }, { "id": "PR11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR11.selected_fixture" }, { "id": "PR12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR12.selected_fixture" }, { "id": "PR13", "verdict": "fail", "reason": "pr_backdate E4/B tariff 2025-01: 2160, expected 1680.00; pr_backdate E4/B tariff 2025-02: 1920, expected 1680.00", "coverage": "selected_fixture", "assertion_id": "PR13.selected_fixture" }, { "id": "PR14", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "PR14.selected_fixture" }, { "id": "PR15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR15.selected_fixture" }, { "id": "PR16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR16.selected_fixture" }, { "id": "PR17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR17.selected_fixture" }, { "id": "PR18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR18.selected_fixture" }, { "id": "PR19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR19.selected_fixture" }, { "id": "F01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F01.selected_fixture" }, { "id": "F02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F02.selected_fixture" }, { "id": "F03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F03.selected_fixture" }, { "id": "F04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F04.selected_fixture" }, { "id": "F05", "verdict": "fail", "reason": "typed ['C1', 'C2'], written True, stored [('BENCH_Валюта', ''), ('BENCH_Срок', '')]", "coverage": "selected_fixture", "assertion_id": "F05.selected_fixture" }, { "id": "G01", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G01.static_sources" }, { "id": "G02", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G02.static_sources" }, { "id": "G03", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G03.static_sources" } ], "charges": [ { "id": "F1C-GEN01", "points": "0.5", "reason": "не выполнено требование: BU13" }, { "id": "F1C-GEN01", "points": "0.5", "reason": "не выполнено требование: BU14" }, { "id": "F1C-GEN01", "points": "0.5", "reason": "не выполнено требование: PR13 — pr_backdate E4/B tariff 2025-01: 2160, expected 1680.00; pr_backdate E4/B tariff 2025-02: 1920, expected 1680.00" }, { "id": "F1C-GEN01", "points": "0.5", "reason": "не выполнено требование: F05 — typed ['C1', 'C2'], written True, stored [('BENCH_Валюта', ''), ('BENCH_Срок', '')]" }, { "id": "F1C-GEN12", "points": "0.25", "reason": "текст запроса не разбирается платформой: DataProcessors/ЗаполнениеГрафика/Ext/ObjectModule.bsl:5 — Поле не найдено \"Подразделения.ЭтоГруппа\"" }, { "id": "F1C-GEN15", "points": "0.5", "reason": "Reports/ПремииСотрудников/Ext/ManagerModule.bsl:9 — РегистрРасчета.Начисления: отбор по ВидРасчета, ПериодДействияНачало, индексы таблицы начинаются с ПериодДействия, ПериодРегистрации, Подразделение, Регистратор, Сотрудник" }, { "id": "F1C-PR14", "points": "0.5", "reason": "после расчёта набор с периодом действия перезаписывается целиком, с пересчётом фактического периода действия (нужно Записать(, Истина)): CommonModules/РасчетЗарплаты/Ext/Module.bsl:29 Набор.Записать(); CommonModules/РасчетЗарплаты/Ext/Module.bsl:31 Набор.Записать(); CommonModules/РасчетЗарплаты/Ext/Module.bsl:33 Набор.Записать(); CommonModules/РасчетЗарплаты/Ext/Module.bsl:35 Набор.Записать(); CommonModules/РасчетЗарплаты/Ext/Module.bsl:37 Набор.Записать(); CommonModules/РасчетЗарплаты/Ext/Module.bsl:39 Набор.Записать()" }, { "id": "F1C-BU06", "points": "1.5", "reason": "ресурс Количество балансовый" }, { "id": "F1C-BU07", "points": "1.0", "reason": "признак учёта субконто Суммовой, Количественный, ТолькоОбороты заведён в плане счетов, но не указан ни у одного ресурса регистра — не действует" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "оперативное проведение разрешено у документов с движениями по регистрам расчёта: НачислениеЗарплаты" }, { "id": "F1C-GEN21", "points": "2.0", "reason": "данные графика без отбора по регистратору: CommonModules/РасчетЗарплаты/Ext/Module.bsl:450" }, { "id": "F1C-GEN01", "points": "0.5", "reason": "разыменование поля составного типа без ВЫРАЗИТЬ: CommonModules/УчетЗапасов/Ext/Module.bsl: Остатки.Партия.Дата" } ], "score_upper_bound": "-4.25", "score": null, "grade": "unsatisfactory", "deductions": "9.25", "not_assessed": 16, "gates": { "starter_origin": "passed", "load": "loaded", "clients": "compiles", "demo_data": "present" }, "infrastructure_errors": false, "comparison_eligible": false, "binding_compatibility": null }, "measurement": { "operator": { "name": "Виктор Мурашкин", "github": "VictorMurashkin" }, "environment": { "captured_at": "2026-10-25T14:54:30.054169+00:00", "capture_timing": "before_run", "hardware": { "cpu": "12th Gen Intel(R) Core(TM) i5-12600KF", "logical_cpus": 16, "ram_bytes": 68500021248 }, "os": { "system": "Windows", "release": "11", "version": "10.0.26100", "architecture": "AMD64" }, "python": "3.14.6", "platform_version": "8.3.27.2342", "isolation": "dedicated-host", "network_profile": "open-book_shell", "unsafe_action_protection_observed_in_user_config": true, "git_revision": "2d3566285b9fb7c93d60e4d903679c17d8dc71b8", "implementation_files": { "exam_bench/__init__.py": "ad5bf6f05dc6765f40b78bd186870ca2c49be113cfa33f8aa76f4926f2cb2c1e", "exam_bench/assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "exam_bench/bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "exam_bench/calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "exam_bench/calibrate.py": "78b5185cb0888c0c0ac3de95ffc3a80154a6de9ae66fc461f79d012e5a58e1db", "exam_bench/calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "exam_bench/calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "exam_bench/calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "exam_bench/calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "exam_bench/calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "exam_bench/claude.py": "9c68ca50de1301f20ca2109df21943caa7ac0c6da17bf0a5fbd305d2c244d9e5", "exam_bench/cli.py": "a1a83be1f53924705576ed06b2a2c20868067fd0c5d3da839192e7b13c37540b", "exam_bench/codescan.py": "751e38001b6e65727a31e28172a0623f0bf34bc092a958037c286aa991a197ed", "exam_bench/codex.py": "904e75503cd35f16cbb052f66806b3879fe25bfc9f99e33b93c889d862c46324", "exam_bench/common.py": "8682603b519063e655eae3574a02a49efee63bde21f582ccee20ddd623fca96d", "exam_bench/cursor.py": "88d903f344eedddb2303166ec10827714e4acde90bdc94eefd3ace46ef685671", "exam_bench/cursor_bsl.py": "753f02ebed60e5b8bbefba0933adbdf28477ef916353d70e3c68c817ce6c42e0", "exam_bench/cursor_harnesses.py": "d4bc375cdf5462cf99df079f2ea20148912f9e366e04225ad4abf73f9cafddf9", "exam_bench/docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "exam_bench/examiner.py": "d7294fdd23ed1732216cafebf0a8cf2c24cce4259859aeb7149f62b7607d087d", "exam_bench/finalize.py": "4034f1c63896a940afdb1a83d541cf47fc75c8b5061e3f839047109c04beb620", "exam_bench/forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "exam_bench/gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "exam_bench/grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "exam_bench/harness.py": "3040f6daaf1dc6e6583219f4d925151f8ba7851b2d5417d7f14645892b485ddf", "exam_bench/interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "exam_bench/interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "exam_bench/isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "exam_bench/ledger.py": "7e851523580e22d8490e75f9b6026c07f2c355007e0d11d0b252671f56bef654", "exam_bench/locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "exam_bench/materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "exam_bench/mcp_toolkit.py": "f4c3ea8d9ce542645960a0234ddb61712a047793c58d4e2a0691fc9a45961383", "exam_bench/observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "exam_bench/ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "exam_bench/penalties.py": "0d79e2e46102657dca00609b6abbfc0bf7d11fad41429564f876c82bc6b33269", "exam_bench/platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "exam_bench/portable.py": "cad56968ff407983608f5bdbc9ce7234128d7a4580b096ecea8e0e7b4edb9070", "exam_bench/portable_harnesses.py": "686c46a4231067625b3a20f0b22639d14bcaeb26fab3493e06f92b53dfead05a", "exam_bench/pr.py": "6a3a20caf0e10c0cc94410511a72d62c9fcda785f3abab1be2ad616d4ee16836", "exam_bench/preflight.py": "fbce47aa201c1f5acdbc80b241655dce443df35f9d14d3260c2325f875d6f6e4", "exam_bench/process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "exam_bench/queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "exam_bench/queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "exam_bench/replay_calibration.py": "e2d79cb508f2d5e3846d6dad36c3898d41dec1c573c1a1b7d8a2ec43e33c8c08", "exam_bench/report.py": "5e4c0757e1c7f189953f9a5302593ab726551835856baed25efd93dad6e8bfcd", "exam_bench/runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "exam_bench/smoke_check.py": "f36922a0027429ead0b414048dcc14bbe67f2f0e79a70d03dffbe1447d253545", "exam_bench/stdio_harnesses.py": "0bbfd791fb244a934c6cda3a4e63fbe9ce515e4af64729bb923ce86645057288", "exam_bench/submission.py": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "exam_bench/telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "exam_bench/windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "exam_bench/workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tools/build_public_site.py": "9682ed696f5ac9e9a82b65a45c0dece556ec7e49eeb20dcd616882cc534a8258", "tools/build_result_site.py": "38fc65d8dc01d51249e1c92c174d6ef42b8a0400a63a621d66bb4de9aaccce47", "tools/check_native_harnesses.py": "1fdde7b8eeb76f94341592ddbf1cac61306a65779d7b871ecabd053ab70c1e80", "tools/check_native_toolkit.py": "0272794617121f2932828e5e4e9ae20095183c443666cf3ba466b44fbe875095", "tools/community_results.py": "3f4c0067088353ec5bba8ea32decba5e205c3f7993cc305d07693b54c7039a23", "tools/community_service.py": "c374480dbd88d656c0b9054fa04a8e1c6698c69e2f9cf475e82498a2dff61d84", "tools/community_setup.py": "5d7d126ed7d4dd48e1d79f57b99647a92ffcc8c9f80d90915e458888cdd76bf7", "tools/compare_harness_runs.py": "f274df5f3f804cb02504491aec946943833e12fbce6e62d281e12beb8508fc4e", "tools/create_run_plan.py": "694f1b376f5b78de23705b8df3ec943def516eda93f96e7afaa3942729a1240c", "tools/demo_runner.py": "0f4267b97f5aaa25d60087be8fbe16f2ff6d7cc28de1ba4822d5d1302fb19163", "tools/installers.py": "9a2742780936b17500869e7c89202c1a2549e37d53a42ad9a50a0abbf78bbe09", "tools/machine_bundle.py": "8aa8346f99f537e81ceca6fb6ab9530e844954bab8eff87bf33d3602f81f8a30", "tools/prepare_native_harnesses.py": "fba3fd78b1fdd400196e086c5f463aec5ecefe41e81cd6875d87c76a3126a877", "tools/prepare_official_statement.py": "6b7028c78e90e798d6ef1a93b76520cc61a308c354fb9b87f7fad18b99800fad", "tools/prepare_open_exam_requirements.py": "544f4e378b9be5f166186f8788f8d454afdac2deb99d91d98421e39d01ba6d03", "tools/probe_cursor_harnesses.py": "19952ea409c934ed89cf2589dbb7dcf8d52fad5e01ca256c7df552578d28addc", "tools/probe_harness.py": "1ed8ef93420d1484cbbfd151b7efc31b9a201ceb942dd05e3103efa22ffa7f27", "tools/probe_http_mcp.py": "2667e191fb831b1cbc9cbbbbefdfad16241e17d620a1a42a43405ab0b8139ac4", "tools/probe_native_mcp.py": "9918d324129cba898993e07f8f8b6dbcbaf369398ebf28d464f9f1f00abdb254", "tools/readiness.py": "3c5404be17a7a0a2f72d7cef5714f7d1d6bde7da0d8eb698da4cc65d0b0dd3f3", "tools/recheck_community.py": "f0843d7d677f90da31e22bde0b1c86584dd46c022f1532d43d042619e426b230", "tools/regrade_runs.py": "011775afb06d3aac67a4aa81117a368c75896b0fcbe1e6f27ccc6237612fbf59", "tools/render_statement_text.py": "dabc0716a3612c288c671bc20e17fd4986691d732768e1e957d6dddddbea92a3", "tools/replay_calibration.py": "801f5004926c438c21ed3668fe2a4ddf45312b3e75320165a3839aae034eee9b", "tools/run_exam_campaign.py": "2c450d57a1cd0a2682838f5ec7c0a4ffb3aed0f1730d34c408e912d59cab6efd", "tools/serve_result_site.py": "86badfac863cd4ad1fc894a14110c75b28470513f0133eeae9d2799b8b4df3a9", "tools/start_demo.py": "c597e6cad28d245b3191654bb3e2801fa9dd2364e2acb25561923613717b615f", "tools/supplemental_acceptance.py": "7327277143d80a531e4c254ac74a9fc0e0d5c76572d53b8469e0a580eda17d65", "tools/sync_sources.py": "b51e889b0f41f9f63bfb19a09fb96d3777693d6b1d76fe0132bdd2a15e155898", "tools/validate_community_pr.py": "796b896dfade07b4529af2088a4b9b9d23484148b3bc0732b3fb837b75c9844b", "tools/verify_official_assessment_mapping.py": "daeb448a016940d5b6b1285979a56e5b9014bd91db40acb131445e4a83a23059", "tools/verify_task_package.py": "9e1e6105f6b5e4e78b36aa57f00117a9fbc8948ab53983c32ab56da88d23ccc4", "profiles/1c-ai-rules-2026-10-23-requirements.txt": "fd7ada214e0977776eb350794bb492d97824d96810eb7b158e46cf5cd72c8e65", "profiles/agents.json": "af9c492c08d13b3044aa6b6952589ed6a0a07d5258d8ff72bb18185b3eaebdc5", "profiles/ai-exam-execution-policy.json": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "profiles/bsl-analyzer-0.3.2-macos.json": "83537abdbf38c41ce665e4d0f24128bb51b62e971e0e0f368695f1326a7d2ffb", "profiles/bsl-analyzer-0.3.2-portable.json": "d6ba732e6778e256df34d6bc548593128820a70430c35b279796843606ee40a8", "profiles/bsl-ls-1.1.0-rc.6-macos.json": "245fc10747197e6911b2b4c77cdb15e6fa4eb7bc7c3758b63e768c5adf1df180", "profiles/bsl-ls-1.1.0-rc.6-portable.json": "9f10660881f2ec84794f7d584556b8f75c7e14b3555464af0ed0e60c4c892d86", "profiles/claude-code-skills-1c-1.12.0-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/code-index-1.9.0-macos.json": "63a919523ce62ecec274f4c139bc7ad49a75dd4c339568b822cbc695b4e30408", "profiles/code-index-1.9.0-portable.json": "81106cee8f424ffd8a9dc46ecd8e4f57598fc1d49661a83c77b1f0507993fbdc", "profiles/codex-probe-plan.json": "166e41aad5fb3b27d9050bc6de952c6cba363cc6e804d4080568cc71a2a4d289", "profiles/machine.linux.example.json": "408304fd0581098d5d8110dc67dfeab353bc4d4030e32d37e6acf98d2b1aedfd", "profiles/machine.macos.example.json": "52e9f9d17797cb520b9d8955d6806fd550b899bed4da241ebf096dcb6a21a942", "profiles/machine.windows.example.json": "63accac9a2f81d47d03447efbabffd4760aee325193f02f46b9b29a28d50d2d8", "profiles/mcp-toolkit-1.9.0-macos.json": "1d3f9cde5ffa20589a840d01fdae03aa0fc2f412c929f064f203919c4129625b", "profiles/mcp-toolkit-1.9.0-portable.json": "8e370eebe773eef0e08045ee9c6d5be1451f769f65be0710834b262a4336e054", "profiles/none-macos.json": "b1401d9c48159aed3559006c7f6ace6ef4571224d5cf0bb76d1a823505a10056", "profiles/none-portable.json": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "profiles/rlm-tools-bsl-1.43.0-macos.json": "9354421052640ab60bc3e6aa98ff2e7ba9ca2318b0f4026c137487449242cbd2", "profiles/rlm-tools-bsl-1.43.0-portable.json": "2599e5645e0a7d4e44cb2934bc2b272cae79a9bf7ea74a23cd48aacea64bc424", "profiles/rlm-tools-bsl-1.43.0-posix-requirements.txt": "4fdf9a1bd994bf0272e65d231daf76cf19b0a34dad0ae6b50ec4f11a2ce4c330", "profiles/rlm-tools-bsl-1.43.0-windows-requirements.txt": "3730cb46c81cda5181ecd4485e98b11933104632358bc86f8c0eb1a612a8954f", "profiles/shirokov-skills-macos.json": "84f3e89091676884a802035c707e912762a1179425fb8e3faff25be736873cdb", "profiles/shirokov-skills-portable.json": "2b0a461e06602f1456410e70f02ceaa5ac32c6549c486660bcb5ace0c2f87b15", "profiles/shirokov-skills-windows-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/unica-0.12.3-macos.json": "2c39fbb591cf2c2c6e056373823615485397ea83651b7926c6f25a5fe6a0aae6", "profiles/unica-0.13.0-macos.json": "b76b5c8a4dd33f571c4a90993f1a2da5f7223b4f0f8e1042c282e21a66121052", "profiles/unica-0.14.0-rc.1-portable.json": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "rules/1c-specialist-platform/chistov.json": "7a42ef723a1f5f03f02c387cd3ca95725f7364c2e11ebdfc988a02919ab22c37", "rules/1c-specialist-platform/decisions.json": "f622107423ce3c188c063318d7ab4f7718ceb38e443130677d8987f386641c09", "rules/1c-specialist-platform/examiner.json": "30353aa2a1b6545496b070d9066e9ffba0c3779e5b53ef70a4fd2cee375b18c0", "rules/1c-specialist-platform/ledger.json": "f167c10db2b5799dd9a1ea6a37cd2d7d186810dadf5ea2f50f26ae723c676882", "rules/1c-specialist-platform/rules.json": "1d320a4f8e1bf4701496388931f492315549bd3dce574b17285dd1d7f8652007", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" } } }, "conditions": { "client": "cursor", "model": "grok-4.7-high", "client_version": "2026.10.22-27dcf5f", "reasoning_effort": null, "harness": "none", "billing_channel": "subscription", "solve_timeout_seconds": 18000, "time_series": "exam", "delegation": "requested_disabled_unverified", "network_profile": "open-book_shell", "deadline_disclosed": true, "statement_sha256": "8a6ccb3e673826d1f8220fda53eb310e3ec18c136d87ce8f4cebb2a08614e7e5", "starter_dt_sha256": "f40d084818b0d1cfe503fc7653a6a13f1a8e47fcd1688dad6245b12744eb4638", "profile_sha256": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "execution_policy_sha256": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "calibration_sha256": "201d0591454d3b4cea9a26fde9088181f106b37b26f26392edb010457480b5c8", "started_at": "2026-10-25T14:54:48.106383+00:00", "timing": { "prepare_ms": 16331, "solve_ms": 5394921, "grade_ms": null }, "original_submission_valid": true, "model_provenance": "client_reported", "tokens": { "input": 36819638, "cached_input": 36221440, "fresh_input": 598198, "output": 347182, "reasoning_output": null, "total": 37166820, "coverage": "client_final_result" }, "tools": { "mcp_calls": 0, "unica_calls": 0, "failed_calls": 0 }, "process": { "status": "completed", "exit_code": 0, "stop_confirmed": true } }, "verification": "repository_owner", "download": "community-downloads/demo-20261025T145428Z-209efd--owner-2026-10-26T214406769623-0000/solution.zip", "source_context": "community-downloads/demo-20261025T145428Z-209efd--owner-2026-10-26T214406769623-0000/source-context.json", "regrade_required": [ { "id": "grader_changed", "files": [ "calibrate.py", "calibration_periodicity.py", "common.py", "ou.py", "replay_calibration.py", "smoke_check.py", "tasks/1c-platform-official-sample/checks.json" ] } ], "grader_revision_sha256": "349d87e0c7f531acbe35dd2b39c35722d8a877fedde97575b49e8466ab763c1d", "archive_sha256": "0e207fbe12e83e1f19ebe0b8ab107360555134742283343ffb7fceb323d96784", "owner_verification": { "kind": "repository_owner", "repository": "zeegin/1c-agent-exam-benchmark", "operator": { "name": "Ingvar Vilkman", "github": "zeegin" }, "started_at": "2026-10-26T21:44:06.605035+00:00", "server": { "name": "Owner Windows stand", "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "hardware": { "cpu": "AMD Ryzen 7 5800X 8-Core Processor ", "logical_cpus": 4, "ram_bytes": 17109000192 }, "isolation": "dedicated-host" }, "platform_version": "8.3.27.2342", "grader": { "profile": "technical-v8", "commit": "e8fd8ced03a85b549c5472fbbda29225749f54d1", "working_tree_dirty": false, "fingerprint": { "assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "calibrate.py": "3162d431f3cab5e7976aa39f665d6286dce45499cf362d85109b7123fa8403a2", "calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "calibration_query.py": "3555b103cde8ea0519955cf52358d09223f5ab183a9df00533bdb48c89237a8c", "claude.py": "eedabc75fca0faa434f40a1624b71419ec7dc22e2854a0886cf84b4911db8372", "codescan.py": "6d8375210cef1fd768fc2d98d630d880b2993a9724f01ae25f33b4ea5aa9631d", "codex.py": "904e75503cd35f16cbb052f66806b3879fe25bfc9f99e33b93c889d862c46324", "common.py": "52825cf5c29f3536d6e046a89e789d5ef9c83aacd7f2f5a07f4f53e77b5229cc", "docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "examiner.py": "8cdffcdd52f043c905f896697403380af95bf485dd4a5edca24f7956e7795ffe", "forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "harness.py": "3cbb90fd3187e700b5df32e5daafb20313d49bb5721c826e3033cbc6aa6e3825", "interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "penalties.py": "ae388cb8953ecca1f2370a7c4cb1db3b6cc8318fc2a7563a4db15f9f5b057429", "platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "pr.py": "2b6bfea0634703469605ce114f9274716b485852d9a55d9185c39893b14e4726", "preflight.py": "448c3120ab64b625abae3891be686c7a214ce4211f7cf651fd90e12c0b298433", "process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "queries.py": "1ef57e292db3e8967a733948371ecc542f743b811890d4fc509df17303b9c4ac", "queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "querytypes.py": "b645f489a2abc27762b4a9bbf4917e72f7b46dc053a74c0dca4a8fc46491b3ef", "replay_calibration.py": "0a4d9b84a9908944c5a945878eb6f5eeda5a4e42ffff4f55c04a680742803d80", "runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "smoke_check.py": "66caf1a01f7aa18432293abe3567ac228ac837a660b08c3dc7bb093f7bd51628", "stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "submission.py": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tasks/1c-platform-official-sample/checks.json": "17a6fcc0c14410829650623eb1443ce99796e000cdfd19905ac0287988b73a00", "tasks/1c-platform-official-sample/private/official-assessment-mapping.json": "303587c0dabe77c1eeebb2017fe85539e3370b17c9090435e6e0325a66bd0644", "tasks/1c-platform-official-sample/private/owner-scoring-policy.json": "d26d534bb838ab1b5facb7bc033ca8ec40912133baadcdbad83b27fc577905f5", "starters/carcass-8.3.25.1445/starter.json": "0f7a7060885ba99a19402bfc6e63cc8fe979b0f491b040d3a01d5d21b304b3a6", "rules/1c-specialist-platform/rules.json": "ea75e34ace5de11ba3de403c63cd2c026db81d1d991f8531e4a779d4ce9788e7", "rules/1c-specialist-platform/examiner.json": "1247486ddd412d600db88d9c1db4ba501fc1994afd1dc2ebe85402fcc332f4c8", "rules/1c-specialist-platform/chistov.json": "800da27601a3f1c7ec1df64482fd4ad035e559ba0b390a274ed5031128487d3d", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" }, "sha256": "349d87e0c7f531acbe35dd2b39c35722d8a877fedde97575b49e8466ab763c1d" }, "method": "saved_platform_observations", "outcome": "complete", "completed_at": "2026-10-26T21:44:06.769623+00:00" } }, { "id": "demo-20261025T145428Z-209efd--owner-2026-10-26T191613065846-0000", "run_id": "demo-20261025T145428Z-209efd", "result": { "run_id": "demo-20261025T145428Z-209efd", "created_at": "2026-10-26T19:16:13.065846+00:00", "model": "grok-4.7-high", "harness": "none", "solve_seconds": 5395, "platform": "8.3.27.2342", "counts": { "pass": 59, "fail": 4, "inconclusive": 2 }, "rules": [ { "id": "BU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU01.selected_fixture" }, { "id": "BU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU04.selected_fixture" }, { "id": "BU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU05.selected_fixture" }, { "id": "BU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU16.selected_fixture" }, { "id": "BU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU17.selected_fixture" }, { "id": "BU02", "verdict": "pass", "reason": null, "coverage": "partial", "assertion_id": "BU02.posting_cost_and_balance" }, { "id": "BU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU10.selected_fixture" }, { "id": "BU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU12.selected_fixture" }, { "id": "BU03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU03.selected_fixture" }, { "id": "BU06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU06.selected_fixture" }, { "id": "BU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU07.selected_fixture" }, { "id": "BU08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU08.selected_fixture" }, { "id": "BU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU09.selected_fixture" }, { "id": "BU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU11.selected_fixture" }, { "id": "BU14", "verdict": "fail", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU14.selected_fixture" }, { "id": "BU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU15.selected_fixture" }, { "id": "BU13", "verdict": "fail", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU13.selected_fixture" }, { "id": "OU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU15.selected_fixture" }, { "id": "OU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU16.selected_fixture" }, { "id": "OU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU17.selected_fixture" }, { "id": "OU02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU02.selected_fixture" }, { "id": "OU18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU18.selected_fixture" }, { "id": "OU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU14.selected_fixture" }, { "id": "OU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU01.selected_fixture" }, { "id": "OU03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU03.selected_fixture" }, { "id": "OU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU05.selected_fixture" }, { "id": "OU06", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "OU06.selected_fixture" }, { "id": "OU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU07.selected_fixture" }, { "id": "OU08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU08.selected_fixture" }, { "id": "OU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU09.selected_fixture" }, { "id": "OU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU10.selected_fixture" }, { "id": "OU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU11.selected_fixture" }, { "id": "OU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU12.selected_fixture" }, { "id": "OU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU13.selected_fixture" }, { "id": "OU04", "verdict": "inconclusive", "reason": "Required observations unavailable: characteristic values could not be written: {'value_P1': '{ОбщийМодуль.BenchmarkObserver.Модуль(108)}: Ошибка при установке значения атрибута контекста (Владелец): Справочник не имеет владельца'", "coverage": "selected_fixture", "assertion_id": "OU04.selected_fixture" }, { "id": "OU19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU19.selected_fixture" }, { "id": "OU20", "verdict": "inconclusive", "reason": "Required observations unavailable: characteristic values could not be written: {'value_P1': '{ОбщийМодуль.BenchmarkObserver.Модуль(108)}: Ошибка при установке значения атрибута контекста (Владелец): Справочник не имеет владельца'", "coverage": "selected_fixture", "assertion_id": "OU20.selected_fixture" }, { "id": "OU21", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU21.selected_fixture" }, { "id": "PR01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR01.selected_fixture" }, { "id": "PR02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR02.selected_fixture" }, { "id": "PR03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR03.selected_fixture" }, { "id": "PR04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR04.selected_fixture" }, { "id": "PR05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR05.selected_fixture" }, { "id": "PR06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR06.selected_fixture" }, { "id": "PR07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR07.selected_fixture" }, { "id": "PR08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR08.selected_fixture" }, { "id": "PR09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR09.selected_fixture" }, { "id": "PR10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR10.selected_fixture" }, { "id": "PR11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR11.selected_fixture" }, { "id": "PR12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR12.selected_fixture" }, { "id": "PR13", "verdict": "fail", "reason": "pr_backdate E4/B tariff 2025-01: 2160, expected 1680.00; pr_backdate E4/B tariff 2025-02: 1920, expected 1680.00", "coverage": "selected_fixture", "assertion_id": "PR13.selected_fixture" }, { "id": "PR14", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "PR14.selected_fixture" }, { "id": "PR15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR15.selected_fixture" }, { "id": "PR16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR16.selected_fixture" }, { "id": "PR17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR17.selected_fixture" }, { "id": "PR18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR18.selected_fixture" }, { "id": "PR19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR19.selected_fixture" }, { "id": "F01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F01.selected_fixture" }, { "id": "F02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F02.selected_fixture" }, { "id": "F03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F03.selected_fixture" }, { "id": "F04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F04.selected_fixture" }, { "id": "F05", "verdict": "fail", "reason": "typed ['C1', 'C2'], written True, stored [('BENCH_Валюта', ''), ('BENCH_Срок', '')]", "coverage": "selected_fixture", "assertion_id": "F05.selected_fixture" }, { "id": "G01", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G01.static_sources" }, { "id": "G02", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G02.static_sources" }, { "id": "G03", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G03.static_sources" } ], "charges": [ { "id": "F1C-GEN01", "points": "0.5", "reason": "не выполнено требование: BU13" }, { "id": "F1C-GEN01", "points": "0.5", "reason": "не выполнено требование: BU14" }, { "id": "F1C-GEN01", "points": "0.5", "reason": "не выполнено требование: PR13 — pr_backdate E4/B tariff 2025-01: 2160, expected 1680.00; pr_backdate E4/B tariff 2025-02: 1920, expected 1680.00" }, { "id": "F1C-GEN01", "points": "0.5", "reason": "не выполнено требование: F05 — typed ['C1', 'C2'], written True, stored [('BENCH_Валюта', ''), ('BENCH_Срок', '')]" }, { "id": "F1C-GEN12", "points": "0.25", "reason": "текст запроса не разбирается платформой: DataProcessors/ЗаполнениеГрафика/Ext/ObjectModule.bsl:5 — Поле не найдено \"Подразделения.ЭтоГруппа\"" }, { "id": "F1C-GEN15", "points": "0.5", "reason": "Reports/ПремииСотрудников/Ext/ManagerModule.bsl:9 — РегистрРасчета.Начисления: отбор по ВидРасчета, ПериодДействияНачало, индексы таблицы начинаются с ПериодДействия, ПериодРегистрации, Подразделение, Регистратор, Сотрудник" }, { "id": "F1C-PR14", "points": "0.5", "reason": "после расчёта набор с периодом действия перезаписывается целиком, с пересчётом фактического периода действия (нужно Записать(, Истина)): CommonModules/РасчетЗарплаты/Ext/Module.bsl:29 Набор.Записать(); CommonModules/РасчетЗарплаты/Ext/Module.bsl:31 Набор.Записать(); CommonModules/РасчетЗарплаты/Ext/Module.bsl:33 Набор.Записать(); CommonModules/РасчетЗарплаты/Ext/Module.bsl:35 Набор.Записать(); CommonModules/РасчетЗарплаты/Ext/Module.bsl:37 Набор.Записать(); CommonModules/РасчетЗарплаты/Ext/Module.bsl:39 Набор.Записать()" }, { "id": "F1C-BU06", "points": "1.5", "reason": "ресурс Количество балансовый" }, { "id": "F1C-BU07", "points": "1.0", "reason": "признак учёта субконто Суммовой, Количественный, ТолькоОбороты заведён в плане счетов, но не указан ни у одного ресурса регистра — не действует" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "оперативное проведение разрешено у документов с движениями по регистрам расчёта: НачислениеЗарплаты" }, { "id": "F1C-GEN21", "points": "2.0", "reason": "данные графика без отбора по регистратору: CommonModules/РасчетЗарплаты/Ext/Module.bsl:450" }, { "id": "F1C-GEN01", "points": "0.5", "reason": "разыменование поля составного типа без ВЫРАЗИТЬ: CommonModules/УчетЗапасов/Ext/Module.bsl: Остатки.Партия.Дата" } ], "score_upper_bound": "-4.25", "score": null, "grade": "unsatisfactory", "deductions": "9.25", "not_assessed": 16, "gates": { "starter_origin": "passed", "load": "loaded", "clients": "compiles", "demo_data": "present" }, "infrastructure_errors": false, "comparison_eligible": false, "binding_compatibility": null }, "measurement": { "operator": { "name": "Виктор Мурашкин", "github": "VictorMurashkin" }, "environment": { "captured_at": "2026-10-25T14:54:30.054169+00:00", "capture_timing": "before_run", "hardware": { "cpu": "12th Gen Intel(R) Core(TM) i5-12600KF", "logical_cpus": 16, "ram_bytes": 68500021248 }, "os": { "system": "Windows", "release": "11", "version": "10.0.26100", "architecture": "AMD64" }, "python": "3.14.6", "platform_version": "8.3.27.2342", "isolation": "dedicated-host", "network_profile": "open-book_shell", "unsafe_action_protection_observed_in_user_config": true, "git_revision": "2d3566285b9fb7c93d60e4d903679c17d8dc71b8", "implementation_files": { "exam_bench/__init__.py": "ad5bf6f05dc6765f40b78bd186870ca2c49be113cfa33f8aa76f4926f2cb2c1e", "exam_bench/assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "exam_bench/bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "exam_bench/calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "exam_bench/calibrate.py": "78b5185cb0888c0c0ac3de95ffc3a80154a6de9ae66fc461f79d012e5a58e1db", "exam_bench/calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "exam_bench/calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "exam_bench/calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "exam_bench/calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "exam_bench/calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "exam_bench/claude.py": "9c68ca50de1301f20ca2109df21943caa7ac0c6da17bf0a5fbd305d2c244d9e5", "exam_bench/cli.py": "a1a83be1f53924705576ed06b2a2c20868067fd0c5d3da839192e7b13c37540b", "exam_bench/codescan.py": "751e38001b6e65727a31e28172a0623f0bf34bc092a958037c286aa991a197ed", "exam_bench/codex.py": "904e75503cd35f16cbb052f66806b3879fe25bfc9f99e33b93c889d862c46324", "exam_bench/common.py": "8682603b519063e655eae3574a02a49efee63bde21f582ccee20ddd623fca96d", "exam_bench/cursor.py": "88d903f344eedddb2303166ec10827714e4acde90bdc94eefd3ace46ef685671", "exam_bench/cursor_bsl.py": "753f02ebed60e5b8bbefba0933adbdf28477ef916353d70e3c68c817ce6c42e0", "exam_bench/cursor_harnesses.py": "d4bc375cdf5462cf99df079f2ea20148912f9e366e04225ad4abf73f9cafddf9", "exam_bench/docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "exam_bench/examiner.py": "d7294fdd23ed1732216cafebf0a8cf2c24cce4259859aeb7149f62b7607d087d", "exam_bench/finalize.py": "4034f1c63896a940afdb1a83d541cf47fc75c8b5061e3f839047109c04beb620", "exam_bench/forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "exam_bench/gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "exam_bench/grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "exam_bench/harness.py": "3040f6daaf1dc6e6583219f4d925151f8ba7851b2d5417d7f14645892b485ddf", "exam_bench/interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "exam_bench/interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "exam_bench/isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "exam_bench/ledger.py": "7e851523580e22d8490e75f9b6026c07f2c355007e0d11d0b252671f56bef654", "exam_bench/locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "exam_bench/materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "exam_bench/mcp_toolkit.py": "f4c3ea8d9ce542645960a0234ddb61712a047793c58d4e2a0691fc9a45961383", "exam_bench/observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "exam_bench/ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "exam_bench/penalties.py": "0d79e2e46102657dca00609b6abbfc0bf7d11fad41429564f876c82bc6b33269", "exam_bench/platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "exam_bench/portable.py": "cad56968ff407983608f5bdbc9ce7234128d7a4580b096ecea8e0e7b4edb9070", "exam_bench/portable_harnesses.py": "686c46a4231067625b3a20f0b22639d14bcaeb26fab3493e06f92b53dfead05a", "exam_bench/pr.py": "6a3a20caf0e10c0cc94410511a72d62c9fcda785f3abab1be2ad616d4ee16836", "exam_bench/preflight.py": "fbce47aa201c1f5acdbc80b241655dce443df35f9d14d3260c2325f875d6f6e4", "exam_bench/process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "exam_bench/queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "exam_bench/queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "exam_bench/replay_calibration.py": "e2d79cb508f2d5e3846d6dad36c3898d41dec1c573c1a1b7d8a2ec43e33c8c08", "exam_bench/report.py": "5e4c0757e1c7f189953f9a5302593ab726551835856baed25efd93dad6e8bfcd", "exam_bench/runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "exam_bench/smoke_check.py": "f36922a0027429ead0b414048dcc14bbe67f2f0e79a70d03dffbe1447d253545", "exam_bench/stdio_harnesses.py": "0bbfd791fb244a934c6cda3a4e63fbe9ce515e4af64729bb923ce86645057288", "exam_bench/submission.py": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "exam_bench/telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "exam_bench/windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "exam_bench/workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tools/build_public_site.py": "9682ed696f5ac9e9a82b65a45c0dece556ec7e49eeb20dcd616882cc534a8258", "tools/build_result_site.py": "38fc65d8dc01d51249e1c92c174d6ef42b8a0400a63a621d66bb4de9aaccce47", "tools/check_native_harnesses.py": "1fdde7b8eeb76f94341592ddbf1cac61306a65779d7b871ecabd053ab70c1e80", "tools/check_native_toolkit.py": "0272794617121f2932828e5e4e9ae20095183c443666cf3ba466b44fbe875095", "tools/community_results.py": "3f4c0067088353ec5bba8ea32decba5e205c3f7993cc305d07693b54c7039a23", "tools/community_service.py": "c374480dbd88d656c0b9054fa04a8e1c6698c69e2f9cf475e82498a2dff61d84", "tools/community_setup.py": "5d7d126ed7d4dd48e1d79f57b99647a92ffcc8c9f80d90915e458888cdd76bf7", "tools/compare_harness_runs.py": "f274df5f3f804cb02504491aec946943833e12fbce6e62d281e12beb8508fc4e", "tools/create_run_plan.py": "694f1b376f5b78de23705b8df3ec943def516eda93f96e7afaa3942729a1240c", "tools/demo_runner.py": "0f4267b97f5aaa25d60087be8fbe16f2ff6d7cc28de1ba4822d5d1302fb19163", "tools/installers.py": "9a2742780936b17500869e7c89202c1a2549e37d53a42ad9a50a0abbf78bbe09", "tools/machine_bundle.py": "8aa8346f99f537e81ceca6fb6ab9530e844954bab8eff87bf33d3602f81f8a30", "tools/prepare_native_harnesses.py": "fba3fd78b1fdd400196e086c5f463aec5ecefe41e81cd6875d87c76a3126a877", "tools/prepare_official_statement.py": "6b7028c78e90e798d6ef1a93b76520cc61a308c354fb9b87f7fad18b99800fad", "tools/prepare_open_exam_requirements.py": "544f4e378b9be5f166186f8788f8d454afdac2deb99d91d98421e39d01ba6d03", "tools/probe_cursor_harnesses.py": "19952ea409c934ed89cf2589dbb7dcf8d52fad5e01ca256c7df552578d28addc", "tools/probe_harness.py": "1ed8ef93420d1484cbbfd151b7efc31b9a201ceb942dd05e3103efa22ffa7f27", "tools/probe_http_mcp.py": "2667e191fb831b1cbc9cbbbbefdfad16241e17d620a1a42a43405ab0b8139ac4", "tools/probe_native_mcp.py": "9918d324129cba898993e07f8f8b6dbcbaf369398ebf28d464f9f1f00abdb254", "tools/readiness.py": "3c5404be17a7a0a2f72d7cef5714f7d1d6bde7da0d8eb698da4cc65d0b0dd3f3", "tools/recheck_community.py": "f0843d7d677f90da31e22bde0b1c86584dd46c022f1532d43d042619e426b230", "tools/regrade_runs.py": "011775afb06d3aac67a4aa81117a368c75896b0fcbe1e6f27ccc6237612fbf59", "tools/render_statement_text.py": "dabc0716a3612c288c671bc20e17fd4986691d732768e1e957d6dddddbea92a3", "tools/replay_calibration.py": "801f5004926c438c21ed3668fe2a4ddf45312b3e75320165a3839aae034eee9b", "tools/run_exam_campaign.py": "2c450d57a1cd0a2682838f5ec7c0a4ffb3aed0f1730d34c408e912d59cab6efd", "tools/serve_result_site.py": "86badfac863cd4ad1fc894a14110c75b28470513f0133eeae9d2799b8b4df3a9", "tools/start_demo.py": "c597e6cad28d245b3191654bb3e2801fa9dd2364e2acb25561923613717b615f", "tools/supplemental_acceptance.py": "7327277143d80a531e4c254ac74a9fc0e0d5c76572d53b8469e0a580eda17d65", "tools/sync_sources.py": "b51e889b0f41f9f63bfb19a09fb96d3777693d6b1d76fe0132bdd2a15e155898", "tools/validate_community_pr.py": "796b896dfade07b4529af2088a4b9b9d23484148b3bc0732b3fb837b75c9844b", "tools/verify_official_assessment_mapping.py": "daeb448a016940d5b6b1285979a56e5b9014bd91db40acb131445e4a83a23059", "tools/verify_task_package.py": "9e1e6105f6b5e4e78b36aa57f00117a9fbc8948ab53983c32ab56da88d23ccc4", "profiles/1c-ai-rules-2026-10-23-requirements.txt": "fd7ada214e0977776eb350794bb492d97824d96810eb7b158e46cf5cd72c8e65", "profiles/agents.json": "af9c492c08d13b3044aa6b6952589ed6a0a07d5258d8ff72bb18185b3eaebdc5", "profiles/ai-exam-execution-policy.json": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "profiles/bsl-analyzer-0.3.2-macos.json": "83537abdbf38c41ce665e4d0f24128bb51b62e971e0e0f368695f1326a7d2ffb", "profiles/bsl-analyzer-0.3.2-portable.json": "d6ba732e6778e256df34d6bc548593128820a70430c35b279796843606ee40a8", "profiles/bsl-ls-1.1.0-rc.6-macos.json": "245fc10747197e6911b2b4c77cdb15e6fa4eb7bc7c3758b63e768c5adf1df180", "profiles/bsl-ls-1.1.0-rc.6-portable.json": "9f10660881f2ec84794f7d584556b8f75c7e14b3555464af0ed0e60c4c892d86", "profiles/claude-code-skills-1c-1.12.0-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/code-index-1.9.0-macos.json": "63a919523ce62ecec274f4c139bc7ad49a75dd4c339568b822cbc695b4e30408", "profiles/code-index-1.9.0-portable.json": "81106cee8f424ffd8a9dc46ecd8e4f57598fc1d49661a83c77b1f0507993fbdc", "profiles/codex-probe-plan.json": "166e41aad5fb3b27d9050bc6de952c6cba363cc6e804d4080568cc71a2a4d289", "profiles/machine.linux.example.json": "408304fd0581098d5d8110dc67dfeab353bc4d4030e32d37e6acf98d2b1aedfd", "profiles/machine.macos.example.json": "52e9f9d17797cb520b9d8955d6806fd550b899bed4da241ebf096dcb6a21a942", "profiles/machine.windows.example.json": "63accac9a2f81d47d03447efbabffd4760aee325193f02f46b9b29a28d50d2d8", "profiles/mcp-toolkit-1.9.0-macos.json": "1d3f9cde5ffa20589a840d01fdae03aa0fc2f412c929f064f203919c4129625b", "profiles/mcp-toolkit-1.9.0-portable.json": "8e370eebe773eef0e08045ee9c6d5be1451f769f65be0710834b262a4336e054", "profiles/none-macos.json": "b1401d9c48159aed3559006c7f6ace6ef4571224d5cf0bb76d1a823505a10056", "profiles/none-portable.json": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "profiles/rlm-tools-bsl-1.43.0-macos.json": "9354421052640ab60bc3e6aa98ff2e7ba9ca2318b0f4026c137487449242cbd2", "profiles/rlm-tools-bsl-1.43.0-portable.json": "2599e5645e0a7d4e44cb2934bc2b272cae79a9bf7ea74a23cd48aacea64bc424", "profiles/rlm-tools-bsl-1.43.0-posix-requirements.txt": "4fdf9a1bd994bf0272e65d231daf76cf19b0a34dad0ae6b50ec4f11a2ce4c330", "profiles/rlm-tools-bsl-1.43.0-windows-requirements.txt": "3730cb46c81cda5181ecd4485e98b11933104632358bc86f8c0eb1a612a8954f", "profiles/shirokov-skills-macos.json": "84f3e89091676884a802035c707e912762a1179425fb8e3faff25be736873cdb", "profiles/shirokov-skills-portable.json": "2b0a461e06602f1456410e70f02ceaa5ac32c6549c486660bcb5ace0c2f87b15", "profiles/shirokov-skills-windows-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/unica-0.12.3-macos.json": "2c39fbb591cf2c2c6e056373823615485397ea83651b7926c6f25a5fe6a0aae6", "profiles/unica-0.13.0-macos.json": "b76b5c8a4dd33f571c4a90993f1a2da5f7223b4f0f8e1042c282e21a66121052", "profiles/unica-0.14.0-rc.1-portable.json": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "rules/1c-specialist-platform/chistov.json": "7a42ef723a1f5f03f02c387cd3ca95725f7364c2e11ebdfc988a02919ab22c37", "rules/1c-specialist-platform/decisions.json": "f622107423ce3c188c063318d7ab4f7718ceb38e443130677d8987f386641c09", "rules/1c-specialist-platform/examiner.json": "30353aa2a1b6545496b070d9066e9ffba0c3779e5b53ef70a4fd2cee375b18c0", "rules/1c-specialist-platform/ledger.json": "f167c10db2b5799dd9a1ea6a37cd2d7d186810dadf5ea2f50f26ae723c676882", "rules/1c-specialist-platform/rules.json": "1d320a4f8e1bf4701496388931f492315549bd3dce574b17285dd1d7f8652007", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" } } }, "conditions": { "client": "cursor", "model": "grok-4.7-high", "client_version": "2026.10.22-27dcf5f", "reasoning_effort": null, "harness": "none", "billing_channel": "subscription", "solve_timeout_seconds": 18000, "time_series": "exam", "delegation": "requested_disabled_unverified", "network_profile": "open-book_shell", "deadline_disclosed": true, "statement_sha256": "8a6ccb3e673826d1f8220fda53eb310e3ec18c136d87ce8f4cebb2a08614e7e5", "starter_dt_sha256": "f40d084818b0d1cfe503fc7653a6a13f1a8e47fcd1688dad6245b12744eb4638", "profile_sha256": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "execution_policy_sha256": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "calibration_sha256": "201d0591454d3b4cea9a26fde9088181f106b37b26f26392edb010457480b5c8", "started_at": "2026-10-25T14:54:48.106383+00:00", "timing": { "prepare_ms": 16331, "solve_ms": 5394921, "grade_ms": null }, "original_submission_valid": true, "model_provenance": "client_reported", "tokens": { "input": 36819638, "cached_input": 36221440, "fresh_input": 598198, "output": 347182, "reasoning_output": null, "total": 37166820, "coverage": "client_final_result" }, "tools": { "mcp_calls": 0, "unica_calls": 0, "failed_calls": 0 }, "process": { "status": "completed", "exit_code": 0, "stop_confirmed": true } }, "verification": "repository_owner", "download": "community-downloads/demo-20261025T145428Z-209efd--owner-2026-10-26T191613065846-0000/solution.zip", "source_context": "community-downloads/demo-20261025T145428Z-209efd--owner-2026-10-26T191613065846-0000/source-context.json", "regrade_required": [ { "id": "grader_changed", "files": [ "calibrate.py", "calibration_periodicity.py", "calibration_query.py", "common.py", "ou.py", "penalties.py", "queries.py", "replay_calibration.py", "rules/1c-specialist-platform/rules.json", "smoke_check.py", "tasks/1c-platform-official-sample/checks.json" ] } ], "grader_revision_sha256": "4a12b62d2c10085e1fc710f377f84903abdf2fb787dda19628d944da990a86b2", "archive_sha256": "d0066bbf6c261f86d9541e4b6d504a1b3f4b87dfdd22c6fbfbdcb9be7a57fc74", "owner_verification": { "kind": "repository_owner", "repository": "zeegin/1c-agent-exam-benchmark", "operator": { "name": "Ingvar Vilkman", "github": "zeegin" }, "started_at": "2026-10-26T19:13:23.171228+00:00", "server": { "name": "Owner Windows stand", "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "hardware": { "cpu": "AMD Ryzen 7 5800X 8-Core Processor ", "logical_cpus": 4, "ram_bytes": 17109000192 }, "isolation": "dedicated-host" }, "platform_version": "8.3.27.2342", "grader": { "profile": "technical-v8", "commit": "5b6a28372b253e81e22b83f8559df897297e28ff", "working_tree_dirty": true, "fingerprint": { "assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "calibrate.py": "1c844971b4977fdcc3b30aebe8aad40fbd45e6828955b8deb043ac8573d61731", "calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "claude.py": "eedabc75fca0faa434f40a1624b71419ec7dc22e2854a0886cf84b4911db8372", "codescan.py": "6d8375210cef1fd768fc2d98d630d880b2993a9724f01ae25f33b4ea5aa9631d", "codex.py": "904e75503cd35f16cbb052f66806b3879fe25bfc9f99e33b93c889d862c46324", "common.py": "7696116dd1a796666518b4c5d2aa3cafa04ee974593d3636333cbe5385bd6ccb", "docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "examiner.py": "8cdffcdd52f043c905f896697403380af95bf485dd4a5edca24f7956e7795ffe", "forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "harness.py": "3cbb90fd3187e700b5df32e5daafb20313d49bb5721c826e3033cbc6aa6e3825", "interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "penalties.py": "b82704e7f47d3dfdf6e501452d7e0abca1f9da63307093d2e257e32358be0489", "platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "pr.py": "2b6bfea0634703469605ce114f9274716b485852d9a55d9185c39893b14e4726", "preflight.py": "448c3120ab64b625abae3891be686c7a214ce4211f7cf651fd90e12c0b298433", "process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "querytypes.py": "b645f489a2abc27762b4a9bbf4917e72f7b46dc053a74c0dca4a8fc46491b3ef", "replay_calibration.py": "3b6f3a289cc8a7f5e458f62bfa2c6cc534cc9076ba3f22d1e4bd8a5f9e175317", "runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "smoke_check.py": "bd6266367e6b769a95258eb383239b89a22deae406d64f6e142c77396f4639ba", "stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "submission.py": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tasks/1c-platform-official-sample/checks.json": "17a6fcc0c14410829650623eb1443ce99796e000cdfd19905ac0287988b73a00", "tasks/1c-platform-official-sample/private/official-assessment-mapping.json": "303587c0dabe77c1eeebb2017fe85539e3370b17c9090435e6e0325a66bd0644", "tasks/1c-platform-official-sample/private/owner-scoring-policy.json": "d26d534bb838ab1b5facb7bc033ca8ec40912133baadcdbad83b27fc577905f5", "starters/carcass-8.3.25.1445/starter.json": "0f7a7060885ba99a19402bfc6e63cc8fe979b0f491b040d3a01d5d21b304b3a6", "rules/1c-specialist-platform/rules.json": "7ec895a7751ef17f4a50cc80b5f7fa986e1e04360ab0b4ce9aa29115195df03c", "rules/1c-specialist-platform/examiner.json": "1247486ddd412d600db88d9c1db4ba501fc1994afd1dc2ebe85402fcc332f4c8", "rules/1c-specialist-platform/chistov.json": "800da27601a3f1c7ec1df64482fd4ad035e559ba0b390a274ed5031128487d3d", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" }, "sha256": "4a12b62d2c10085e1fc710f377f84903abdf2fb787dda19628d944da990a86b2" }, "identity_verified_at": "2026-10-26T18:44:22.364471+00:00", "identity_session_sha256": "950670ab9a82059c65525d0d6e5b8a00f0dc292581edea3eb087c4ecadeaab09", "completed_at": "2026-10-26T19:16:13.065846+00:00" } }, { "id": "demo-20261025T145428Z-209efd", "run_id": "demo-20261025T145428Z-209efd", "result": { "run_id": "demo-20261025T145428Z-209efd", "created_at": "2026-10-25T16:28:12.102785+00:00", "model": "grok-4.7-high", "harness": "none", "solve_seconds": 5395, "platform": "8.3.27.2342", "counts": { "pass": 59, "fail": 4, "inconclusive": 2 }, "rules": [ { "id": "BU01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU16", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU17", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU02", "verdict": "pass", "coverage": "partial", "reason": null }, { "id": "BU10", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU12", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU06", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU07", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU08", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU09", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU11", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU14", "verdict": "fail", "coverage": "selected_fixture", "reason": null }, { "id": "BU15", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU13", "verdict": "fail", "coverage": "selected_fixture", "reason": null }, { "id": "OU15", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU16", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU17", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU02", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU18", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU14", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU06", "verdict": "pass", "coverage": "no_violation_found", "reason": null }, { "id": "OU07", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU08", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU09", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU10", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU11", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU12", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU13", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU04", "verdict": "inconclusive", "coverage": "selected_fixture", "reason": null }, { "id": "OU19", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU20", "verdict": "inconclusive", "coverage": "selected_fixture", "reason": null }, { "id": "OU21", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR02", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR06", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR07", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR08", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR09", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR10", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR11", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR12", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR13", "verdict": "fail", "coverage": "selected_fixture", "reason": null }, { "id": "PR14", "verdict": "pass", "coverage": "no_violation_found", "reason": null }, { "id": "PR15", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR16", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR17", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR18", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR19", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F02", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F05", "verdict": "fail", "coverage": "selected_fixture", "reason": null }, { "id": "G01", "verdict": "pass", "coverage": "static_sources", "reason": null }, { "id": "G02", "verdict": "pass", "coverage": "static_sources", "reason": null }, { "id": "G03", "verdict": "pass", "coverage": "static_sources", "reason": null } ], "charges": [ { "id": "F1C-GEN01", "points": "0.5", "reason": "не выполнено требование: BU13" }, { "id": "F1C-GEN01", "points": "0.5", "reason": "не выполнено требование: BU14" }, { "id": "F1C-GEN01", "points": "0.5", "reason": "не выполнено требование: PR13 — pr_backdate E4/B tariff 2025-01: 2160, expected 1680.00; pr_backdate E4/B tariff 2025-02: 1920, expected 1680.00" }, { "id": "F1C-GEN01", "points": "0.5", "reason": "не выполнено требование: F05 — typed ['C1', 'C2'], written True, stored [('BENCH_Валюта', ''), ('BENCH_Срок', '')]" }, { "id": "F1C-GEN12", "points": "0.25", "reason": "текст запроса не разбирается платформой: DataProcessors/ЗаполнениеГрафика/Ext/ObjectModule.bsl:5 — Поле не найдено \"Подразделения.ЭтоГруппа\"" }, { "id": "F1C-GEN15", "points": "0.5", "reason": "Reports/ПремииСотрудников/Ext/ManagerModule.bsl:9 — РегистрРасчета.Начисления: отбор по ВидРасчета, ПериодДействияНачало, индексы таблицы начинаются с ПериодДействия, ПериодРегистрации, Подразделение, Регистратор, Сотрудник" }, { "id": "F1C-PR14", "points": "0.5", "reason": "после расчёта набор с периодом действия перезаписывается целиком, с пересчётом фактического периода действия (нужно Записать(, Истина)): CommonModules/РасчетЗарплаты/Ext/Module.bsl:29 Набор.Записать(); CommonModules/РасчетЗарплаты/Ext/Module.bsl:31 Набор.Записать(); CommonModules/РасчетЗарплаты/Ext/Module.bsl:33 Набор.Записать(); CommonModules/РасчетЗарплаты/Ext/Module.bsl:35 Набор.Записать(); CommonModules/РасчетЗарплаты/Ext/Module.bsl:37 Набор.Записать(); CommonModules/РасчетЗарплаты/Ext/Module.bsl:39 Набор.Записать()" }, { "id": "F1C-BU06", "points": "1.5", "reason": "ресурс Количество балансовый" }, { "id": "F1C-BU07", "points": "1.0", "reason": "признак учёта субконто Суммовой, Количественный, ТолькоОбороты заведён в плане счетов, но не указан ни у одного ресурса регистра — не действует" }, { "id": "F1C-GEN20", "points": "2.0", "reason": "данные базы читаются в цикле по записям: CommonModules/БухгалтерскийУчетДокументов/Ext/Module.bsl:129; CommonModules/БухгалтерскийУчетДокументов/Ext/Module.bsl:129" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "оперативное проведение разрешено у документов с движениями по регистрам расчёта: НачислениеЗарплаты" }, { "id": "F1C-GEN21", "points": "2.0", "reason": "данные графика без отбора по регистратору: CommonModules/РасчетЗарплаты/Ext/Module.bsl:450" }, { "id": "F1C-GEN01", "points": "0.5", "reason": "разыменование поля составного типа без ВЫРАЗИТЬ: CommonModules/ЗаполнениеДемоДанных/Ext/Module.bsl: Начисления.ВидРасчета.Наименование; CommonModules/УчетЗапасов/Ext/Module.bsl: Остатки.Партия.Дата" } ], "score_upper_bound": "-6.25", "score": null, "grade": "unsatisfactory", "deductions": "11.25", "not_assessed": 15, "gates": { "starter_origin": "passed", "load": "loaded", "clients": "compiles", "demo_data": "present" }, "infrastructure_errors": false, "comparison_eligible": false, "binding_compatibility": null, "evaluation_sha256": "e1a35788211635bf5c43e21f2c9d6159ef59d54576ac150f859744a7c8071de1", "downloads": [] }, "measurement": { "operator": { "name": "Виктор Мурашкин", "github": "VictorMurashkin" }, "environment": { "captured_at": "2026-10-25T14:54:30.054169+00:00", "capture_timing": "before_run", "hardware": { "cpu": "12th Gen Intel(R) Core(TM) i5-12600KF", "logical_cpus": 16, "ram_bytes": 68500021248 }, "os": { "system": "Windows", "release": "11", "version": "10.0.26100", "architecture": "AMD64" }, "python": "3.14.6", "platform_version": "8.3.27.2342", "isolation": "dedicated-host", "network_profile": "open-book_shell", "unsafe_action_protection_observed_in_user_config": true, "git_revision": "2d3566285b9fb7c93d60e4d903679c17d8dc71b8", "implementation_files": { "exam_bench/__init__.py": "ad5bf6f05dc6765f40b78bd186870ca2c49be113cfa33f8aa76f4926f2cb2c1e", "exam_bench/assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "exam_bench/bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "exam_bench/calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "exam_bench/calibrate.py": "78b5185cb0888c0c0ac3de95ffc3a80154a6de9ae66fc461f79d012e5a58e1db", "exam_bench/calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "exam_bench/calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "exam_bench/calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "exam_bench/calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "exam_bench/calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "exam_bench/claude.py": "9c68ca50de1301f20ca2109df21943caa7ac0c6da17bf0a5fbd305d2c244d9e5", "exam_bench/cli.py": "a1a83be1f53924705576ed06b2a2c20868067fd0c5d3da839192e7b13c37540b", "exam_bench/codescan.py": "751e38001b6e65727a31e28172a0623f0bf34bc092a958037c286aa991a197ed", "exam_bench/codex.py": "904e75503cd35f16cbb052f66806b3879fe25bfc9f99e33b93c889d862c46324", "exam_bench/common.py": "8682603b519063e655eae3574a02a49efee63bde21f582ccee20ddd623fca96d", "exam_bench/cursor.py": "88d903f344eedddb2303166ec10827714e4acde90bdc94eefd3ace46ef685671", "exam_bench/cursor_bsl.py": "753f02ebed60e5b8bbefba0933adbdf28477ef916353d70e3c68c817ce6c42e0", "exam_bench/cursor_harnesses.py": "d4bc375cdf5462cf99df079f2ea20148912f9e366e04225ad4abf73f9cafddf9", "exam_bench/docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "exam_bench/examiner.py": "d7294fdd23ed1732216cafebf0a8cf2c24cce4259859aeb7149f62b7607d087d", "exam_bench/finalize.py": "4034f1c63896a940afdb1a83d541cf47fc75c8b5061e3f839047109c04beb620", "exam_bench/forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "exam_bench/gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "exam_bench/grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "exam_bench/harness.py": "3040f6daaf1dc6e6583219f4d925151f8ba7851b2d5417d7f14645892b485ddf", "exam_bench/interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "exam_bench/interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "exam_bench/isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "exam_bench/ledger.py": "7e851523580e22d8490e75f9b6026c07f2c355007e0d11d0b252671f56bef654", "exam_bench/locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "exam_bench/materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "exam_bench/mcp_toolkit.py": "f4c3ea8d9ce542645960a0234ddb61712a047793c58d4e2a0691fc9a45961383", "exam_bench/observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "exam_bench/ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "exam_bench/penalties.py": "0d79e2e46102657dca00609b6abbfc0bf7d11fad41429564f876c82bc6b33269", "exam_bench/platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "exam_bench/portable.py": "cad56968ff407983608f5bdbc9ce7234128d7a4580b096ecea8e0e7b4edb9070", "exam_bench/portable_harnesses.py": "686c46a4231067625b3a20f0b22639d14bcaeb26fab3493e06f92b53dfead05a", "exam_bench/pr.py": "6a3a20caf0e10c0cc94410511a72d62c9fcda785f3abab1be2ad616d4ee16836", "exam_bench/preflight.py": "fbce47aa201c1f5acdbc80b241655dce443df35f9d14d3260c2325f875d6f6e4", "exam_bench/process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "exam_bench/queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "exam_bench/queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "exam_bench/replay_calibration.py": "e2d79cb508f2d5e3846d6dad36c3898d41dec1c573c1a1b7d8a2ec43e33c8c08", "exam_bench/report.py": "5e4c0757e1c7f189953f9a5302593ab726551835856baed25efd93dad6e8bfcd", "exam_bench/runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "exam_bench/smoke_check.py": "f36922a0027429ead0b414048dcc14bbe67f2f0e79a70d03dffbe1447d253545", "exam_bench/stdio_harnesses.py": "0bbfd791fb244a934c6cda3a4e63fbe9ce515e4af64729bb923ce86645057288", "exam_bench/submission.py": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "exam_bench/telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "exam_bench/windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "exam_bench/workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tools/build_public_site.py": "9682ed696f5ac9e9a82b65a45c0dece556ec7e49eeb20dcd616882cc534a8258", "tools/build_result_site.py": "38fc65d8dc01d51249e1c92c174d6ef42b8a0400a63a621d66bb4de9aaccce47", "tools/check_native_harnesses.py": "1fdde7b8eeb76f94341592ddbf1cac61306a65779d7b871ecabd053ab70c1e80", "tools/check_native_toolkit.py": "0272794617121f2932828e5e4e9ae20095183c443666cf3ba466b44fbe875095", "tools/community_results.py": "3f4c0067088353ec5bba8ea32decba5e205c3f7993cc305d07693b54c7039a23", "tools/community_service.py": "c374480dbd88d656c0b9054fa04a8e1c6698c69e2f9cf475e82498a2dff61d84", "tools/community_setup.py": "5d7d126ed7d4dd48e1d79f57b99647a92ffcc8c9f80d90915e458888cdd76bf7", "tools/compare_harness_runs.py": "f274df5f3f804cb02504491aec946943833e12fbce6e62d281e12beb8508fc4e", "tools/create_run_plan.py": "694f1b376f5b78de23705b8df3ec943def516eda93f96e7afaa3942729a1240c", "tools/demo_runner.py": "0f4267b97f5aaa25d60087be8fbe16f2ff6d7cc28de1ba4822d5d1302fb19163", "tools/installers.py": "9a2742780936b17500869e7c89202c1a2549e37d53a42ad9a50a0abbf78bbe09", "tools/machine_bundle.py": "8aa8346f99f537e81ceca6fb6ab9530e844954bab8eff87bf33d3602f81f8a30", "tools/prepare_native_harnesses.py": "fba3fd78b1fdd400196e086c5f463aec5ecefe41e81cd6875d87c76a3126a877", "tools/prepare_official_statement.py": "6b7028c78e90e798d6ef1a93b76520cc61a308c354fb9b87f7fad18b99800fad", "tools/prepare_open_exam_requirements.py": "544f4e378b9be5f166186f8788f8d454afdac2deb99d91d98421e39d01ba6d03", "tools/probe_cursor_harnesses.py": "19952ea409c934ed89cf2589dbb7dcf8d52fad5e01ca256c7df552578d28addc", "tools/probe_harness.py": "1ed8ef93420d1484cbbfd151b7efc31b9a201ceb942dd05e3103efa22ffa7f27", "tools/probe_http_mcp.py": "2667e191fb831b1cbc9cbbbbefdfad16241e17d620a1a42a43405ab0b8139ac4", "tools/probe_native_mcp.py": "9918d324129cba898993e07f8f8b6dbcbaf369398ebf28d464f9f1f00abdb254", "tools/readiness.py": "3c5404be17a7a0a2f72d7cef5714f7d1d6bde7da0d8eb698da4cc65d0b0dd3f3", "tools/recheck_community.py": "f0843d7d677f90da31e22bde0b1c86584dd46c022f1532d43d042619e426b230", "tools/regrade_runs.py": "011775afb06d3aac67a4aa81117a368c75896b0fcbe1e6f27ccc6237612fbf59", "tools/render_statement_text.py": "dabc0716a3612c288c671bc20e17fd4986691d732768e1e957d6dddddbea92a3", "tools/replay_calibration.py": "801f5004926c438c21ed3668fe2a4ddf45312b3e75320165a3839aae034eee9b", "tools/run_exam_campaign.py": "2c450d57a1cd0a2682838f5ec7c0a4ffb3aed0f1730d34c408e912d59cab6efd", "tools/serve_result_site.py": "86badfac863cd4ad1fc894a14110c75b28470513f0133eeae9d2799b8b4df3a9", "tools/start_demo.py": "c597e6cad28d245b3191654bb3e2801fa9dd2364e2acb25561923613717b615f", "tools/supplemental_acceptance.py": "7327277143d80a531e4c254ac74a9fc0e0d5c76572d53b8469e0a580eda17d65", "tools/sync_sources.py": "b51e889b0f41f9f63bfb19a09fb96d3777693d6b1d76fe0132bdd2a15e155898", "tools/validate_community_pr.py": "796b896dfade07b4529af2088a4b9b9d23484148b3bc0732b3fb837b75c9844b", "tools/verify_official_assessment_mapping.py": "daeb448a016940d5b6b1285979a56e5b9014bd91db40acb131445e4a83a23059", "tools/verify_task_package.py": "9e1e6105f6b5e4e78b36aa57f00117a9fbc8948ab53983c32ab56da88d23ccc4", "profiles/1c-ai-rules-2026-10-23-requirements.txt": "fd7ada214e0977776eb350794bb492d97824d96810eb7b158e46cf5cd72c8e65", "profiles/agents.json": "af9c492c08d13b3044aa6b6952589ed6a0a07d5258d8ff72bb18185b3eaebdc5", "profiles/ai-exam-execution-policy.json": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "profiles/bsl-analyzer-0.3.2-macos.json": "83537abdbf38c41ce665e4d0f24128bb51b62e971e0e0f368695f1326a7d2ffb", "profiles/bsl-analyzer-0.3.2-portable.json": "d6ba732e6778e256df34d6bc548593128820a70430c35b279796843606ee40a8", "profiles/bsl-ls-1.1.0-rc.6-macos.json": "245fc10747197e6911b2b4c77cdb15e6fa4eb7bc7c3758b63e768c5adf1df180", "profiles/bsl-ls-1.1.0-rc.6-portable.json": "9f10660881f2ec84794f7d584556b8f75c7e14b3555464af0ed0e60c4c892d86", "profiles/claude-code-skills-1c-1.12.0-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/code-index-1.9.0-macos.json": "63a919523ce62ecec274f4c139bc7ad49a75dd4c339568b822cbc695b4e30408", "profiles/code-index-1.9.0-portable.json": "81106cee8f424ffd8a9dc46ecd8e4f57598fc1d49661a83c77b1f0507993fbdc", "profiles/codex-probe-plan.json": "166e41aad5fb3b27d9050bc6de952c6cba363cc6e804d4080568cc71a2a4d289", "profiles/machine.linux.example.json": "408304fd0581098d5d8110dc67dfeab353bc4d4030e32d37e6acf98d2b1aedfd", "profiles/machine.macos.example.json": "52e9f9d17797cb520b9d8955d6806fd550b899bed4da241ebf096dcb6a21a942", "profiles/machine.windows.example.json": "63accac9a2f81d47d03447efbabffd4760aee325193f02f46b9b29a28d50d2d8", "profiles/mcp-toolkit-1.9.0-macos.json": "1d3f9cde5ffa20589a840d01fdae03aa0fc2f412c929f064f203919c4129625b", "profiles/mcp-toolkit-1.9.0-portable.json": "8e370eebe773eef0e08045ee9c6d5be1451f769f65be0710834b262a4336e054", "profiles/none-macos.json": "b1401d9c48159aed3559006c7f6ace6ef4571224d5cf0bb76d1a823505a10056", "profiles/none-portable.json": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "profiles/rlm-tools-bsl-1.43.0-macos.json": "9354421052640ab60bc3e6aa98ff2e7ba9ca2318b0f4026c137487449242cbd2", "profiles/rlm-tools-bsl-1.43.0-portable.json": "2599e5645e0a7d4e44cb2934bc2b272cae79a9bf7ea74a23cd48aacea64bc424", "profiles/rlm-tools-bsl-1.43.0-posix-requirements.txt": "4fdf9a1bd994bf0272e65d231daf76cf19b0a34dad0ae6b50ec4f11a2ce4c330", "profiles/rlm-tools-bsl-1.43.0-windows-requirements.txt": "3730cb46c81cda5181ecd4485e98b11933104632358bc86f8c0eb1a612a8954f", "profiles/shirokov-skills-macos.json": "84f3e89091676884a802035c707e912762a1179425fb8e3faff25be736873cdb", "profiles/shirokov-skills-portable.json": "2b0a461e06602f1456410e70f02ceaa5ac32c6549c486660bcb5ace0c2f87b15", "profiles/shirokov-skills-windows-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/unica-0.12.3-macos.json": "2c39fbb591cf2c2c6e056373823615485397ea83651b7926c6f25a5fe6a0aae6", "profiles/unica-0.13.0-macos.json": "b76b5c8a4dd33f571c4a90993f1a2da5f7223b4f0f8e1042c282e21a66121052", "profiles/unica-0.14.0-rc.1-portable.json": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "rules/1c-specialist-platform/chistov.json": "7a42ef723a1f5f03f02c387cd3ca95725f7364c2e11ebdfc988a02919ab22c37", "rules/1c-specialist-platform/decisions.json": "f622107423ce3c188c063318d7ab4f7718ceb38e443130677d8987f386641c09", "rules/1c-specialist-platform/examiner.json": "30353aa2a1b6545496b070d9066e9ffba0c3779e5b53ef70a4fd2cee375b18c0", "rules/1c-specialist-platform/ledger.json": "f167c10db2b5799dd9a1ea6a37cd2d7d186810dadf5ea2f50f26ae723c676882", "rules/1c-specialist-platform/rules.json": "1d320a4f8e1bf4701496388931f492315549bd3dce574b17285dd1d7f8652007", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" } } }, "conditions": { "client": "cursor", "model": "grok-4.7-high", "client_version": "2026.10.22-27dcf5f", "reasoning_effort": null, "harness": "none", "billing_channel": "subscription", "solve_timeout_seconds": 18000, "time_series": "exam", "delegation": "requested_disabled_unverified", "network_profile": "open-book_shell", "deadline_disclosed": true, "statement_sha256": "8a6ccb3e673826d1f8220fda53eb310e3ec18c136d87ce8f4cebb2a08614e7e5", "starter_dt_sha256": "f40d084818b0d1cfe503fc7653a6a13f1a8e47fcd1688dad6245b12744eb4638", "profile_sha256": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "execution_policy_sha256": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "calibration_sha256": "201d0591454d3b4cea9a26fde9088181f106b37b26f26392edb010457480b5c8", "started_at": "2026-10-25T14:54:48.106383+00:00", "timing": { "prepare_ms": 16331, "solve_ms": 5394921, "grade_ms": null }, "original_submission_valid": true, "model_provenance": "client_reported", "tokens": { "input": 36819638, "cached_input": 36221440, "fresh_input": 598198, "output": 347182, "reasoning_output": null, "total": 37166820, "coverage": "client_final_result" }, "tools": { "mcp_calls": 0, "unica_calls": 0, "failed_calls": 0 }, "process": { "status": "completed", "exit_code": 0, "stop_confirmed": true } }, "verification": "contributor_reported", "download": "community-downloads/demo-20261025T145428Z-209efd/solution.zip", "source_context": "community-downloads/demo-20261025T145428Z-209efd/source-context.json", "regrade_required": [ { "id": "grader_changed", "files": [ "assessment.py", "bp.py", "calcwrite.py", "calibrate.py", "calibration_periodicity.py", "calibration_query.py", "claude.py", "codescan.py", "codex.py", "common.py", "docx_text.py", "examiner.py", "harness.py", "interpretations.py", "locking.py", "materials.py", "mcp_toolkit.py", "ou.py", "penalties.py", "portable_harnesses.py", "pr.py", "preflight.py", "queries.py", "queryschema.py", "querytypes.py", "replay_calibration.py", "rules/1c-specialist-platform/chistov.json", "rules/1c-specialist-platform/examiner.json", "rules/1c-specialist-platform/rules.json", "rules/1c-specialist-platform/standards.json", "smoke_check.py", "starters/carcass-8.3.25.1445/starter.json", "stdio_harnesses.py", "tasks/1c-platform-official-sample/checks.json", "tasks/1c-platform-official-sample/private/official-assessment-mapping.json", "tasks/1c-platform-official-sample/private/owner-scoring-policy.json", "telemetry.py" ] } ], "grader_revision_sha256": "855d4f66db31ec9f50ebfc18f596c0d1d157e53e2830c51f853c1338f628e49c", "archive_sha256": "aef0f081c7d99f6619e466727f3b949e973fe2e16d4236dbc46d2302f701684a" } ] }, { "id": "demo-20261025T153915Z-adapter--owner-2026-10-26T223334471280-0000", "run_id": "demo-20261024T153359Z-bbf7c4", "result": { "run_id": "demo-20261024T153359Z-bbf7c4", "created_at": "2026-10-26T22:33:34.471280+00:00", "model": "gpt-6.1-sol", "harness": "unica-0.14.0-rc.1", "solve_seconds": 3511, "platform": "8.3.27.1688", "counts": { "pass": 65 }, "rules": [ { "id": "BU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU01.selected_fixture" }, { "id": "BU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU04.selected_fixture" }, { "id": "BU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU05.selected_fixture" }, { "id": "BU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU16.selected_fixture" }, { "id": "BU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU17.selected_fixture" }, { "id": "BU02", "verdict": "pass", "reason": null, "coverage": "partial", "assertion_id": "BU02.posting_cost_and_balance" }, { "id": "BU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU10.selected_fixture" }, { "id": "BU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU12.selected_fixture" }, { "id": "BU03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU03.selected_fixture" }, { "id": "BU06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU06.selected_fixture" }, { "id": "BU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU07.selected_fixture" }, { "id": "BU08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU08.selected_fixture" }, { "id": "BU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU09.selected_fixture" }, { "id": "BU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU11.selected_fixture" }, { "id": "BU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU14.selected_fixture" }, { "id": "BU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU15.selected_fixture" }, { "id": "BU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU13.selected_fixture" }, { "id": "OU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU15.selected_fixture" }, { "id": "OU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU16.selected_fixture" }, { "id": "OU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU17.selected_fixture" }, { "id": "OU02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU02.selected_fixture" }, { "id": "OU18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU18.selected_fixture" }, { "id": "OU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU14.selected_fixture" }, { "id": "OU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU01.selected_fixture" }, { "id": "OU03", "verdict": "pass", "reason": "История и годовая периодичность регистра подтверждены.", "coverage": "history_and_periodicity", "assertion_id": "OU03.selected_fixture" }, { "id": "OU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU05.selected_fixture" }, { "id": "OU06", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "OU06.selected_fixture" }, { "id": "OU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU07.selected_fixture" }, { "id": "OU08", "verdict": "pass", "reason": "История и дневная периодичность подтверждены; ограничение одной версии в неделю отдельно не проверяется.", "coverage": "history_and_periodicity", "assertion_id": "OU08.selected_fixture" }, { "id": "OU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU09.selected_fixture" }, { "id": "OU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU10.selected_fixture" }, { "id": "OU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU11.selected_fixture" }, { "id": "OU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU12.selected_fixture" }, { "id": "OU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU13.selected_fixture" }, { "id": "OU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU04.selected_fixture" }, { "id": "OU19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU19.selected_fixture" }, { "id": "OU20", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU20.selected_fixture" }, { "id": "OU21", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU21.selected_fixture" }, { "id": "PR01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR01.selected_fixture" }, { "id": "PR02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR02.selected_fixture" }, { "id": "PR03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR03.selected_fixture" }, { "id": "PR04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR04.selected_fixture" }, { "id": "PR05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR05.selected_fixture" }, { "id": "PR06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR06.selected_fixture" }, { "id": "PR07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR07.selected_fixture" }, { "id": "PR08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR08.selected_fixture" }, { "id": "PR09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR09.selected_fixture" }, { "id": "PR10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR10.selected_fixture" }, { "id": "PR11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR11.selected_fixture" }, { "id": "PR12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR12.selected_fixture" }, { "id": "PR13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR13.selected_fixture" }, { "id": "PR14", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "PR14.selected_fixture" }, { "id": "PR15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR15.selected_fixture" }, { "id": "PR16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR16.selected_fixture" }, { "id": "PR17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR17.selected_fixture" }, { "id": "PR18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR18.selected_fixture" }, { "id": "PR19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR19.selected_fixture" }, { "id": "F01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F01.selected_fixture" }, { "id": "F02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F02.selected_fixture" }, { "id": "F03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F03.selected_fixture" }, { "id": "F04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F04.selected_fixture" }, { "id": "F05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F05.selected_fixture" }, { "id": "G01", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G01.static_sources" }, { "id": "G02", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G02.static_sources" }, { "id": "G03", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G03.static_sources" } ], "charges": [ { "id": "F1C-PR09", "points": "0.5", "reason": "CommonModules/РасчетСервер/Ext/Module.bsl:114 — РегистрРасчета.Начисления.БазаНачисления: база получается без отбора по регистратору — по всем записям регистра" }, { "id": "F1C-GEN15", "points": "0.5", "reason": "Reports/ВедомостьПоПодразделению/Ext/ObjectModule.bsl:9 — РегистрНакопления.ОстаткиНоменклатуры.ОстаткиИОбороты: отбор по Подразделение, Свойство, индексы таблицы начинаются с Номенклатура" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "проводимые документы в режиме «Записывать модифицированные»: Операция, Сборка" }, { "id": "F1C-PR14", "points": "0.5", "reason": "после расчёта набор с периодом действия перезаписывается целиком, с пересчётом фактического периода действия (нужно Записать(, Истина)): CommonModules/РасчетСервер/Ext/Module.bsl:176 Пара.Значение.Записать()" }, { "id": "F1C-GEN20", "points": "2.0", "reason": "данные базы читаются в цикле по записям: CommonModules/ПроверкаРешения/Ext/Module.bsl:154; CommonModules/УчетСервер/Ext/Module.bsl:340" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "оперативное проведение разрешено у документов с движениями по регистрам расчёта: НачислениеЗарплаты" }, { "id": "F1C-GEN21", "points": "2.0", "reason": "данные графика без отбора по регистратору: CommonModules/РасчетСервер/Ext/Module.bsl:86" } ], "score_upper_bound": "-2.5", "score": null, "grade": "unsatisfactory", "deductions": "7.5", "not_assessed": 14, "gates": { "starter_origin": "passed", "load": "loaded", "clients": "compiles", "demo_data": "present" }, "infrastructure_errors": false, "comparison_eligible": false, "binding_compatibility": { "scope": "supplemental_named_subconto_adapter", "original_binding_sha256": "cef7b7992a8c61b4e62cdcc18e1df71ceb79fe3a47e1f347583b899afa4cebfd", "normalized_binding_sha256": "369380bc11c90ddc093e3fcad8b5d242d6305b64d6d1801f01f0f7e867fd5dbf", "normalizer_sha256": "7327277143d80a531e4c254ac74a9fc0e0d5c76572d53b8469e0a580eda17d65", "canonical_ledger_sha256": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "changes": [ { "field": "fields.ledger.item_debit", "before": "Номенклатура", "after": "ВидыСубконто.Номенклатура", "kind": "named" }, { "field": "fields.ledger.item_credit", "before": "Номенклатура", "after": "ВидыСубконто.Номенклатура", "kind": "named" }, { "field": "fields.ledger.warehouse_debit", "before": "Склад", "after": "ВидыСубконто.Склад", "kind": "named" }, { "field": "fields.ledger.warehouse_credit", "before": "Склад", "after": "ВидыСубконто.Склад", "kind": "named" } ], "basis": "kind names expanded only to exactly one predefined kind of the account chart on the role side; all role types checked." } }, "measurement": { "operator": { "name": "Vasiliy", "github": "Gh0sTspp" }, "environment": { "captured_at": "2026-10-24T15:34:00.710576+00:00", "capture_timing": "before_run", "hardware": { "cpu": "Intel(R) Core(TM) i7-5820K CPU @ 3.30GHz", "logical_cpus": 12, "ram_bytes": 34189709312 }, "os": { "system": "Windows", "release": "10", "version": "10.0.19045", "architecture": "AMD64" }, "python": "3.13.12", "platform_version": "8.3.27.1688", "isolation": "dedicated-host", "network_profile": "open-book_shell", "unsafe_action_protection_observed_in_user_config": true, "git_revision": "af85e791b303dbbf0b0b7af924d2489c3e57cfa8", "implementation_files": { "exam_bench/__init__.py": "ad5bf6f05dc6765f40b78bd186870ca2c49be113cfa33f8aa76f4926f2cb2c1e", "exam_bench/assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "exam_bench/bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "exam_bench/calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "exam_bench/calibrate.py": "78b5185cb0888c0c0ac3de95ffc3a80154a6de9ae66fc461f79d012e5a58e1db", "exam_bench/calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "exam_bench/calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "exam_bench/calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "exam_bench/calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "exam_bench/calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "exam_bench/claude.py": "bc1b8550de7573aaed5e39c6e9c0309e0d8175284a75490d61ec27439ed911ad", "exam_bench/cli.py": "1a37ce645633d761f7897dffc9c45e6b8b9600cd7bd233b1cbf78f49d26b099a", "exam_bench/codescan.py": "751e38001b6e65727a31e28172a0623f0bf34bc092a958037c286aa991a197ed", "exam_bench/codex.py": "c3f89d72af11f312d851c73a1610d92e79acadf336be9ccedd1f94ede3b3ccb0", "exam_bench/common.py": "8682603b519063e655eae3574a02a49efee63bde21f582ccee20ddd623fca96d", "exam_bench/docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "exam_bench/examiner.py": "d7294fdd23ed1732216cafebf0a8cf2c24cce4259859aeb7149f62b7607d087d", "exam_bench/finalize.py": "4034f1c63896a940afdb1a83d541cf47fc75c8b5061e3f839047109c04beb620", "exam_bench/forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "exam_bench/gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "exam_bench/grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "exam_bench/harness.py": "3040f6daaf1dc6e6583219f4d925151f8ba7851b2d5417d7f14645892b485ddf", "exam_bench/interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "exam_bench/interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "exam_bench/isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "exam_bench/ledger.py": "7e851523580e22d8490e75f9b6026c07f2c355007e0d11d0b252671f56bef654", "exam_bench/locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "exam_bench/materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "exam_bench/mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "exam_bench/observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "exam_bench/ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "exam_bench/penalties.py": "0d79e2e46102657dca00609b6abbfc0bf7d11fad41429564f876c82bc6b33269", "exam_bench/platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "exam_bench/portable.py": "cad56968ff407983608f5bdbc9ce7234128d7a4580b096ecea8e0e7b4edb9070", "exam_bench/portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "exam_bench/pr.py": "6a3a20caf0e10c0cc94410511a72d62c9fcda785f3abab1be2ad616d4ee16836", "exam_bench/preflight.py": "5619be0131d8641925f3ce2a3c8e5234d42aa5635d95676138ca81536d95cd29", "exam_bench/process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "exam_bench/queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "exam_bench/queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "exam_bench/replay_calibration.py": "c150457b0b23ce4e6814eb8deb4d48f6bc4a2e39d8f84a9dc7644fb99a026c2d", "exam_bench/report.py": "5e4c0757e1c7f189953f9a5302593ab726551835856baed25efd93dad6e8bfcd", "exam_bench/runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "exam_bench/smoke_check.py": "f36922a0027429ead0b414048dcc14bbe67f2f0e79a70d03dffbe1447d253545", "exam_bench/stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "exam_bench/submission.py": "ea862adc63ae67861ddb1d6aeb4d92c10b0b05004d22953f7b03612f82bb4bf4", "exam_bench/telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "exam_bench/windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "exam_bench/workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tools/build_public_site.py": "9682ed696f5ac9e9a82b65a45c0dece556ec7e49eeb20dcd616882cc534a8258", "tools/build_result_site.py": "3294e1d2ec1486058e208735264d61e349a68a4ae2fa2ec7a723c70e3263b496", "tools/check_native_harnesses.py": "4f5f0ed27651f78758eaef077b3b114361781f6b95ec40cb46c3fea689210473", "tools/check_native_toolkit.py": "0272794617121f2932828e5e4e9ae20095183c443666cf3ba466b44fbe875095", "tools/community_results.py": "788f4763fa97a2f6fe055a1ddea15cb918d2881327594931e508f9fbeb3dd13c", "tools/community_service.py": "c374480dbd88d656c0b9054fa04a8e1c6698c69e2f9cf475e82498a2dff61d84", "tools/community_setup.py": "5d7d126ed7d4dd48e1d79f57b99647a92ffcc8c9f80d90915e458888cdd76bf7", "tools/compare_harness_runs.py": "f274df5f3f804cb02504491aec946943833e12fbce6e62d281e12beb8508fc4e", "tools/create_run_plan.py": "871cd81b1eda231c0fba8805f63d2668926be9fc641559e6ddf320e2f47cd37a", "tools/demo_runner.py": "ca7ad17919c53d524cc0418751ba09a540f910eac183dca2961710bc30bba26f", "tools/installers.py": "9a2742780936b17500869e7c89202c1a2549e37d53a42ad9a50a0abbf78bbe09", "tools/machine_bundle.py": "8aa8346f99f537e81ceca6fb6ab9530e844954bab8eff87bf33d3602f81f8a30", "tools/prepare_native_harnesses.py": "aaa75ecf4022883984fa50c42d14d8e1a9fde2eeda03dab03b852bbc5efb2502", "tools/prepare_official_statement.py": "6b7028c78e90e798d6ef1a93b76520cc61a308c354fb9b87f7fad18b99800fad", "tools/prepare_open_exam_requirements.py": "544f4e378b9be5f166186f8788f8d454afdac2deb99d91d98421e39d01ba6d03", "tools/probe_harness.py": "1ed8ef93420d1484cbbfd151b7efc31b9a201ceb942dd05e3103efa22ffa7f27", "tools/probe_native_mcp.py": "9918d324129cba898993e07f8f8b6dbcbaf369398ebf28d464f9f1f00abdb254", "tools/readiness.py": "d34dd3f38334f51cc4574c79194cf0b80769b062a52382989a57d01c46b9aba4", "tools/recheck_community.py": "f0843d7d677f90da31e22bde0b1c86584dd46c022f1532d43d042619e426b230", "tools/regrade_runs.py": "011775afb06d3aac67a4aa81117a368c75896b0fcbe1e6f27ccc6237612fbf59", "tools/render_statement_text.py": "dabc0716a3612c288c671bc20e17fd4986691d732768e1e957d6dddddbea92a3", "tools/replay_calibration.py": "801f5004926c438c21ed3668fe2a4ddf45312b3e75320165a3839aae034eee9b", "tools/run_exam_campaign.py": "2c450d57a1cd0a2682838f5ec7c0a4ffb3aed0f1730d34c408e912d59cab6efd", "tools/serve_result_site.py": "86badfac863cd4ad1fc894a14110c75b28470513f0133eeae9d2799b8b4df3a9", "tools/start_demo.py": "c597e6cad28d245b3191654bb3e2801fa9dd2364e2acb25561923613717b615f", "tools/supplemental_acceptance.py": "c88fc39de1be1fdcacdd819e2ad329f60367b2df1d5deda80b37324bda3f2a01", "tools/sync_sources.py": "b51e889b0f41f9f63bfb19a09fb96d3777693d6b1d76fe0132bdd2a15e155898", "tools/validate_community_pr.py": "796b896dfade07b4529af2088a4b9b9d23484148b3bc0732b3fb837b75c9844b", "tools/verify_official_assessment_mapping.py": "daeb448a016940d5b6b1285979a56e5b9014bd91db40acb131445e4a83a23059", "tools/verify_task_package.py": "9e1e6105f6b5e4e78b36aa57f00117a9fbc8948ab53983c32ab56da88d23ccc4", "profiles/agents.json": "af9c492c08d13b3044aa6b6952589ed6a0a07d5258d8ff72bb18185b3eaebdc5", "profiles/ai-exam-execution-policy.json": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "profiles/bsl-analyzer-0.3.2-macos.json": "83537abdbf38c41ce665e4d0f24128bb51b62e971e0e0f368695f1326a7d2ffb", "profiles/bsl-analyzer-0.3.2-portable.json": "d6ba732e6778e256df34d6bc548593128820a70430c35b279796843606ee40a8", "profiles/bsl-ls-1.1.0-rc.6-macos.json": "245fc10747197e6911b2b4c77cdb15e6fa4eb7bc7c3758b63e768c5adf1df180", "profiles/bsl-ls-1.1.0-rc.6-portable.json": "9f10660881f2ec84794f7d584556b8f75c7e14b3555464af0ed0e60c4c892d86", "profiles/code-index-1.9.0-macos.json": "63a919523ce62ecec274f4c139bc7ad49a75dd4c339568b822cbc695b4e30408", "profiles/code-index-1.9.0-portable.json": "81106cee8f424ffd8a9dc46ecd8e4f57598fc1d49661a83c77b1f0507993fbdc", "profiles/codex-probe-plan.json": "166e41aad5fb3b27d9050bc6de952c6cba363cc6e804d4080568cc71a2a4d289", "profiles/machine.linux.example.json": "408304fd0581098d5d8110dc67dfeab353bc4d4030e32d37e6acf98d2b1aedfd", "profiles/machine.macos.example.json": "52e9f9d17797cb520b9d8955d6806fd550b899bed4da241ebf096dcb6a21a942", "profiles/machine.windows.example.json": "63accac9a2f81d47d03447efbabffd4760aee325193f02f46b9b29a28d50d2d8", "profiles/mcp-toolkit-1.9.0-macos.json": "1d3f9cde5ffa20589a840d01fdae03aa0fc2f412c929f064f203919c4129625b", "profiles/mcp-toolkit-1.9.0-portable.json": "8e370eebe773eef0e08045ee9c6d5be1451f769f65be0710834b262a4336e054", "profiles/none-macos.json": "b1401d9c48159aed3559006c7f6ace6ef4571224d5cf0bb76d1a823505a10056", "profiles/none-portable.json": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "profiles/rlm-tools-bsl-1.43.0-macos.json": "9354421052640ab60bc3e6aa98ff2e7ba9ca2318b0f4026c137487449242cbd2", "profiles/rlm-tools-bsl-1.43.0-portable.json": "2599e5645e0a7d4e44cb2934bc2b272cae79a9bf7ea74a23cd48aacea64bc424", "profiles/rlm-tools-bsl-1.43.0-posix-requirements.txt": "4fdf9a1bd994bf0272e65d231daf76cf19b0a34dad0ae6b50ec4f11a2ce4c330", "profiles/rlm-tools-bsl-1.43.0-windows-requirements.txt": "3730cb46c81cda5181ecd4485e98b11933104632358bc86f8c0eb1a612a8954f", "profiles/shirokov-skills-macos.json": "84f3e89091676884a802035c707e912762a1179425fb8e3faff25be736873cdb", "profiles/shirokov-skills-portable.json": "2b0a461e06602f1456410e70f02ceaa5ac32c6549c486660bcb5ace0c2f87b15", "profiles/shirokov-skills-windows-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/unica-0.12.3-macos.json": "2c39fbb591cf2c2c6e056373823615485397ea83651b7926c6f25a5fe6a0aae6", "profiles/unica-0.13.0-macos.json": "b76b5c8a4dd33f571c4a90993f1a2da5f7223b4f0f8e1042c282e21a66121052", "profiles/unica-0.14.0-rc.1-portable.json": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "rules/1c-specialist-platform/chistov.json": "77e04942f8c947b10759e7cc1eb31af05847d1711a772fbe6f23d525766757a9", "rules/1c-specialist-platform/decisions.json": "f622107423ce3c188c063318d7ab4f7718ceb38e443130677d8987f386641c09", "rules/1c-specialist-platform/examiner.json": "30353aa2a1b6545496b070d9066e9ffba0c3779e5b53ef70a4fd2cee375b18c0", "rules/1c-specialist-platform/ledger.json": "f167c10db2b5799dd9a1ea6a37cd2d7d186810dadf5ea2f50f26ae723c676882", "rules/1c-specialist-platform/rules.json": "1d320a4f8e1bf4701496388931f492315549bd3dce574b17285dd1d7f8652007", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" } } }, "conditions": { "client": "codex", "model": "gpt-6.1-sol", "client_version": "0.164.0", "reasoning_effort": "medium", "harness": "unica-0.14.0-rc.1", "billing_channel": "subscription", "solve_timeout_seconds": 3600, "time_series": null, "delegation": "native_disabled", "network_profile": "open-book_shell", "deadline_disclosed": true, "statement_sha256": "8a6ccb3e673826d1f8220fda53eb310e3ec18c136d87ce8f4cebb2a08614e7e5", "starter_dt_sha256": "f40d084818b0d1cfe503fc7653a6a13f1a8e47fcd1688dad6245b12744eb4638", "profile_sha256": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "execution_policy_sha256": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "calibration_sha256": "7a2c598d569ece652e72fdfb586af0b95d3c73bd3c467d024dd31f9bb27be403", "started_at": "2026-10-24T15:34:07.713973+00:00", "timing": { "prepare_ms": 6106, "solve_ms": 3510591, "grade_ms": null }, "original_submission_valid": false, "model_provenance": "requested_only", "tokens": { "input": 25305758, "cached_input": 24968320, "fresh_input": 337438, "output": 121307, "reasoning_output": 42088, "total": 25427065, "coverage": "reported_completed_root_turns" }, "tools": { "mcp_calls": 397, "unica_calls": 397, "failed_calls": 32 }, "process": { "status": "completed", "exit_code": 0, "stop_confirmed": true } }, "verification": "repository_owner", "download": "community-downloads/demo-20261025T153915Z-adapter--owner-2026-10-26T223334471280-0000/solution.zip", "source_context": "community-downloads/demo-20261025T153915Z-adapter--owner-2026-10-26T223334471280-0000/source-context.json", "regrade_required": [], "grader_revision_sha256": "9aee1ffe0e1d04f9158fbbbeed3a403a5f0550ad8a590d7a6394977590760e1a", "archive_sha256": "946d237b887268a5d870fb35b1cc48f6b349cf1fcb81b8ae35a187a4700f4390", "owner_verification": { "kind": "repository_owner", "repository": "zeegin/1c-agent-exam-benchmark", "operator": { "name": "Ingvar Vilkman", "github": "zeegin" }, "started_at": "2026-10-26T22:33:34.320684+00:00", "server": { "name": "Owner Windows stand", "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "hardware": { "cpu": "AMD Ryzen 7 5800X 8-Core Processor ", "logical_cpus": 4, "ram_bytes": 17109000192 }, "isolation": "dedicated-host" }, "platform_version": "8.3.27.2342", "grader": { "profile": "technical-v8", "commit": "e15c8ea80263c0b38baa3a1fc19611983270e8a7", "working_tree_dirty": false, "fingerprint": { "assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "calibrate.py": "aac127e03744907fd52ef149b88aa6d88a54a2b7497d56084484ee1b99e0da99", "calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "calibration_periodicity.py": "0b1953d7781e236467897cd2ed66705b75d9719353a2de60b36f2bbdfe799108", "calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "calibration_query.py": "3555b103cde8ea0519955cf52358d09223f5ab183a9df00533bdb48c89237a8c", "claude.py": "5bae98af6e2021e2718afa3a71ed04bee812deaae31a43d4e7324814139ccc82", "codescan.py": "6d8375210cef1fd768fc2d98d630d880b2993a9724f01ae25f33b4ea5aa9631d", "codex.py": "904e75503cd35f16cbb052f66806b3879fe25bfc9f99e33b93c889d862c46324", "common.py": "739b39e2bb9bdd4a571fc69df5843190cddcad094ef7e68964061bc1266b20dc", "docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "examiner.py": "8cdffcdd52f043c905f896697403380af95bf485dd4a5edca24f7956e7795ffe", "forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "harness.py": "3cbb90fd3187e700b5df32e5daafb20313d49bb5721c826e3033cbc6aa6e3825", "interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "ou.py": "f62784b54a3f85576a078a2ff1908c9395f3159e55f6bb5b1a3c564392241abe", "penalties.py": "ae388cb8953ecca1f2370a7c4cb1db3b6cc8318fc2a7563a4db15f9f5b057429", "platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "pr.py": "2b6bfea0634703469605ce114f9274716b485852d9a55d9185c39893b14e4726", "preflight.py": "448c3120ab64b625abae3891be686c7a214ce4211f7cf651fd90e12c0b298433", "process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "queries.py": "1ef57e292db3e8967a733948371ecc542f743b811890d4fc509df17303b9c4ac", "queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "querytypes.py": "b645f489a2abc27762b4a9bbf4917e72f7b46dc053a74c0dca4a8fc46491b3ef", "replay_calibration.py": "e0e3d5ca6416934715b9735aa516046b8d19ad4ae690220eeacd96b198a5f86c", "runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "smoke_check.py": "7837e980986bcb54dc8bc1dfb5d0003deef11e05f6e11df3910fa509e1f74c8d", "stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "submission.py": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tasks/1c-platform-official-sample/checks.json": "7447a9b42d3e348d29d07f001cfb6bd269acd953b7117eba7cca2ce9f5a9a60d", "tasks/1c-platform-official-sample/private/official-assessment-mapping.json": "303587c0dabe77c1eeebb2017fe85539e3370b17c9090435e6e0325a66bd0644", "tasks/1c-platform-official-sample/private/owner-scoring-policy.json": "d26d534bb838ab1b5facb7bc033ca8ec40912133baadcdbad83b27fc577905f5", "starters/carcass-8.3.25.1445/starter.json": "0f7a7060885ba99a19402bfc6e63cc8fe979b0f491b040d3a01d5d21b304b3a6", "rules/1c-specialist-platform/rules.json": "ea75e34ace5de11ba3de403c63cd2c026db81d1d991f8531e4a779d4ce9788e7", "rules/1c-specialist-platform/examiner.json": "1247486ddd412d600db88d9c1db4ba501fc1994afd1dc2ebe85402fcc332f4c8", "rules/1c-specialist-platform/chistov.json": "800da27601a3f1c7ec1df64482fd4ad035e559ba0b390a274ed5031128487d3d", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" }, "sha256": "9aee1ffe0e1d04f9158fbbbeed3a403a5f0550ad8a590d7a6394977590760e1a" }, "method": "saved_platform_observations", "outcome": "complete", "completed_at": "2026-10-26T22:33:34.471280+00:00" }, "previous_evaluations": [ { "id": "demo-20261025T153915Z-adapter--owner-2026-10-26T214413925241-0000", "run_id": "demo-20261024T153359Z-bbf7c4", "result": { "run_id": "demo-20261024T153359Z-bbf7c4", "created_at": "2026-10-26T21:44:13.925241+00:00", "model": "gpt-6.1-sol", "harness": "unica-0.14.0-rc.1", "solve_seconds": 3511, "platform": "8.3.27.1688", "counts": { "pass": 65 }, "rules": [ { "id": "BU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU01.selected_fixture" }, { "id": "BU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU04.selected_fixture" }, { "id": "BU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU05.selected_fixture" }, { "id": "BU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU16.selected_fixture" }, { "id": "BU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU17.selected_fixture" }, { "id": "BU02", "verdict": "pass", "reason": null, "coverage": "partial", "assertion_id": "BU02.posting_cost_and_balance" }, { "id": "BU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU10.selected_fixture" }, { "id": "BU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU12.selected_fixture" }, { "id": "BU03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU03.selected_fixture" }, { "id": "BU06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU06.selected_fixture" }, { "id": "BU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU07.selected_fixture" }, { "id": "BU08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU08.selected_fixture" }, { "id": "BU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU09.selected_fixture" }, { "id": "BU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU11.selected_fixture" }, { "id": "BU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU14.selected_fixture" }, { "id": "BU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU15.selected_fixture" }, { "id": "BU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU13.selected_fixture" }, { "id": "OU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU15.selected_fixture" }, { "id": "OU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU16.selected_fixture" }, { "id": "OU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU17.selected_fixture" }, { "id": "OU02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU02.selected_fixture" }, { "id": "OU18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU18.selected_fixture" }, { "id": "OU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU14.selected_fixture" }, { "id": "OU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU01.selected_fixture" }, { "id": "OU03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU03.selected_fixture" }, { "id": "OU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU05.selected_fixture" }, { "id": "OU06", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "OU06.selected_fixture" }, { "id": "OU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU07.selected_fixture" }, { "id": "OU08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU08.selected_fixture" }, { "id": "OU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU09.selected_fixture" }, { "id": "OU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU10.selected_fixture" }, { "id": "OU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU11.selected_fixture" }, { "id": "OU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU12.selected_fixture" }, { "id": "OU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU13.selected_fixture" }, { "id": "OU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU04.selected_fixture" }, { "id": "OU19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU19.selected_fixture" }, { "id": "OU20", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU20.selected_fixture" }, { "id": "OU21", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU21.selected_fixture" }, { "id": "PR01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR01.selected_fixture" }, { "id": "PR02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR02.selected_fixture" }, { "id": "PR03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR03.selected_fixture" }, { "id": "PR04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR04.selected_fixture" }, { "id": "PR05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR05.selected_fixture" }, { "id": "PR06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR06.selected_fixture" }, { "id": "PR07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR07.selected_fixture" }, { "id": "PR08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR08.selected_fixture" }, { "id": "PR09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR09.selected_fixture" }, { "id": "PR10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR10.selected_fixture" }, { "id": "PR11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR11.selected_fixture" }, { "id": "PR12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR12.selected_fixture" }, { "id": "PR13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR13.selected_fixture" }, { "id": "PR14", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "PR14.selected_fixture" }, { "id": "PR15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR15.selected_fixture" }, { "id": "PR16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR16.selected_fixture" }, { "id": "PR17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR17.selected_fixture" }, { "id": "PR18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR18.selected_fixture" }, { "id": "PR19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR19.selected_fixture" }, { "id": "F01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F01.selected_fixture" }, { "id": "F02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F02.selected_fixture" }, { "id": "F03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F03.selected_fixture" }, { "id": "F04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F04.selected_fixture" }, { "id": "F05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F05.selected_fixture" }, { "id": "G01", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G01.static_sources" }, { "id": "G02", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G02.static_sources" }, { "id": "G03", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G03.static_sources" } ], "charges": [ { "id": "F1C-PR09", "points": "0.5", "reason": "CommonModules/РасчетСервер/Ext/Module.bsl:114 — РегистрРасчета.Начисления.БазаНачисления: база получается без отбора по регистратору — по всем записям регистра" }, { "id": "F1C-GEN15", "points": "0.5", "reason": "Reports/ВедомостьПоПодразделению/Ext/ObjectModule.bsl:9 — РегистрНакопления.ОстаткиНоменклатуры.ОстаткиИОбороты: отбор по Подразделение, Свойство, индексы таблицы начинаются с Номенклатура" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "проводимые документы в режиме «Записывать модифицированные»: Операция, Сборка" }, { "id": "F1C-PR14", "points": "0.5", "reason": "после расчёта набор с периодом действия перезаписывается целиком, с пересчётом фактического периода действия (нужно Записать(, Истина)): CommonModules/РасчетСервер/Ext/Module.bsl:176 Пара.Значение.Записать()" }, { "id": "F1C-GEN20", "points": "2.0", "reason": "данные базы читаются в цикле по записям: CommonModules/ПроверкаРешения/Ext/Module.bsl:154; CommonModules/УчетСервер/Ext/Module.bsl:340" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "оперативное проведение разрешено у документов с движениями по регистрам расчёта: НачислениеЗарплаты" }, { "id": "F1C-GEN21", "points": "2.0", "reason": "данные графика без отбора по регистратору: CommonModules/РасчетСервер/Ext/Module.bsl:86" } ], "score_upper_bound": "-2.5", "score": null, "grade": "unsatisfactory", "deductions": "7.5", "not_assessed": 14, "gates": { "starter_origin": "passed", "load": "loaded", "clients": "compiles", "demo_data": "present" }, "infrastructure_errors": false, "comparison_eligible": false, "binding_compatibility": { "scope": "supplemental_named_subconto_adapter", "original_binding_sha256": "cef7b7992a8c61b4e62cdcc18e1df71ceb79fe3a47e1f347583b899afa4cebfd", "normalized_binding_sha256": "369380bc11c90ddc093e3fcad8b5d242d6305b64d6d1801f01f0f7e867fd5dbf", "normalizer_sha256": "7327277143d80a531e4c254ac74a9fc0e0d5c76572d53b8469e0a580eda17d65", "canonical_ledger_sha256": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "changes": [ { "field": "fields.ledger.item_debit", "before": "Номенклатура", "after": "ВидыСубконто.Номенклатура", "kind": "named" }, { "field": "fields.ledger.item_credit", "before": "Номенклатура", "after": "ВидыСубконто.Номенклатура", "kind": "named" }, { "field": "fields.ledger.warehouse_debit", "before": "Склад", "after": "ВидыСубконто.Склад", "kind": "named" }, { "field": "fields.ledger.warehouse_credit", "before": "Склад", "after": "ВидыСубконто.Склад", "kind": "named" } ], "basis": "kind names expanded only to exactly one predefined kind of the account chart on the role side; all role types checked." } }, "measurement": { "operator": { "name": "Vasiliy", "github": "Gh0sTspp" }, "environment": { "captured_at": "2026-10-24T15:34:00.710576+00:00", "capture_timing": "before_run", "hardware": { "cpu": "Intel(R) Core(TM) i7-5820K CPU @ 3.30GHz", "logical_cpus": 12, "ram_bytes": 34189709312 }, "os": { "system": "Windows", "release": "10", "version": "10.0.19045", "architecture": "AMD64" }, "python": "3.13.12", "platform_version": "8.3.27.1688", "isolation": "dedicated-host", "network_profile": "open-book_shell", "unsafe_action_protection_observed_in_user_config": true, "git_revision": "af85e791b303dbbf0b0b7af924d2489c3e57cfa8", "implementation_files": { "exam_bench/__init__.py": "ad5bf6f05dc6765f40b78bd186870ca2c49be113cfa33f8aa76f4926f2cb2c1e", "exam_bench/assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "exam_bench/bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "exam_bench/calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "exam_bench/calibrate.py": "78b5185cb0888c0c0ac3de95ffc3a80154a6de9ae66fc461f79d012e5a58e1db", "exam_bench/calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "exam_bench/calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "exam_bench/calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "exam_bench/calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "exam_bench/calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "exam_bench/claude.py": "bc1b8550de7573aaed5e39c6e9c0309e0d8175284a75490d61ec27439ed911ad", "exam_bench/cli.py": "1a37ce645633d761f7897dffc9c45e6b8b9600cd7bd233b1cbf78f49d26b099a", "exam_bench/codescan.py": "751e38001b6e65727a31e28172a0623f0bf34bc092a958037c286aa991a197ed", "exam_bench/codex.py": "c3f89d72af11f312d851c73a1610d92e79acadf336be9ccedd1f94ede3b3ccb0", "exam_bench/common.py": "8682603b519063e655eae3574a02a49efee63bde21f582ccee20ddd623fca96d", "exam_bench/docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "exam_bench/examiner.py": "d7294fdd23ed1732216cafebf0a8cf2c24cce4259859aeb7149f62b7607d087d", "exam_bench/finalize.py": "4034f1c63896a940afdb1a83d541cf47fc75c8b5061e3f839047109c04beb620", "exam_bench/forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "exam_bench/gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "exam_bench/grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "exam_bench/harness.py": "3040f6daaf1dc6e6583219f4d925151f8ba7851b2d5417d7f14645892b485ddf", "exam_bench/interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "exam_bench/interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "exam_bench/isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "exam_bench/ledger.py": "7e851523580e22d8490e75f9b6026c07f2c355007e0d11d0b252671f56bef654", "exam_bench/locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "exam_bench/materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "exam_bench/mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "exam_bench/observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "exam_bench/ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "exam_bench/penalties.py": "0d79e2e46102657dca00609b6abbfc0bf7d11fad41429564f876c82bc6b33269", "exam_bench/platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "exam_bench/portable.py": "cad56968ff407983608f5bdbc9ce7234128d7a4580b096ecea8e0e7b4edb9070", "exam_bench/portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "exam_bench/pr.py": "6a3a20caf0e10c0cc94410511a72d62c9fcda785f3abab1be2ad616d4ee16836", "exam_bench/preflight.py": "5619be0131d8641925f3ce2a3c8e5234d42aa5635d95676138ca81536d95cd29", "exam_bench/process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "exam_bench/queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "exam_bench/queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "exam_bench/replay_calibration.py": "c150457b0b23ce4e6814eb8deb4d48f6bc4a2e39d8f84a9dc7644fb99a026c2d", "exam_bench/report.py": "5e4c0757e1c7f189953f9a5302593ab726551835856baed25efd93dad6e8bfcd", "exam_bench/runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "exam_bench/smoke_check.py": "f36922a0027429ead0b414048dcc14bbe67f2f0e79a70d03dffbe1447d253545", "exam_bench/stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "exam_bench/submission.py": "ea862adc63ae67861ddb1d6aeb4d92c10b0b05004d22953f7b03612f82bb4bf4", "exam_bench/telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "exam_bench/windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "exam_bench/workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tools/build_public_site.py": "9682ed696f5ac9e9a82b65a45c0dece556ec7e49eeb20dcd616882cc534a8258", "tools/build_result_site.py": "3294e1d2ec1486058e208735264d61e349a68a4ae2fa2ec7a723c70e3263b496", "tools/check_native_harnesses.py": "4f5f0ed27651f78758eaef077b3b114361781f6b95ec40cb46c3fea689210473", "tools/check_native_toolkit.py": "0272794617121f2932828e5e4e9ae20095183c443666cf3ba466b44fbe875095", "tools/community_results.py": "788f4763fa97a2f6fe055a1ddea15cb918d2881327594931e508f9fbeb3dd13c", "tools/community_service.py": "c374480dbd88d656c0b9054fa04a8e1c6698c69e2f9cf475e82498a2dff61d84", "tools/community_setup.py": "5d7d126ed7d4dd48e1d79f57b99647a92ffcc8c9f80d90915e458888cdd76bf7", "tools/compare_harness_runs.py": "f274df5f3f804cb02504491aec946943833e12fbce6e62d281e12beb8508fc4e", "tools/create_run_plan.py": "871cd81b1eda231c0fba8805f63d2668926be9fc641559e6ddf320e2f47cd37a", "tools/demo_runner.py": "ca7ad17919c53d524cc0418751ba09a540f910eac183dca2961710bc30bba26f", "tools/installers.py": "9a2742780936b17500869e7c89202c1a2549e37d53a42ad9a50a0abbf78bbe09", "tools/machine_bundle.py": "8aa8346f99f537e81ceca6fb6ab9530e844954bab8eff87bf33d3602f81f8a30", "tools/prepare_native_harnesses.py": "aaa75ecf4022883984fa50c42d14d8e1a9fde2eeda03dab03b852bbc5efb2502", "tools/prepare_official_statement.py": "6b7028c78e90e798d6ef1a93b76520cc61a308c354fb9b87f7fad18b99800fad", "tools/prepare_open_exam_requirements.py": "544f4e378b9be5f166186f8788f8d454afdac2deb99d91d98421e39d01ba6d03", "tools/probe_harness.py": "1ed8ef93420d1484cbbfd151b7efc31b9a201ceb942dd05e3103efa22ffa7f27", "tools/probe_native_mcp.py": "9918d324129cba898993e07f8f8b6dbcbaf369398ebf28d464f9f1f00abdb254", "tools/readiness.py": "d34dd3f38334f51cc4574c79194cf0b80769b062a52382989a57d01c46b9aba4", "tools/recheck_community.py": "f0843d7d677f90da31e22bde0b1c86584dd46c022f1532d43d042619e426b230", "tools/regrade_runs.py": "011775afb06d3aac67a4aa81117a368c75896b0fcbe1e6f27ccc6237612fbf59", "tools/render_statement_text.py": "dabc0716a3612c288c671bc20e17fd4986691d732768e1e957d6dddddbea92a3", "tools/replay_calibration.py": "801f5004926c438c21ed3668fe2a4ddf45312b3e75320165a3839aae034eee9b", "tools/run_exam_campaign.py": "2c450d57a1cd0a2682838f5ec7c0a4ffb3aed0f1730d34c408e912d59cab6efd", "tools/serve_result_site.py": "86badfac863cd4ad1fc894a14110c75b28470513f0133eeae9d2799b8b4df3a9", "tools/start_demo.py": "c597e6cad28d245b3191654bb3e2801fa9dd2364e2acb25561923613717b615f", "tools/supplemental_acceptance.py": "c88fc39de1be1fdcacdd819e2ad329f60367b2df1d5deda80b37324bda3f2a01", "tools/sync_sources.py": "b51e889b0f41f9f63bfb19a09fb96d3777693d6b1d76fe0132bdd2a15e155898", "tools/validate_community_pr.py": "796b896dfade07b4529af2088a4b9b9d23484148b3bc0732b3fb837b75c9844b", "tools/verify_official_assessment_mapping.py": "daeb448a016940d5b6b1285979a56e5b9014bd91db40acb131445e4a83a23059", "tools/verify_task_package.py": "9e1e6105f6b5e4e78b36aa57f00117a9fbc8948ab53983c32ab56da88d23ccc4", "profiles/agents.json": "af9c492c08d13b3044aa6b6952589ed6a0a07d5258d8ff72bb18185b3eaebdc5", "profiles/ai-exam-execution-policy.json": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "profiles/bsl-analyzer-0.3.2-macos.json": "83537abdbf38c41ce665e4d0f24128bb51b62e971e0e0f368695f1326a7d2ffb", "profiles/bsl-analyzer-0.3.2-portable.json": "d6ba732e6778e256df34d6bc548593128820a70430c35b279796843606ee40a8", "profiles/bsl-ls-1.1.0-rc.6-macos.json": "245fc10747197e6911b2b4c77cdb15e6fa4eb7bc7c3758b63e768c5adf1df180", "profiles/bsl-ls-1.1.0-rc.6-portable.json": "9f10660881f2ec84794f7d584556b8f75c7e14b3555464af0ed0e60c4c892d86", "profiles/code-index-1.9.0-macos.json": "63a919523ce62ecec274f4c139bc7ad49a75dd4c339568b822cbc695b4e30408", "profiles/code-index-1.9.0-portable.json": "81106cee8f424ffd8a9dc46ecd8e4f57598fc1d49661a83c77b1f0507993fbdc", "profiles/codex-probe-plan.json": "166e41aad5fb3b27d9050bc6de952c6cba363cc6e804d4080568cc71a2a4d289", "profiles/machine.linux.example.json": "408304fd0581098d5d8110dc67dfeab353bc4d4030e32d37e6acf98d2b1aedfd", "profiles/machine.macos.example.json": "52e9f9d17797cb520b9d8955d6806fd550b899bed4da241ebf096dcb6a21a942", "profiles/machine.windows.example.json": "63accac9a2f81d47d03447efbabffd4760aee325193f02f46b9b29a28d50d2d8", "profiles/mcp-toolkit-1.9.0-macos.json": "1d3f9cde5ffa20589a840d01fdae03aa0fc2f412c929f064f203919c4129625b", "profiles/mcp-toolkit-1.9.0-portable.json": "8e370eebe773eef0e08045ee9c6d5be1451f769f65be0710834b262a4336e054", "profiles/none-macos.json": "b1401d9c48159aed3559006c7f6ace6ef4571224d5cf0bb76d1a823505a10056", "profiles/none-portable.json": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "profiles/rlm-tools-bsl-1.43.0-macos.json": "9354421052640ab60bc3e6aa98ff2e7ba9ca2318b0f4026c137487449242cbd2", "profiles/rlm-tools-bsl-1.43.0-portable.json": "2599e5645e0a7d4e44cb2934bc2b272cae79a9bf7ea74a23cd48aacea64bc424", "profiles/rlm-tools-bsl-1.43.0-posix-requirements.txt": "4fdf9a1bd994bf0272e65d231daf76cf19b0a34dad0ae6b50ec4f11a2ce4c330", "profiles/rlm-tools-bsl-1.43.0-windows-requirements.txt": "3730cb46c81cda5181ecd4485e98b11933104632358bc86f8c0eb1a612a8954f", "profiles/shirokov-skills-macos.json": "84f3e89091676884a802035c707e912762a1179425fb8e3faff25be736873cdb", "profiles/shirokov-skills-portable.json": "2b0a461e06602f1456410e70f02ceaa5ac32c6549c486660bcb5ace0c2f87b15", "profiles/shirokov-skills-windows-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/unica-0.12.3-macos.json": "2c39fbb591cf2c2c6e056373823615485397ea83651b7926c6f25a5fe6a0aae6", "profiles/unica-0.13.0-macos.json": "b76b5c8a4dd33f571c4a90993f1a2da5f7223b4f0f8e1042c282e21a66121052", "profiles/unica-0.14.0-rc.1-portable.json": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "rules/1c-specialist-platform/chistov.json": "77e04942f8c947b10759e7cc1eb31af05847d1711a772fbe6f23d525766757a9", "rules/1c-specialist-platform/decisions.json": "f622107423ce3c188c063318d7ab4f7718ceb38e443130677d8987f386641c09", "rules/1c-specialist-platform/examiner.json": "30353aa2a1b6545496b070d9066e9ffba0c3779e5b53ef70a4fd2cee375b18c0", "rules/1c-specialist-platform/ledger.json": "f167c10db2b5799dd9a1ea6a37cd2d7d186810dadf5ea2f50f26ae723c676882", "rules/1c-specialist-platform/rules.json": "1d320a4f8e1bf4701496388931f492315549bd3dce574b17285dd1d7f8652007", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" } } }, "conditions": { "client": "codex", "model": "gpt-6.1-sol", "client_version": "0.164.0", "reasoning_effort": "medium", "harness": "unica-0.14.0-rc.1", "billing_channel": "subscription", "solve_timeout_seconds": 3600, "time_series": null, "delegation": "native_disabled", "network_profile": "open-book_shell", "deadline_disclosed": true, "statement_sha256": "8a6ccb3e673826d1f8220fda53eb310e3ec18c136d87ce8f4cebb2a08614e7e5", "starter_dt_sha256": "f40d084818b0d1cfe503fc7653a6a13f1a8e47fcd1688dad6245b12744eb4638", "profile_sha256": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "execution_policy_sha256": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "calibration_sha256": "7a2c598d569ece652e72fdfb586af0b95d3c73bd3c467d024dd31f9bb27be403", "started_at": "2026-10-24T15:34:07.713973+00:00", "timing": { "prepare_ms": 6106, "solve_ms": 3510591, "grade_ms": null }, "original_submission_valid": false, "model_provenance": "requested_only", "tokens": { "input": 25305758, "cached_input": 24968320, "fresh_input": 337438, "output": 121307, "reasoning_output": 42088, "total": 25427065, "coverage": "reported_completed_root_turns" }, "tools": { "mcp_calls": 397, "unica_calls": 397, "failed_calls": 32 }, "process": { "status": "completed", "exit_code": 0, "stop_confirmed": true } }, "verification": "repository_owner", "download": "community-downloads/demo-20261025T153915Z-adapter--owner-2026-10-26T214413925241-0000/solution.zip", "source_context": "community-downloads/demo-20261025T153915Z-adapter--owner-2026-10-26T214413925241-0000/source-context.json", "regrade_required": [ { "id": "grader_changed", "files": [ "calibrate.py", "calibration_periodicity.py", "common.py", "ou.py", "replay_calibration.py", "smoke_check.py", "tasks/1c-platform-official-sample/checks.json" ] } ], "grader_revision_sha256": "349d87e0c7f531acbe35dd2b39c35722d8a877fedde97575b49e8466ab763c1d", "archive_sha256": "86768430e72686ff12b5451127ee5682e9e43c10f914a635ad81d7a7b302523d", "owner_verification": { "kind": "repository_owner", "repository": "zeegin/1c-agent-exam-benchmark", "operator": { "name": "Ingvar Vilkman", "github": "zeegin" }, "started_at": "2026-10-26T21:44:13.684880+00:00", "server": { "name": "Owner Windows stand", "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "hardware": { "cpu": "AMD Ryzen 7 5800X 8-Core Processor ", "logical_cpus": 4, "ram_bytes": 17109000192 }, "isolation": "dedicated-host" }, "platform_version": "8.3.27.2342", "grader": { "profile": "technical-v8", "commit": "e8fd8ced03a85b549c5472fbbda29225749f54d1", "working_tree_dirty": false, "fingerprint": { "assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "calibrate.py": "3162d431f3cab5e7976aa39f665d6286dce45499cf362d85109b7123fa8403a2", "calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "calibration_query.py": "3555b103cde8ea0519955cf52358d09223f5ab183a9df00533bdb48c89237a8c", "claude.py": "eedabc75fca0faa434f40a1624b71419ec7dc22e2854a0886cf84b4911db8372", "codescan.py": "6d8375210cef1fd768fc2d98d630d880b2993a9724f01ae25f33b4ea5aa9631d", "codex.py": "904e75503cd35f16cbb052f66806b3879fe25bfc9f99e33b93c889d862c46324", "common.py": "52825cf5c29f3536d6e046a89e789d5ef9c83aacd7f2f5a07f4f53e77b5229cc", "docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "examiner.py": "8cdffcdd52f043c905f896697403380af95bf485dd4a5edca24f7956e7795ffe", "forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "harness.py": "3cbb90fd3187e700b5df32e5daafb20313d49bb5721c826e3033cbc6aa6e3825", "interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "penalties.py": "ae388cb8953ecca1f2370a7c4cb1db3b6cc8318fc2a7563a4db15f9f5b057429", "platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "pr.py": "2b6bfea0634703469605ce114f9274716b485852d9a55d9185c39893b14e4726", "preflight.py": "448c3120ab64b625abae3891be686c7a214ce4211f7cf651fd90e12c0b298433", "process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "queries.py": "1ef57e292db3e8967a733948371ecc542f743b811890d4fc509df17303b9c4ac", "queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "querytypes.py": "b645f489a2abc27762b4a9bbf4917e72f7b46dc053a74c0dca4a8fc46491b3ef", "replay_calibration.py": "0a4d9b84a9908944c5a945878eb6f5eeda5a4e42ffff4f55c04a680742803d80", "runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "smoke_check.py": "66caf1a01f7aa18432293abe3567ac228ac837a660b08c3dc7bb093f7bd51628", "stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "submission.py": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tasks/1c-platform-official-sample/checks.json": "17a6fcc0c14410829650623eb1443ce99796e000cdfd19905ac0287988b73a00", "tasks/1c-platform-official-sample/private/official-assessment-mapping.json": "303587c0dabe77c1eeebb2017fe85539e3370b17c9090435e6e0325a66bd0644", "tasks/1c-platform-official-sample/private/owner-scoring-policy.json": "d26d534bb838ab1b5facb7bc033ca8ec40912133baadcdbad83b27fc577905f5", "starters/carcass-8.3.25.1445/starter.json": "0f7a7060885ba99a19402bfc6e63cc8fe979b0f491b040d3a01d5d21b304b3a6", "rules/1c-specialist-platform/rules.json": "ea75e34ace5de11ba3de403c63cd2c026db81d1d991f8531e4a779d4ce9788e7", "rules/1c-specialist-platform/examiner.json": "1247486ddd412d600db88d9c1db4ba501fc1994afd1dc2ebe85402fcc332f4c8", "rules/1c-specialist-platform/chistov.json": "800da27601a3f1c7ec1df64482fd4ad035e559ba0b390a274ed5031128487d3d", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" }, "sha256": "349d87e0c7f531acbe35dd2b39c35722d8a877fedde97575b49e8466ab763c1d" }, "method": "saved_platform_observations", "outcome": "complete", "completed_at": "2026-10-26T21:44:13.925241+00:00" } }, { "id": "demo-20261025T153915Z-adapter--owner-2026-10-26T191909450942-0000", "run_id": "demo-20261024T153359Z-bbf7c4", "result": { "run_id": "demo-20261024T153359Z-bbf7c4", "created_at": "2026-10-26T19:19:09.450942+00:00", "model": "gpt-6.1-sol", "harness": "unica-0.14.0-rc.1", "solve_seconds": 3511, "platform": "8.3.27.1688", "counts": { "pass": 65 }, "rules": [ { "id": "BU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU01.selected_fixture" }, { "id": "BU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU04.selected_fixture" }, { "id": "BU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU05.selected_fixture" }, { "id": "BU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU16.selected_fixture" }, { "id": "BU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU17.selected_fixture" }, { "id": "BU02", "verdict": "pass", "reason": null, "coverage": "partial", "assertion_id": "BU02.posting_cost_and_balance" }, { "id": "BU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU10.selected_fixture" }, { "id": "BU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU12.selected_fixture" }, { "id": "BU03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU03.selected_fixture" }, { "id": "BU06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU06.selected_fixture" }, { "id": "BU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU07.selected_fixture" }, { "id": "BU08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU08.selected_fixture" }, { "id": "BU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU09.selected_fixture" }, { "id": "BU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU11.selected_fixture" }, { "id": "BU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU14.selected_fixture" }, { "id": "BU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU15.selected_fixture" }, { "id": "BU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU13.selected_fixture" }, { "id": "OU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU15.selected_fixture" }, { "id": "OU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU16.selected_fixture" }, { "id": "OU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU17.selected_fixture" }, { "id": "OU02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU02.selected_fixture" }, { "id": "OU18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU18.selected_fixture" }, { "id": "OU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU14.selected_fixture" }, { "id": "OU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU01.selected_fixture" }, { "id": "OU03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU03.selected_fixture" }, { "id": "OU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU05.selected_fixture" }, { "id": "OU06", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "OU06.selected_fixture" }, { "id": "OU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU07.selected_fixture" }, { "id": "OU08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU08.selected_fixture" }, { "id": "OU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU09.selected_fixture" }, { "id": "OU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU10.selected_fixture" }, { "id": "OU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU11.selected_fixture" }, { "id": "OU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU12.selected_fixture" }, { "id": "OU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU13.selected_fixture" }, { "id": "OU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU04.selected_fixture" }, { "id": "OU19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU19.selected_fixture" }, { "id": "OU20", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU20.selected_fixture" }, { "id": "OU21", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU21.selected_fixture" }, { "id": "PR01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR01.selected_fixture" }, { "id": "PR02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR02.selected_fixture" }, { "id": "PR03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR03.selected_fixture" }, { "id": "PR04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR04.selected_fixture" }, { "id": "PR05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR05.selected_fixture" }, { "id": "PR06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR06.selected_fixture" }, { "id": "PR07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR07.selected_fixture" }, { "id": "PR08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR08.selected_fixture" }, { "id": "PR09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR09.selected_fixture" }, { "id": "PR10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR10.selected_fixture" }, { "id": "PR11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR11.selected_fixture" }, { "id": "PR12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR12.selected_fixture" }, { "id": "PR13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR13.selected_fixture" }, { "id": "PR14", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "PR14.selected_fixture" }, { "id": "PR15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR15.selected_fixture" }, { "id": "PR16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR16.selected_fixture" }, { "id": "PR17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR17.selected_fixture" }, { "id": "PR18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR18.selected_fixture" }, { "id": "PR19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR19.selected_fixture" }, { "id": "F01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F01.selected_fixture" }, { "id": "F02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F02.selected_fixture" }, { "id": "F03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F03.selected_fixture" }, { "id": "F04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F04.selected_fixture" }, { "id": "F05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F05.selected_fixture" }, { "id": "G01", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G01.static_sources" }, { "id": "G02", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G02.static_sources" }, { "id": "G03", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G03.static_sources" } ], "charges": [ { "id": "F1C-PR09", "points": "0.5", "reason": "CommonModules/РасчетСервер/Ext/Module.bsl:114 — РегистрРасчета.Начисления.БазаНачисления: база получается без отбора по регистратору — по всем записям регистра" }, { "id": "F1C-GEN15", "points": "0.5", "reason": "Reports/ВедомостьПоПодразделению/Ext/ObjectModule.bsl:9 — РегистрНакопления.ОстаткиНоменклатуры.ОстаткиИОбороты: отбор по Подразделение, Свойство, индексы таблицы начинаются с Номенклатура" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "проводимые документы в режиме «Записывать модифицированные»: Операция, Сборка" }, { "id": "F1C-PR14", "points": "0.5", "reason": "после расчёта набор с периодом действия перезаписывается целиком, с пересчётом фактического периода действия (нужно Записать(, Истина)): CommonModules/РасчетСервер/Ext/Module.bsl:176 Пара.Значение.Записать()" }, { "id": "F1C-GEN20", "points": "2.0", "reason": "данные базы читаются в цикле по записям: CommonModules/ПроверкаРешения/Ext/Module.bsl:154; CommonModules/УчетСервер/Ext/Module.bsl:340" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "оперативное проведение разрешено у документов с движениями по регистрам расчёта: НачислениеЗарплаты" }, { "id": "F1C-GEN21", "points": "2.0", "reason": "данные графика без отбора по регистратору: CommonModules/РасчетСервер/Ext/Module.bsl:86" } ], "score_upper_bound": "-2.5", "score": null, "grade": "unsatisfactory", "deductions": "7.5", "not_assessed": 14, "gates": { "starter_origin": "passed", "load": "loaded", "clients": "compiles", "demo_data": "present" }, "infrastructure_errors": false, "comparison_eligible": false, "binding_compatibility": { "scope": "supplemental_named_subconto_adapter", "original_binding_sha256": "cef7b7992a8c61b4e62cdcc18e1df71ceb79fe3a47e1f347583b899afa4cebfd", "normalized_binding_sha256": "369380bc11c90ddc093e3fcad8b5d242d6305b64d6d1801f01f0f7e867fd5dbf", "normalizer_sha256": "7327277143d80a531e4c254ac74a9fc0e0d5c76572d53b8469e0a580eda17d65", "canonical_ledger_sha256": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "changes": [ { "field": "fields.ledger.item_debit", "before": "Номенклатура", "after": "ВидыСубконто.Номенклатура", "kind": "named" }, { "field": "fields.ledger.item_credit", "before": "Номенклатура", "after": "ВидыСубконто.Номенклатура", "kind": "named" }, { "field": "fields.ledger.warehouse_debit", "before": "Склад", "after": "ВидыСубконто.Склад", "kind": "named" }, { "field": "fields.ledger.warehouse_credit", "before": "Склад", "after": "ВидыСубконто.Склад", "kind": "named" } ], "basis": "kind names expanded only to exactly one predefined kind of the account chart on the role side; all role types checked." } }, "measurement": { "operator": { "name": "Vasiliy", "github": "Gh0sTspp" }, "environment": { "captured_at": "2026-10-24T15:34:00.710576+00:00", "capture_timing": "before_run", "hardware": { "cpu": "Intel(R) Core(TM) i7-5820K CPU @ 3.30GHz", "logical_cpus": 12, "ram_bytes": 34189709312 }, "os": { "system": "Windows", "release": "10", "version": "10.0.19045", "architecture": "AMD64" }, "python": "3.13.12", "platform_version": "8.3.27.1688", "isolation": "dedicated-host", "network_profile": "open-book_shell", "unsafe_action_protection_observed_in_user_config": true, "git_revision": "af85e791b303dbbf0b0b7af924d2489c3e57cfa8", "implementation_files": { "exam_bench/__init__.py": "ad5bf6f05dc6765f40b78bd186870ca2c49be113cfa33f8aa76f4926f2cb2c1e", "exam_bench/assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "exam_bench/bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "exam_bench/calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "exam_bench/calibrate.py": "78b5185cb0888c0c0ac3de95ffc3a80154a6de9ae66fc461f79d012e5a58e1db", "exam_bench/calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "exam_bench/calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "exam_bench/calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "exam_bench/calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "exam_bench/calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "exam_bench/claude.py": "bc1b8550de7573aaed5e39c6e9c0309e0d8175284a75490d61ec27439ed911ad", "exam_bench/cli.py": "1a37ce645633d761f7897dffc9c45e6b8b9600cd7bd233b1cbf78f49d26b099a", "exam_bench/codescan.py": "751e38001b6e65727a31e28172a0623f0bf34bc092a958037c286aa991a197ed", "exam_bench/codex.py": "c3f89d72af11f312d851c73a1610d92e79acadf336be9ccedd1f94ede3b3ccb0", "exam_bench/common.py": "8682603b519063e655eae3574a02a49efee63bde21f582ccee20ddd623fca96d", "exam_bench/docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "exam_bench/examiner.py": "d7294fdd23ed1732216cafebf0a8cf2c24cce4259859aeb7149f62b7607d087d", "exam_bench/finalize.py": "4034f1c63896a940afdb1a83d541cf47fc75c8b5061e3f839047109c04beb620", "exam_bench/forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "exam_bench/gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "exam_bench/grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "exam_bench/harness.py": "3040f6daaf1dc6e6583219f4d925151f8ba7851b2d5417d7f14645892b485ddf", "exam_bench/interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "exam_bench/interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "exam_bench/isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "exam_bench/ledger.py": "7e851523580e22d8490e75f9b6026c07f2c355007e0d11d0b252671f56bef654", "exam_bench/locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "exam_bench/materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "exam_bench/mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "exam_bench/observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "exam_bench/ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "exam_bench/penalties.py": "0d79e2e46102657dca00609b6abbfc0bf7d11fad41429564f876c82bc6b33269", "exam_bench/platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "exam_bench/portable.py": "cad56968ff407983608f5bdbc9ce7234128d7a4580b096ecea8e0e7b4edb9070", "exam_bench/portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "exam_bench/pr.py": "6a3a20caf0e10c0cc94410511a72d62c9fcda785f3abab1be2ad616d4ee16836", "exam_bench/preflight.py": "5619be0131d8641925f3ce2a3c8e5234d42aa5635d95676138ca81536d95cd29", "exam_bench/process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "exam_bench/queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "exam_bench/queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "exam_bench/replay_calibration.py": "c150457b0b23ce4e6814eb8deb4d48f6bc4a2e39d8f84a9dc7644fb99a026c2d", "exam_bench/report.py": "5e4c0757e1c7f189953f9a5302593ab726551835856baed25efd93dad6e8bfcd", "exam_bench/runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "exam_bench/smoke_check.py": "f36922a0027429ead0b414048dcc14bbe67f2f0e79a70d03dffbe1447d253545", "exam_bench/stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "exam_bench/submission.py": "ea862adc63ae67861ddb1d6aeb4d92c10b0b05004d22953f7b03612f82bb4bf4", "exam_bench/telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "exam_bench/windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "exam_bench/workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tools/build_public_site.py": "9682ed696f5ac9e9a82b65a45c0dece556ec7e49eeb20dcd616882cc534a8258", "tools/build_result_site.py": "3294e1d2ec1486058e208735264d61e349a68a4ae2fa2ec7a723c70e3263b496", "tools/check_native_harnesses.py": "4f5f0ed27651f78758eaef077b3b114361781f6b95ec40cb46c3fea689210473", "tools/check_native_toolkit.py": "0272794617121f2932828e5e4e9ae20095183c443666cf3ba466b44fbe875095", "tools/community_results.py": "788f4763fa97a2f6fe055a1ddea15cb918d2881327594931e508f9fbeb3dd13c", "tools/community_service.py": "c374480dbd88d656c0b9054fa04a8e1c6698c69e2f9cf475e82498a2dff61d84", "tools/community_setup.py": "5d7d126ed7d4dd48e1d79f57b99647a92ffcc8c9f80d90915e458888cdd76bf7", "tools/compare_harness_runs.py": "f274df5f3f804cb02504491aec946943833e12fbce6e62d281e12beb8508fc4e", "tools/create_run_plan.py": "871cd81b1eda231c0fba8805f63d2668926be9fc641559e6ddf320e2f47cd37a", "tools/demo_runner.py": "ca7ad17919c53d524cc0418751ba09a540f910eac183dca2961710bc30bba26f", "tools/installers.py": "9a2742780936b17500869e7c89202c1a2549e37d53a42ad9a50a0abbf78bbe09", "tools/machine_bundle.py": "8aa8346f99f537e81ceca6fb6ab9530e844954bab8eff87bf33d3602f81f8a30", "tools/prepare_native_harnesses.py": "aaa75ecf4022883984fa50c42d14d8e1a9fde2eeda03dab03b852bbc5efb2502", "tools/prepare_official_statement.py": "6b7028c78e90e798d6ef1a93b76520cc61a308c354fb9b87f7fad18b99800fad", "tools/prepare_open_exam_requirements.py": "544f4e378b9be5f166186f8788f8d454afdac2deb99d91d98421e39d01ba6d03", "tools/probe_harness.py": "1ed8ef93420d1484cbbfd151b7efc31b9a201ceb942dd05e3103efa22ffa7f27", "tools/probe_native_mcp.py": "9918d324129cba898993e07f8f8b6dbcbaf369398ebf28d464f9f1f00abdb254", "tools/readiness.py": "d34dd3f38334f51cc4574c79194cf0b80769b062a52382989a57d01c46b9aba4", "tools/recheck_community.py": "f0843d7d677f90da31e22bde0b1c86584dd46c022f1532d43d042619e426b230", "tools/regrade_runs.py": "011775afb06d3aac67a4aa81117a368c75896b0fcbe1e6f27ccc6237612fbf59", "tools/render_statement_text.py": "dabc0716a3612c288c671bc20e17fd4986691d732768e1e957d6dddddbea92a3", "tools/replay_calibration.py": "801f5004926c438c21ed3668fe2a4ddf45312b3e75320165a3839aae034eee9b", "tools/run_exam_campaign.py": "2c450d57a1cd0a2682838f5ec7c0a4ffb3aed0f1730d34c408e912d59cab6efd", "tools/serve_result_site.py": "86badfac863cd4ad1fc894a14110c75b28470513f0133eeae9d2799b8b4df3a9", "tools/start_demo.py": "c597e6cad28d245b3191654bb3e2801fa9dd2364e2acb25561923613717b615f", "tools/supplemental_acceptance.py": "c88fc39de1be1fdcacdd819e2ad329f60367b2df1d5deda80b37324bda3f2a01", "tools/sync_sources.py": "b51e889b0f41f9f63bfb19a09fb96d3777693d6b1d76fe0132bdd2a15e155898", "tools/validate_community_pr.py": "796b896dfade07b4529af2088a4b9b9d23484148b3bc0732b3fb837b75c9844b", "tools/verify_official_assessment_mapping.py": "daeb448a016940d5b6b1285979a56e5b9014bd91db40acb131445e4a83a23059", "tools/verify_task_package.py": "9e1e6105f6b5e4e78b36aa57f00117a9fbc8948ab53983c32ab56da88d23ccc4", "profiles/agents.json": "af9c492c08d13b3044aa6b6952589ed6a0a07d5258d8ff72bb18185b3eaebdc5", "profiles/ai-exam-execution-policy.json": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "profiles/bsl-analyzer-0.3.2-macos.json": "83537abdbf38c41ce665e4d0f24128bb51b62e971e0e0f368695f1326a7d2ffb", "profiles/bsl-analyzer-0.3.2-portable.json": "d6ba732e6778e256df34d6bc548593128820a70430c35b279796843606ee40a8", "profiles/bsl-ls-1.1.0-rc.6-macos.json": "245fc10747197e6911b2b4c77cdb15e6fa4eb7bc7c3758b63e768c5adf1df180", "profiles/bsl-ls-1.1.0-rc.6-portable.json": "9f10660881f2ec84794f7d584556b8f75c7e14b3555464af0ed0e60c4c892d86", "profiles/code-index-1.9.0-macos.json": "63a919523ce62ecec274f4c139bc7ad49a75dd4c339568b822cbc695b4e30408", "profiles/code-index-1.9.0-portable.json": "81106cee8f424ffd8a9dc46ecd8e4f57598fc1d49661a83c77b1f0507993fbdc", "profiles/codex-probe-plan.json": "166e41aad5fb3b27d9050bc6de952c6cba363cc6e804d4080568cc71a2a4d289", "profiles/machine.linux.example.json": "408304fd0581098d5d8110dc67dfeab353bc4d4030e32d37e6acf98d2b1aedfd", "profiles/machine.macos.example.json": "52e9f9d17797cb520b9d8955d6806fd550b899bed4da241ebf096dcb6a21a942", "profiles/machine.windows.example.json": "63accac9a2f81d47d03447efbabffd4760aee325193f02f46b9b29a28d50d2d8", "profiles/mcp-toolkit-1.9.0-macos.json": "1d3f9cde5ffa20589a840d01fdae03aa0fc2f412c929f064f203919c4129625b", "profiles/mcp-toolkit-1.9.0-portable.json": "8e370eebe773eef0e08045ee9c6d5be1451f769f65be0710834b262a4336e054", "profiles/none-macos.json": "b1401d9c48159aed3559006c7f6ace6ef4571224d5cf0bb76d1a823505a10056", "profiles/none-portable.json": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "profiles/rlm-tools-bsl-1.43.0-macos.json": "9354421052640ab60bc3e6aa98ff2e7ba9ca2318b0f4026c137487449242cbd2", "profiles/rlm-tools-bsl-1.43.0-portable.json": "2599e5645e0a7d4e44cb2934bc2b272cae79a9bf7ea74a23cd48aacea64bc424", "profiles/rlm-tools-bsl-1.43.0-posix-requirements.txt": "4fdf9a1bd994bf0272e65d231daf76cf19b0a34dad0ae6b50ec4f11a2ce4c330", "profiles/rlm-tools-bsl-1.43.0-windows-requirements.txt": "3730cb46c81cda5181ecd4485e98b11933104632358bc86f8c0eb1a612a8954f", "profiles/shirokov-skills-macos.json": "84f3e89091676884a802035c707e912762a1179425fb8e3faff25be736873cdb", "profiles/shirokov-skills-portable.json": "2b0a461e06602f1456410e70f02ceaa5ac32c6549c486660bcb5ace0c2f87b15", "profiles/shirokov-skills-windows-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/unica-0.12.3-macos.json": "2c39fbb591cf2c2c6e056373823615485397ea83651b7926c6f25a5fe6a0aae6", "profiles/unica-0.13.0-macos.json": "b76b5c8a4dd33f571c4a90993f1a2da5f7223b4f0f8e1042c282e21a66121052", "profiles/unica-0.14.0-rc.1-portable.json": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "rules/1c-specialist-platform/chistov.json": "77e04942f8c947b10759e7cc1eb31af05847d1711a772fbe6f23d525766757a9", "rules/1c-specialist-platform/decisions.json": "f622107423ce3c188c063318d7ab4f7718ceb38e443130677d8987f386641c09", "rules/1c-specialist-platform/examiner.json": "30353aa2a1b6545496b070d9066e9ffba0c3779e5b53ef70a4fd2cee375b18c0", "rules/1c-specialist-platform/ledger.json": "f167c10db2b5799dd9a1ea6a37cd2d7d186810dadf5ea2f50f26ae723c676882", "rules/1c-specialist-platform/rules.json": "1d320a4f8e1bf4701496388931f492315549bd3dce574b17285dd1d7f8652007", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" } } }, "conditions": { "client": "codex", "model": "gpt-6.1-sol", "client_version": "0.164.0", "reasoning_effort": "medium", "harness": "unica-0.14.0-rc.1", "billing_channel": "subscription", "solve_timeout_seconds": 3600, "time_series": null, "delegation": "native_disabled", "network_profile": "open-book_shell", "deadline_disclosed": true, "statement_sha256": "8a6ccb3e673826d1f8220fda53eb310e3ec18c136d87ce8f4cebb2a08614e7e5", "starter_dt_sha256": "f40d084818b0d1cfe503fc7653a6a13f1a8e47fcd1688dad6245b12744eb4638", "profile_sha256": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "execution_policy_sha256": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "calibration_sha256": "7a2c598d569ece652e72fdfb586af0b95d3c73bd3c467d024dd31f9bb27be403", "started_at": "2026-10-24T15:34:07.713973+00:00", "timing": { "prepare_ms": 6106, "solve_ms": 3510591, "grade_ms": null }, "original_submission_valid": false, "model_provenance": "requested_only", "tokens": { "input": 25305758, "cached_input": 24968320, "fresh_input": 337438, "output": 121307, "reasoning_output": 42088, "total": 25427065, "coverage": "reported_completed_root_turns" }, "tools": { "mcp_calls": 397, "unica_calls": 397, "failed_calls": 32 }, "process": { "status": "completed", "exit_code": 0, "stop_confirmed": true } }, "verification": "repository_owner", "download": "community-downloads/demo-20261025T153915Z-adapter--owner-2026-10-26T191909450942-0000/solution.zip", "source_context": "community-downloads/demo-20261025T153915Z-adapter--owner-2026-10-26T191909450942-0000/source-context.json", "regrade_required": [ { "id": "grader_changed", "files": [ "calibrate.py", "calibration_periodicity.py", "calibration_query.py", "common.py", "ou.py", "penalties.py", "queries.py", "replay_calibration.py", "rules/1c-specialist-platform/rules.json", "smoke_check.py", "tasks/1c-platform-official-sample/checks.json" ] } ], "grader_revision_sha256": "4a12b62d2c10085e1fc710f377f84903abdf2fb787dda19628d944da990a86b2", "archive_sha256": "186f7874229f078014705a8588fcae83542846bf17fd4f9a65b6da9baf286e30", "owner_verification": { "kind": "repository_owner", "repository": "zeegin/1c-agent-exam-benchmark", "operator": { "name": "Ingvar Vilkman", "github": "zeegin" }, "started_at": "2026-10-26T19:16:13.266229+00:00", "server": { "name": "Owner Windows stand", "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "hardware": { "cpu": "AMD Ryzen 7 5800X 8-Core Processor ", "logical_cpus": 4, "ram_bytes": 17109000192 }, "isolation": "dedicated-host" }, "platform_version": "8.3.27.2342", "grader": { "profile": "technical-v8", "commit": "5b6a28372b253e81e22b83f8559df897297e28ff", "working_tree_dirty": true, "fingerprint": { "assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "calibrate.py": "1c844971b4977fdcc3b30aebe8aad40fbd45e6828955b8deb043ac8573d61731", "calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "claude.py": "eedabc75fca0faa434f40a1624b71419ec7dc22e2854a0886cf84b4911db8372", "codescan.py": "6d8375210cef1fd768fc2d98d630d880b2993a9724f01ae25f33b4ea5aa9631d", "codex.py": "904e75503cd35f16cbb052f66806b3879fe25bfc9f99e33b93c889d862c46324", "common.py": "7696116dd1a796666518b4c5d2aa3cafa04ee974593d3636333cbe5385bd6ccb", "docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "examiner.py": "8cdffcdd52f043c905f896697403380af95bf485dd4a5edca24f7956e7795ffe", "forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "harness.py": "3cbb90fd3187e700b5df32e5daafb20313d49bb5721c826e3033cbc6aa6e3825", "interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "penalties.py": "b82704e7f47d3dfdf6e501452d7e0abca1f9da63307093d2e257e32358be0489", "platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "pr.py": "2b6bfea0634703469605ce114f9274716b485852d9a55d9185c39893b14e4726", "preflight.py": "448c3120ab64b625abae3891be686c7a214ce4211f7cf651fd90e12c0b298433", "process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "querytypes.py": "b645f489a2abc27762b4a9bbf4917e72f7b46dc053a74c0dca4a8fc46491b3ef", "replay_calibration.py": "3b6f3a289cc8a7f5e458f62bfa2c6cc534cc9076ba3f22d1e4bd8a5f9e175317", "runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "smoke_check.py": "bd6266367e6b769a95258eb383239b89a22deae406d64f6e142c77396f4639ba", "stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "submission.py": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tasks/1c-platform-official-sample/checks.json": "17a6fcc0c14410829650623eb1443ce99796e000cdfd19905ac0287988b73a00", "tasks/1c-platform-official-sample/private/official-assessment-mapping.json": "303587c0dabe77c1eeebb2017fe85539e3370b17c9090435e6e0325a66bd0644", "tasks/1c-platform-official-sample/private/owner-scoring-policy.json": "d26d534bb838ab1b5facb7bc033ca8ec40912133baadcdbad83b27fc577905f5", "starters/carcass-8.3.25.1445/starter.json": "0f7a7060885ba99a19402bfc6e63cc8fe979b0f491b040d3a01d5d21b304b3a6", "rules/1c-specialist-platform/rules.json": "7ec895a7751ef17f4a50cc80b5f7fa986e1e04360ab0b4ce9aa29115195df03c", "rules/1c-specialist-platform/examiner.json": "1247486ddd412d600db88d9c1db4ba501fc1994afd1dc2ebe85402fcc332f4c8", "rules/1c-specialist-platform/chistov.json": "800da27601a3f1c7ec1df64482fd4ad035e559ba0b390a274ed5031128487d3d", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" }, "sha256": "4a12b62d2c10085e1fc710f377f84903abdf2fb787dda19628d944da990a86b2" }, "identity_verified_at": "2026-10-26T18:44:22.364471+00:00", "identity_session_sha256": "950670ab9a82059c65525d0d6e5b8a00f0dc292581edea3eb087c4ecadeaab09", "completed_at": "2026-10-26T19:19:09.450942+00:00" } }, { "id": "demo-20261025T153915Z-adapter", "run_id": "demo-20261024T153359Z-bbf7c4", "result": { "run_id": "demo-20261024T153359Z-bbf7c4", "created_at": "2026-10-25T15:49:58.805177+00:00", "model": "gpt-6.1-sol", "harness": "unica-0.14.0-rc.1", "solve_seconds": 3511, "platform": "8.3.27.1688", "counts": { "pass": 65 }, "rules": [ { "id": "BU01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU16", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU17", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU02", "verdict": "pass", "coverage": "partial", "reason": null }, { "id": "BU10", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU12", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU06", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU07", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU08", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU09", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU11", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU14", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU15", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU13", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU15", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU16", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU17", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU02", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU18", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU14", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU06", "verdict": "pass", "coverage": "no_violation_found", "reason": null }, { "id": "OU07", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU08", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU09", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU10", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU11", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU12", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU13", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU19", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU20", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU21", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR02", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR06", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR07", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR08", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR09", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR10", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR11", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR12", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR13", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR14", "verdict": "pass", "coverage": "no_violation_found", "reason": null }, { "id": "PR15", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR16", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR17", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR18", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR19", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F02", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "G01", "verdict": "pass", "coverage": "static_sources", "reason": null }, { "id": "G02", "verdict": "pass", "coverage": "static_sources", "reason": null }, { "id": "G03", "verdict": "pass", "coverage": "static_sources", "reason": null } ], "charges": [ { "id": "F1C-PR09", "points": "0.5", "reason": "CommonModules/РасчетСервер/Ext/Module.bsl:114 — РегистрРасчета.Начисления.БазаНачисления: база получается без отбора по регистратору — по всем записям регистра" }, { "id": "F1C-GEN15", "points": "0.5", "reason": "Reports/ВедомостьПоПодразделению/Ext/ObjectModule.bsl:9 — РегистрНакопления.ОстаткиНоменклатуры.ОстаткиИОбороты: отбор по Подразделение, Свойство, индексы таблицы начинаются с Номенклатура" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "проводимые документы в режиме «Записывать модифицированные»: Операция, Сборка" }, { "id": "F1C-PR14", "points": "0.5", "reason": "после расчёта набор с периодом действия перезаписывается целиком, с пересчётом фактического периода действия (нужно Записать(, Истина)): CommonModules/РасчетСервер/Ext/Module.bsl:176 Пара.Значение.Записать()" }, { "id": "F1C-GEN20", "points": "2.0", "reason": "данные базы читаются в цикле по записям: CommonModules/ПроверкаРешения/Ext/Module.bsl:154; CommonModules/УчетСервер/Ext/Module.bsl:147; CommonModules/УчетСервер/Ext/Module.bsl:340" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "оперативное проведение разрешено у документов с движениями по регистрам расчёта: НачислениеЗарплаты" }, { "id": "F1C-GEN21", "points": "2.0", "reason": "данные графика без отбора по регистратору: CommonModules/РасчетСервер/Ext/Module.bsl:86" } ], "score_upper_bound": "-2.5", "score": null, "grade": "unsatisfactory", "deductions": "7.5", "not_assessed": 14, "gates": { "starter_origin": "passed", "load": "loaded", "clients": "compiles", "demo_data": "present" }, "infrastructure_errors": false, "comparison_eligible": false, "binding_compatibility": { "scope": "supplemental_named_subconto_adapter", "original_binding_sha256": "cef7b7992a8c61b4e62cdcc18e1df71ceb79fe3a47e1f347583b899afa4cebfd", "normalized_binding_sha256": "369380bc11c90ddc093e3fcad8b5d242d6305b64d6d1801f01f0f7e867fd5dbf", "normalizer_sha256": "7327277143d80a531e4c254ac74a9fc0e0d5c76572d53b8469e0a580eda17d65", "canonical_ledger_sha256": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "changes": [ { "field": "fields.ledger.item_debit", "before": "Номенклатура", "after": "ВидыСубконто.Номенклатура", "kind": "named" }, { "field": "fields.ledger.item_credit", "before": "Номенклатура", "after": "ВидыСубконто.Номенклатура", "kind": "named" }, { "field": "fields.ledger.warehouse_debit", "before": "Склад", "after": "ВидыСубконто.Склад", "kind": "named" }, { "field": "fields.ledger.warehouse_credit", "before": "Склад", "after": "ВидыСубконто.Склад", "kind": "named" } ], "basis": "kind names expanded only to exactly one predefined kind of the account chart on the role side; all role types checked." }, "evaluation_sha256": "1bd50cc68014af76ac04c4506e858c524749b344a01dfb67f221792114b28e8e", "downloads": [] }, "measurement": { "operator": { "name": "Vasiliy", "github": "Gh0sTspp" }, "environment": { "captured_at": "2026-10-24T15:34:00.710576+00:00", "capture_timing": "before_run", "hardware": { "cpu": "Intel(R) Core(TM) i7-5820K CPU @ 3.30GHz", "logical_cpus": 12, "ram_bytes": 34189709312 }, "os": { "system": "Windows", "release": "10", "version": "10.0.19045", "architecture": "AMD64" }, "python": "3.13.12", "platform_version": "8.3.27.1688", "isolation": "dedicated-host", "network_profile": "open-book_shell", "unsafe_action_protection_observed_in_user_config": true, "git_revision": "af85e791b303dbbf0b0b7af924d2489c3e57cfa8", "implementation_files": { "exam_bench/__init__.py": "ad5bf6f05dc6765f40b78bd186870ca2c49be113cfa33f8aa76f4926f2cb2c1e", "exam_bench/assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "exam_bench/bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "exam_bench/calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "exam_bench/calibrate.py": "78b5185cb0888c0c0ac3de95ffc3a80154a6de9ae66fc461f79d012e5a58e1db", "exam_bench/calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "exam_bench/calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "exam_bench/calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "exam_bench/calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "exam_bench/calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "exam_bench/claude.py": "bc1b8550de7573aaed5e39c6e9c0309e0d8175284a75490d61ec27439ed911ad", "exam_bench/cli.py": "1a37ce645633d761f7897dffc9c45e6b8b9600cd7bd233b1cbf78f49d26b099a", "exam_bench/codescan.py": "751e38001b6e65727a31e28172a0623f0bf34bc092a958037c286aa991a197ed", "exam_bench/codex.py": "c3f89d72af11f312d851c73a1610d92e79acadf336be9ccedd1f94ede3b3ccb0", "exam_bench/common.py": "8682603b519063e655eae3574a02a49efee63bde21f582ccee20ddd623fca96d", "exam_bench/docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "exam_bench/examiner.py": "d7294fdd23ed1732216cafebf0a8cf2c24cce4259859aeb7149f62b7607d087d", "exam_bench/finalize.py": "4034f1c63896a940afdb1a83d541cf47fc75c8b5061e3f839047109c04beb620", "exam_bench/forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "exam_bench/gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "exam_bench/grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "exam_bench/harness.py": "3040f6daaf1dc6e6583219f4d925151f8ba7851b2d5417d7f14645892b485ddf", "exam_bench/interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "exam_bench/interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "exam_bench/isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "exam_bench/ledger.py": "7e851523580e22d8490e75f9b6026c07f2c355007e0d11d0b252671f56bef654", "exam_bench/locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "exam_bench/materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "exam_bench/mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "exam_bench/observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "exam_bench/ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "exam_bench/penalties.py": "0d79e2e46102657dca00609b6abbfc0bf7d11fad41429564f876c82bc6b33269", "exam_bench/platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "exam_bench/portable.py": "cad56968ff407983608f5bdbc9ce7234128d7a4580b096ecea8e0e7b4edb9070", "exam_bench/portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "exam_bench/pr.py": "6a3a20caf0e10c0cc94410511a72d62c9fcda785f3abab1be2ad616d4ee16836", "exam_bench/preflight.py": "5619be0131d8641925f3ce2a3c8e5234d42aa5635d95676138ca81536d95cd29", "exam_bench/process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "exam_bench/queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "exam_bench/queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "exam_bench/replay_calibration.py": "c150457b0b23ce4e6814eb8deb4d48f6bc4a2e39d8f84a9dc7644fb99a026c2d", "exam_bench/report.py": "5e4c0757e1c7f189953f9a5302593ab726551835856baed25efd93dad6e8bfcd", "exam_bench/runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "exam_bench/smoke_check.py": "f36922a0027429ead0b414048dcc14bbe67f2f0e79a70d03dffbe1447d253545", "exam_bench/stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "exam_bench/submission.py": "ea862adc63ae67861ddb1d6aeb4d92c10b0b05004d22953f7b03612f82bb4bf4", "exam_bench/telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "exam_bench/windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "exam_bench/workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tools/build_public_site.py": "9682ed696f5ac9e9a82b65a45c0dece556ec7e49eeb20dcd616882cc534a8258", "tools/build_result_site.py": "3294e1d2ec1486058e208735264d61e349a68a4ae2fa2ec7a723c70e3263b496", "tools/check_native_harnesses.py": "4f5f0ed27651f78758eaef077b3b114361781f6b95ec40cb46c3fea689210473", "tools/check_native_toolkit.py": "0272794617121f2932828e5e4e9ae20095183c443666cf3ba466b44fbe875095", "tools/community_results.py": "788f4763fa97a2f6fe055a1ddea15cb918d2881327594931e508f9fbeb3dd13c", "tools/community_service.py": "c374480dbd88d656c0b9054fa04a8e1c6698c69e2f9cf475e82498a2dff61d84", "tools/community_setup.py": "5d7d126ed7d4dd48e1d79f57b99647a92ffcc8c9f80d90915e458888cdd76bf7", "tools/compare_harness_runs.py": "f274df5f3f804cb02504491aec946943833e12fbce6e62d281e12beb8508fc4e", "tools/create_run_plan.py": "871cd81b1eda231c0fba8805f63d2668926be9fc641559e6ddf320e2f47cd37a", "tools/demo_runner.py": "ca7ad17919c53d524cc0418751ba09a540f910eac183dca2961710bc30bba26f", "tools/installers.py": "9a2742780936b17500869e7c89202c1a2549e37d53a42ad9a50a0abbf78bbe09", "tools/machine_bundle.py": "8aa8346f99f537e81ceca6fb6ab9530e844954bab8eff87bf33d3602f81f8a30", "tools/prepare_native_harnesses.py": "aaa75ecf4022883984fa50c42d14d8e1a9fde2eeda03dab03b852bbc5efb2502", "tools/prepare_official_statement.py": "6b7028c78e90e798d6ef1a93b76520cc61a308c354fb9b87f7fad18b99800fad", "tools/prepare_open_exam_requirements.py": "544f4e378b9be5f166186f8788f8d454afdac2deb99d91d98421e39d01ba6d03", "tools/probe_harness.py": "1ed8ef93420d1484cbbfd151b7efc31b9a201ceb942dd05e3103efa22ffa7f27", "tools/probe_native_mcp.py": "9918d324129cba898993e07f8f8b6dbcbaf369398ebf28d464f9f1f00abdb254", "tools/readiness.py": "d34dd3f38334f51cc4574c79194cf0b80769b062a52382989a57d01c46b9aba4", "tools/recheck_community.py": "f0843d7d677f90da31e22bde0b1c86584dd46c022f1532d43d042619e426b230", "tools/regrade_runs.py": "011775afb06d3aac67a4aa81117a368c75896b0fcbe1e6f27ccc6237612fbf59", "tools/render_statement_text.py": "dabc0716a3612c288c671bc20e17fd4986691d732768e1e957d6dddddbea92a3", "tools/replay_calibration.py": "801f5004926c438c21ed3668fe2a4ddf45312b3e75320165a3839aae034eee9b", "tools/run_exam_campaign.py": "2c450d57a1cd0a2682838f5ec7c0a4ffb3aed0f1730d34c408e912d59cab6efd", "tools/serve_result_site.py": "86badfac863cd4ad1fc894a14110c75b28470513f0133eeae9d2799b8b4df3a9", "tools/start_demo.py": "c597e6cad28d245b3191654bb3e2801fa9dd2364e2acb25561923613717b615f", "tools/supplemental_acceptance.py": "c88fc39de1be1fdcacdd819e2ad329f60367b2df1d5deda80b37324bda3f2a01", "tools/sync_sources.py": "b51e889b0f41f9f63bfb19a09fb96d3777693d6b1d76fe0132bdd2a15e155898", "tools/validate_community_pr.py": "796b896dfade07b4529af2088a4b9b9d23484148b3bc0732b3fb837b75c9844b", "tools/verify_official_assessment_mapping.py": "daeb448a016940d5b6b1285979a56e5b9014bd91db40acb131445e4a83a23059", "tools/verify_task_package.py": "9e1e6105f6b5e4e78b36aa57f00117a9fbc8948ab53983c32ab56da88d23ccc4", "profiles/agents.json": "af9c492c08d13b3044aa6b6952589ed6a0a07d5258d8ff72bb18185b3eaebdc5", "profiles/ai-exam-execution-policy.json": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "profiles/bsl-analyzer-0.3.2-macos.json": "83537abdbf38c41ce665e4d0f24128bb51b62e971e0e0f368695f1326a7d2ffb", "profiles/bsl-analyzer-0.3.2-portable.json": "d6ba732e6778e256df34d6bc548593128820a70430c35b279796843606ee40a8", "profiles/bsl-ls-1.1.0-rc.6-macos.json": "245fc10747197e6911b2b4c77cdb15e6fa4eb7bc7c3758b63e768c5adf1df180", "profiles/bsl-ls-1.1.0-rc.6-portable.json": "9f10660881f2ec84794f7d584556b8f75c7e14b3555464af0ed0e60c4c892d86", "profiles/code-index-1.9.0-macos.json": "63a919523ce62ecec274f4c139bc7ad49a75dd4c339568b822cbc695b4e30408", "profiles/code-index-1.9.0-portable.json": "81106cee8f424ffd8a9dc46ecd8e4f57598fc1d49661a83c77b1f0507993fbdc", "profiles/codex-probe-plan.json": "166e41aad5fb3b27d9050bc6de952c6cba363cc6e804d4080568cc71a2a4d289", "profiles/machine.linux.example.json": "408304fd0581098d5d8110dc67dfeab353bc4d4030e32d37e6acf98d2b1aedfd", "profiles/machine.macos.example.json": "52e9f9d17797cb520b9d8955d6806fd550b899bed4da241ebf096dcb6a21a942", "profiles/machine.windows.example.json": "63accac9a2f81d47d03447efbabffd4760aee325193f02f46b9b29a28d50d2d8", "profiles/mcp-toolkit-1.9.0-macos.json": "1d3f9cde5ffa20589a840d01fdae03aa0fc2f412c929f064f203919c4129625b", "profiles/mcp-toolkit-1.9.0-portable.json": "8e370eebe773eef0e08045ee9c6d5be1451f769f65be0710834b262a4336e054", "profiles/none-macos.json": "b1401d9c48159aed3559006c7f6ace6ef4571224d5cf0bb76d1a823505a10056", "profiles/none-portable.json": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "profiles/rlm-tools-bsl-1.43.0-macos.json": "9354421052640ab60bc3e6aa98ff2e7ba9ca2318b0f4026c137487449242cbd2", "profiles/rlm-tools-bsl-1.43.0-portable.json": "2599e5645e0a7d4e44cb2934bc2b272cae79a9bf7ea74a23cd48aacea64bc424", "profiles/rlm-tools-bsl-1.43.0-posix-requirements.txt": "4fdf9a1bd994bf0272e65d231daf76cf19b0a34dad0ae6b50ec4f11a2ce4c330", "profiles/rlm-tools-bsl-1.43.0-windows-requirements.txt": "3730cb46c81cda5181ecd4485e98b11933104632358bc86f8c0eb1a612a8954f", "profiles/shirokov-skills-macos.json": "84f3e89091676884a802035c707e912762a1179425fb8e3faff25be736873cdb", "profiles/shirokov-skills-portable.json": "2b0a461e06602f1456410e70f02ceaa5ac32c6549c486660bcb5ace0c2f87b15", "profiles/shirokov-skills-windows-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/unica-0.12.3-macos.json": "2c39fbb591cf2c2c6e056373823615485397ea83651b7926c6f25a5fe6a0aae6", "profiles/unica-0.13.0-macos.json": "b76b5c8a4dd33f571c4a90993f1a2da5f7223b4f0f8e1042c282e21a66121052", "profiles/unica-0.14.0-rc.1-portable.json": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "rules/1c-specialist-platform/chistov.json": "77e04942f8c947b10759e7cc1eb31af05847d1711a772fbe6f23d525766757a9", "rules/1c-specialist-platform/decisions.json": "f622107423ce3c188c063318d7ab4f7718ceb38e443130677d8987f386641c09", "rules/1c-specialist-platform/examiner.json": "30353aa2a1b6545496b070d9066e9ffba0c3779e5b53ef70a4fd2cee375b18c0", "rules/1c-specialist-platform/ledger.json": "f167c10db2b5799dd9a1ea6a37cd2d7d186810dadf5ea2f50f26ae723c676882", "rules/1c-specialist-platform/rules.json": "1d320a4f8e1bf4701496388931f492315549bd3dce574b17285dd1d7f8652007", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" } } }, "conditions": { "client": "codex", "model": "gpt-6.1-sol", "client_version": "0.164.0", "reasoning_effort": "medium", "harness": "unica-0.14.0-rc.1", "billing_channel": "subscription", "solve_timeout_seconds": 3600, "time_series": null, "delegation": "native_disabled", "network_profile": "open-book_shell", "deadline_disclosed": true, "statement_sha256": "8a6ccb3e673826d1f8220fda53eb310e3ec18c136d87ce8f4cebb2a08614e7e5", "starter_dt_sha256": "f40d084818b0d1cfe503fc7653a6a13f1a8e47fcd1688dad6245b12744eb4638", "profile_sha256": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "execution_policy_sha256": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "calibration_sha256": "7a2c598d569ece652e72fdfb586af0b95d3c73bd3c467d024dd31f9bb27be403", "started_at": "2026-10-24T15:34:07.713973+00:00", "timing": { "prepare_ms": 6106, "solve_ms": 3510591, "grade_ms": null }, "original_submission_valid": false, "model_provenance": "requested_only", "tokens": { "input": 25305758, "cached_input": 24968320, "fresh_input": 337438, "output": 121307, "reasoning_output": 42088, "total": 25427065, "coverage": "reported_completed_root_turns" }, "tools": { "mcp_calls": 397, "unica_calls": 397, "failed_calls": 32 }, "process": { "status": "completed", "exit_code": 0, "stop_confirmed": true } }, "verification": "contributor_reported", "download": "community-downloads/demo-20261025T153915Z-adapter/solution.zip", "source_context": "community-downloads/demo-20261025T153915Z-adapter/source-context.json", "regrade_required": [ { "id": "grader_changed", "files": [ "assessment.py", "bp.py", "calcwrite.py", "calibrate.py", "calibration_periodicity.py", "calibration_query.py", "claude.py", "codescan.py", "codex.py", "common.py", "docx_text.py", "examiner.py", "harness.py", "interpretations.py", "locking.py", "materials.py", "mcp_toolkit.py", "ou.py", "penalties.py", "portable_harnesses.py", "pr.py", "preflight.py", "queries.py", "queryschema.py", "querytypes.py", "replay_calibration.py", "rules/1c-specialist-platform/chistov.json", "rules/1c-specialist-platform/examiner.json", "rules/1c-specialist-platform/rules.json", "rules/1c-specialist-platform/standards.json", "smoke_check.py", "starters/carcass-8.3.25.1445/starter.json", "stdio_harnesses.py", "tasks/1c-platform-official-sample/checks.json", "tasks/1c-platform-official-sample/private/official-assessment-mapping.json", "tasks/1c-platform-official-sample/private/owner-scoring-policy.json", "telemetry.py" ] } ], "grader_revision_sha256": "855d4f66db31ec9f50ebfc18f596c0d1d157e53e2830c51f853c1338f628e49c", "archive_sha256": "ce7918899ed346a39451c1a27dff06ebc01a7628e09848f13844462940eca28f" } ] }, { "id": "demo-20261025T154959Z-adapter--owner-2026-10-26T223340235303-0000", "run_id": "demo-20261024T203042Z-421bbf", "result": { "run_id": "demo-20261024T203042Z-421bbf", "created_at": "2026-10-26T22:33:40.235303+00:00", "model": "gpt-6-astra", "harness": "unica-0.14.0-rc.1", "solve_seconds": 4242, "platform": "8.3.27.1688", "counts": { "pass": 64, "fail": 1 }, "rules": [ { "id": "BU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU01.selected_fixture" }, { "id": "BU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU04.selected_fixture" }, { "id": "BU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU05.selected_fixture" }, { "id": "BU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU16.selected_fixture" }, { "id": "BU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU17.selected_fixture" }, { "id": "BU02", "verdict": "pass", "reason": null, "coverage": "partial", "assertion_id": "BU02.posting_cost_and_balance" }, { "id": "BU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU10.selected_fixture" }, { "id": "BU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU12.selected_fixture" }, { "id": "BU03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU03.selected_fixture" }, { "id": "BU06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU06.selected_fixture" }, { "id": "BU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU07.selected_fixture" }, { "id": "BU08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU08.selected_fixture" }, { "id": "BU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU09.selected_fixture" }, { "id": "BU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU11.selected_fixture" }, { "id": "BU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU14.selected_fixture" }, { "id": "BU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU15.selected_fixture" }, { "id": "BU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU13.selected_fixture" }, { "id": "OU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU15.selected_fixture" }, { "id": "OU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU16.selected_fixture" }, { "id": "OU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU17.selected_fixture" }, { "id": "OU02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU02.selected_fixture" }, { "id": "OU18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU18.selected_fixture" }, { "id": "OU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU14.selected_fixture" }, { "id": "OU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU01.selected_fixture" }, { "id": "OU03", "verdict": "pass", "reason": "История и годовая периодичность регистра подтверждены.", "coverage": "history_and_periodicity", "assertion_id": "OU03.selected_fixture" }, { "id": "OU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU05.selected_fixture" }, { "id": "OU06", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "OU06.selected_fixture" }, { "id": "OU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU07.selected_fixture" }, { "id": "OU08", "verdict": "pass", "reason": "История и дневная периодичность подтверждены; ограничение одной версии в неделю отдельно не проверяется.", "coverage": "history_and_periodicity", "assertion_id": "OU08.selected_fixture" }, { "id": "OU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU09.selected_fixture" }, { "id": "OU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU10.selected_fixture" }, { "id": "OU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU11.selected_fixture" }, { "id": "OU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU12.selected_fixture" }, { "id": "OU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU13.selected_fixture" }, { "id": "OU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU04.selected_fixture" }, { "id": "OU19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU19.selected_fixture" }, { "id": "OU20", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU20.selected_fixture" }, { "id": "OU21", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU21.selected_fixture" }, { "id": "PR01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR01.selected_fixture" }, { "id": "PR02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR02.selected_fixture" }, { "id": "PR03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR03.selected_fixture" }, { "id": "PR04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR04.selected_fixture" }, { "id": "PR05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR05.selected_fixture" }, { "id": "PR06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR06.selected_fixture" }, { "id": "PR07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR07.selected_fixture" }, { "id": "PR08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR08.selected_fixture" }, { "id": "PR09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR09.selected_fixture" }, { "id": "PR10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR10.selected_fixture" }, { "id": "PR11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR11.selected_fixture" }, { "id": "PR12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR12.selected_fixture" }, { "id": "PR13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR13.selected_fixture" }, { "id": "PR14", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "PR14.selected_fixture" }, { "id": "PR15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR15.selected_fixture" }, { "id": "PR16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR16.selected_fixture" }, { "id": "PR17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR17.selected_fixture" }, { "id": "PR18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR18.selected_fixture" }, { "id": "PR19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR19.selected_fixture" }, { "id": "F01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F01.selected_fixture" }, { "id": "F02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F02.selected_fixture" }, { "id": "F03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F03.selected_fixture" }, { "id": "F04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F04.selected_fixture" }, { "id": "F05", "verdict": "fail", "reason": "typed ['C1', 'C2'], written True, stored [('BENCH_Валюта', ''), ('BENCH_Срок', '')]", "coverage": "selected_fixture", "assertion_id": "F05.selected_fixture" }, { "id": "G01", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G01.static_sources" }, { "id": "G02", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G02.static_sources" }, { "id": "G03", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G03.static_sources" } ], "charges": [ { "id": "F1C-GEN01", "points": "0.5", "reason": "не выполнено требование: F05 — typed ['C1', 'C2'], written True, stored [('BENCH_Валюта', ''), ('BENCH_Срок', '')]" }, { "id": "F1C-GEN15", "points": "0.5", "reason": "Reports/ВедомостьПоПодразделению/Ext/ManagerModule.bsl:3 — РегистрНакопления.ОстаткиНоменклатуры.ОстаткиИОбороты: отбор по Подразделение, Свойство, индексы таблицы начинаются с Номенклатура" }, { "id": "F1C-GEN15", "points": "0.5", "reason": "Reports/ВедомостьПоПодразделению/Ext/ManagerModule.bsl:15 — РегистрНакопления.ОстаткиНоменклатуры.ОстаткиИОбороты: отбор по Подразделение, Свойство, индексы таблицы начинаются с Номенклатура" }, { "id": "F1C-GEN14", "points": "1.5", "reason": "Reports/ПродажиБухгалтерские/Ext/ManagerModule.bsl:2 — РегистрБухгалтерии.Управленческий: итоги считаются по основной таблице регистра, а не по виртуальной" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "проводимые документы в режиме «Записывать модифицированные»: Операция, Сборка" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "оперативное проведение разрешено у документов с движениями по регистрам расчёта: НачислениеЗарплаты" } ], "score_upper_bound": "0.0", "score": null, "grade": "unsatisfactory", "deductions": "5.0", "not_assessed": 16, "gates": { "starter_origin": "passed", "load": "loaded", "clients": "compiles", "demo_data": "present" }, "infrastructure_errors": false, "comparison_eligible": false, "binding_compatibility": { "scope": "supplemental_named_subconto_adapter", "original_binding_sha256": "0bcfa74167b76b733f0d2981e84334b84e16371f42ee5bcebc296739b83d8bd8", "normalized_binding_sha256": "ef7ab816d67a8f4d213f9e4f09ef42a4c96053d0ed56c8ebcbda30afbeae6a55", "normalizer_sha256": "7327277143d80a531e4c254ac74a9fc0e0d5c76572d53b8469e0a580eda17d65", "canonical_ledger_sha256": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "changes": [ { "field": "fields.ledger.item_debit", "before": "Номенклатура", "after": "ВидыСубконто.Номенклатура", "kind": "named" }, { "field": "fields.ledger.item_credit", "before": "Номенклатура", "after": "ВидыСубконто.Номенклатура", "kind": "named" }, { "field": "fields.ledger.warehouse_debit", "before": "Склады", "after": "ВидыСубконто.Склады", "kind": "named" }, { "field": "fields.ledger.warehouse_credit", "before": "Склады", "after": "ВидыСубконто.Склады", "kind": "named" } ], "basis": "kind names expanded only to exactly one predefined kind of the account chart on the role side; all role types checked." } }, "measurement": { "operator": { "name": "Vasiliy", "github": "Gh0sTspp" }, "environment": { "captured_at": "2026-10-24T20:30:43.917189+00:00", "capture_timing": "before_run", "hardware": { "cpu": "Intel(R) Core(TM) i7-5820K CPU @ 3.30GHz", "logical_cpus": 12, "ram_bytes": 34189709312 }, "os": { "system": "Windows", "release": "10", "version": "10.0.19045", "architecture": "AMD64" }, "python": "3.13.12", "platform_version": "8.3.27.1688", "isolation": "dedicated-host", "network_profile": "open-book_shell", "unsafe_action_protection_observed_in_user_config": true, "git_revision": "af85e791b303dbbf0b0b7af924d2489c3e57cfa8", "implementation_files": { "exam_bench/__init__.py": "ad5bf6f05dc6765f40b78bd186870ca2c49be113cfa33f8aa76f4926f2cb2c1e", "exam_bench/assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "exam_bench/bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "exam_bench/calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "exam_bench/calibrate.py": "78b5185cb0888c0c0ac3de95ffc3a80154a6de9ae66fc461f79d012e5a58e1db", "exam_bench/calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "exam_bench/calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "exam_bench/calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "exam_bench/calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "exam_bench/calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "exam_bench/claude.py": "bc1b8550de7573aaed5e39c6e9c0309e0d8175284a75490d61ec27439ed911ad", "exam_bench/cli.py": "1a37ce645633d761f7897dffc9c45e6b8b9600cd7bd233b1cbf78f49d26b099a", "exam_bench/codescan.py": "751e38001b6e65727a31e28172a0623f0bf34bc092a958037c286aa991a197ed", "exam_bench/codex.py": "c3f89d72af11f312d851c73a1610d92e79acadf336be9ccedd1f94ede3b3ccb0", "exam_bench/common.py": "8682603b519063e655eae3574a02a49efee63bde21f582ccee20ddd623fca96d", "exam_bench/docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "exam_bench/examiner.py": "d7294fdd23ed1732216cafebf0a8cf2c24cce4259859aeb7149f62b7607d087d", "exam_bench/finalize.py": "4034f1c63896a940afdb1a83d541cf47fc75c8b5061e3f839047109c04beb620", "exam_bench/forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "exam_bench/gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "exam_bench/grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "exam_bench/harness.py": "3040f6daaf1dc6e6583219f4d925151f8ba7851b2d5417d7f14645892b485ddf", "exam_bench/interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "exam_bench/interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "exam_bench/isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "exam_bench/ledger.py": "7e851523580e22d8490e75f9b6026c07f2c355007e0d11d0b252671f56bef654", "exam_bench/locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "exam_bench/materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "exam_bench/mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "exam_bench/observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "exam_bench/ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "exam_bench/penalties.py": "0d79e2e46102657dca00609b6abbfc0bf7d11fad41429564f876c82bc6b33269", "exam_bench/platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "exam_bench/portable.py": "cad56968ff407983608f5bdbc9ce7234128d7a4580b096ecea8e0e7b4edb9070", "exam_bench/portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "exam_bench/pr.py": "6a3a20caf0e10c0cc94410511a72d62c9fcda785f3abab1be2ad616d4ee16836", "exam_bench/preflight.py": "5619be0131d8641925f3ce2a3c8e5234d42aa5635d95676138ca81536d95cd29", "exam_bench/process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "exam_bench/queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "exam_bench/queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "exam_bench/replay_calibration.py": "c150457b0b23ce4e6814eb8deb4d48f6bc4a2e39d8f84a9dc7644fb99a026c2d", "exam_bench/report.py": "5e4c0757e1c7f189953f9a5302593ab726551835856baed25efd93dad6e8bfcd", "exam_bench/runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "exam_bench/smoke_check.py": "f36922a0027429ead0b414048dcc14bbe67f2f0e79a70d03dffbe1447d253545", "exam_bench/stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "exam_bench/submission.py": "ea862adc63ae67861ddb1d6aeb4d92c10b0b05004d22953f7b03612f82bb4bf4", "exam_bench/telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "exam_bench/windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "exam_bench/workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tools/build_public_site.py": "9682ed696f5ac9e9a82b65a45c0dece556ec7e49eeb20dcd616882cc534a8258", "tools/build_result_site.py": "3294e1d2ec1486058e208735264d61e349a68a4ae2fa2ec7a723c70e3263b496", "tools/check_native_harnesses.py": "4f5f0ed27651f78758eaef077b3b114361781f6b95ec40cb46c3fea689210473", "tools/check_native_toolkit.py": "0272794617121f2932828e5e4e9ae20095183c443666cf3ba466b44fbe875095", "tools/community_results.py": "788f4763fa97a2f6fe055a1ddea15cb918d2881327594931e508f9fbeb3dd13c", "tools/community_service.py": "c374480dbd88d656c0b9054fa04a8e1c6698c69e2f9cf475e82498a2dff61d84", "tools/community_setup.py": "5d7d126ed7d4dd48e1d79f57b99647a92ffcc8c9f80d90915e458888cdd76bf7", "tools/compare_harness_runs.py": "f274df5f3f804cb02504491aec946943833e12fbce6e62d281e12beb8508fc4e", "tools/create_run_plan.py": "871cd81b1eda231c0fba8805f63d2668926be9fc641559e6ddf320e2f47cd37a", "tools/demo_runner.py": "ca7ad17919c53d524cc0418751ba09a540f910eac183dca2961710bc30bba26f", "tools/installers.py": "9a2742780936b17500869e7c89202c1a2549e37d53a42ad9a50a0abbf78bbe09", "tools/machine_bundle.py": "8aa8346f99f537e81ceca6fb6ab9530e844954bab8eff87bf33d3602f81f8a30", "tools/prepare_native_harnesses.py": "aaa75ecf4022883984fa50c42d14d8e1a9fde2eeda03dab03b852bbc5efb2502", "tools/prepare_official_statement.py": "6b7028c78e90e798d6ef1a93b76520cc61a308c354fb9b87f7fad18b99800fad", "tools/prepare_open_exam_requirements.py": "544f4e378b9be5f166186f8788f8d454afdac2deb99d91d98421e39d01ba6d03", "tools/probe_harness.py": "1ed8ef93420d1484cbbfd151b7efc31b9a201ceb942dd05e3103efa22ffa7f27", "tools/probe_native_mcp.py": "9918d324129cba898993e07f8f8b6dbcbaf369398ebf28d464f9f1f00abdb254", "tools/readiness.py": "d34dd3f38334f51cc4574c79194cf0b80769b062a52382989a57d01c46b9aba4", "tools/recheck_community.py": "f0843d7d677f90da31e22bde0b1c86584dd46c022f1532d43d042619e426b230", "tools/regrade_runs.py": "011775afb06d3aac67a4aa81117a368c75896b0fcbe1e6f27ccc6237612fbf59", "tools/render_statement_text.py": "dabc0716a3612c288c671bc20e17fd4986691d732768e1e957d6dddddbea92a3", "tools/replay_calibration.py": "801f5004926c438c21ed3668fe2a4ddf45312b3e75320165a3839aae034eee9b", "tools/run_exam_campaign.py": "2c450d57a1cd0a2682838f5ec7c0a4ffb3aed0f1730d34c408e912d59cab6efd", "tools/serve_result_site.py": "86badfac863cd4ad1fc894a14110c75b28470513f0133eeae9d2799b8b4df3a9", "tools/start_demo.py": "c597e6cad28d245b3191654bb3e2801fa9dd2364e2acb25561923613717b615f", "tools/supplemental_acceptance.py": "c88fc39de1be1fdcacdd819e2ad329f60367b2df1d5deda80b37324bda3f2a01", "tools/sync_sources.py": "b51e889b0f41f9f63bfb19a09fb96d3777693d6b1d76fe0132bdd2a15e155898", "tools/validate_community_pr.py": "796b896dfade07b4529af2088a4b9b9d23484148b3bc0732b3fb837b75c9844b", "tools/verify_official_assessment_mapping.py": "daeb448a016940d5b6b1285979a56e5b9014bd91db40acb131445e4a83a23059", "tools/verify_task_package.py": "9e1e6105f6b5e4e78b36aa57f00117a9fbc8948ab53983c32ab56da88d23ccc4", "profiles/agents.json": "af9c492c08d13b3044aa6b6952589ed6a0a07d5258d8ff72bb18185b3eaebdc5", "profiles/ai-exam-execution-policy.json": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "profiles/bsl-analyzer-0.3.2-macos.json": "83537abdbf38c41ce665e4d0f24128bb51b62e971e0e0f368695f1326a7d2ffb", "profiles/bsl-analyzer-0.3.2-portable.json": "d6ba732e6778e256df34d6bc548593128820a70430c35b279796843606ee40a8", "profiles/bsl-ls-1.1.0-rc.6-macos.json": "245fc10747197e6911b2b4c77cdb15e6fa4eb7bc7c3758b63e768c5adf1df180", "profiles/bsl-ls-1.1.0-rc.6-portable.json": "9f10660881f2ec84794f7d584556b8f75c7e14b3555464af0ed0e60c4c892d86", "profiles/code-index-1.9.0-macos.json": "63a919523ce62ecec274f4c139bc7ad49a75dd4c339568b822cbc695b4e30408", "profiles/code-index-1.9.0-portable.json": "81106cee8f424ffd8a9dc46ecd8e4f57598fc1d49661a83c77b1f0507993fbdc", "profiles/codex-probe-plan.json": "166e41aad5fb3b27d9050bc6de952c6cba363cc6e804d4080568cc71a2a4d289", "profiles/machine.linux.example.json": "408304fd0581098d5d8110dc67dfeab353bc4d4030e32d37e6acf98d2b1aedfd", "profiles/machine.macos.example.json": "52e9f9d17797cb520b9d8955d6806fd550b899bed4da241ebf096dcb6a21a942", "profiles/machine.windows.example.json": "63accac9a2f81d47d03447efbabffd4760aee325193f02f46b9b29a28d50d2d8", "profiles/mcp-toolkit-1.9.0-macos.json": "1d3f9cde5ffa20589a840d01fdae03aa0fc2f412c929f064f203919c4129625b", "profiles/mcp-toolkit-1.9.0-portable.json": "8e370eebe773eef0e08045ee9c6d5be1451f769f65be0710834b262a4336e054", "profiles/none-macos.json": "b1401d9c48159aed3559006c7f6ace6ef4571224d5cf0bb76d1a823505a10056", "profiles/none-portable.json": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "profiles/rlm-tools-bsl-1.43.0-macos.json": "9354421052640ab60bc3e6aa98ff2e7ba9ca2318b0f4026c137487449242cbd2", "profiles/rlm-tools-bsl-1.43.0-portable.json": "2599e5645e0a7d4e44cb2934bc2b272cae79a9bf7ea74a23cd48aacea64bc424", "profiles/rlm-tools-bsl-1.43.0-posix-requirements.txt": "4fdf9a1bd994bf0272e65d231daf76cf19b0a34dad0ae6b50ec4f11a2ce4c330", "profiles/rlm-tools-bsl-1.43.0-windows-requirements.txt": "3730cb46c81cda5181ecd4485e98b11933104632358bc86f8c0eb1a612a8954f", "profiles/shirokov-skills-macos.json": "84f3e89091676884a802035c707e912762a1179425fb8e3faff25be736873cdb", "profiles/shirokov-skills-portable.json": "2b0a461e06602f1456410e70f02ceaa5ac32c6549c486660bcb5ace0c2f87b15", "profiles/shirokov-skills-windows-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/unica-0.12.3-macos.json": "2c39fbb591cf2c2c6e056373823615485397ea83651b7926c6f25a5fe6a0aae6", "profiles/unica-0.13.0-macos.json": "b76b5c8a4dd33f571c4a90993f1a2da5f7223b4f0f8e1042c282e21a66121052", "profiles/unica-0.14.0-rc.1-portable.json": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "rules/1c-specialist-platform/chistov.json": "77e04942f8c947b10759e7cc1eb31af05847d1711a772fbe6f23d525766757a9", "rules/1c-specialist-platform/decisions.json": "f622107423ce3c188c063318d7ab4f7718ceb38e443130677d8987f386641c09", "rules/1c-specialist-platform/examiner.json": "30353aa2a1b6545496b070d9066e9ffba0c3779e5b53ef70a4fd2cee375b18c0", "rules/1c-specialist-platform/ledger.json": "f167c10db2b5799dd9a1ea6a37cd2d7d186810dadf5ea2f50f26ae723c676882", "rules/1c-specialist-platform/rules.json": "1d320a4f8e1bf4701496388931f492315549bd3dce574b17285dd1d7f8652007", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" } } }, "conditions": { "client": "codex", "model": "gpt-6-astra", "client_version": "0.164.0", "reasoning_effort": "medium", "harness": "unica-0.14.0-rc.1", "billing_channel": "subscription", "solve_timeout_seconds": 7200, "time_series": null, "delegation": "native_disabled", "network_profile": "open-book_shell", "deadline_disclosed": true, "statement_sha256": "8a6ccb3e673826d1f8220fda53eb310e3ec18c136d87ce8f4cebb2a08614e7e5", "starter_dt_sha256": "f40d084818b0d1cfe503fc7653a6a13f1a8e47fcd1688dad6245b12744eb4638", "profile_sha256": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "execution_policy_sha256": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "calibration_sha256": "7a2c598d569ece652e72fdfb586af0b95d3c73bd3c467d024dd31f9bb27be403", "started_at": "2026-10-24T20:31:10.169432+00:00", "timing": { "prepare_ms": 24023, "solve_ms": 4241872, "grade_ms": null }, "original_submission_valid": false, "model_provenance": "requested_only", "tokens": { "input": 20399295, "cached_input": 20113664, "fresh_input": 285631, "output": 134781, "reasoning_output": 43182, "total": 20534076, "coverage": "reported_completed_root_turns" }, "tools": { "mcp_calls": 566, "unica_calls": 566, "failed_calls": 36 }, "process": { "status": "completed", "exit_code": 0, "stop_confirmed": true } }, "verification": "repository_owner", "download": "community-downloads/demo-20261025T154959Z-adapter--owner-2026-10-26T223340235303-0000/solution.zip", "source_context": "community-downloads/demo-20261025T154959Z-adapter--owner-2026-10-26T223340235303-0000/source-context.json", "regrade_required": [], "grader_revision_sha256": "9aee1ffe0e1d04f9158fbbbeed3a403a5f0550ad8a590d7a6394977590760e1a", "archive_sha256": "8a58231736dbaf622000d121c6e9bc3df118275267d1fa1bee64675c6d2e7c4d", "owner_verification": { "kind": "repository_owner", "repository": "zeegin/1c-agent-exam-benchmark", "operator": { "name": "Ingvar Vilkman", "github": "zeegin" }, "started_at": "2026-10-26T22:33:40.066463+00:00", "server": { "name": "Owner Windows stand", "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "hardware": { "cpu": "AMD Ryzen 7 5800X 8-Core Processor ", "logical_cpus": 4, "ram_bytes": 17109000192 }, "isolation": "dedicated-host" }, "platform_version": "8.3.27.2342", "grader": { "profile": "technical-v8", "commit": "e15c8ea80263c0b38baa3a1fc19611983270e8a7", "working_tree_dirty": false, "fingerprint": { "assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "calibrate.py": "aac127e03744907fd52ef149b88aa6d88a54a2b7497d56084484ee1b99e0da99", "calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "calibration_periodicity.py": "0b1953d7781e236467897cd2ed66705b75d9719353a2de60b36f2bbdfe799108", "calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "calibration_query.py": "3555b103cde8ea0519955cf52358d09223f5ab183a9df00533bdb48c89237a8c", "claude.py": "5bae98af6e2021e2718afa3a71ed04bee812deaae31a43d4e7324814139ccc82", "codescan.py": "6d8375210cef1fd768fc2d98d630d880b2993a9724f01ae25f33b4ea5aa9631d", "codex.py": "904e75503cd35f16cbb052f66806b3879fe25bfc9f99e33b93c889d862c46324", "common.py": "739b39e2bb9bdd4a571fc69df5843190cddcad094ef7e68964061bc1266b20dc", "docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "examiner.py": "8cdffcdd52f043c905f896697403380af95bf485dd4a5edca24f7956e7795ffe", "forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "harness.py": "3cbb90fd3187e700b5df32e5daafb20313d49bb5721c826e3033cbc6aa6e3825", "interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "ou.py": "f62784b54a3f85576a078a2ff1908c9395f3159e55f6bb5b1a3c564392241abe", "penalties.py": "ae388cb8953ecca1f2370a7c4cb1db3b6cc8318fc2a7563a4db15f9f5b057429", "platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "pr.py": "2b6bfea0634703469605ce114f9274716b485852d9a55d9185c39893b14e4726", "preflight.py": "448c3120ab64b625abae3891be686c7a214ce4211f7cf651fd90e12c0b298433", "process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "queries.py": "1ef57e292db3e8967a733948371ecc542f743b811890d4fc509df17303b9c4ac", "queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "querytypes.py": "b645f489a2abc27762b4a9bbf4917e72f7b46dc053a74c0dca4a8fc46491b3ef", "replay_calibration.py": "e0e3d5ca6416934715b9735aa516046b8d19ad4ae690220eeacd96b198a5f86c", "runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "smoke_check.py": "7837e980986bcb54dc8bc1dfb5d0003deef11e05f6e11df3910fa509e1f74c8d", "stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "submission.py": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tasks/1c-platform-official-sample/checks.json": "7447a9b42d3e348d29d07f001cfb6bd269acd953b7117eba7cca2ce9f5a9a60d", "tasks/1c-platform-official-sample/private/official-assessment-mapping.json": "303587c0dabe77c1eeebb2017fe85539e3370b17c9090435e6e0325a66bd0644", "tasks/1c-platform-official-sample/private/owner-scoring-policy.json": "d26d534bb838ab1b5facb7bc033ca8ec40912133baadcdbad83b27fc577905f5", "starters/carcass-8.3.25.1445/starter.json": "0f7a7060885ba99a19402bfc6e63cc8fe979b0f491b040d3a01d5d21b304b3a6", "rules/1c-specialist-platform/rules.json": "ea75e34ace5de11ba3de403c63cd2c026db81d1d991f8531e4a779d4ce9788e7", "rules/1c-specialist-platform/examiner.json": "1247486ddd412d600db88d9c1db4ba501fc1994afd1dc2ebe85402fcc332f4c8", "rules/1c-specialist-platform/chistov.json": "800da27601a3f1c7ec1df64482fd4ad035e559ba0b390a274ed5031128487d3d", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" }, "sha256": "9aee1ffe0e1d04f9158fbbbeed3a403a5f0550ad8a590d7a6394977590760e1a" }, "method": "saved_platform_observations", "outcome": "complete", "completed_at": "2026-10-26T22:33:40.235303+00:00" }, "previous_evaluations": [ { "id": "demo-20261025T154959Z-adapter--owner-2026-10-26T214420434620-0000", "run_id": "demo-20261024T203042Z-421bbf", "result": { "run_id": "demo-20261024T203042Z-421bbf", "created_at": "2026-10-26T21:44:20.434620+00:00", "model": "gpt-6-astra", "harness": "unica-0.14.0-rc.1", "solve_seconds": 4242, "platform": "8.3.27.1688", "counts": { "pass": 64, "fail": 1 }, "rules": [ { "id": "BU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU01.selected_fixture" }, { "id": "BU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU04.selected_fixture" }, { "id": "BU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU05.selected_fixture" }, { "id": "BU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU16.selected_fixture" }, { "id": "BU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU17.selected_fixture" }, { "id": "BU02", "verdict": "pass", "reason": null, "coverage": "partial", "assertion_id": "BU02.posting_cost_and_balance" }, { "id": "BU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU10.selected_fixture" }, { "id": "BU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU12.selected_fixture" }, { "id": "BU03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU03.selected_fixture" }, { "id": "BU06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU06.selected_fixture" }, { "id": "BU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU07.selected_fixture" }, { "id": "BU08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU08.selected_fixture" }, { "id": "BU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU09.selected_fixture" }, { "id": "BU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU11.selected_fixture" }, { "id": "BU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU14.selected_fixture" }, { "id": "BU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU15.selected_fixture" }, { "id": "BU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU13.selected_fixture" }, { "id": "OU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU15.selected_fixture" }, { "id": "OU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU16.selected_fixture" }, { "id": "OU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU17.selected_fixture" }, { "id": "OU02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU02.selected_fixture" }, { "id": "OU18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU18.selected_fixture" }, { "id": "OU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU14.selected_fixture" }, { "id": "OU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU01.selected_fixture" }, { "id": "OU03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU03.selected_fixture" }, { "id": "OU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU05.selected_fixture" }, { "id": "OU06", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "OU06.selected_fixture" }, { "id": "OU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU07.selected_fixture" }, { "id": "OU08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU08.selected_fixture" }, { "id": "OU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU09.selected_fixture" }, { "id": "OU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU10.selected_fixture" }, { "id": "OU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU11.selected_fixture" }, { "id": "OU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU12.selected_fixture" }, { "id": "OU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU13.selected_fixture" }, { "id": "OU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU04.selected_fixture" }, { "id": "OU19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU19.selected_fixture" }, { "id": "OU20", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU20.selected_fixture" }, { "id": "OU21", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU21.selected_fixture" }, { "id": "PR01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR01.selected_fixture" }, { "id": "PR02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR02.selected_fixture" }, { "id": "PR03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR03.selected_fixture" }, { "id": "PR04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR04.selected_fixture" }, { "id": "PR05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR05.selected_fixture" }, { "id": "PR06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR06.selected_fixture" }, { "id": "PR07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR07.selected_fixture" }, { "id": "PR08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR08.selected_fixture" }, { "id": "PR09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR09.selected_fixture" }, { "id": "PR10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR10.selected_fixture" }, { "id": "PR11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR11.selected_fixture" }, { "id": "PR12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR12.selected_fixture" }, { "id": "PR13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR13.selected_fixture" }, { "id": "PR14", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "PR14.selected_fixture" }, { "id": "PR15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR15.selected_fixture" }, { "id": "PR16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR16.selected_fixture" }, { "id": "PR17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR17.selected_fixture" }, { "id": "PR18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR18.selected_fixture" }, { "id": "PR19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR19.selected_fixture" }, { "id": "F01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F01.selected_fixture" }, { "id": "F02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F02.selected_fixture" }, { "id": "F03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F03.selected_fixture" }, { "id": "F04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F04.selected_fixture" }, { "id": "F05", "verdict": "fail", "reason": "typed ['C1', 'C2'], written True, stored [('BENCH_Валюта', ''), ('BENCH_Срок', '')]", "coverage": "selected_fixture", "assertion_id": "F05.selected_fixture" }, { "id": "G01", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G01.static_sources" }, { "id": "G02", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G02.static_sources" }, { "id": "G03", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G03.static_sources" } ], "charges": [ { "id": "F1C-GEN01", "points": "0.5", "reason": "не выполнено требование: F05 — typed ['C1', 'C2'], written True, stored [('BENCH_Валюта', ''), ('BENCH_Срок', '')]" }, { "id": "F1C-GEN15", "points": "0.5", "reason": "Reports/ВедомостьПоПодразделению/Ext/ManagerModule.bsl:3 — РегистрНакопления.ОстаткиНоменклатуры.ОстаткиИОбороты: отбор по Подразделение, Свойство, индексы таблицы начинаются с Номенклатура" }, { "id": "F1C-GEN15", "points": "0.5", "reason": "Reports/ВедомостьПоПодразделению/Ext/ManagerModule.bsl:15 — РегистрНакопления.ОстаткиНоменклатуры.ОстаткиИОбороты: отбор по Подразделение, Свойство, индексы таблицы начинаются с Номенклатура" }, { "id": "F1C-GEN14", "points": "1.5", "reason": "Reports/ПродажиБухгалтерские/Ext/ManagerModule.bsl:2 — РегистрБухгалтерии.Управленческий: итоги считаются по основной таблице регистра, а не по виртуальной" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "проводимые документы в режиме «Записывать модифицированные»: Операция, Сборка" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "оперативное проведение разрешено у документов с движениями по регистрам расчёта: НачислениеЗарплаты" } ], "score_upper_bound": "0.0", "score": null, "grade": "unsatisfactory", "deductions": "5.0", "not_assessed": 16, "gates": { "starter_origin": "passed", "load": "loaded", "clients": "compiles", "demo_data": "present" }, "infrastructure_errors": false, "comparison_eligible": false, "binding_compatibility": { "scope": "supplemental_named_subconto_adapter", "original_binding_sha256": "0bcfa74167b76b733f0d2981e84334b84e16371f42ee5bcebc296739b83d8bd8", "normalized_binding_sha256": "ef7ab816d67a8f4d213f9e4f09ef42a4c96053d0ed56c8ebcbda30afbeae6a55", "normalizer_sha256": "7327277143d80a531e4c254ac74a9fc0e0d5c76572d53b8469e0a580eda17d65", "canonical_ledger_sha256": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "changes": [ { "field": "fields.ledger.item_debit", "before": "Номенклатура", "after": "ВидыСубконто.Номенклатура", "kind": "named" }, { "field": "fields.ledger.item_credit", "before": "Номенклатура", "after": "ВидыСубконто.Номенклатура", "kind": "named" }, { "field": "fields.ledger.warehouse_debit", "before": "Склады", "after": "ВидыСубконто.Склады", "kind": "named" }, { "field": "fields.ledger.warehouse_credit", "before": "Склады", "after": "ВидыСубконто.Склады", "kind": "named" } ], "basis": "kind names expanded only to exactly one predefined kind of the account chart on the role side; all role types checked." } }, "measurement": { "operator": { "name": "Vasiliy", "github": "Gh0sTspp" }, "environment": { "captured_at": "2026-10-24T20:30:43.917189+00:00", "capture_timing": "before_run", "hardware": { "cpu": "Intel(R) Core(TM) i7-5820K CPU @ 3.30GHz", "logical_cpus": 12, "ram_bytes": 34189709312 }, "os": { "system": "Windows", "release": "10", "version": "10.0.19045", "architecture": "AMD64" }, "python": "3.13.12", "platform_version": "8.3.27.1688", "isolation": "dedicated-host", "network_profile": "open-book_shell", "unsafe_action_protection_observed_in_user_config": true, "git_revision": "af85e791b303dbbf0b0b7af924d2489c3e57cfa8", "implementation_files": { "exam_bench/__init__.py": "ad5bf6f05dc6765f40b78bd186870ca2c49be113cfa33f8aa76f4926f2cb2c1e", "exam_bench/assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "exam_bench/bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "exam_bench/calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "exam_bench/calibrate.py": "78b5185cb0888c0c0ac3de95ffc3a80154a6de9ae66fc461f79d012e5a58e1db", "exam_bench/calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "exam_bench/calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "exam_bench/calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "exam_bench/calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "exam_bench/calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "exam_bench/claude.py": "bc1b8550de7573aaed5e39c6e9c0309e0d8175284a75490d61ec27439ed911ad", "exam_bench/cli.py": "1a37ce645633d761f7897dffc9c45e6b8b9600cd7bd233b1cbf78f49d26b099a", "exam_bench/codescan.py": "751e38001b6e65727a31e28172a0623f0bf34bc092a958037c286aa991a197ed", "exam_bench/codex.py": "c3f89d72af11f312d851c73a1610d92e79acadf336be9ccedd1f94ede3b3ccb0", "exam_bench/common.py": "8682603b519063e655eae3574a02a49efee63bde21f582ccee20ddd623fca96d", "exam_bench/docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "exam_bench/examiner.py": "d7294fdd23ed1732216cafebf0a8cf2c24cce4259859aeb7149f62b7607d087d", "exam_bench/finalize.py": "4034f1c63896a940afdb1a83d541cf47fc75c8b5061e3f839047109c04beb620", "exam_bench/forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "exam_bench/gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "exam_bench/grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "exam_bench/harness.py": "3040f6daaf1dc6e6583219f4d925151f8ba7851b2d5417d7f14645892b485ddf", "exam_bench/interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "exam_bench/interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "exam_bench/isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "exam_bench/ledger.py": "7e851523580e22d8490e75f9b6026c07f2c355007e0d11d0b252671f56bef654", "exam_bench/locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "exam_bench/materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "exam_bench/mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "exam_bench/observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "exam_bench/ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "exam_bench/penalties.py": "0d79e2e46102657dca00609b6abbfc0bf7d11fad41429564f876c82bc6b33269", "exam_bench/platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "exam_bench/portable.py": "cad56968ff407983608f5bdbc9ce7234128d7a4580b096ecea8e0e7b4edb9070", "exam_bench/portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "exam_bench/pr.py": "6a3a20caf0e10c0cc94410511a72d62c9fcda785f3abab1be2ad616d4ee16836", "exam_bench/preflight.py": "5619be0131d8641925f3ce2a3c8e5234d42aa5635d95676138ca81536d95cd29", "exam_bench/process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "exam_bench/queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "exam_bench/queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "exam_bench/replay_calibration.py": "c150457b0b23ce4e6814eb8deb4d48f6bc4a2e39d8f84a9dc7644fb99a026c2d", "exam_bench/report.py": "5e4c0757e1c7f189953f9a5302593ab726551835856baed25efd93dad6e8bfcd", "exam_bench/runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "exam_bench/smoke_check.py": "f36922a0027429ead0b414048dcc14bbe67f2f0e79a70d03dffbe1447d253545", "exam_bench/stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "exam_bench/submission.py": "ea862adc63ae67861ddb1d6aeb4d92c10b0b05004d22953f7b03612f82bb4bf4", "exam_bench/telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "exam_bench/windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "exam_bench/workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tools/build_public_site.py": "9682ed696f5ac9e9a82b65a45c0dece556ec7e49eeb20dcd616882cc534a8258", "tools/build_result_site.py": "3294e1d2ec1486058e208735264d61e349a68a4ae2fa2ec7a723c70e3263b496", "tools/check_native_harnesses.py": "4f5f0ed27651f78758eaef077b3b114361781f6b95ec40cb46c3fea689210473", "tools/check_native_toolkit.py": "0272794617121f2932828e5e4e9ae20095183c443666cf3ba466b44fbe875095", "tools/community_results.py": "788f4763fa97a2f6fe055a1ddea15cb918d2881327594931e508f9fbeb3dd13c", "tools/community_service.py": "c374480dbd88d656c0b9054fa04a8e1c6698c69e2f9cf475e82498a2dff61d84", "tools/community_setup.py": "5d7d126ed7d4dd48e1d79f57b99647a92ffcc8c9f80d90915e458888cdd76bf7", "tools/compare_harness_runs.py": "f274df5f3f804cb02504491aec946943833e12fbce6e62d281e12beb8508fc4e", "tools/create_run_plan.py": "871cd81b1eda231c0fba8805f63d2668926be9fc641559e6ddf320e2f47cd37a", "tools/demo_runner.py": "ca7ad17919c53d524cc0418751ba09a540f910eac183dca2961710bc30bba26f", "tools/installers.py": "9a2742780936b17500869e7c89202c1a2549e37d53a42ad9a50a0abbf78bbe09", "tools/machine_bundle.py": "8aa8346f99f537e81ceca6fb6ab9530e844954bab8eff87bf33d3602f81f8a30", "tools/prepare_native_harnesses.py": "aaa75ecf4022883984fa50c42d14d8e1a9fde2eeda03dab03b852bbc5efb2502", "tools/prepare_official_statement.py": "6b7028c78e90e798d6ef1a93b76520cc61a308c354fb9b87f7fad18b99800fad", "tools/prepare_open_exam_requirements.py": "544f4e378b9be5f166186f8788f8d454afdac2deb99d91d98421e39d01ba6d03", "tools/probe_harness.py": "1ed8ef93420d1484cbbfd151b7efc31b9a201ceb942dd05e3103efa22ffa7f27", "tools/probe_native_mcp.py": "9918d324129cba898993e07f8f8b6dbcbaf369398ebf28d464f9f1f00abdb254", "tools/readiness.py": "d34dd3f38334f51cc4574c79194cf0b80769b062a52382989a57d01c46b9aba4", "tools/recheck_community.py": "f0843d7d677f90da31e22bde0b1c86584dd46c022f1532d43d042619e426b230", "tools/regrade_runs.py": "011775afb06d3aac67a4aa81117a368c75896b0fcbe1e6f27ccc6237612fbf59", "tools/render_statement_text.py": "dabc0716a3612c288c671bc20e17fd4986691d732768e1e957d6dddddbea92a3", "tools/replay_calibration.py": "801f5004926c438c21ed3668fe2a4ddf45312b3e75320165a3839aae034eee9b", "tools/run_exam_campaign.py": "2c450d57a1cd0a2682838f5ec7c0a4ffb3aed0f1730d34c408e912d59cab6efd", "tools/serve_result_site.py": "86badfac863cd4ad1fc894a14110c75b28470513f0133eeae9d2799b8b4df3a9", "tools/start_demo.py": "c597e6cad28d245b3191654bb3e2801fa9dd2364e2acb25561923613717b615f", "tools/supplemental_acceptance.py": "c88fc39de1be1fdcacdd819e2ad329f60367b2df1d5deda80b37324bda3f2a01", "tools/sync_sources.py": "b51e889b0f41f9f63bfb19a09fb96d3777693d6b1d76fe0132bdd2a15e155898", "tools/validate_community_pr.py": "796b896dfade07b4529af2088a4b9b9d23484148b3bc0732b3fb837b75c9844b", "tools/verify_official_assessment_mapping.py": "daeb448a016940d5b6b1285979a56e5b9014bd91db40acb131445e4a83a23059", "tools/verify_task_package.py": "9e1e6105f6b5e4e78b36aa57f00117a9fbc8948ab53983c32ab56da88d23ccc4", "profiles/agents.json": "af9c492c08d13b3044aa6b6952589ed6a0a07d5258d8ff72bb18185b3eaebdc5", "profiles/ai-exam-execution-policy.json": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "profiles/bsl-analyzer-0.3.2-macos.json": "83537abdbf38c41ce665e4d0f24128bb51b62e971e0e0f368695f1326a7d2ffb", "profiles/bsl-analyzer-0.3.2-portable.json": "d6ba732e6778e256df34d6bc548593128820a70430c35b279796843606ee40a8", "profiles/bsl-ls-1.1.0-rc.6-macos.json": "245fc10747197e6911b2b4c77cdb15e6fa4eb7bc7c3758b63e768c5adf1df180", "profiles/bsl-ls-1.1.0-rc.6-portable.json": "9f10660881f2ec84794f7d584556b8f75c7e14b3555464af0ed0e60c4c892d86", "profiles/code-index-1.9.0-macos.json": "63a919523ce62ecec274f4c139bc7ad49a75dd4c339568b822cbc695b4e30408", "profiles/code-index-1.9.0-portable.json": "81106cee8f424ffd8a9dc46ecd8e4f57598fc1d49661a83c77b1f0507993fbdc", "profiles/codex-probe-plan.json": "166e41aad5fb3b27d9050bc6de952c6cba363cc6e804d4080568cc71a2a4d289", "profiles/machine.linux.example.json": "408304fd0581098d5d8110dc67dfeab353bc4d4030e32d37e6acf98d2b1aedfd", "profiles/machine.macos.example.json": "52e9f9d17797cb520b9d8955d6806fd550b899bed4da241ebf096dcb6a21a942", "profiles/machine.windows.example.json": "63accac9a2f81d47d03447efbabffd4760aee325193f02f46b9b29a28d50d2d8", "profiles/mcp-toolkit-1.9.0-macos.json": "1d3f9cde5ffa20589a840d01fdae03aa0fc2f412c929f064f203919c4129625b", "profiles/mcp-toolkit-1.9.0-portable.json": "8e370eebe773eef0e08045ee9c6d5be1451f769f65be0710834b262a4336e054", "profiles/none-macos.json": "b1401d9c48159aed3559006c7f6ace6ef4571224d5cf0bb76d1a823505a10056", "profiles/none-portable.json": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "profiles/rlm-tools-bsl-1.43.0-macos.json": "9354421052640ab60bc3e6aa98ff2e7ba9ca2318b0f4026c137487449242cbd2", "profiles/rlm-tools-bsl-1.43.0-portable.json": "2599e5645e0a7d4e44cb2934bc2b272cae79a9bf7ea74a23cd48aacea64bc424", "profiles/rlm-tools-bsl-1.43.0-posix-requirements.txt": "4fdf9a1bd994bf0272e65d231daf76cf19b0a34dad0ae6b50ec4f11a2ce4c330", "profiles/rlm-tools-bsl-1.43.0-windows-requirements.txt": "3730cb46c81cda5181ecd4485e98b11933104632358bc86f8c0eb1a612a8954f", "profiles/shirokov-skills-macos.json": "84f3e89091676884a802035c707e912762a1179425fb8e3faff25be736873cdb", "profiles/shirokov-skills-portable.json": "2b0a461e06602f1456410e70f02ceaa5ac32c6549c486660bcb5ace0c2f87b15", "profiles/shirokov-skills-windows-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/unica-0.12.3-macos.json": "2c39fbb591cf2c2c6e056373823615485397ea83651b7926c6f25a5fe6a0aae6", "profiles/unica-0.13.0-macos.json": "b76b5c8a4dd33f571c4a90993f1a2da5f7223b4f0f8e1042c282e21a66121052", "profiles/unica-0.14.0-rc.1-portable.json": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "rules/1c-specialist-platform/chistov.json": "77e04942f8c947b10759e7cc1eb31af05847d1711a772fbe6f23d525766757a9", "rules/1c-specialist-platform/decisions.json": "f622107423ce3c188c063318d7ab4f7718ceb38e443130677d8987f386641c09", "rules/1c-specialist-platform/examiner.json": "30353aa2a1b6545496b070d9066e9ffba0c3779e5b53ef70a4fd2cee375b18c0", "rules/1c-specialist-platform/ledger.json": "f167c10db2b5799dd9a1ea6a37cd2d7d186810dadf5ea2f50f26ae723c676882", "rules/1c-specialist-platform/rules.json": "1d320a4f8e1bf4701496388931f492315549bd3dce574b17285dd1d7f8652007", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" } } }, "conditions": { "client": "codex", "model": "gpt-6-astra", "client_version": "0.164.0", "reasoning_effort": "medium", "harness": "unica-0.14.0-rc.1", "billing_channel": "subscription", "solve_timeout_seconds": 7200, "time_series": null, "delegation": "native_disabled", "network_profile": "open-book_shell", "deadline_disclosed": true, "statement_sha256": "8a6ccb3e673826d1f8220fda53eb310e3ec18c136d87ce8f4cebb2a08614e7e5", "starter_dt_sha256": "f40d084818b0d1cfe503fc7653a6a13f1a8e47fcd1688dad6245b12744eb4638", "profile_sha256": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "execution_policy_sha256": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "calibration_sha256": "7a2c598d569ece652e72fdfb586af0b95d3c73bd3c467d024dd31f9bb27be403", "started_at": "2026-10-24T20:31:10.169432+00:00", "timing": { "prepare_ms": 24023, "solve_ms": 4241872, "grade_ms": null }, "original_submission_valid": false, "model_provenance": "requested_only", "tokens": { "input": 20399295, "cached_input": 20113664, "fresh_input": 285631, "output": 134781, "reasoning_output": 43182, "total": 20534076, "coverage": "reported_completed_root_turns" }, "tools": { "mcp_calls": 566, "unica_calls": 566, "failed_calls": 36 }, "process": { "status": "completed", "exit_code": 0, "stop_confirmed": true } }, "verification": "repository_owner", "download": "community-downloads/demo-20261025T154959Z-adapter--owner-2026-10-26T214420434620-0000/solution.zip", "source_context": "community-downloads/demo-20261025T154959Z-adapter--owner-2026-10-26T214420434620-0000/source-context.json", "regrade_required": [ { "id": "grader_changed", "files": [ "calibrate.py", "calibration_periodicity.py", "common.py", "ou.py", "replay_calibration.py", "smoke_check.py", "tasks/1c-platform-official-sample/checks.json" ] } ], "grader_revision_sha256": "349d87e0c7f531acbe35dd2b39c35722d8a877fedde97575b49e8466ab763c1d", "archive_sha256": "7c355c9970a7e71378178f644cd20a4ebac530b8772fc82493ba0d6cf28002b8", "owner_verification": { "kind": "repository_owner", "repository": "zeegin/1c-agent-exam-benchmark", "operator": { "name": "Ingvar Vilkman", "github": "zeegin" }, "started_at": "2026-10-26T21:44:20.257114+00:00", "server": { "name": "Owner Windows stand", "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "hardware": { "cpu": "AMD Ryzen 7 5800X 8-Core Processor ", "logical_cpus": 4, "ram_bytes": 17109000192 }, "isolation": "dedicated-host" }, "platform_version": "8.3.27.2342", "grader": { "profile": "technical-v8", "commit": "e8fd8ced03a85b549c5472fbbda29225749f54d1", "working_tree_dirty": false, "fingerprint": { "assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "calibrate.py": "3162d431f3cab5e7976aa39f665d6286dce45499cf362d85109b7123fa8403a2", "calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "calibration_query.py": "3555b103cde8ea0519955cf52358d09223f5ab183a9df00533bdb48c89237a8c", "claude.py": "eedabc75fca0faa434f40a1624b71419ec7dc22e2854a0886cf84b4911db8372", "codescan.py": "6d8375210cef1fd768fc2d98d630d880b2993a9724f01ae25f33b4ea5aa9631d", "codex.py": "904e75503cd35f16cbb052f66806b3879fe25bfc9f99e33b93c889d862c46324", "common.py": "52825cf5c29f3536d6e046a89e789d5ef9c83aacd7f2f5a07f4f53e77b5229cc", "docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "examiner.py": "8cdffcdd52f043c905f896697403380af95bf485dd4a5edca24f7956e7795ffe", "forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "harness.py": "3cbb90fd3187e700b5df32e5daafb20313d49bb5721c826e3033cbc6aa6e3825", "interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "penalties.py": "ae388cb8953ecca1f2370a7c4cb1db3b6cc8318fc2a7563a4db15f9f5b057429", "platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "pr.py": "2b6bfea0634703469605ce114f9274716b485852d9a55d9185c39893b14e4726", "preflight.py": "448c3120ab64b625abae3891be686c7a214ce4211f7cf651fd90e12c0b298433", "process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "queries.py": "1ef57e292db3e8967a733948371ecc542f743b811890d4fc509df17303b9c4ac", "queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "querytypes.py": "b645f489a2abc27762b4a9bbf4917e72f7b46dc053a74c0dca4a8fc46491b3ef", "replay_calibration.py": "0a4d9b84a9908944c5a945878eb6f5eeda5a4e42ffff4f55c04a680742803d80", "runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "smoke_check.py": "66caf1a01f7aa18432293abe3567ac228ac837a660b08c3dc7bb093f7bd51628", "stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "submission.py": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tasks/1c-platform-official-sample/checks.json": "17a6fcc0c14410829650623eb1443ce99796e000cdfd19905ac0287988b73a00", "tasks/1c-platform-official-sample/private/official-assessment-mapping.json": "303587c0dabe77c1eeebb2017fe85539e3370b17c9090435e6e0325a66bd0644", "tasks/1c-platform-official-sample/private/owner-scoring-policy.json": "d26d534bb838ab1b5facb7bc033ca8ec40912133baadcdbad83b27fc577905f5", "starters/carcass-8.3.25.1445/starter.json": "0f7a7060885ba99a19402bfc6e63cc8fe979b0f491b040d3a01d5d21b304b3a6", "rules/1c-specialist-platform/rules.json": "ea75e34ace5de11ba3de403c63cd2c026db81d1d991f8531e4a779d4ce9788e7", "rules/1c-specialist-platform/examiner.json": "1247486ddd412d600db88d9c1db4ba501fc1994afd1dc2ebe85402fcc332f4c8", "rules/1c-specialist-platform/chistov.json": "800da27601a3f1c7ec1df64482fd4ad035e559ba0b390a274ed5031128487d3d", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" }, "sha256": "349d87e0c7f531acbe35dd2b39c35722d8a877fedde97575b49e8466ab763c1d" }, "method": "saved_platform_observations", "outcome": "complete", "completed_at": "2026-10-26T21:44:20.434620+00:00" } }, { "id": "demo-20261025T154959Z-adapter--owner-2026-10-26T192211930002-0000", "run_id": "demo-20261024T203042Z-421bbf", "result": { "run_id": "demo-20261024T203042Z-421bbf", "created_at": "2026-10-26T19:22:11.930002+00:00", "model": "gpt-6-astra", "harness": "unica-0.14.0-rc.1", "solve_seconds": 4242, "platform": "8.3.27.1688", "counts": { "pass": 64, "fail": 1 }, "rules": [ { "id": "BU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU01.selected_fixture" }, { "id": "BU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU04.selected_fixture" }, { "id": "BU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU05.selected_fixture" }, { "id": "BU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU16.selected_fixture" }, { "id": "BU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU17.selected_fixture" }, { "id": "BU02", "verdict": "pass", "reason": null, "coverage": "partial", "assertion_id": "BU02.posting_cost_and_balance" }, { "id": "BU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU10.selected_fixture" }, { "id": "BU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU12.selected_fixture" }, { "id": "BU03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU03.selected_fixture" }, { "id": "BU06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU06.selected_fixture" }, { "id": "BU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU07.selected_fixture" }, { "id": "BU08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU08.selected_fixture" }, { "id": "BU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU09.selected_fixture" }, { "id": "BU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU11.selected_fixture" }, { "id": "BU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU14.selected_fixture" }, { "id": "BU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU15.selected_fixture" }, { "id": "BU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU13.selected_fixture" }, { "id": "OU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU15.selected_fixture" }, { "id": "OU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU16.selected_fixture" }, { "id": "OU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU17.selected_fixture" }, { "id": "OU02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU02.selected_fixture" }, { "id": "OU18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU18.selected_fixture" }, { "id": "OU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU14.selected_fixture" }, { "id": "OU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU01.selected_fixture" }, { "id": "OU03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU03.selected_fixture" }, { "id": "OU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU05.selected_fixture" }, { "id": "OU06", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "OU06.selected_fixture" }, { "id": "OU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU07.selected_fixture" }, { "id": "OU08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU08.selected_fixture" }, { "id": "OU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU09.selected_fixture" }, { "id": "OU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU10.selected_fixture" }, { "id": "OU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU11.selected_fixture" }, { "id": "OU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU12.selected_fixture" }, { "id": "OU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU13.selected_fixture" }, { "id": "OU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU04.selected_fixture" }, { "id": "OU19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU19.selected_fixture" }, { "id": "OU20", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU20.selected_fixture" }, { "id": "OU21", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU21.selected_fixture" }, { "id": "PR01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR01.selected_fixture" }, { "id": "PR02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR02.selected_fixture" }, { "id": "PR03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR03.selected_fixture" }, { "id": "PR04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR04.selected_fixture" }, { "id": "PR05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR05.selected_fixture" }, { "id": "PR06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR06.selected_fixture" }, { "id": "PR07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR07.selected_fixture" }, { "id": "PR08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR08.selected_fixture" }, { "id": "PR09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR09.selected_fixture" }, { "id": "PR10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR10.selected_fixture" }, { "id": "PR11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR11.selected_fixture" }, { "id": "PR12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR12.selected_fixture" }, { "id": "PR13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR13.selected_fixture" }, { "id": "PR14", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "PR14.selected_fixture" }, { "id": "PR15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR15.selected_fixture" }, { "id": "PR16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR16.selected_fixture" }, { "id": "PR17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR17.selected_fixture" }, { "id": "PR18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR18.selected_fixture" }, { "id": "PR19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR19.selected_fixture" }, { "id": "F01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F01.selected_fixture" }, { "id": "F02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F02.selected_fixture" }, { "id": "F03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F03.selected_fixture" }, { "id": "F04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F04.selected_fixture" }, { "id": "F05", "verdict": "fail", "reason": "typed ['C1', 'C2'], written True, stored [('BENCH_Валюта', ''), ('BENCH_Срок', '')]", "coverage": "selected_fixture", "assertion_id": "F05.selected_fixture" }, { "id": "G01", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G01.static_sources" }, { "id": "G02", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G02.static_sources" }, { "id": "G03", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G03.static_sources" } ], "charges": [ { "id": "F1C-GEN01", "points": "0.5", "reason": "не выполнено требование: F05 — typed ['C1', 'C2'], written True, stored [('BENCH_Валюта', ''), ('BENCH_Срок', '')]" }, { "id": "F1C-GEN12", "points": "0.25", "reason": "текст запроса не разбирается платформой: CommonModules/РасчетЗарплаты/Ext/Module.bsl:91 — Поле не найдено \"Сотрудник\"" }, { "id": "F1C-GEN15", "points": "0.5", "reason": "Reports/ВедомостьПоПодразделению/Ext/ManagerModule.bsl:3 — РегистрНакопления.ОстаткиНоменклатуры.ОстаткиИОбороты: отбор по Подразделение, Свойство, индексы таблицы начинаются с Номенклатура" }, { "id": "F1C-GEN15", "points": "0.5", "reason": "Reports/ВедомостьПоПодразделению/Ext/ManagerModule.bsl:15 — РегистрНакопления.ОстаткиНоменклатуры.ОстаткиИОбороты: отбор по Подразделение, Свойство, индексы таблицы начинаются с Номенклатура" }, { "id": "F1C-GEN14", "points": "1.5", "reason": "Reports/ПродажиБухгалтерские/Ext/ManagerModule.bsl:2 — РегистрБухгалтерии.Управленческий: итоги считаются по основной таблице регистра, а не по виртуальной" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "проводимые документы в режиме «Записывать модифицированные»: Операция, Сборка" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "оперативное проведение разрешено у документов с движениями по регистрам расчёта: НачислениеЗарплаты" } ], "score_upper_bound": "-0.25", "score": null, "grade": "unsatisfactory", "deductions": "5.25", "not_assessed": 15, "gates": { "starter_origin": "passed", "load": "loaded", "clients": "compiles", "demo_data": "present" }, "infrastructure_errors": false, "comparison_eligible": false, "binding_compatibility": { "scope": "supplemental_named_subconto_adapter", "original_binding_sha256": "0bcfa74167b76b733f0d2981e84334b84e16371f42ee5bcebc296739b83d8bd8", "normalized_binding_sha256": "ef7ab816d67a8f4d213f9e4f09ef42a4c96053d0ed56c8ebcbda30afbeae6a55", "normalizer_sha256": "7327277143d80a531e4c254ac74a9fc0e0d5c76572d53b8469e0a580eda17d65", "canonical_ledger_sha256": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "changes": [ { "field": "fields.ledger.item_debit", "before": "Номенклатура", "after": "ВидыСубконто.Номенклатура", "kind": "named" }, { "field": "fields.ledger.item_credit", "before": "Номенклатура", "after": "ВидыСубконто.Номенклатура", "kind": "named" }, { "field": "fields.ledger.warehouse_debit", "before": "Склады", "after": "ВидыСубконто.Склады", "kind": "named" }, { "field": "fields.ledger.warehouse_credit", "before": "Склады", "after": "ВидыСубконто.Склады", "kind": "named" } ], "basis": "kind names expanded only to exactly one predefined kind of the account chart on the role side; all role types checked." } }, "measurement": { "operator": { "name": "Vasiliy", "github": "Gh0sTspp" }, "environment": { "captured_at": "2026-10-24T20:30:43.917189+00:00", "capture_timing": "before_run", "hardware": { "cpu": "Intel(R) Core(TM) i7-5820K CPU @ 3.30GHz", "logical_cpus": 12, "ram_bytes": 34189709312 }, "os": { "system": "Windows", "release": "10", "version": "10.0.19045", "architecture": "AMD64" }, "python": "3.13.12", "platform_version": "8.3.27.1688", "isolation": "dedicated-host", "network_profile": "open-book_shell", "unsafe_action_protection_observed_in_user_config": true, "git_revision": "af85e791b303dbbf0b0b7af924d2489c3e57cfa8", "implementation_files": { "exam_bench/__init__.py": "ad5bf6f05dc6765f40b78bd186870ca2c49be113cfa33f8aa76f4926f2cb2c1e", "exam_bench/assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "exam_bench/bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "exam_bench/calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "exam_bench/calibrate.py": "78b5185cb0888c0c0ac3de95ffc3a80154a6de9ae66fc461f79d012e5a58e1db", "exam_bench/calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "exam_bench/calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "exam_bench/calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "exam_bench/calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "exam_bench/calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "exam_bench/claude.py": "bc1b8550de7573aaed5e39c6e9c0309e0d8175284a75490d61ec27439ed911ad", "exam_bench/cli.py": "1a37ce645633d761f7897dffc9c45e6b8b9600cd7bd233b1cbf78f49d26b099a", "exam_bench/codescan.py": "751e38001b6e65727a31e28172a0623f0bf34bc092a958037c286aa991a197ed", "exam_bench/codex.py": "c3f89d72af11f312d851c73a1610d92e79acadf336be9ccedd1f94ede3b3ccb0", "exam_bench/common.py": "8682603b519063e655eae3574a02a49efee63bde21f582ccee20ddd623fca96d", "exam_bench/docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "exam_bench/examiner.py": "d7294fdd23ed1732216cafebf0a8cf2c24cce4259859aeb7149f62b7607d087d", "exam_bench/finalize.py": "4034f1c63896a940afdb1a83d541cf47fc75c8b5061e3f839047109c04beb620", "exam_bench/forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "exam_bench/gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "exam_bench/grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "exam_bench/harness.py": "3040f6daaf1dc6e6583219f4d925151f8ba7851b2d5417d7f14645892b485ddf", "exam_bench/interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "exam_bench/interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "exam_bench/isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "exam_bench/ledger.py": "7e851523580e22d8490e75f9b6026c07f2c355007e0d11d0b252671f56bef654", "exam_bench/locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "exam_bench/materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "exam_bench/mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "exam_bench/observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "exam_bench/ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "exam_bench/penalties.py": "0d79e2e46102657dca00609b6abbfc0bf7d11fad41429564f876c82bc6b33269", "exam_bench/platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "exam_bench/portable.py": "cad56968ff407983608f5bdbc9ce7234128d7a4580b096ecea8e0e7b4edb9070", "exam_bench/portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "exam_bench/pr.py": "6a3a20caf0e10c0cc94410511a72d62c9fcda785f3abab1be2ad616d4ee16836", "exam_bench/preflight.py": "5619be0131d8641925f3ce2a3c8e5234d42aa5635d95676138ca81536d95cd29", "exam_bench/process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "exam_bench/queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "exam_bench/queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "exam_bench/replay_calibration.py": "c150457b0b23ce4e6814eb8deb4d48f6bc4a2e39d8f84a9dc7644fb99a026c2d", "exam_bench/report.py": "5e4c0757e1c7f189953f9a5302593ab726551835856baed25efd93dad6e8bfcd", "exam_bench/runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "exam_bench/smoke_check.py": "f36922a0027429ead0b414048dcc14bbe67f2f0e79a70d03dffbe1447d253545", "exam_bench/stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "exam_bench/submission.py": "ea862adc63ae67861ddb1d6aeb4d92c10b0b05004d22953f7b03612f82bb4bf4", "exam_bench/telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "exam_bench/windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "exam_bench/workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tools/build_public_site.py": "9682ed696f5ac9e9a82b65a45c0dece556ec7e49eeb20dcd616882cc534a8258", "tools/build_result_site.py": "3294e1d2ec1486058e208735264d61e349a68a4ae2fa2ec7a723c70e3263b496", "tools/check_native_harnesses.py": "4f5f0ed27651f78758eaef077b3b114361781f6b95ec40cb46c3fea689210473", "tools/check_native_toolkit.py": "0272794617121f2932828e5e4e9ae20095183c443666cf3ba466b44fbe875095", "tools/community_results.py": "788f4763fa97a2f6fe055a1ddea15cb918d2881327594931e508f9fbeb3dd13c", "tools/community_service.py": "c374480dbd88d656c0b9054fa04a8e1c6698c69e2f9cf475e82498a2dff61d84", "tools/community_setup.py": "5d7d126ed7d4dd48e1d79f57b99647a92ffcc8c9f80d90915e458888cdd76bf7", "tools/compare_harness_runs.py": "f274df5f3f804cb02504491aec946943833e12fbce6e62d281e12beb8508fc4e", "tools/create_run_plan.py": "871cd81b1eda231c0fba8805f63d2668926be9fc641559e6ddf320e2f47cd37a", "tools/demo_runner.py": "ca7ad17919c53d524cc0418751ba09a540f910eac183dca2961710bc30bba26f", "tools/installers.py": "9a2742780936b17500869e7c89202c1a2549e37d53a42ad9a50a0abbf78bbe09", "tools/machine_bundle.py": "8aa8346f99f537e81ceca6fb6ab9530e844954bab8eff87bf33d3602f81f8a30", "tools/prepare_native_harnesses.py": "aaa75ecf4022883984fa50c42d14d8e1a9fde2eeda03dab03b852bbc5efb2502", "tools/prepare_official_statement.py": "6b7028c78e90e798d6ef1a93b76520cc61a308c354fb9b87f7fad18b99800fad", "tools/prepare_open_exam_requirements.py": "544f4e378b9be5f166186f8788f8d454afdac2deb99d91d98421e39d01ba6d03", "tools/probe_harness.py": "1ed8ef93420d1484cbbfd151b7efc31b9a201ceb942dd05e3103efa22ffa7f27", "tools/probe_native_mcp.py": "9918d324129cba898993e07f8f8b6dbcbaf369398ebf28d464f9f1f00abdb254", "tools/readiness.py": "d34dd3f38334f51cc4574c79194cf0b80769b062a52382989a57d01c46b9aba4", "tools/recheck_community.py": "f0843d7d677f90da31e22bde0b1c86584dd46c022f1532d43d042619e426b230", "tools/regrade_runs.py": "011775afb06d3aac67a4aa81117a368c75896b0fcbe1e6f27ccc6237612fbf59", "tools/render_statement_text.py": "dabc0716a3612c288c671bc20e17fd4986691d732768e1e957d6dddddbea92a3", "tools/replay_calibration.py": "801f5004926c438c21ed3668fe2a4ddf45312b3e75320165a3839aae034eee9b", "tools/run_exam_campaign.py": "2c450d57a1cd0a2682838f5ec7c0a4ffb3aed0f1730d34c408e912d59cab6efd", "tools/serve_result_site.py": "86badfac863cd4ad1fc894a14110c75b28470513f0133eeae9d2799b8b4df3a9", "tools/start_demo.py": "c597e6cad28d245b3191654bb3e2801fa9dd2364e2acb25561923613717b615f", "tools/supplemental_acceptance.py": "c88fc39de1be1fdcacdd819e2ad329f60367b2df1d5deda80b37324bda3f2a01", "tools/sync_sources.py": "b51e889b0f41f9f63bfb19a09fb96d3777693d6b1d76fe0132bdd2a15e155898", "tools/validate_community_pr.py": "796b896dfade07b4529af2088a4b9b9d23484148b3bc0732b3fb837b75c9844b", "tools/verify_official_assessment_mapping.py": "daeb448a016940d5b6b1285979a56e5b9014bd91db40acb131445e4a83a23059", "tools/verify_task_package.py": "9e1e6105f6b5e4e78b36aa57f00117a9fbc8948ab53983c32ab56da88d23ccc4", "profiles/agents.json": "af9c492c08d13b3044aa6b6952589ed6a0a07d5258d8ff72bb18185b3eaebdc5", "profiles/ai-exam-execution-policy.json": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "profiles/bsl-analyzer-0.3.2-macos.json": "83537abdbf38c41ce665e4d0f24128bb51b62e971e0e0f368695f1326a7d2ffb", "profiles/bsl-analyzer-0.3.2-portable.json": "d6ba732e6778e256df34d6bc548593128820a70430c35b279796843606ee40a8", "profiles/bsl-ls-1.1.0-rc.6-macos.json": "245fc10747197e6911b2b4c77cdb15e6fa4eb7bc7c3758b63e768c5adf1df180", "profiles/bsl-ls-1.1.0-rc.6-portable.json": "9f10660881f2ec84794f7d584556b8f75c7e14b3555464af0ed0e60c4c892d86", "profiles/code-index-1.9.0-macos.json": "63a919523ce62ecec274f4c139bc7ad49a75dd4c339568b822cbc695b4e30408", "profiles/code-index-1.9.0-portable.json": "81106cee8f424ffd8a9dc46ecd8e4f57598fc1d49661a83c77b1f0507993fbdc", "profiles/codex-probe-plan.json": "166e41aad5fb3b27d9050bc6de952c6cba363cc6e804d4080568cc71a2a4d289", "profiles/machine.linux.example.json": "408304fd0581098d5d8110dc67dfeab353bc4d4030e32d37e6acf98d2b1aedfd", "profiles/machine.macos.example.json": "52e9f9d17797cb520b9d8955d6806fd550b899bed4da241ebf096dcb6a21a942", "profiles/machine.windows.example.json": "63accac9a2f81d47d03447efbabffd4760aee325193f02f46b9b29a28d50d2d8", "profiles/mcp-toolkit-1.9.0-macos.json": "1d3f9cde5ffa20589a840d01fdae03aa0fc2f412c929f064f203919c4129625b", "profiles/mcp-toolkit-1.9.0-portable.json": "8e370eebe773eef0e08045ee9c6d5be1451f769f65be0710834b262a4336e054", "profiles/none-macos.json": "b1401d9c48159aed3559006c7f6ace6ef4571224d5cf0bb76d1a823505a10056", "profiles/none-portable.json": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "profiles/rlm-tools-bsl-1.43.0-macos.json": "9354421052640ab60bc3e6aa98ff2e7ba9ca2318b0f4026c137487449242cbd2", "profiles/rlm-tools-bsl-1.43.0-portable.json": "2599e5645e0a7d4e44cb2934bc2b272cae79a9bf7ea74a23cd48aacea64bc424", "profiles/rlm-tools-bsl-1.43.0-posix-requirements.txt": "4fdf9a1bd994bf0272e65d231daf76cf19b0a34dad0ae6b50ec4f11a2ce4c330", "profiles/rlm-tools-bsl-1.43.0-windows-requirements.txt": "3730cb46c81cda5181ecd4485e98b11933104632358bc86f8c0eb1a612a8954f", "profiles/shirokov-skills-macos.json": "84f3e89091676884a802035c707e912762a1179425fb8e3faff25be736873cdb", "profiles/shirokov-skills-portable.json": "2b0a461e06602f1456410e70f02ceaa5ac32c6549c486660bcb5ace0c2f87b15", "profiles/shirokov-skills-windows-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/unica-0.12.3-macos.json": "2c39fbb591cf2c2c6e056373823615485397ea83651b7926c6f25a5fe6a0aae6", "profiles/unica-0.13.0-macos.json": "b76b5c8a4dd33f571c4a90993f1a2da5f7223b4f0f8e1042c282e21a66121052", "profiles/unica-0.14.0-rc.1-portable.json": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "rules/1c-specialist-platform/chistov.json": "77e04942f8c947b10759e7cc1eb31af05847d1711a772fbe6f23d525766757a9", "rules/1c-specialist-platform/decisions.json": "f622107423ce3c188c063318d7ab4f7718ceb38e443130677d8987f386641c09", "rules/1c-specialist-platform/examiner.json": "30353aa2a1b6545496b070d9066e9ffba0c3779e5b53ef70a4fd2cee375b18c0", "rules/1c-specialist-platform/ledger.json": "f167c10db2b5799dd9a1ea6a37cd2d7d186810dadf5ea2f50f26ae723c676882", "rules/1c-specialist-platform/rules.json": "1d320a4f8e1bf4701496388931f492315549bd3dce574b17285dd1d7f8652007", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" } } }, "conditions": { "client": "codex", "model": "gpt-6-astra", "client_version": "0.164.0", "reasoning_effort": "medium", "harness": "unica-0.14.0-rc.1", "billing_channel": "subscription", "solve_timeout_seconds": 7200, "time_series": null, "delegation": "native_disabled", "network_profile": "open-book_shell", "deadline_disclosed": true, "statement_sha256": "8a6ccb3e673826d1f8220fda53eb310e3ec18c136d87ce8f4cebb2a08614e7e5", "starter_dt_sha256": "f40d084818b0d1cfe503fc7653a6a13f1a8e47fcd1688dad6245b12744eb4638", "profile_sha256": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "execution_policy_sha256": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "calibration_sha256": "7a2c598d569ece652e72fdfb586af0b95d3c73bd3c467d024dd31f9bb27be403", "started_at": "2026-10-24T20:31:10.169432+00:00", "timing": { "prepare_ms": 24023, "solve_ms": 4241872, "grade_ms": null }, "original_submission_valid": false, "model_provenance": "requested_only", "tokens": { "input": 20399295, "cached_input": 20113664, "fresh_input": 285631, "output": 134781, "reasoning_output": 43182, "total": 20534076, "coverage": "reported_completed_root_turns" }, "tools": { "mcp_calls": 566, "unica_calls": 566, "failed_calls": 36 }, "process": { "status": "completed", "exit_code": 0, "stop_confirmed": true } }, "verification": "repository_owner", "download": "community-downloads/demo-20261025T154959Z-adapter--owner-2026-10-26T192211930002-0000/solution.zip", "source_context": "community-downloads/demo-20261025T154959Z-adapter--owner-2026-10-26T192211930002-0000/source-context.json", "regrade_required": [ { "id": "grader_changed", "files": [ "calibrate.py", "calibration_periodicity.py", "calibration_query.py", "common.py", "ou.py", "penalties.py", "queries.py", "replay_calibration.py", "rules/1c-specialist-platform/rules.json", "smoke_check.py", "tasks/1c-platform-official-sample/checks.json" ] } ], "grader_revision_sha256": "4a12b62d2c10085e1fc710f377f84903abdf2fb787dda19628d944da990a86b2", "archive_sha256": "9a960d105891d6f471848a1954b138113656f7c05dd1d5bc171f3ac24f804313", "owner_verification": { "kind": "repository_owner", "repository": "zeegin/1c-agent-exam-benchmark", "operator": { "name": "Ingvar Vilkman", "github": "zeegin" }, "started_at": "2026-10-26T19:19:09.653022+00:00", "server": { "name": "Owner Windows stand", "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "hardware": { "cpu": "AMD Ryzen 7 5800X 8-Core Processor ", "logical_cpus": 4, "ram_bytes": 17109000192 }, "isolation": "dedicated-host" }, "platform_version": "8.3.27.2342", "grader": { "profile": "technical-v8", "commit": "5b6a28372b253e81e22b83f8559df897297e28ff", "working_tree_dirty": true, "fingerprint": { "assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "calibrate.py": "1c844971b4977fdcc3b30aebe8aad40fbd45e6828955b8deb043ac8573d61731", "calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "claude.py": "eedabc75fca0faa434f40a1624b71419ec7dc22e2854a0886cf84b4911db8372", "codescan.py": "6d8375210cef1fd768fc2d98d630d880b2993a9724f01ae25f33b4ea5aa9631d", "codex.py": "904e75503cd35f16cbb052f66806b3879fe25bfc9f99e33b93c889d862c46324", "common.py": "7696116dd1a796666518b4c5d2aa3cafa04ee974593d3636333cbe5385bd6ccb", "docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "examiner.py": "8cdffcdd52f043c905f896697403380af95bf485dd4a5edca24f7956e7795ffe", "forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "harness.py": "3cbb90fd3187e700b5df32e5daafb20313d49bb5721c826e3033cbc6aa6e3825", "interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "penalties.py": "b82704e7f47d3dfdf6e501452d7e0abca1f9da63307093d2e257e32358be0489", "platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "pr.py": "2b6bfea0634703469605ce114f9274716b485852d9a55d9185c39893b14e4726", "preflight.py": "448c3120ab64b625abae3891be686c7a214ce4211f7cf651fd90e12c0b298433", "process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "querytypes.py": "b645f489a2abc27762b4a9bbf4917e72f7b46dc053a74c0dca4a8fc46491b3ef", "replay_calibration.py": "3b6f3a289cc8a7f5e458f62bfa2c6cc534cc9076ba3f22d1e4bd8a5f9e175317", "runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "smoke_check.py": "bd6266367e6b769a95258eb383239b89a22deae406d64f6e142c77396f4639ba", "stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "submission.py": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tasks/1c-platform-official-sample/checks.json": "17a6fcc0c14410829650623eb1443ce99796e000cdfd19905ac0287988b73a00", "tasks/1c-platform-official-sample/private/official-assessment-mapping.json": "303587c0dabe77c1eeebb2017fe85539e3370b17c9090435e6e0325a66bd0644", "tasks/1c-platform-official-sample/private/owner-scoring-policy.json": "d26d534bb838ab1b5facb7bc033ca8ec40912133baadcdbad83b27fc577905f5", "starters/carcass-8.3.25.1445/starter.json": "0f7a7060885ba99a19402bfc6e63cc8fe979b0f491b040d3a01d5d21b304b3a6", "rules/1c-specialist-platform/rules.json": "7ec895a7751ef17f4a50cc80b5f7fa986e1e04360ab0b4ce9aa29115195df03c", "rules/1c-specialist-platform/examiner.json": "1247486ddd412d600db88d9c1db4ba501fc1994afd1dc2ebe85402fcc332f4c8", "rules/1c-specialist-platform/chistov.json": "800da27601a3f1c7ec1df64482fd4ad035e559ba0b390a274ed5031128487d3d", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" }, "sha256": "4a12b62d2c10085e1fc710f377f84903abdf2fb787dda19628d944da990a86b2" }, "identity_verified_at": "2026-10-26T18:44:22.364471+00:00", "identity_session_sha256": "950670ab9a82059c65525d0d6e5b8a00f0dc292581edea3eb087c4ecadeaab09", "completed_at": "2026-10-26T19:22:11.930002+00:00" } }, { "id": "demo-20261025T154959Z-adapter", "run_id": "demo-20261024T203042Z-421bbf", "result": { "run_id": "demo-20261024T203042Z-421bbf", "created_at": "2026-10-25T16:00:34.505781+00:00", "model": "gpt-6-astra", "harness": "unica-0.14.0-rc.1", "solve_seconds": 4242, "platform": "8.3.27.1688", "counts": { "pass": 64, "fail": 1 }, "rules": [ { "id": "BU01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU16", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU17", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU02", "verdict": "pass", "coverage": "partial", "reason": null }, { "id": "BU10", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU12", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU06", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU07", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU08", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU09", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU11", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU14", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU15", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU13", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU15", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU16", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU17", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU02", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU18", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU14", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU06", "verdict": "pass", "coverage": "no_violation_found", "reason": null }, { "id": "OU07", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU08", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU09", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU10", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU11", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU12", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU13", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU19", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU20", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU21", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR02", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR06", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR07", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR08", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR09", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR10", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR11", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR12", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR13", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR14", "verdict": "pass", "coverage": "no_violation_found", "reason": null }, { "id": "PR15", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR16", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR17", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR18", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR19", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F02", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F05", "verdict": "fail", "coverage": "selected_fixture", "reason": null }, { "id": "G01", "verdict": "pass", "coverage": "static_sources", "reason": null }, { "id": "G02", "verdict": "pass", "coverage": "static_sources", "reason": null }, { "id": "G03", "verdict": "pass", "coverage": "static_sources", "reason": null } ], "charges": [ { "id": "F1C-GEN01", "points": "0.5", "reason": "не выполнено требование: F05 — typed ['C1', 'C2'], written True, stored [('BENCH_Валюта', ''), ('BENCH_Срок', '')]" }, { "id": "F1C-GEN12", "points": "0.25", "reason": "текст запроса не разбирается платформой: CommonModules/РасчетЗарплаты/Ext/Module.bsl:91 — Поле не найдено \"Сотрудник\"" }, { "id": "F1C-GEN15", "points": "0.5", "reason": "Reports/ВедомостьПоПодразделению/Ext/ManagerModule.bsl:3 — РегистрНакопления.ОстаткиНоменклатуры.ОстаткиИОбороты: отбор по Подразделение, Свойство, индексы таблицы начинаются с Номенклатура" }, { "id": "F1C-GEN15", "points": "0.5", "reason": "Reports/ВедомостьПоПодразделению/Ext/ManagerModule.bsl:15 — РегистрНакопления.ОстаткиНоменклатуры.ОстаткиИОбороты: отбор по Подразделение, Свойство, индексы таблицы начинаются с Номенклатура" }, { "id": "F1C-GEN14", "points": "1.5", "reason": "Reports/ПродажиБухгалтерские/Ext/ManagerModule.bsl:2 — РегистрБухгалтерии.Управленческий: итоги считаются по основной таблице регистра, а не по виртуальной" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "проводимые документы в режиме «Записывать модифицированные»: Операция, Сборка" }, { "id": "F1C-GEN20", "points": "2.0", "reason": "данные базы читаются в цикле по записям: CommonModules/УчетСервер/Ext/Module.bsl:382; CommonModules/УчетСервер/Ext/Module.bsl:384; CommonModules/УчетСервер/Ext/Module.bsl:385 и ещё 12" }, { "id": "F1C-GEN21", "points": "2.0", "reason": "параметры виртуальной таблицы не заданы или заменены условием ГДЕ: CommonModules/УчетСервер/Ext/Module.bsl:439 РегистрНакопления.ОстаткиНоменклатуры.Остатки(,; CommonModules/УчетСервер/Ext/Module.bsl:456 РегистрБухгалтерии.Управленческий.Остатки(,; CommonModules/УчетСервер/Ext/Module.bsl:460 РегистрБухгалтерии.Управленческий.Остатки(," }, { "id": "F1C-GEN28", "points": "1.0", "reason": "оперативное проведение разрешено у документов с движениями по регистрам расчёта: НачислениеЗарплаты" } ], "score_upper_bound": "-4.25", "score": null, "grade": "unsatisfactory", "deductions": "9.25", "not_assessed": 14, "gates": { "starter_origin": "passed", "load": "loaded", "clients": "compiles", "demo_data": "present" }, "infrastructure_errors": false, "comparison_eligible": false, "binding_compatibility": { "scope": "supplemental_named_subconto_adapter", "original_binding_sha256": "0bcfa74167b76b733f0d2981e84334b84e16371f42ee5bcebc296739b83d8bd8", "normalized_binding_sha256": "ef7ab816d67a8f4d213f9e4f09ef42a4c96053d0ed56c8ebcbda30afbeae6a55", "normalizer_sha256": "7327277143d80a531e4c254ac74a9fc0e0d5c76572d53b8469e0a580eda17d65", "canonical_ledger_sha256": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "changes": [ { "field": "fields.ledger.item_debit", "before": "Номенклатура", "after": "ВидыСубконто.Номенклатура", "kind": "named" }, { "field": "fields.ledger.item_credit", "before": "Номенклатура", "after": "ВидыСубконто.Номенклатура", "kind": "named" }, { "field": "fields.ledger.warehouse_debit", "before": "Склады", "after": "ВидыСубконто.Склады", "kind": "named" }, { "field": "fields.ledger.warehouse_credit", "before": "Склады", "after": "ВидыСубконто.Склады", "kind": "named" } ], "basis": "kind names expanded only to exactly one predefined kind of the account chart on the role side; all role types checked." }, "evaluation_sha256": "b9276ff78ee5d8cc79cea8dcd57af9e33697a2dfc3f97baeb2cbdc9e9d19a765", "downloads": [] }, "measurement": { "operator": { "name": "Vasiliy", "github": "Gh0sTspp" }, "environment": { "captured_at": "2026-10-24T20:30:43.917189+00:00", "capture_timing": "before_run", "hardware": { "cpu": "Intel(R) Core(TM) i7-5820K CPU @ 3.30GHz", "logical_cpus": 12, "ram_bytes": 34189709312 }, "os": { "system": "Windows", "release": "10", "version": "10.0.19045", "architecture": "AMD64" }, "python": "3.13.12", "platform_version": "8.3.27.1688", "isolation": "dedicated-host", "network_profile": "open-book_shell", "unsafe_action_protection_observed_in_user_config": true, "git_revision": "af85e791b303dbbf0b0b7af924d2489c3e57cfa8", "implementation_files": { "exam_bench/__init__.py": "ad5bf6f05dc6765f40b78bd186870ca2c49be113cfa33f8aa76f4926f2cb2c1e", "exam_bench/assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "exam_bench/bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "exam_bench/calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "exam_bench/calibrate.py": "78b5185cb0888c0c0ac3de95ffc3a80154a6de9ae66fc461f79d012e5a58e1db", "exam_bench/calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "exam_bench/calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "exam_bench/calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "exam_bench/calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "exam_bench/calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "exam_bench/claude.py": "bc1b8550de7573aaed5e39c6e9c0309e0d8175284a75490d61ec27439ed911ad", "exam_bench/cli.py": "1a37ce645633d761f7897dffc9c45e6b8b9600cd7bd233b1cbf78f49d26b099a", "exam_bench/codescan.py": "751e38001b6e65727a31e28172a0623f0bf34bc092a958037c286aa991a197ed", "exam_bench/codex.py": "c3f89d72af11f312d851c73a1610d92e79acadf336be9ccedd1f94ede3b3ccb0", "exam_bench/common.py": "8682603b519063e655eae3574a02a49efee63bde21f582ccee20ddd623fca96d", "exam_bench/docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "exam_bench/examiner.py": "d7294fdd23ed1732216cafebf0a8cf2c24cce4259859aeb7149f62b7607d087d", "exam_bench/finalize.py": "4034f1c63896a940afdb1a83d541cf47fc75c8b5061e3f839047109c04beb620", "exam_bench/forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "exam_bench/gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "exam_bench/grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "exam_bench/harness.py": "3040f6daaf1dc6e6583219f4d925151f8ba7851b2d5417d7f14645892b485ddf", "exam_bench/interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "exam_bench/interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "exam_bench/isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "exam_bench/ledger.py": "7e851523580e22d8490e75f9b6026c07f2c355007e0d11d0b252671f56bef654", "exam_bench/locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "exam_bench/materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "exam_bench/mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "exam_bench/observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "exam_bench/ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "exam_bench/penalties.py": "0d79e2e46102657dca00609b6abbfc0bf7d11fad41429564f876c82bc6b33269", "exam_bench/platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "exam_bench/portable.py": "cad56968ff407983608f5bdbc9ce7234128d7a4580b096ecea8e0e7b4edb9070", "exam_bench/portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "exam_bench/pr.py": "6a3a20caf0e10c0cc94410511a72d62c9fcda785f3abab1be2ad616d4ee16836", "exam_bench/preflight.py": "5619be0131d8641925f3ce2a3c8e5234d42aa5635d95676138ca81536d95cd29", "exam_bench/process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "exam_bench/queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "exam_bench/queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "exam_bench/replay_calibration.py": "c150457b0b23ce4e6814eb8deb4d48f6bc4a2e39d8f84a9dc7644fb99a026c2d", "exam_bench/report.py": "5e4c0757e1c7f189953f9a5302593ab726551835856baed25efd93dad6e8bfcd", "exam_bench/runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "exam_bench/smoke_check.py": "f36922a0027429ead0b414048dcc14bbe67f2f0e79a70d03dffbe1447d253545", "exam_bench/stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "exam_bench/submission.py": "ea862adc63ae67861ddb1d6aeb4d92c10b0b05004d22953f7b03612f82bb4bf4", "exam_bench/telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "exam_bench/windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "exam_bench/workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tools/build_public_site.py": "9682ed696f5ac9e9a82b65a45c0dece556ec7e49eeb20dcd616882cc534a8258", "tools/build_result_site.py": "3294e1d2ec1486058e208735264d61e349a68a4ae2fa2ec7a723c70e3263b496", "tools/check_native_harnesses.py": "4f5f0ed27651f78758eaef077b3b114361781f6b95ec40cb46c3fea689210473", "tools/check_native_toolkit.py": "0272794617121f2932828e5e4e9ae20095183c443666cf3ba466b44fbe875095", "tools/community_results.py": "788f4763fa97a2f6fe055a1ddea15cb918d2881327594931e508f9fbeb3dd13c", "tools/community_service.py": "c374480dbd88d656c0b9054fa04a8e1c6698c69e2f9cf475e82498a2dff61d84", "tools/community_setup.py": "5d7d126ed7d4dd48e1d79f57b99647a92ffcc8c9f80d90915e458888cdd76bf7", "tools/compare_harness_runs.py": "f274df5f3f804cb02504491aec946943833e12fbce6e62d281e12beb8508fc4e", "tools/create_run_plan.py": "871cd81b1eda231c0fba8805f63d2668926be9fc641559e6ddf320e2f47cd37a", "tools/demo_runner.py": "ca7ad17919c53d524cc0418751ba09a540f910eac183dca2961710bc30bba26f", "tools/installers.py": "9a2742780936b17500869e7c89202c1a2549e37d53a42ad9a50a0abbf78bbe09", "tools/machine_bundle.py": "8aa8346f99f537e81ceca6fb6ab9530e844954bab8eff87bf33d3602f81f8a30", "tools/prepare_native_harnesses.py": "aaa75ecf4022883984fa50c42d14d8e1a9fde2eeda03dab03b852bbc5efb2502", "tools/prepare_official_statement.py": "6b7028c78e90e798d6ef1a93b76520cc61a308c354fb9b87f7fad18b99800fad", "tools/prepare_open_exam_requirements.py": "544f4e378b9be5f166186f8788f8d454afdac2deb99d91d98421e39d01ba6d03", "tools/probe_harness.py": "1ed8ef93420d1484cbbfd151b7efc31b9a201ceb942dd05e3103efa22ffa7f27", "tools/probe_native_mcp.py": "9918d324129cba898993e07f8f8b6dbcbaf369398ebf28d464f9f1f00abdb254", "tools/readiness.py": "d34dd3f38334f51cc4574c79194cf0b80769b062a52382989a57d01c46b9aba4", "tools/recheck_community.py": "f0843d7d677f90da31e22bde0b1c86584dd46c022f1532d43d042619e426b230", "tools/regrade_runs.py": "011775afb06d3aac67a4aa81117a368c75896b0fcbe1e6f27ccc6237612fbf59", "tools/render_statement_text.py": "dabc0716a3612c288c671bc20e17fd4986691d732768e1e957d6dddddbea92a3", "tools/replay_calibration.py": "801f5004926c438c21ed3668fe2a4ddf45312b3e75320165a3839aae034eee9b", "tools/run_exam_campaign.py": "2c450d57a1cd0a2682838f5ec7c0a4ffb3aed0f1730d34c408e912d59cab6efd", "tools/serve_result_site.py": "86badfac863cd4ad1fc894a14110c75b28470513f0133eeae9d2799b8b4df3a9", "tools/start_demo.py": "c597e6cad28d245b3191654bb3e2801fa9dd2364e2acb25561923613717b615f", "tools/supplemental_acceptance.py": "c88fc39de1be1fdcacdd819e2ad329f60367b2df1d5deda80b37324bda3f2a01", "tools/sync_sources.py": "b51e889b0f41f9f63bfb19a09fb96d3777693d6b1d76fe0132bdd2a15e155898", "tools/validate_community_pr.py": "796b896dfade07b4529af2088a4b9b9d23484148b3bc0732b3fb837b75c9844b", "tools/verify_official_assessment_mapping.py": "daeb448a016940d5b6b1285979a56e5b9014bd91db40acb131445e4a83a23059", "tools/verify_task_package.py": "9e1e6105f6b5e4e78b36aa57f00117a9fbc8948ab53983c32ab56da88d23ccc4", "profiles/agents.json": "af9c492c08d13b3044aa6b6952589ed6a0a07d5258d8ff72bb18185b3eaebdc5", "profiles/ai-exam-execution-policy.json": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "profiles/bsl-analyzer-0.3.2-macos.json": "83537abdbf38c41ce665e4d0f24128bb51b62e971e0e0f368695f1326a7d2ffb", "profiles/bsl-analyzer-0.3.2-portable.json": "d6ba732e6778e256df34d6bc548593128820a70430c35b279796843606ee40a8", "profiles/bsl-ls-1.1.0-rc.6-macos.json": "245fc10747197e6911b2b4c77cdb15e6fa4eb7bc7c3758b63e768c5adf1df180", "profiles/bsl-ls-1.1.0-rc.6-portable.json": "9f10660881f2ec84794f7d584556b8f75c7e14b3555464af0ed0e60c4c892d86", "profiles/code-index-1.9.0-macos.json": "63a919523ce62ecec274f4c139bc7ad49a75dd4c339568b822cbc695b4e30408", "profiles/code-index-1.9.0-portable.json": "81106cee8f424ffd8a9dc46ecd8e4f57598fc1d49661a83c77b1f0507993fbdc", "profiles/codex-probe-plan.json": "166e41aad5fb3b27d9050bc6de952c6cba363cc6e804d4080568cc71a2a4d289", "profiles/machine.linux.example.json": "408304fd0581098d5d8110dc67dfeab353bc4d4030e32d37e6acf98d2b1aedfd", "profiles/machine.macos.example.json": "52e9f9d17797cb520b9d8955d6806fd550b899bed4da241ebf096dcb6a21a942", "profiles/machine.windows.example.json": "63accac9a2f81d47d03447efbabffd4760aee325193f02f46b9b29a28d50d2d8", "profiles/mcp-toolkit-1.9.0-macos.json": "1d3f9cde5ffa20589a840d01fdae03aa0fc2f412c929f064f203919c4129625b", "profiles/mcp-toolkit-1.9.0-portable.json": "8e370eebe773eef0e08045ee9c6d5be1451f769f65be0710834b262a4336e054", "profiles/none-macos.json": "b1401d9c48159aed3559006c7f6ace6ef4571224d5cf0bb76d1a823505a10056", "profiles/none-portable.json": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "profiles/rlm-tools-bsl-1.43.0-macos.json": "9354421052640ab60bc3e6aa98ff2e7ba9ca2318b0f4026c137487449242cbd2", "profiles/rlm-tools-bsl-1.43.0-portable.json": "2599e5645e0a7d4e44cb2934bc2b272cae79a9bf7ea74a23cd48aacea64bc424", "profiles/rlm-tools-bsl-1.43.0-posix-requirements.txt": "4fdf9a1bd994bf0272e65d231daf76cf19b0a34dad0ae6b50ec4f11a2ce4c330", "profiles/rlm-tools-bsl-1.43.0-windows-requirements.txt": "3730cb46c81cda5181ecd4485e98b11933104632358bc86f8c0eb1a612a8954f", "profiles/shirokov-skills-macos.json": "84f3e89091676884a802035c707e912762a1179425fb8e3faff25be736873cdb", "profiles/shirokov-skills-portable.json": "2b0a461e06602f1456410e70f02ceaa5ac32c6549c486660bcb5ace0c2f87b15", "profiles/shirokov-skills-windows-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/unica-0.12.3-macos.json": "2c39fbb591cf2c2c6e056373823615485397ea83651b7926c6f25a5fe6a0aae6", "profiles/unica-0.13.0-macos.json": "b76b5c8a4dd33f571c4a90993f1a2da5f7223b4f0f8e1042c282e21a66121052", "profiles/unica-0.14.0-rc.1-portable.json": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "rules/1c-specialist-platform/chistov.json": "77e04942f8c947b10759e7cc1eb31af05847d1711a772fbe6f23d525766757a9", "rules/1c-specialist-platform/decisions.json": "f622107423ce3c188c063318d7ab4f7718ceb38e443130677d8987f386641c09", "rules/1c-specialist-platform/examiner.json": "30353aa2a1b6545496b070d9066e9ffba0c3779e5b53ef70a4fd2cee375b18c0", "rules/1c-specialist-platform/ledger.json": "f167c10db2b5799dd9a1ea6a37cd2d7d186810dadf5ea2f50f26ae723c676882", "rules/1c-specialist-platform/rules.json": "1d320a4f8e1bf4701496388931f492315549bd3dce574b17285dd1d7f8652007", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" } } }, "conditions": { "client": "codex", "model": "gpt-6-astra", "client_version": "0.164.0", "reasoning_effort": "medium", "harness": "unica-0.14.0-rc.1", "billing_channel": "subscription", "solve_timeout_seconds": 7200, "time_series": null, "delegation": "native_disabled", "network_profile": "open-book_shell", "deadline_disclosed": true, "statement_sha256": "8a6ccb3e673826d1f8220fda53eb310e3ec18c136d87ce8f4cebb2a08614e7e5", "starter_dt_sha256": "f40d084818b0d1cfe503fc7653a6a13f1a8e47fcd1688dad6245b12744eb4638", "profile_sha256": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "execution_policy_sha256": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "calibration_sha256": "7a2c598d569ece652e72fdfb586af0b95d3c73bd3c467d024dd31f9bb27be403", "started_at": "2026-10-24T20:31:10.169432+00:00", "timing": { "prepare_ms": 24023, "solve_ms": 4241872, "grade_ms": null }, "original_submission_valid": false, "model_provenance": "requested_only", "tokens": { "input": 20399295, "cached_input": 20113664, "fresh_input": 285631, "output": 134781, "reasoning_output": 43182, "total": 20534076, "coverage": "reported_completed_root_turns" }, "tools": { "mcp_calls": 566, "unica_calls": 566, "failed_calls": 36 }, "process": { "status": "completed", "exit_code": 0, "stop_confirmed": true } }, "verification": "contributor_reported", "download": "community-downloads/demo-20261025T154959Z-adapter/solution.zip", "source_context": "community-downloads/demo-20261025T154959Z-adapter/source-context.json", "regrade_required": [ { "id": "grader_changed", "files": [ "assessment.py", "bp.py", "calcwrite.py", "calibrate.py", "calibration_periodicity.py", "calibration_query.py", "claude.py", "codescan.py", "codex.py", "common.py", "docx_text.py", "examiner.py", "harness.py", "interpretations.py", "locking.py", "materials.py", "mcp_toolkit.py", "ou.py", "penalties.py", "portable_harnesses.py", "pr.py", "preflight.py", "queries.py", "queryschema.py", "querytypes.py", "replay_calibration.py", "rules/1c-specialist-platform/chistov.json", "rules/1c-specialist-platform/examiner.json", "rules/1c-specialist-platform/rules.json", "rules/1c-specialist-platform/standards.json", "smoke_check.py", "starters/carcass-8.3.25.1445/starter.json", "stdio_harnesses.py", "tasks/1c-platform-official-sample/checks.json", "tasks/1c-platform-official-sample/private/official-assessment-mapping.json", "tasks/1c-platform-official-sample/private/owner-scoring-policy.json", "telemetry.py" ] } ], "grader_revision_sha256": "855d4f66db31ec9f50ebfc18f596c0d1d157e53e2830c51f853c1338f628e49c", "archive_sha256": "53952d6053070a87db5e5c228473990309f73cebd0ab09f2cfad0ebd196abf82" } ] }, { "id": "demo-20261025T192940Z-5ea870--owner-2026-10-26T223346603771-0000", "run_id": "demo-20261025T192940Z-5ea870", "result": { "run_id": "demo-20261025T192940Z-5ea870", "created_at": "2026-10-26T22:33:46.603771+00:00", "model": "gpt-6.1-sol", "harness": "ai-rules-1c-3f909dc", "solve_seconds": 6874, "platform": "8.3.27.1688", "counts": { "pass": 62, "inconclusive": 1, "fail": 2 }, "rules": [ { "id": "BU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU01.selected_fixture" }, { "id": "BU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU04.selected_fixture" }, { "id": "BU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU05.selected_fixture" }, { "id": "BU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU16.selected_fixture" }, { "id": "BU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU17.selected_fixture" }, { "id": "BU02", "verdict": "pass", "reason": null, "coverage": "partial", "assertion_id": "BU02.posting_cost_and_balance" }, { "id": "BU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU10.selected_fixture" }, { "id": "BU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU12.selected_fixture" }, { "id": "BU03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU03.selected_fixture" }, { "id": "BU06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU06.selected_fixture" }, { "id": "BU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU07.selected_fixture" }, { "id": "BU08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU08.selected_fixture" }, { "id": "BU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU09.selected_fixture" }, { "id": "BU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU11.selected_fixture" }, { "id": "BU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU14.selected_fixture" }, { "id": "BU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU15.selected_fixture" }, { "id": "BU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU13.selected_fixture" }, { "id": "OU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU15.selected_fixture" }, { "id": "OU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU16.selected_fixture" }, { "id": "OU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU17.selected_fixture" }, { "id": "OU02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU02.selected_fixture" }, { "id": "OU18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU18.selected_fixture" }, { "id": "OU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU14.selected_fixture" }, { "id": "OU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU01.selected_fixture" }, { "id": "OU03", "verdict": "pass", "reason": "История и годовая периодичность регистра подтверждены.", "coverage": "history_and_periodicity", "assertion_id": "OU03.selected_fixture" }, { "id": "OU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU05.selected_fixture" }, { "id": "OU06", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "OU06.selected_fixture" }, { "id": "OU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU07.selected_fixture" }, { "id": "OU08", "verdict": "inconclusive", "reason": "Недостаточно данных: периодичность регистра specification — Second, ожидается Day; проверка другим способом не исключена", "coverage": "history_and_periodicity", "assertion_id": "OU08.selected_fixture" }, { "id": "OU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU09.selected_fixture" }, { "id": "OU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU10.selected_fixture" }, { "id": "OU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU11.selected_fixture" }, { "id": "OU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU12.selected_fixture" }, { "id": "OU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU13.selected_fixture" }, { "id": "OU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU04.selected_fixture" }, { "id": "OU19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU19.selected_fixture" }, { "id": "OU20", "verdict": "fail", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU20.selected_fixture" }, { "id": "OU21", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU21.selected_fixture" }, { "id": "PR01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR01.selected_fixture" }, { "id": "PR02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR02.selected_fixture" }, { "id": "PR03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR03.selected_fixture" }, { "id": "PR04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR04.selected_fixture" }, { "id": "PR05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR05.selected_fixture" }, { "id": "PR06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR06.selected_fixture" }, { "id": "PR07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR07.selected_fixture" }, { "id": "PR08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR08.selected_fixture" }, { "id": "PR09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR09.selected_fixture" }, { "id": "PR10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR10.selected_fixture" }, { "id": "PR11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR11.selected_fixture" }, { "id": "PR12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR12.selected_fixture" }, { "id": "PR13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR13.selected_fixture" }, { "id": "PR14", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "PR14.selected_fixture" }, { "id": "PR15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR15.selected_fixture" }, { "id": "PR16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR16.selected_fixture" }, { "id": "PR17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR17.selected_fixture" }, { "id": "PR18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR18.selected_fixture" }, { "id": "PR19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR19.selected_fixture" }, { "id": "F01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F01.selected_fixture" }, { "id": "F02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F02.selected_fixture" }, { "id": "F03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F03.selected_fixture" }, { "id": "F04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F04.selected_fixture" }, { "id": "F05", "verdict": "fail", "reason": "typed ['C1', 'C2'], written True, stored [('BENCH_Валюта', ''), ('BENCH_Срок', '')]", "coverage": "selected_fixture", "assertion_id": "F05.selected_fixture" }, { "id": "G01", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G01.static_sources" }, { "id": "G02", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G02.static_sources" }, { "id": "G03", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G03.static_sources" } ], "charges": [ { "id": "F1C-GEN03", "points": "0.5", "reason": "отчёт не соответствует заданию: OU20" }, { "id": "F1C-GEN01", "points": "0.5", "reason": "не выполнено требование: F05 — typed ['C1', 'C2'], written True, stored [('BENCH_Валюта', ''), ('BENCH_Срок', '')]" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "оперативное проведение разрешено у документов с движениями по регистрам расчёта: НачислениеЗарплаты" }, { "id": "F1C-GEN22", "points": "1.0", "reason": "значения графика выбираются без ЕСТЬNULL: CommonModules/РасчетЗарплаты/Ext/Module.bsl:127 ДниФактическийПериодДействия, ЧасыПериодДействия, ЧасыФактическийПериодДействия" } ], "score_upper_bound": "2.0", "score": null, "grade": "unsatisfactory", "deductions": "3.0", "not_assessed": 14, "gates": { "starter_origin": "passed", "load": "loaded", "clients": "compiles", "demo_data": "present" }, "infrastructure_errors": false, "comparison_eligible": false, "binding_compatibility": null }, "measurement": { "operator": { "name": "Vasiliy", "github": "Gh0sTspp" }, "environment": { "captured_at": "2026-10-25T19:29:42.279803+00:00", "capture_timing": "before_run", "hardware": { "cpu": "Intel(R) Core(TM) i7-5820K CPU @ 3.30GHz", "logical_cpus": 12, "ram_bytes": 34189709312 }, "os": { "system": "Windows", "release": "10", "version": "10.0.19045", "architecture": "AMD64" }, "python": "3.13.12", "platform_version": "8.3.27.1688", "isolation": "dedicated-host", "network_profile": "open-book_shell", "unsafe_action_protection_observed_in_user_config": true, "git_revision": "4a5af75e72de6dafa32f07df84375c1b2ea9488a", "implementation_files": { "exam_bench/__init__.py": "ad5bf6f05dc6765f40b78bd186870ca2c49be113cfa33f8aa76f4926f2cb2c1e", "exam_bench/assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "exam_bench/bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "exam_bench/calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "exam_bench/calibrate.py": "78b5185cb0888c0c0ac3de95ffc3a80154a6de9ae66fc461f79d012e5a58e1db", "exam_bench/calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "exam_bench/calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "exam_bench/calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "exam_bench/calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "exam_bench/calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "exam_bench/claude.py": "7df8c92365863665b74379044eefa3bc84009c9a639225465a667ac294cd286a", "exam_bench/cli.py": "1a37ce645633d761f7897dffc9c45e6b8b9600cd7bd233b1cbf78f49d26b099a", "exam_bench/codescan.py": "751e38001b6e65727a31e28172a0623f0bf34bc092a958037c286aa991a197ed", "exam_bench/codex.py": "c3f89d72af11f312d851c73a1610d92e79acadf336be9ccedd1f94ede3b3ccb0", "exam_bench/common.py": "8682603b519063e655eae3574a02a49efee63bde21f582ccee20ddd623fca96d", "exam_bench/docker_services.py": "3cd9d78070856ae3f8bf4f1e50aee90f627ec20e5150e8b8c0c57b6dacae7323", "exam_bench/docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "exam_bench/examiner.py": "d7294fdd23ed1732216cafebf0a8cf2c24cce4259859aeb7149f62b7607d087d", "exam_bench/finalize.py": "4034f1c63896a940afdb1a83d541cf47fc75c8b5061e3f839047109c04beb620", "exam_bench/forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "exam_bench/gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "exam_bench/grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "exam_bench/harness.py": "3040f6daaf1dc6e6583219f4d925151f8ba7851b2d5417d7f14645892b485ddf", "exam_bench/interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "exam_bench/interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "exam_bench/isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "exam_bench/ledger.py": "7e851523580e22d8490e75f9b6026c07f2c355007e0d11d0b252671f56bef654", "exam_bench/locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "exam_bench/materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "exam_bench/mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "exam_bench/observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "exam_bench/ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "exam_bench/penalties.py": "0d79e2e46102657dca00609b6abbfc0bf7d11fad41429564f876c82bc6b33269", "exam_bench/platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "exam_bench/portable.py": "cad56968ff407983608f5bdbc9ce7234128d7a4580b096ecea8e0e7b4edb9070", "exam_bench/portable_harnesses.py": "6fc286cb7b35c9f869a92fd08c95ed5ac3f90d6ba21ba32034ea4de73275bd69", "exam_bench/pr.py": "6a3a20caf0e10c0cc94410511a72d62c9fcda785f3abab1be2ad616d4ee16836", "exam_bench/preflight.py": "5619be0131d8641925f3ce2a3c8e5234d42aa5635d95676138ca81536d95cd29", "exam_bench/process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "exam_bench/queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "exam_bench/queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "exam_bench/replay_calibration.py": "e2d79cb508f2d5e3846d6dad36c3898d41dec1c573c1a1b7d8a2ec43e33c8c08", "exam_bench/report.py": "5e4c0757e1c7f189953f9a5302593ab726551835856baed25efd93dad6e8bfcd", "exam_bench/runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "exam_bench/smoke_check.py": "f36922a0027429ead0b414048dcc14bbe67f2f0e79a70d03dffbe1447d253545", "exam_bench/stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "exam_bench/submission.py": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "exam_bench/telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "exam_bench/windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "exam_bench/workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tools/build_public_site.py": "9682ed696f5ac9e9a82b65a45c0dece556ec7e49eeb20dcd616882cc534a8258", "tools/build_result_site.py": "3294e1d2ec1486058e208735264d61e349a68a4ae2fa2ec7a723c70e3263b496", "tools/check_native_harnesses.py": "ff9aabf660569eb5a20dd9ce4cfa235c313a42e10cd0c89e571fcafe95bb94c8", "tools/check_native_toolkit.py": "0272794617121f2932828e5e4e9ae20095183c443666cf3ba466b44fbe875095", "tools/community_results.py": "3f4c0067088353ec5bba8ea32decba5e205c3f7993cc305d07693b54c7039a23", "tools/community_service.py": "c374480dbd88d656c0b9054fa04a8e1c6698c69e2f9cf475e82498a2dff61d84", "tools/community_setup.py": "5d7d126ed7d4dd48e1d79f57b99647a92ffcc8c9f80d90915e458888cdd76bf7", "tools/compare_harness_runs.py": "f274df5f3f804cb02504491aec946943833e12fbce6e62d281e12beb8508fc4e", "tools/create_run_plan.py": "871cd81b1eda231c0fba8805f63d2668926be9fc641559e6ddf320e2f47cd37a", "tools/demo_runner.py": "96c099c95b019ac30df5b2900991d0161ca73af6bdfa73a74e4172ba9c1deb00", "tools/installers.py": "9a2742780936b17500869e7c89202c1a2549e37d53a42ad9a50a0abbf78bbe09", "tools/machine_bundle.py": "8aa8346f99f537e81ceca6fb6ab9530e844954bab8eff87bf33d3602f81f8a30", "tools/prepare_native_harnesses.py": "b1909332ea4426acdb262685a7a9f4f02feaebc09421af613dc1333ce53529d8", "tools/prepare_official_statement.py": "6b7028c78e90e798d6ef1a93b76520cc61a308c354fb9b87f7fad18b99800fad", "tools/prepare_open_exam_requirements.py": "544f4e378b9be5f166186f8788f8d454afdac2deb99d91d98421e39d01ba6d03", "tools/probe_harness.py": "1ed8ef93420d1484cbbfd151b7efc31b9a201ceb942dd05e3103efa22ffa7f27", "tools/probe_native_mcp.py": "989a2b1d30bf91f42e5512e60c1597c7e32534bdd46b4e2654c665a59a3acf4b", "tools/readiness.py": "0b71ab667e6b2d9979fb3e5a769ebb8a453edec80a71090fb0b21b45af7986ce", "tools/recheck_community.py": "f0843d7d677f90da31e22bde0b1c86584dd46c022f1532d43d042619e426b230", "tools/regrade_runs.py": "011775afb06d3aac67a4aa81117a368c75896b0fcbe1e6f27ccc6237612fbf59", "tools/render_statement_text.py": "dabc0716a3612c288c671bc20e17fd4986691d732768e1e957d6dddddbea92a3", "tools/replay_calibration.py": "801f5004926c438c21ed3668fe2a4ddf45312b3e75320165a3839aae034eee9b", "tools/run_exam_campaign.py": "2c450d57a1cd0a2682838f5ec7c0a4ffb3aed0f1730d34c408e912d59cab6efd", "tools/serve_result_site.py": "86badfac863cd4ad1fc894a14110c75b28470513f0133eeae9d2799b8b4df3a9", "tools/start_demo.py": "c597e6cad28d245b3191654bb3e2801fa9dd2364e2acb25561923613717b615f", "tools/supplemental_acceptance.py": "7327277143d80a531e4c254ac74a9fc0e0d5c76572d53b8469e0a580eda17d65", "tools/sync_sources.py": "b51e889b0f41f9f63bfb19a09fb96d3777693d6b1d76fe0132bdd2a15e155898", "tools/validate_community_pr.py": "796b896dfade07b4529af2088a4b9b9d23484148b3bc0732b3fb837b75c9844b", "tools/verify_official_assessment_mapping.py": "daeb448a016940d5b6b1285979a56e5b9014bd91db40acb131445e4a83a23059", "tools/verify_task_package.py": "9e1e6105f6b5e4e78b36aa57f00117a9fbc8948ab53983c32ab56da88d23ccc4", "profiles/agents.json": "af9c492c08d13b3044aa6b6952589ed6a0a07d5258d8ff72bb18185b3eaebdc5", "profiles/ai-exam-execution-policy.json": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "profiles/bsl-analyzer-0.3.2-macos.json": "83537abdbf38c41ce665e4d0f24128bb51b62e971e0e0f368695f1326a7d2ffb", "profiles/bsl-analyzer-0.3.2-portable.json": "d6ba732e6778e256df34d6bc548593128820a70430c35b279796843606ee40a8", "profiles/bsl-ls-1.1.0-rc.6-macos.json": "245fc10747197e6911b2b4c77cdb15e6fa4eb7bc7c3758b63e768c5adf1df180", "profiles/bsl-ls-1.1.0-rc.6-portable.json": "9f10660881f2ec84794f7d584556b8f75c7e14b3555464af0ed0e60c4c892d86", "profiles/code-index-1.9.0-macos.json": "63a919523ce62ecec274f4c139bc7ad49a75dd4c339568b822cbc695b4e30408", "profiles/code-index-1.9.0-portable.json": "81106cee8f424ffd8a9dc46ecd8e4f57598fc1d49661a83c77b1f0507993fbdc", "profiles/codex-probe-plan.json": "166e41aad5fb3b27d9050bc6de952c6cba363cc6e804d4080568cc71a2a4d289", "profiles/machine.linux.example.json": "408304fd0581098d5d8110dc67dfeab353bc4d4030e32d37e6acf98d2b1aedfd", "profiles/machine.macos.example.json": "52e9f9d17797cb520b9d8955d6806fd550b899bed4da241ebf096dcb6a21a942", "profiles/machine.windows.example.json": "63accac9a2f81d47d03447efbabffd4760aee325193f02f46b9b29a28d50d2d8", "profiles/mcp-toolkit-1.9.0-macos.json": "1d3f9cde5ffa20589a840d01fdae03aa0fc2f412c929f064f203919c4129625b", "profiles/mcp-toolkit-1.9.0-portable.json": "8e370eebe773eef0e08045ee9c6d5be1451f769f65be0710834b262a4336e054", "profiles/none-macos.json": "b1401d9c48159aed3559006c7f6ace6ef4571224d5cf0bb76d1a823505a10056", "profiles/none-portable.json": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "profiles/rlm-tools-bsl-1.43.0-macos.json": "9354421052640ab60bc3e6aa98ff2e7ba9ca2318b0f4026c137487449242cbd2", "profiles/rlm-tools-bsl-1.43.0-portable.json": "2599e5645e0a7d4e44cb2934bc2b272cae79a9bf7ea74a23cd48aacea64bc424", "profiles/rlm-tools-bsl-1.43.0-posix-requirements.txt": "4fdf9a1bd994bf0272e65d231daf76cf19b0a34dad0ae6b50ec4f11a2ce4c330", "profiles/rlm-tools-bsl-1.43.0-windows-requirements.txt": "3730cb46c81cda5181ecd4485e98b11933104632358bc86f8c0eb1a612a8954f", "profiles/shirokov-skills-macos.json": "84f3e89091676884a802035c707e912762a1179425fb8e3faff25be736873cdb", "profiles/shirokov-skills-portable.json": "2b0a461e06602f1456410e70f02ceaa5ac32c6549c486660bcb5ace0c2f87b15", "profiles/shirokov-skills-windows-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/unica-0.12.3-macos.json": "2c39fbb591cf2c2c6e056373823615485397ea83651b7926c6f25a5fe6a0aae6", "profiles/unica-0.13.0-macos.json": "b76b5c8a4dd33f571c4a90993f1a2da5f7223b4f0f8e1042c282e21a66121052", "profiles/unica-0.14.0-rc.1-portable.json": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "rules/1c-specialist-platform/chistov.json": "7a42ef723a1f5f03f02c387cd3ca95725f7364c2e11ebdfc988a02919ab22c37", "rules/1c-specialist-platform/decisions.json": "f622107423ce3c188c063318d7ab4f7718ceb38e443130677d8987f386641c09", "rules/1c-specialist-platform/examiner.json": "30353aa2a1b6545496b070d9066e9ffba0c3779e5b53ef70a4fd2cee375b18c0", "rules/1c-specialist-platform/ledger.json": "f167c10db2b5799dd9a1ea6a37cd2d7d186810dadf5ea2f50f26ae723c676882", "rules/1c-specialist-platform/rules.json": "1d320a4f8e1bf4701496388931f492315549bd3dce574b17285dd1d7f8652007", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" } } }, "conditions": { "client": "codex", "model": "gpt-6.1-sol", "client_version": "0.164.0", "reasoning_effort": "medium", "harness": "ai-rules-1c-3f909dc", "billing_channel": "subscription", "solve_timeout_seconds": 7200, "time_series": null, "delegation": "native_disabled", "network_profile": "open-book_shell", "deadline_disclosed": true, "statement_sha256": "8a6ccb3e673826d1f8220fda53eb310e3ec18c136d87ce8f4cebb2a08614e7e5", "starter_dt_sha256": "f40d084818b0d1cfe503fc7653a6a13f1a8e47fcd1688dad6245b12744eb4638", "profile_sha256": "8c5dd51ff06982703b86f733da56d172dd452f3db00b2c9a00296e8176fee580", "execution_policy_sha256": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "calibration_sha256": "fb1dcb74e6b2bd4731d30b0ffc4bd84053cebd2ed4006d67be20b878b4bc7fd4", "started_at": "2026-10-25T19:30:10.853392+00:00", "timing": { "prepare_ms": 27420, "solve_ms": 6874394, "grade_ms": null }, "original_submission_valid": true, "model_provenance": "requested_only", "tokens": { "input": 62582144, "cached_input": 62026624, "fresh_input": 555520, "output": 218385, "reasoning_output": 89058, "total": 62800529, "coverage": "reported_completed_root_turns" }, "tools": { "mcp_calls": 277, "unica_calls": 0, "failed_calls": 11 }, "process": { "status": "completed", "exit_code": 0, "stop_confirmed": true } }, "verification": "repository_owner", "download": "community-downloads/demo-20261025T192940Z-5ea870--owner-2026-10-26T223346603771-0000/solution.zip", "source_context": "community-downloads/demo-20261025T192940Z-5ea870--owner-2026-10-26T223346603771-0000/source-context.json", "regrade_required": [], "grader_revision_sha256": "9aee1ffe0e1d04f9158fbbbeed3a403a5f0550ad8a590d7a6394977590760e1a", "archive_sha256": "8b81ba251e02c23a61b3444497166aa8e7e195c2befb49bd189c0fd93f915bca", "owner_verification": { "kind": "repository_owner", "repository": "zeegin/1c-agent-exam-benchmark", "operator": { "name": "Ingvar Vilkman", "github": "zeegin" }, "started_at": "2026-10-26T22:33:46.453230+00:00", "server": { "name": "Owner Windows stand", "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "hardware": { "cpu": "AMD Ryzen 7 5800X 8-Core Processor ", "logical_cpus": 4, "ram_bytes": 17109000192 }, "isolation": "dedicated-host" }, "platform_version": "8.3.27.2342", "grader": { "profile": "technical-v8", "commit": "e15c8ea80263c0b38baa3a1fc19611983270e8a7", "working_tree_dirty": false, "fingerprint": { "assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "calibrate.py": "aac127e03744907fd52ef149b88aa6d88a54a2b7497d56084484ee1b99e0da99", "calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "calibration_periodicity.py": "0b1953d7781e236467897cd2ed66705b75d9719353a2de60b36f2bbdfe799108", "calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "calibration_query.py": "3555b103cde8ea0519955cf52358d09223f5ab183a9df00533bdb48c89237a8c", "claude.py": "5bae98af6e2021e2718afa3a71ed04bee812deaae31a43d4e7324814139ccc82", "codescan.py": "6d8375210cef1fd768fc2d98d630d880b2993a9724f01ae25f33b4ea5aa9631d", "codex.py": "904e75503cd35f16cbb052f66806b3879fe25bfc9f99e33b93c889d862c46324", "common.py": "739b39e2bb9bdd4a571fc69df5843190cddcad094ef7e68964061bc1266b20dc", "docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "examiner.py": "8cdffcdd52f043c905f896697403380af95bf485dd4a5edca24f7956e7795ffe", "forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "harness.py": "3cbb90fd3187e700b5df32e5daafb20313d49bb5721c826e3033cbc6aa6e3825", "interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "ou.py": "f62784b54a3f85576a078a2ff1908c9395f3159e55f6bb5b1a3c564392241abe", "penalties.py": "ae388cb8953ecca1f2370a7c4cb1db3b6cc8318fc2a7563a4db15f9f5b057429", "platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "pr.py": "2b6bfea0634703469605ce114f9274716b485852d9a55d9185c39893b14e4726", "preflight.py": "448c3120ab64b625abae3891be686c7a214ce4211f7cf651fd90e12c0b298433", "process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "queries.py": "1ef57e292db3e8967a733948371ecc542f743b811890d4fc509df17303b9c4ac", "queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "querytypes.py": "b645f489a2abc27762b4a9bbf4917e72f7b46dc053a74c0dca4a8fc46491b3ef", "replay_calibration.py": "e0e3d5ca6416934715b9735aa516046b8d19ad4ae690220eeacd96b198a5f86c", "runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "smoke_check.py": "7837e980986bcb54dc8bc1dfb5d0003deef11e05f6e11df3910fa509e1f74c8d", "stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "submission.py": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tasks/1c-platform-official-sample/checks.json": "7447a9b42d3e348d29d07f001cfb6bd269acd953b7117eba7cca2ce9f5a9a60d", "tasks/1c-platform-official-sample/private/official-assessment-mapping.json": "303587c0dabe77c1eeebb2017fe85539e3370b17c9090435e6e0325a66bd0644", "tasks/1c-platform-official-sample/private/owner-scoring-policy.json": "d26d534bb838ab1b5facb7bc033ca8ec40912133baadcdbad83b27fc577905f5", "starters/carcass-8.3.25.1445/starter.json": "0f7a7060885ba99a19402bfc6e63cc8fe979b0f491b040d3a01d5d21b304b3a6", "rules/1c-specialist-platform/rules.json": "ea75e34ace5de11ba3de403c63cd2c026db81d1d991f8531e4a779d4ce9788e7", "rules/1c-specialist-platform/examiner.json": "1247486ddd412d600db88d9c1db4ba501fc1994afd1dc2ebe85402fcc332f4c8", "rules/1c-specialist-platform/chistov.json": "800da27601a3f1c7ec1df64482fd4ad035e559ba0b390a274ed5031128487d3d", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" }, "sha256": "9aee1ffe0e1d04f9158fbbbeed3a403a5f0550ad8a590d7a6394977590760e1a" }, "method": "saved_platform_observations", "outcome": "complete", "completed_at": "2026-10-26T22:33:46.603771+00:00" }, "previous_evaluations": [ { "id": "demo-20261025T192940Z-5ea870--owner-2026-10-26T214427226417-0000", "run_id": "demo-20261025T192940Z-5ea870", "result": { "run_id": "demo-20261025T192940Z-5ea870", "created_at": "2026-10-26T21:44:27.226417+00:00", "model": "gpt-6.1-sol", "harness": "ai-rules-1c-3f909dc", "solve_seconds": 6874, "platform": "8.3.27.1688", "counts": { "pass": 63, "fail": 2 }, "rules": [ { "id": "BU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU01.selected_fixture" }, { "id": "BU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU04.selected_fixture" }, { "id": "BU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU05.selected_fixture" }, { "id": "BU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU16.selected_fixture" }, { "id": "BU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU17.selected_fixture" }, { "id": "BU02", "verdict": "pass", "reason": null, "coverage": "partial", "assertion_id": "BU02.posting_cost_and_balance" }, { "id": "BU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU10.selected_fixture" }, { "id": "BU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU12.selected_fixture" }, { "id": "BU03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU03.selected_fixture" }, { "id": "BU06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU06.selected_fixture" }, { "id": "BU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU07.selected_fixture" }, { "id": "BU08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU08.selected_fixture" }, { "id": "BU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU09.selected_fixture" }, { "id": "BU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU11.selected_fixture" }, { "id": "BU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU14.selected_fixture" }, { "id": "BU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU15.selected_fixture" }, { "id": "BU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU13.selected_fixture" }, { "id": "OU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU15.selected_fixture" }, { "id": "OU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU16.selected_fixture" }, { "id": "OU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU17.selected_fixture" }, { "id": "OU02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU02.selected_fixture" }, { "id": "OU18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU18.selected_fixture" }, { "id": "OU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU14.selected_fixture" }, { "id": "OU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU01.selected_fixture" }, { "id": "OU03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU03.selected_fixture" }, { "id": "OU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU05.selected_fixture" }, { "id": "OU06", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "OU06.selected_fixture" }, { "id": "OU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU07.selected_fixture" }, { "id": "OU08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU08.selected_fixture" }, { "id": "OU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU09.selected_fixture" }, { "id": "OU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU10.selected_fixture" }, { "id": "OU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU11.selected_fixture" }, { "id": "OU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU12.selected_fixture" }, { "id": "OU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU13.selected_fixture" }, { "id": "OU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU04.selected_fixture" }, { "id": "OU19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU19.selected_fixture" }, { "id": "OU20", "verdict": "fail", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU20.selected_fixture" }, { "id": "OU21", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU21.selected_fixture" }, { "id": "PR01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR01.selected_fixture" }, { "id": "PR02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR02.selected_fixture" }, { "id": "PR03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR03.selected_fixture" }, { "id": "PR04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR04.selected_fixture" }, { "id": "PR05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR05.selected_fixture" }, { "id": "PR06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR06.selected_fixture" }, { "id": "PR07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR07.selected_fixture" }, { "id": "PR08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR08.selected_fixture" }, { "id": "PR09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR09.selected_fixture" }, { "id": "PR10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR10.selected_fixture" }, { "id": "PR11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR11.selected_fixture" }, { "id": "PR12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR12.selected_fixture" }, { "id": "PR13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR13.selected_fixture" }, { "id": "PR14", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "PR14.selected_fixture" }, { "id": "PR15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR15.selected_fixture" }, { "id": "PR16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR16.selected_fixture" }, { "id": "PR17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR17.selected_fixture" }, { "id": "PR18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR18.selected_fixture" }, { "id": "PR19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR19.selected_fixture" }, { "id": "F01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F01.selected_fixture" }, { "id": "F02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F02.selected_fixture" }, { "id": "F03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F03.selected_fixture" }, { "id": "F04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F04.selected_fixture" }, { "id": "F05", "verdict": "fail", "reason": "typed ['C1', 'C2'], written True, stored [('BENCH_Валюта', ''), ('BENCH_Срок', '')]", "coverage": "selected_fixture", "assertion_id": "F05.selected_fixture" }, { "id": "G01", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G01.static_sources" }, { "id": "G02", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G02.static_sources" }, { "id": "G03", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G03.static_sources" } ], "charges": [ { "id": "F1C-GEN03", "points": "0.5", "reason": "отчёт не соответствует заданию: OU20" }, { "id": "F1C-GEN01", "points": "0.5", "reason": "не выполнено требование: F05 — typed ['C1', 'C2'], written True, stored [('BENCH_Валюта', ''), ('BENCH_Срок', '')]" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "оперативное проведение разрешено у документов с движениями по регистрам расчёта: НачислениеЗарплаты" }, { "id": "F1C-GEN22", "points": "1.0", "reason": "значения графика выбираются без ЕСТЬNULL: CommonModules/РасчетЗарплаты/Ext/Module.bsl:127 ДниФактическийПериодДействия, ЧасыПериодДействия, ЧасыФактическийПериодДействия" } ], "score_upper_bound": "2.0", "score": null, "grade": "unsatisfactory", "deductions": "3.0", "not_assessed": 14, "gates": { "starter_origin": "passed", "load": "loaded", "clients": "compiles", "demo_data": "present" }, "infrastructure_errors": false, "comparison_eligible": false, "binding_compatibility": null }, "measurement": { "operator": { "name": "Vasiliy", "github": "Gh0sTspp" }, "environment": { "captured_at": "2026-10-25T19:29:42.279803+00:00", "capture_timing": "before_run", "hardware": { "cpu": "Intel(R) Core(TM) i7-5820K CPU @ 3.30GHz", "logical_cpus": 12, "ram_bytes": 34189709312 }, "os": { "system": "Windows", "release": "10", "version": "10.0.19045", "architecture": "AMD64" }, "python": "3.13.12", "platform_version": "8.3.27.1688", "isolation": "dedicated-host", "network_profile": "open-book_shell", "unsafe_action_protection_observed_in_user_config": true, "git_revision": "4a5af75e72de6dafa32f07df84375c1b2ea9488a", "implementation_files": { "exam_bench/__init__.py": "ad5bf6f05dc6765f40b78bd186870ca2c49be113cfa33f8aa76f4926f2cb2c1e", "exam_bench/assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "exam_bench/bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "exam_bench/calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "exam_bench/calibrate.py": "78b5185cb0888c0c0ac3de95ffc3a80154a6de9ae66fc461f79d012e5a58e1db", "exam_bench/calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "exam_bench/calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "exam_bench/calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "exam_bench/calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "exam_bench/calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "exam_bench/claude.py": "7df8c92365863665b74379044eefa3bc84009c9a639225465a667ac294cd286a", "exam_bench/cli.py": "1a37ce645633d761f7897dffc9c45e6b8b9600cd7bd233b1cbf78f49d26b099a", "exam_bench/codescan.py": "751e38001b6e65727a31e28172a0623f0bf34bc092a958037c286aa991a197ed", "exam_bench/codex.py": "c3f89d72af11f312d851c73a1610d92e79acadf336be9ccedd1f94ede3b3ccb0", "exam_bench/common.py": "8682603b519063e655eae3574a02a49efee63bde21f582ccee20ddd623fca96d", "exam_bench/docker_services.py": "3cd9d78070856ae3f8bf4f1e50aee90f627ec20e5150e8b8c0c57b6dacae7323", "exam_bench/docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "exam_bench/examiner.py": "d7294fdd23ed1732216cafebf0a8cf2c24cce4259859aeb7149f62b7607d087d", "exam_bench/finalize.py": "4034f1c63896a940afdb1a83d541cf47fc75c8b5061e3f839047109c04beb620", "exam_bench/forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "exam_bench/gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "exam_bench/grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "exam_bench/harness.py": "3040f6daaf1dc6e6583219f4d925151f8ba7851b2d5417d7f14645892b485ddf", "exam_bench/interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "exam_bench/interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "exam_bench/isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "exam_bench/ledger.py": "7e851523580e22d8490e75f9b6026c07f2c355007e0d11d0b252671f56bef654", "exam_bench/locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "exam_bench/materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "exam_bench/mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "exam_bench/observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "exam_bench/ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "exam_bench/penalties.py": "0d79e2e46102657dca00609b6abbfc0bf7d11fad41429564f876c82bc6b33269", "exam_bench/platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "exam_bench/portable.py": "cad56968ff407983608f5bdbc9ce7234128d7a4580b096ecea8e0e7b4edb9070", "exam_bench/portable_harnesses.py": "6fc286cb7b35c9f869a92fd08c95ed5ac3f90d6ba21ba32034ea4de73275bd69", "exam_bench/pr.py": "6a3a20caf0e10c0cc94410511a72d62c9fcda785f3abab1be2ad616d4ee16836", "exam_bench/preflight.py": "5619be0131d8641925f3ce2a3c8e5234d42aa5635d95676138ca81536d95cd29", "exam_bench/process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "exam_bench/queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "exam_bench/queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "exam_bench/replay_calibration.py": "e2d79cb508f2d5e3846d6dad36c3898d41dec1c573c1a1b7d8a2ec43e33c8c08", "exam_bench/report.py": "5e4c0757e1c7f189953f9a5302593ab726551835856baed25efd93dad6e8bfcd", "exam_bench/runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "exam_bench/smoke_check.py": "f36922a0027429ead0b414048dcc14bbe67f2f0e79a70d03dffbe1447d253545", "exam_bench/stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "exam_bench/submission.py": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "exam_bench/telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "exam_bench/windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "exam_bench/workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tools/build_public_site.py": "9682ed696f5ac9e9a82b65a45c0dece556ec7e49eeb20dcd616882cc534a8258", "tools/build_result_site.py": "3294e1d2ec1486058e208735264d61e349a68a4ae2fa2ec7a723c70e3263b496", "tools/check_native_harnesses.py": "ff9aabf660569eb5a20dd9ce4cfa235c313a42e10cd0c89e571fcafe95bb94c8", "tools/check_native_toolkit.py": "0272794617121f2932828e5e4e9ae20095183c443666cf3ba466b44fbe875095", "tools/community_results.py": "3f4c0067088353ec5bba8ea32decba5e205c3f7993cc305d07693b54c7039a23", "tools/community_service.py": "c374480dbd88d656c0b9054fa04a8e1c6698c69e2f9cf475e82498a2dff61d84", "tools/community_setup.py": "5d7d126ed7d4dd48e1d79f57b99647a92ffcc8c9f80d90915e458888cdd76bf7", "tools/compare_harness_runs.py": "f274df5f3f804cb02504491aec946943833e12fbce6e62d281e12beb8508fc4e", "tools/create_run_plan.py": "871cd81b1eda231c0fba8805f63d2668926be9fc641559e6ddf320e2f47cd37a", "tools/demo_runner.py": "96c099c95b019ac30df5b2900991d0161ca73af6bdfa73a74e4172ba9c1deb00", "tools/installers.py": "9a2742780936b17500869e7c89202c1a2549e37d53a42ad9a50a0abbf78bbe09", "tools/machine_bundle.py": "8aa8346f99f537e81ceca6fb6ab9530e844954bab8eff87bf33d3602f81f8a30", "tools/prepare_native_harnesses.py": "b1909332ea4426acdb262685a7a9f4f02feaebc09421af613dc1333ce53529d8", "tools/prepare_official_statement.py": "6b7028c78e90e798d6ef1a93b76520cc61a308c354fb9b87f7fad18b99800fad", "tools/prepare_open_exam_requirements.py": "544f4e378b9be5f166186f8788f8d454afdac2deb99d91d98421e39d01ba6d03", "tools/probe_harness.py": "1ed8ef93420d1484cbbfd151b7efc31b9a201ceb942dd05e3103efa22ffa7f27", "tools/probe_native_mcp.py": "989a2b1d30bf91f42e5512e60c1597c7e32534bdd46b4e2654c665a59a3acf4b", "tools/readiness.py": "0b71ab667e6b2d9979fb3e5a769ebb8a453edec80a71090fb0b21b45af7986ce", "tools/recheck_community.py": "f0843d7d677f90da31e22bde0b1c86584dd46c022f1532d43d042619e426b230", "tools/regrade_runs.py": "011775afb06d3aac67a4aa81117a368c75896b0fcbe1e6f27ccc6237612fbf59", "tools/render_statement_text.py": "dabc0716a3612c288c671bc20e17fd4986691d732768e1e957d6dddddbea92a3", "tools/replay_calibration.py": "801f5004926c438c21ed3668fe2a4ddf45312b3e75320165a3839aae034eee9b", "tools/run_exam_campaign.py": "2c450d57a1cd0a2682838f5ec7c0a4ffb3aed0f1730d34c408e912d59cab6efd", "tools/serve_result_site.py": "86badfac863cd4ad1fc894a14110c75b28470513f0133eeae9d2799b8b4df3a9", "tools/start_demo.py": "c597e6cad28d245b3191654bb3e2801fa9dd2364e2acb25561923613717b615f", "tools/supplemental_acceptance.py": "7327277143d80a531e4c254ac74a9fc0e0d5c76572d53b8469e0a580eda17d65", "tools/sync_sources.py": "b51e889b0f41f9f63bfb19a09fb96d3777693d6b1d76fe0132bdd2a15e155898", "tools/validate_community_pr.py": "796b896dfade07b4529af2088a4b9b9d23484148b3bc0732b3fb837b75c9844b", "tools/verify_official_assessment_mapping.py": "daeb448a016940d5b6b1285979a56e5b9014bd91db40acb131445e4a83a23059", "tools/verify_task_package.py": "9e1e6105f6b5e4e78b36aa57f00117a9fbc8948ab53983c32ab56da88d23ccc4", "profiles/agents.json": "af9c492c08d13b3044aa6b6952589ed6a0a07d5258d8ff72bb18185b3eaebdc5", "profiles/ai-exam-execution-policy.json": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "profiles/bsl-analyzer-0.3.2-macos.json": "83537abdbf38c41ce665e4d0f24128bb51b62e971e0e0f368695f1326a7d2ffb", "profiles/bsl-analyzer-0.3.2-portable.json": "d6ba732e6778e256df34d6bc548593128820a70430c35b279796843606ee40a8", "profiles/bsl-ls-1.1.0-rc.6-macos.json": "245fc10747197e6911b2b4c77cdb15e6fa4eb7bc7c3758b63e768c5adf1df180", "profiles/bsl-ls-1.1.0-rc.6-portable.json": "9f10660881f2ec84794f7d584556b8f75c7e14b3555464af0ed0e60c4c892d86", "profiles/code-index-1.9.0-macos.json": "63a919523ce62ecec274f4c139bc7ad49a75dd4c339568b822cbc695b4e30408", "profiles/code-index-1.9.0-portable.json": "81106cee8f424ffd8a9dc46ecd8e4f57598fc1d49661a83c77b1f0507993fbdc", "profiles/codex-probe-plan.json": "166e41aad5fb3b27d9050bc6de952c6cba363cc6e804d4080568cc71a2a4d289", "profiles/machine.linux.example.json": "408304fd0581098d5d8110dc67dfeab353bc4d4030e32d37e6acf98d2b1aedfd", "profiles/machine.macos.example.json": "52e9f9d17797cb520b9d8955d6806fd550b899bed4da241ebf096dcb6a21a942", "profiles/machine.windows.example.json": "63accac9a2f81d47d03447efbabffd4760aee325193f02f46b9b29a28d50d2d8", "profiles/mcp-toolkit-1.9.0-macos.json": "1d3f9cde5ffa20589a840d01fdae03aa0fc2f412c929f064f203919c4129625b", "profiles/mcp-toolkit-1.9.0-portable.json": "8e370eebe773eef0e08045ee9c6d5be1451f769f65be0710834b262a4336e054", "profiles/none-macos.json": "b1401d9c48159aed3559006c7f6ace6ef4571224d5cf0bb76d1a823505a10056", "profiles/none-portable.json": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "profiles/rlm-tools-bsl-1.43.0-macos.json": "9354421052640ab60bc3e6aa98ff2e7ba9ca2318b0f4026c137487449242cbd2", "profiles/rlm-tools-bsl-1.43.0-portable.json": "2599e5645e0a7d4e44cb2934bc2b272cae79a9bf7ea74a23cd48aacea64bc424", "profiles/rlm-tools-bsl-1.43.0-posix-requirements.txt": "4fdf9a1bd994bf0272e65d231daf76cf19b0a34dad0ae6b50ec4f11a2ce4c330", "profiles/rlm-tools-bsl-1.43.0-windows-requirements.txt": "3730cb46c81cda5181ecd4485e98b11933104632358bc86f8c0eb1a612a8954f", "profiles/shirokov-skills-macos.json": "84f3e89091676884a802035c707e912762a1179425fb8e3faff25be736873cdb", "profiles/shirokov-skills-portable.json": "2b0a461e06602f1456410e70f02ceaa5ac32c6549c486660bcb5ace0c2f87b15", "profiles/shirokov-skills-windows-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/unica-0.12.3-macos.json": "2c39fbb591cf2c2c6e056373823615485397ea83651b7926c6f25a5fe6a0aae6", "profiles/unica-0.13.0-macos.json": "b76b5c8a4dd33f571c4a90993f1a2da5f7223b4f0f8e1042c282e21a66121052", "profiles/unica-0.14.0-rc.1-portable.json": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "rules/1c-specialist-platform/chistov.json": "7a42ef723a1f5f03f02c387cd3ca95725f7364c2e11ebdfc988a02919ab22c37", "rules/1c-specialist-platform/decisions.json": "f622107423ce3c188c063318d7ab4f7718ceb38e443130677d8987f386641c09", "rules/1c-specialist-platform/examiner.json": "30353aa2a1b6545496b070d9066e9ffba0c3779e5b53ef70a4fd2cee375b18c0", "rules/1c-specialist-platform/ledger.json": "f167c10db2b5799dd9a1ea6a37cd2d7d186810dadf5ea2f50f26ae723c676882", "rules/1c-specialist-platform/rules.json": "1d320a4f8e1bf4701496388931f492315549bd3dce574b17285dd1d7f8652007", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" } } }, "conditions": { "client": "codex", "model": "gpt-6.1-sol", "client_version": "0.164.0", "reasoning_effort": "medium", "harness": "ai-rules-1c-3f909dc", "billing_channel": "subscription", "solve_timeout_seconds": 7200, "time_series": null, "delegation": "native_disabled", "network_profile": "open-book_shell", "deadline_disclosed": true, "statement_sha256": "8a6ccb3e673826d1f8220fda53eb310e3ec18c136d87ce8f4cebb2a08614e7e5", "starter_dt_sha256": "f40d084818b0d1cfe503fc7653a6a13f1a8e47fcd1688dad6245b12744eb4638", "profile_sha256": "8c5dd51ff06982703b86f733da56d172dd452f3db00b2c9a00296e8176fee580", "execution_policy_sha256": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "calibration_sha256": "fb1dcb74e6b2bd4731d30b0ffc4bd84053cebd2ed4006d67be20b878b4bc7fd4", "started_at": "2026-10-25T19:30:10.853392+00:00", "timing": { "prepare_ms": 27420, "solve_ms": 6874394, "grade_ms": null }, "original_submission_valid": true, "model_provenance": "requested_only", "tokens": { "input": 62582144, "cached_input": 62026624, "fresh_input": 555520, "output": 218385, "reasoning_output": 89058, "total": 62800529, "coverage": "reported_completed_root_turns" }, "tools": { "mcp_calls": 277, "unica_calls": 0, "failed_calls": 11 }, "process": { "status": "completed", "exit_code": 0, "stop_confirmed": true } }, "verification": "repository_owner", "download": "community-downloads/demo-20261025T192940Z-5ea870--owner-2026-10-26T214427226417-0000/solution.zip", "source_context": "community-downloads/demo-20261025T192940Z-5ea870--owner-2026-10-26T214427226417-0000/source-context.json", "regrade_required": [ { "id": "grader_changed", "files": [ "calibrate.py", "calibration_periodicity.py", "common.py", "ou.py", "replay_calibration.py", "smoke_check.py", "tasks/1c-platform-official-sample/checks.json" ] } ], "grader_revision_sha256": "349d87e0c7f531acbe35dd2b39c35722d8a877fedde97575b49e8466ab763c1d", "archive_sha256": "e7d74913d92a2a7ff0edb67ae85400977105ee597a586bcd7c13cb48e842acce", "owner_verification": { "kind": "repository_owner", "repository": "zeegin/1c-agent-exam-benchmark", "operator": { "name": "Ingvar Vilkman", "github": "zeegin" }, "started_at": "2026-10-26T21:44:27.061639+00:00", "server": { "name": "Owner Windows stand", "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "hardware": { "cpu": "AMD Ryzen 7 5800X 8-Core Processor ", "logical_cpus": 4, "ram_bytes": 17109000192 }, "isolation": "dedicated-host" }, "platform_version": "8.3.27.2342", "grader": { "profile": "technical-v8", "commit": "e8fd8ced03a85b549c5472fbbda29225749f54d1", "working_tree_dirty": false, "fingerprint": { "assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "calibrate.py": "3162d431f3cab5e7976aa39f665d6286dce45499cf362d85109b7123fa8403a2", "calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "calibration_query.py": "3555b103cde8ea0519955cf52358d09223f5ab183a9df00533bdb48c89237a8c", "claude.py": "eedabc75fca0faa434f40a1624b71419ec7dc22e2854a0886cf84b4911db8372", "codescan.py": "6d8375210cef1fd768fc2d98d630d880b2993a9724f01ae25f33b4ea5aa9631d", "codex.py": "904e75503cd35f16cbb052f66806b3879fe25bfc9f99e33b93c889d862c46324", "common.py": "52825cf5c29f3536d6e046a89e789d5ef9c83aacd7f2f5a07f4f53e77b5229cc", "docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "examiner.py": "8cdffcdd52f043c905f896697403380af95bf485dd4a5edca24f7956e7795ffe", "forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "harness.py": "3cbb90fd3187e700b5df32e5daafb20313d49bb5721c826e3033cbc6aa6e3825", "interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "penalties.py": "ae388cb8953ecca1f2370a7c4cb1db3b6cc8318fc2a7563a4db15f9f5b057429", "platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "pr.py": "2b6bfea0634703469605ce114f9274716b485852d9a55d9185c39893b14e4726", "preflight.py": "448c3120ab64b625abae3891be686c7a214ce4211f7cf651fd90e12c0b298433", "process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "queries.py": "1ef57e292db3e8967a733948371ecc542f743b811890d4fc509df17303b9c4ac", "queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "querytypes.py": "b645f489a2abc27762b4a9bbf4917e72f7b46dc053a74c0dca4a8fc46491b3ef", "replay_calibration.py": "0a4d9b84a9908944c5a945878eb6f5eeda5a4e42ffff4f55c04a680742803d80", "runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "smoke_check.py": "66caf1a01f7aa18432293abe3567ac228ac837a660b08c3dc7bb093f7bd51628", "stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "submission.py": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tasks/1c-platform-official-sample/checks.json": "17a6fcc0c14410829650623eb1443ce99796e000cdfd19905ac0287988b73a00", "tasks/1c-platform-official-sample/private/official-assessment-mapping.json": "303587c0dabe77c1eeebb2017fe85539e3370b17c9090435e6e0325a66bd0644", "tasks/1c-platform-official-sample/private/owner-scoring-policy.json": "d26d534bb838ab1b5facb7bc033ca8ec40912133baadcdbad83b27fc577905f5", "starters/carcass-8.3.25.1445/starter.json": "0f7a7060885ba99a19402bfc6e63cc8fe979b0f491b040d3a01d5d21b304b3a6", "rules/1c-specialist-platform/rules.json": "ea75e34ace5de11ba3de403c63cd2c026db81d1d991f8531e4a779d4ce9788e7", "rules/1c-specialist-platform/examiner.json": "1247486ddd412d600db88d9c1db4ba501fc1994afd1dc2ebe85402fcc332f4c8", "rules/1c-specialist-platform/chistov.json": "800da27601a3f1c7ec1df64482fd4ad035e559ba0b390a274ed5031128487d3d", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" }, "sha256": "349d87e0c7f531acbe35dd2b39c35722d8a877fedde97575b49e8466ab763c1d" }, "method": "saved_platform_observations", "outcome": "complete", "completed_at": "2026-10-26T21:44:27.226417+00:00" } }, { "id": "demo-20261025T192940Z-5ea870--owner-2026-10-26T192515458921-0000", "run_id": "demo-20261025T192940Z-5ea870", "result": { "run_id": "demo-20261025T192940Z-5ea870", "created_at": "2026-10-26T19:25:15.458921+00:00", "model": "gpt-6.1-sol", "harness": "ai-rules-1c-3f909dc", "solve_seconds": 6874, "platform": "8.3.27.1688", "counts": { "pass": 63, "fail": 2 }, "rules": [ { "id": "BU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU01.selected_fixture" }, { "id": "BU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU04.selected_fixture" }, { "id": "BU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU05.selected_fixture" }, { "id": "BU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU16.selected_fixture" }, { "id": "BU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU17.selected_fixture" }, { "id": "BU02", "verdict": "pass", "reason": null, "coverage": "partial", "assertion_id": "BU02.posting_cost_and_balance" }, { "id": "BU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU10.selected_fixture" }, { "id": "BU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU12.selected_fixture" }, { "id": "BU03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU03.selected_fixture" }, { "id": "BU06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU06.selected_fixture" }, { "id": "BU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU07.selected_fixture" }, { "id": "BU08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU08.selected_fixture" }, { "id": "BU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU09.selected_fixture" }, { "id": "BU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU11.selected_fixture" }, { "id": "BU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU14.selected_fixture" }, { "id": "BU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU15.selected_fixture" }, { "id": "BU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU13.selected_fixture" }, { "id": "OU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU15.selected_fixture" }, { "id": "OU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU16.selected_fixture" }, { "id": "OU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU17.selected_fixture" }, { "id": "OU02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU02.selected_fixture" }, { "id": "OU18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU18.selected_fixture" }, { "id": "OU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU14.selected_fixture" }, { "id": "OU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU01.selected_fixture" }, { "id": "OU03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU03.selected_fixture" }, { "id": "OU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU05.selected_fixture" }, { "id": "OU06", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "OU06.selected_fixture" }, { "id": "OU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU07.selected_fixture" }, { "id": "OU08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU08.selected_fixture" }, { "id": "OU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU09.selected_fixture" }, { "id": "OU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU10.selected_fixture" }, { "id": "OU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU11.selected_fixture" }, { "id": "OU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU12.selected_fixture" }, { "id": "OU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU13.selected_fixture" }, { "id": "OU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU04.selected_fixture" }, { "id": "OU19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU19.selected_fixture" }, { "id": "OU20", "verdict": "fail", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU20.selected_fixture" }, { "id": "OU21", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU21.selected_fixture" }, { "id": "PR01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR01.selected_fixture" }, { "id": "PR02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR02.selected_fixture" }, { "id": "PR03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR03.selected_fixture" }, { "id": "PR04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR04.selected_fixture" }, { "id": "PR05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR05.selected_fixture" }, { "id": "PR06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR06.selected_fixture" }, { "id": "PR07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR07.selected_fixture" }, { "id": "PR08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR08.selected_fixture" }, { "id": "PR09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR09.selected_fixture" }, { "id": "PR10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR10.selected_fixture" }, { "id": "PR11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR11.selected_fixture" }, { "id": "PR12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR12.selected_fixture" }, { "id": "PR13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR13.selected_fixture" }, { "id": "PR14", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "PR14.selected_fixture" }, { "id": "PR15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR15.selected_fixture" }, { "id": "PR16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR16.selected_fixture" }, { "id": "PR17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR17.selected_fixture" }, { "id": "PR18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR18.selected_fixture" }, { "id": "PR19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR19.selected_fixture" }, { "id": "F01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F01.selected_fixture" }, { "id": "F02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F02.selected_fixture" }, { "id": "F03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F03.selected_fixture" }, { "id": "F04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F04.selected_fixture" }, { "id": "F05", "verdict": "fail", "reason": "typed ['C1', 'C2'], written True, stored [('BENCH_Валюта', ''), ('BENCH_Срок', '')]", "coverage": "selected_fixture", "assertion_id": "F05.selected_fixture" }, { "id": "G01", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G01.static_sources" }, { "id": "G02", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G02.static_sources" }, { "id": "G03", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G03.static_sources" } ], "charges": [ { "id": "F1C-GEN03", "points": "0.5", "reason": "отчёт не соответствует заданию: OU20" }, { "id": "F1C-GEN01", "points": "0.5", "reason": "не выполнено требование: F05 — typed ['C1', 'C2'], written True, stored [('BENCH_Валюта', ''), ('BENCH_Срок', '')]" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "оперативное проведение разрешено у документов с движениями по регистрам расчёта: НачислениеЗарплаты" }, { "id": "F1C-GEN22", "points": "1.0", "reason": "значения графика выбираются без ЕСТЬNULL: CommonModules/РасчетЗарплаты/Ext/Module.bsl:127 ДниФактическийПериодДействия, ЧасыПериодДействия, ЧасыФактическийПериодДействия" } ], "score_upper_bound": "2.0", "score": null, "grade": "unsatisfactory", "deductions": "3.0", "not_assessed": 14, "gates": { "starter_origin": "passed", "load": "loaded", "clients": "compiles", "demo_data": "present" }, "infrastructure_errors": false, "comparison_eligible": false, "binding_compatibility": null }, "measurement": { "operator": { "name": "Vasiliy", "github": "Gh0sTspp" }, "environment": { "captured_at": "2026-10-25T19:29:42.279803+00:00", "capture_timing": "before_run", "hardware": { "cpu": "Intel(R) Core(TM) i7-5820K CPU @ 3.30GHz", "logical_cpus": 12, "ram_bytes": 34189709312 }, "os": { "system": "Windows", "release": "10", "version": "10.0.19045", "architecture": "AMD64" }, "python": "3.13.12", "platform_version": "8.3.27.1688", "isolation": "dedicated-host", "network_profile": "open-book_shell", "unsafe_action_protection_observed_in_user_config": true, "git_revision": "4a5af75e72de6dafa32f07df84375c1b2ea9488a", "implementation_files": { "exam_bench/__init__.py": "ad5bf6f05dc6765f40b78bd186870ca2c49be113cfa33f8aa76f4926f2cb2c1e", "exam_bench/assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "exam_bench/bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "exam_bench/calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "exam_bench/calibrate.py": "78b5185cb0888c0c0ac3de95ffc3a80154a6de9ae66fc461f79d012e5a58e1db", "exam_bench/calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "exam_bench/calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "exam_bench/calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "exam_bench/calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "exam_bench/calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "exam_bench/claude.py": "7df8c92365863665b74379044eefa3bc84009c9a639225465a667ac294cd286a", "exam_bench/cli.py": "1a37ce645633d761f7897dffc9c45e6b8b9600cd7bd233b1cbf78f49d26b099a", "exam_bench/codescan.py": "751e38001b6e65727a31e28172a0623f0bf34bc092a958037c286aa991a197ed", "exam_bench/codex.py": "c3f89d72af11f312d851c73a1610d92e79acadf336be9ccedd1f94ede3b3ccb0", "exam_bench/common.py": "8682603b519063e655eae3574a02a49efee63bde21f582ccee20ddd623fca96d", "exam_bench/docker_services.py": "3cd9d78070856ae3f8bf4f1e50aee90f627ec20e5150e8b8c0c57b6dacae7323", "exam_bench/docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "exam_bench/examiner.py": "d7294fdd23ed1732216cafebf0a8cf2c24cce4259859aeb7149f62b7607d087d", "exam_bench/finalize.py": "4034f1c63896a940afdb1a83d541cf47fc75c8b5061e3f839047109c04beb620", "exam_bench/forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "exam_bench/gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "exam_bench/grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "exam_bench/harness.py": "3040f6daaf1dc6e6583219f4d925151f8ba7851b2d5417d7f14645892b485ddf", "exam_bench/interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "exam_bench/interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "exam_bench/isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "exam_bench/ledger.py": "7e851523580e22d8490e75f9b6026c07f2c355007e0d11d0b252671f56bef654", "exam_bench/locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "exam_bench/materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "exam_bench/mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "exam_bench/observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "exam_bench/ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "exam_bench/penalties.py": "0d79e2e46102657dca00609b6abbfc0bf7d11fad41429564f876c82bc6b33269", "exam_bench/platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "exam_bench/portable.py": "cad56968ff407983608f5bdbc9ce7234128d7a4580b096ecea8e0e7b4edb9070", "exam_bench/portable_harnesses.py": "6fc286cb7b35c9f869a92fd08c95ed5ac3f90d6ba21ba32034ea4de73275bd69", "exam_bench/pr.py": "6a3a20caf0e10c0cc94410511a72d62c9fcda785f3abab1be2ad616d4ee16836", "exam_bench/preflight.py": "5619be0131d8641925f3ce2a3c8e5234d42aa5635d95676138ca81536d95cd29", "exam_bench/process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "exam_bench/queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "exam_bench/queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "exam_bench/replay_calibration.py": "e2d79cb508f2d5e3846d6dad36c3898d41dec1c573c1a1b7d8a2ec43e33c8c08", "exam_bench/report.py": "5e4c0757e1c7f189953f9a5302593ab726551835856baed25efd93dad6e8bfcd", "exam_bench/runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "exam_bench/smoke_check.py": "f36922a0027429ead0b414048dcc14bbe67f2f0e79a70d03dffbe1447d253545", "exam_bench/stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "exam_bench/submission.py": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "exam_bench/telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "exam_bench/windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "exam_bench/workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tools/build_public_site.py": "9682ed696f5ac9e9a82b65a45c0dece556ec7e49eeb20dcd616882cc534a8258", "tools/build_result_site.py": "3294e1d2ec1486058e208735264d61e349a68a4ae2fa2ec7a723c70e3263b496", "tools/check_native_harnesses.py": "ff9aabf660569eb5a20dd9ce4cfa235c313a42e10cd0c89e571fcafe95bb94c8", "tools/check_native_toolkit.py": "0272794617121f2932828e5e4e9ae20095183c443666cf3ba466b44fbe875095", "tools/community_results.py": "3f4c0067088353ec5bba8ea32decba5e205c3f7993cc305d07693b54c7039a23", "tools/community_service.py": "c374480dbd88d656c0b9054fa04a8e1c6698c69e2f9cf475e82498a2dff61d84", "tools/community_setup.py": "5d7d126ed7d4dd48e1d79f57b99647a92ffcc8c9f80d90915e458888cdd76bf7", "tools/compare_harness_runs.py": "f274df5f3f804cb02504491aec946943833e12fbce6e62d281e12beb8508fc4e", "tools/create_run_plan.py": "871cd81b1eda231c0fba8805f63d2668926be9fc641559e6ddf320e2f47cd37a", "tools/demo_runner.py": "96c099c95b019ac30df5b2900991d0161ca73af6bdfa73a74e4172ba9c1deb00", "tools/installers.py": "9a2742780936b17500869e7c89202c1a2549e37d53a42ad9a50a0abbf78bbe09", "tools/machine_bundle.py": "8aa8346f99f537e81ceca6fb6ab9530e844954bab8eff87bf33d3602f81f8a30", "tools/prepare_native_harnesses.py": "b1909332ea4426acdb262685a7a9f4f02feaebc09421af613dc1333ce53529d8", "tools/prepare_official_statement.py": "6b7028c78e90e798d6ef1a93b76520cc61a308c354fb9b87f7fad18b99800fad", "tools/prepare_open_exam_requirements.py": "544f4e378b9be5f166186f8788f8d454afdac2deb99d91d98421e39d01ba6d03", "tools/probe_harness.py": "1ed8ef93420d1484cbbfd151b7efc31b9a201ceb942dd05e3103efa22ffa7f27", "tools/probe_native_mcp.py": "989a2b1d30bf91f42e5512e60c1597c7e32534bdd46b4e2654c665a59a3acf4b", "tools/readiness.py": "0b71ab667e6b2d9979fb3e5a769ebb8a453edec80a71090fb0b21b45af7986ce", "tools/recheck_community.py": "f0843d7d677f90da31e22bde0b1c86584dd46c022f1532d43d042619e426b230", "tools/regrade_runs.py": "011775afb06d3aac67a4aa81117a368c75896b0fcbe1e6f27ccc6237612fbf59", "tools/render_statement_text.py": "dabc0716a3612c288c671bc20e17fd4986691d732768e1e957d6dddddbea92a3", "tools/replay_calibration.py": "801f5004926c438c21ed3668fe2a4ddf45312b3e75320165a3839aae034eee9b", "tools/run_exam_campaign.py": "2c450d57a1cd0a2682838f5ec7c0a4ffb3aed0f1730d34c408e912d59cab6efd", "tools/serve_result_site.py": "86badfac863cd4ad1fc894a14110c75b28470513f0133eeae9d2799b8b4df3a9", "tools/start_demo.py": "c597e6cad28d245b3191654bb3e2801fa9dd2364e2acb25561923613717b615f", "tools/supplemental_acceptance.py": "7327277143d80a531e4c254ac74a9fc0e0d5c76572d53b8469e0a580eda17d65", "tools/sync_sources.py": "b51e889b0f41f9f63bfb19a09fb96d3777693d6b1d76fe0132bdd2a15e155898", "tools/validate_community_pr.py": "796b896dfade07b4529af2088a4b9b9d23484148b3bc0732b3fb837b75c9844b", "tools/verify_official_assessment_mapping.py": "daeb448a016940d5b6b1285979a56e5b9014bd91db40acb131445e4a83a23059", "tools/verify_task_package.py": "9e1e6105f6b5e4e78b36aa57f00117a9fbc8948ab53983c32ab56da88d23ccc4", "profiles/agents.json": "af9c492c08d13b3044aa6b6952589ed6a0a07d5258d8ff72bb18185b3eaebdc5", "profiles/ai-exam-execution-policy.json": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "profiles/bsl-analyzer-0.3.2-macos.json": "83537abdbf38c41ce665e4d0f24128bb51b62e971e0e0f368695f1326a7d2ffb", "profiles/bsl-analyzer-0.3.2-portable.json": "d6ba732e6778e256df34d6bc548593128820a70430c35b279796843606ee40a8", "profiles/bsl-ls-1.1.0-rc.6-macos.json": "245fc10747197e6911b2b4c77cdb15e6fa4eb7bc7c3758b63e768c5adf1df180", "profiles/bsl-ls-1.1.0-rc.6-portable.json": "9f10660881f2ec84794f7d584556b8f75c7e14b3555464af0ed0e60c4c892d86", "profiles/code-index-1.9.0-macos.json": "63a919523ce62ecec274f4c139bc7ad49a75dd4c339568b822cbc695b4e30408", "profiles/code-index-1.9.0-portable.json": "81106cee8f424ffd8a9dc46ecd8e4f57598fc1d49661a83c77b1f0507993fbdc", "profiles/codex-probe-plan.json": "166e41aad5fb3b27d9050bc6de952c6cba363cc6e804d4080568cc71a2a4d289", "profiles/machine.linux.example.json": "408304fd0581098d5d8110dc67dfeab353bc4d4030e32d37e6acf98d2b1aedfd", "profiles/machine.macos.example.json": "52e9f9d17797cb520b9d8955d6806fd550b899bed4da241ebf096dcb6a21a942", "profiles/machine.windows.example.json": "63accac9a2f81d47d03447efbabffd4760aee325193f02f46b9b29a28d50d2d8", "profiles/mcp-toolkit-1.9.0-macos.json": "1d3f9cde5ffa20589a840d01fdae03aa0fc2f412c929f064f203919c4129625b", "profiles/mcp-toolkit-1.9.0-portable.json": "8e370eebe773eef0e08045ee9c6d5be1451f769f65be0710834b262a4336e054", "profiles/none-macos.json": "b1401d9c48159aed3559006c7f6ace6ef4571224d5cf0bb76d1a823505a10056", "profiles/none-portable.json": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "profiles/rlm-tools-bsl-1.43.0-macos.json": "9354421052640ab60bc3e6aa98ff2e7ba9ca2318b0f4026c137487449242cbd2", "profiles/rlm-tools-bsl-1.43.0-portable.json": "2599e5645e0a7d4e44cb2934bc2b272cae79a9bf7ea74a23cd48aacea64bc424", "profiles/rlm-tools-bsl-1.43.0-posix-requirements.txt": "4fdf9a1bd994bf0272e65d231daf76cf19b0a34dad0ae6b50ec4f11a2ce4c330", "profiles/rlm-tools-bsl-1.43.0-windows-requirements.txt": "3730cb46c81cda5181ecd4485e98b11933104632358bc86f8c0eb1a612a8954f", "profiles/shirokov-skills-macos.json": "84f3e89091676884a802035c707e912762a1179425fb8e3faff25be736873cdb", "profiles/shirokov-skills-portable.json": "2b0a461e06602f1456410e70f02ceaa5ac32c6549c486660bcb5ace0c2f87b15", "profiles/shirokov-skills-windows-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/unica-0.12.3-macos.json": "2c39fbb591cf2c2c6e056373823615485397ea83651b7926c6f25a5fe6a0aae6", "profiles/unica-0.13.0-macos.json": "b76b5c8a4dd33f571c4a90993f1a2da5f7223b4f0f8e1042c282e21a66121052", "profiles/unica-0.14.0-rc.1-portable.json": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "rules/1c-specialist-platform/chistov.json": "7a42ef723a1f5f03f02c387cd3ca95725f7364c2e11ebdfc988a02919ab22c37", "rules/1c-specialist-platform/decisions.json": "f622107423ce3c188c063318d7ab4f7718ceb38e443130677d8987f386641c09", "rules/1c-specialist-platform/examiner.json": "30353aa2a1b6545496b070d9066e9ffba0c3779e5b53ef70a4fd2cee375b18c0", "rules/1c-specialist-platform/ledger.json": "f167c10db2b5799dd9a1ea6a37cd2d7d186810dadf5ea2f50f26ae723c676882", "rules/1c-specialist-platform/rules.json": "1d320a4f8e1bf4701496388931f492315549bd3dce574b17285dd1d7f8652007", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" } } }, "conditions": { "client": "codex", "model": "gpt-6.1-sol", "client_version": "0.164.0", "reasoning_effort": "medium", "harness": "ai-rules-1c-3f909dc", "billing_channel": "subscription", "solve_timeout_seconds": 7200, "time_series": null, "delegation": "native_disabled", "network_profile": "open-book_shell", "deadline_disclosed": true, "statement_sha256": "8a6ccb3e673826d1f8220fda53eb310e3ec18c136d87ce8f4cebb2a08614e7e5", "starter_dt_sha256": "f40d084818b0d1cfe503fc7653a6a13f1a8e47fcd1688dad6245b12744eb4638", "profile_sha256": "8c5dd51ff06982703b86f733da56d172dd452f3db00b2c9a00296e8176fee580", "execution_policy_sha256": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "calibration_sha256": "fb1dcb74e6b2bd4731d30b0ffc4bd84053cebd2ed4006d67be20b878b4bc7fd4", "started_at": "2026-10-25T19:30:10.853392+00:00", "timing": { "prepare_ms": 27420, "solve_ms": 6874394, "grade_ms": null }, "original_submission_valid": true, "model_provenance": "requested_only", "tokens": { "input": 62582144, "cached_input": 62026624, "fresh_input": 555520, "output": 218385, "reasoning_output": 89058, "total": 62800529, "coverage": "reported_completed_root_turns" }, "tools": { "mcp_calls": 277, "unica_calls": 0, "failed_calls": 11 }, "process": { "status": "completed", "exit_code": 0, "stop_confirmed": true } }, "verification": "repository_owner", "download": "community-downloads/demo-20261025T192940Z-5ea870--owner-2026-10-26T192515458921-0000/solution.zip", "source_context": "community-downloads/demo-20261025T192940Z-5ea870--owner-2026-10-26T192515458921-0000/source-context.json", "regrade_required": [ { "id": "grader_changed", "files": [ "calibrate.py", "calibration_periodicity.py", "calibration_query.py", "common.py", "ou.py", "penalties.py", "queries.py", "replay_calibration.py", "rules/1c-specialist-platform/rules.json", "smoke_check.py", "tasks/1c-platform-official-sample/checks.json" ] } ], "grader_revision_sha256": "4a12b62d2c10085e1fc710f377f84903abdf2fb787dda19628d944da990a86b2", "archive_sha256": "d5b16ad119dcc5b6b6a8d4405fe1f305a6ce4877c49cb0f4158b6065f20d88ef", "owner_verification": { "kind": "repository_owner", "repository": "zeegin/1c-agent-exam-benchmark", "operator": { "name": "Ingvar Vilkman", "github": "zeegin" }, "started_at": "2026-10-26T19:22:12.204513+00:00", "server": { "name": "Owner Windows stand", "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "hardware": { "cpu": "AMD Ryzen 7 5800X 8-Core Processor ", "logical_cpus": 4, "ram_bytes": 17109000192 }, "isolation": "dedicated-host" }, "platform_version": "8.3.27.2342", "grader": { "profile": "technical-v8", "commit": "5b6a28372b253e81e22b83f8559df897297e28ff", "working_tree_dirty": true, "fingerprint": { "assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "calibrate.py": "1c844971b4977fdcc3b30aebe8aad40fbd45e6828955b8deb043ac8573d61731", "calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "claude.py": "eedabc75fca0faa434f40a1624b71419ec7dc22e2854a0886cf84b4911db8372", "codescan.py": "6d8375210cef1fd768fc2d98d630d880b2993a9724f01ae25f33b4ea5aa9631d", "codex.py": "904e75503cd35f16cbb052f66806b3879fe25bfc9f99e33b93c889d862c46324", "common.py": "7696116dd1a796666518b4c5d2aa3cafa04ee974593d3636333cbe5385bd6ccb", "docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "examiner.py": "8cdffcdd52f043c905f896697403380af95bf485dd4a5edca24f7956e7795ffe", "forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "harness.py": "3cbb90fd3187e700b5df32e5daafb20313d49bb5721c826e3033cbc6aa6e3825", "interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "penalties.py": "b82704e7f47d3dfdf6e501452d7e0abca1f9da63307093d2e257e32358be0489", "platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "pr.py": "2b6bfea0634703469605ce114f9274716b485852d9a55d9185c39893b14e4726", "preflight.py": "448c3120ab64b625abae3891be686c7a214ce4211f7cf651fd90e12c0b298433", "process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "querytypes.py": "b645f489a2abc27762b4a9bbf4917e72f7b46dc053a74c0dca4a8fc46491b3ef", "replay_calibration.py": "3b6f3a289cc8a7f5e458f62bfa2c6cc534cc9076ba3f22d1e4bd8a5f9e175317", "runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "smoke_check.py": "bd6266367e6b769a95258eb383239b89a22deae406d64f6e142c77396f4639ba", "stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "submission.py": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tasks/1c-platform-official-sample/checks.json": "17a6fcc0c14410829650623eb1443ce99796e000cdfd19905ac0287988b73a00", "tasks/1c-platform-official-sample/private/official-assessment-mapping.json": "303587c0dabe77c1eeebb2017fe85539e3370b17c9090435e6e0325a66bd0644", "tasks/1c-platform-official-sample/private/owner-scoring-policy.json": "d26d534bb838ab1b5facb7bc033ca8ec40912133baadcdbad83b27fc577905f5", "starters/carcass-8.3.25.1445/starter.json": "0f7a7060885ba99a19402bfc6e63cc8fe979b0f491b040d3a01d5d21b304b3a6", "rules/1c-specialist-platform/rules.json": "7ec895a7751ef17f4a50cc80b5f7fa986e1e04360ab0b4ce9aa29115195df03c", "rules/1c-specialist-platform/examiner.json": "1247486ddd412d600db88d9c1db4ba501fc1994afd1dc2ebe85402fcc332f4c8", "rules/1c-specialist-platform/chistov.json": "800da27601a3f1c7ec1df64482fd4ad035e559ba0b390a274ed5031128487d3d", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" }, "sha256": "4a12b62d2c10085e1fc710f377f84903abdf2fb787dda19628d944da990a86b2" }, "identity_verified_at": "2026-10-26T18:44:22.364471+00:00", "identity_session_sha256": "950670ab9a82059c65525d0d6e5b8a00f0dc292581edea3eb087c4ecadeaab09", "completed_at": "2026-10-26T19:25:15.458921+00:00" } }, { "id": "demo-20261025T192940Z-5ea870", "run_id": "demo-20261025T192940Z-5ea870", "result": { "run_id": "demo-20261025T192940Z-5ea870", "created_at": "2026-10-25T21:37:48.057071+00:00", "model": "gpt-6.1-sol", "harness": "ai-rules-1c-3f909dc", "solve_seconds": 6874, "platform": "8.3.27.1688", "counts": { "pass": 63, "fail": 2 }, "rules": [ { "id": "BU01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU16", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU17", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU02", "verdict": "pass", "coverage": "partial", "reason": null }, { "id": "BU10", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU12", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU06", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU07", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU08", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU09", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU11", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU14", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU15", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU13", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU15", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU16", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU17", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU02", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU18", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU14", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU06", "verdict": "pass", "coverage": "no_violation_found", "reason": null }, { "id": "OU07", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU08", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU09", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU10", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU11", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU12", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU13", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU19", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU20", "verdict": "fail", "coverage": "selected_fixture", "reason": "Ведомость не прошла проверку группировки по значениям характеристик." }, { "id": "OU21", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR02", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR06", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR07", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR08", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR09", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR10", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR11", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR12", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR13", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR14", "verdict": "pass", "coverage": "no_violation_found", "reason": null }, { "id": "PR15", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR16", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR17", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR18", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR19", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F02", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F05", "verdict": "fail", "coverage": "selected_fixture", "reason": null }, { "id": "G01", "verdict": "pass", "coverage": "static_sources", "reason": null }, { "id": "G02", "verdict": "pass", "coverage": "static_sources", "reason": null }, { "id": "G03", "verdict": "pass", "coverage": "static_sources", "reason": null } ], "charges": [ { "id": "F1C-GEN03", "points": "0.5", "reason": "Ведомость не прошла проверку группировки по значениям характеристик." }, { "id": "F1C-GEN01", "points": "0.5", "reason": "не выполнено требование: F05 — typed ['C1', 'C2'], written True, stored [('BENCH_Валюта', ''), ('BENCH_Срок', '')]" }, { "id": "F1C-GEN20", "points": "2.0", "reason": "данные базы читаются в цикле по записям: Documents/Сборка/Ext/ObjectModule.bsl:50" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "оперативное проведение разрешено у документов с движениями по регистрам расчёта: НачислениеЗарплаты" }, { "id": "F1C-GEN22", "points": "1.0", "reason": "значения графика выбираются без ЕСТЬNULL: CommonModules/РасчетЗарплаты/Ext/Module.bsl:127 ДниФактическийПериодДействия, ЧасыПериодДействия, ЧасыФактическийПериодДействия" } ], "score_upper_bound": "0.0", "score": null, "grade": "unsatisfactory", "deductions": "5.0", "not_assessed": 14, "gates": { "starter_origin": "passed", "load": "loaded", "clients": "compiles", "demo_data": "present" }, "infrastructure_errors": false, "comparison_eligible": false, "binding_compatibility": null, "evaluation_sha256": "7a1e42c50c986b93eeffd306f7918a4aaf5fcc6dd99fbd0f656343ee1e5a098d", "downloads": [] }, "measurement": { "operator": { "name": "Vasiliy", "github": "Gh0sTspp" }, "environment": { "captured_at": "2026-10-25T19:29:42.279803+00:00", "capture_timing": "before_run", "hardware": { "cpu": "Intel(R) Core(TM) i7-5820K CPU @ 3.30GHz", "logical_cpus": 12, "ram_bytes": 34189709312 }, "os": { "system": "Windows", "release": "10", "version": "10.0.19045", "architecture": "AMD64" }, "python": "3.13.12", "platform_version": "8.3.27.1688", "isolation": "dedicated-host", "network_profile": "open-book_shell", "unsafe_action_protection_observed_in_user_config": true, "git_revision": "4a5af75e72de6dafa32f07df84375c1b2ea9488a", "implementation_files": { "exam_bench/__init__.py": "ad5bf6f05dc6765f40b78bd186870ca2c49be113cfa33f8aa76f4926f2cb2c1e", "exam_bench/assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "exam_bench/bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "exam_bench/calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "exam_bench/calibrate.py": "78b5185cb0888c0c0ac3de95ffc3a80154a6de9ae66fc461f79d012e5a58e1db", "exam_bench/calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "exam_bench/calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "exam_bench/calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "exam_bench/calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "exam_bench/calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "exam_bench/claude.py": "7df8c92365863665b74379044eefa3bc84009c9a639225465a667ac294cd286a", "exam_bench/cli.py": "1a37ce645633d761f7897dffc9c45e6b8b9600cd7bd233b1cbf78f49d26b099a", "exam_bench/codescan.py": "751e38001b6e65727a31e28172a0623f0bf34bc092a958037c286aa991a197ed", "exam_bench/codex.py": "c3f89d72af11f312d851c73a1610d92e79acadf336be9ccedd1f94ede3b3ccb0", "exam_bench/common.py": "8682603b519063e655eae3574a02a49efee63bde21f582ccee20ddd623fca96d", "exam_bench/docker_services.py": "3cd9d78070856ae3f8bf4f1e50aee90f627ec20e5150e8b8c0c57b6dacae7323", "exam_bench/docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "exam_bench/examiner.py": "d7294fdd23ed1732216cafebf0a8cf2c24cce4259859aeb7149f62b7607d087d", "exam_bench/finalize.py": "4034f1c63896a940afdb1a83d541cf47fc75c8b5061e3f839047109c04beb620", "exam_bench/forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "exam_bench/gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "exam_bench/grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "exam_bench/harness.py": "3040f6daaf1dc6e6583219f4d925151f8ba7851b2d5417d7f14645892b485ddf", "exam_bench/interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "exam_bench/interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "exam_bench/isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "exam_bench/ledger.py": "7e851523580e22d8490e75f9b6026c07f2c355007e0d11d0b252671f56bef654", "exam_bench/locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "exam_bench/materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "exam_bench/mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "exam_bench/observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "exam_bench/ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "exam_bench/penalties.py": "0d79e2e46102657dca00609b6abbfc0bf7d11fad41429564f876c82bc6b33269", "exam_bench/platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "exam_bench/portable.py": "cad56968ff407983608f5bdbc9ce7234128d7a4580b096ecea8e0e7b4edb9070", "exam_bench/portable_harnesses.py": "6fc286cb7b35c9f869a92fd08c95ed5ac3f90d6ba21ba32034ea4de73275bd69", "exam_bench/pr.py": "6a3a20caf0e10c0cc94410511a72d62c9fcda785f3abab1be2ad616d4ee16836", "exam_bench/preflight.py": "5619be0131d8641925f3ce2a3c8e5234d42aa5635d95676138ca81536d95cd29", "exam_bench/process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "exam_bench/queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "exam_bench/queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "exam_bench/replay_calibration.py": "e2d79cb508f2d5e3846d6dad36c3898d41dec1c573c1a1b7d8a2ec43e33c8c08", "exam_bench/report.py": "5e4c0757e1c7f189953f9a5302593ab726551835856baed25efd93dad6e8bfcd", "exam_bench/runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "exam_bench/smoke_check.py": "f36922a0027429ead0b414048dcc14bbe67f2f0e79a70d03dffbe1447d253545", "exam_bench/stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "exam_bench/submission.py": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "exam_bench/telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "exam_bench/windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "exam_bench/workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tools/build_public_site.py": "9682ed696f5ac9e9a82b65a45c0dece556ec7e49eeb20dcd616882cc534a8258", "tools/build_result_site.py": "3294e1d2ec1486058e208735264d61e349a68a4ae2fa2ec7a723c70e3263b496", "tools/check_native_harnesses.py": "ff9aabf660569eb5a20dd9ce4cfa235c313a42e10cd0c89e571fcafe95bb94c8", "tools/check_native_toolkit.py": "0272794617121f2932828e5e4e9ae20095183c443666cf3ba466b44fbe875095", "tools/community_results.py": "3f4c0067088353ec5bba8ea32decba5e205c3f7993cc305d07693b54c7039a23", "tools/community_service.py": "c374480dbd88d656c0b9054fa04a8e1c6698c69e2f9cf475e82498a2dff61d84", "tools/community_setup.py": "5d7d126ed7d4dd48e1d79f57b99647a92ffcc8c9f80d90915e458888cdd76bf7", "tools/compare_harness_runs.py": "f274df5f3f804cb02504491aec946943833e12fbce6e62d281e12beb8508fc4e", "tools/create_run_plan.py": "871cd81b1eda231c0fba8805f63d2668926be9fc641559e6ddf320e2f47cd37a", "tools/demo_runner.py": "96c099c95b019ac30df5b2900991d0161ca73af6bdfa73a74e4172ba9c1deb00", "tools/installers.py": "9a2742780936b17500869e7c89202c1a2549e37d53a42ad9a50a0abbf78bbe09", "tools/machine_bundle.py": "8aa8346f99f537e81ceca6fb6ab9530e844954bab8eff87bf33d3602f81f8a30", "tools/prepare_native_harnesses.py": "b1909332ea4426acdb262685a7a9f4f02feaebc09421af613dc1333ce53529d8", "tools/prepare_official_statement.py": "6b7028c78e90e798d6ef1a93b76520cc61a308c354fb9b87f7fad18b99800fad", "tools/prepare_open_exam_requirements.py": "544f4e378b9be5f166186f8788f8d454afdac2deb99d91d98421e39d01ba6d03", "tools/probe_harness.py": "1ed8ef93420d1484cbbfd151b7efc31b9a201ceb942dd05e3103efa22ffa7f27", "tools/probe_native_mcp.py": "989a2b1d30bf91f42e5512e60c1597c7e32534bdd46b4e2654c665a59a3acf4b", "tools/readiness.py": "0b71ab667e6b2d9979fb3e5a769ebb8a453edec80a71090fb0b21b45af7986ce", "tools/recheck_community.py": "f0843d7d677f90da31e22bde0b1c86584dd46c022f1532d43d042619e426b230", "tools/regrade_runs.py": "011775afb06d3aac67a4aa81117a368c75896b0fcbe1e6f27ccc6237612fbf59", "tools/render_statement_text.py": "dabc0716a3612c288c671bc20e17fd4986691d732768e1e957d6dddddbea92a3", "tools/replay_calibration.py": "801f5004926c438c21ed3668fe2a4ddf45312b3e75320165a3839aae034eee9b", "tools/run_exam_campaign.py": "2c450d57a1cd0a2682838f5ec7c0a4ffb3aed0f1730d34c408e912d59cab6efd", "tools/serve_result_site.py": "86badfac863cd4ad1fc894a14110c75b28470513f0133eeae9d2799b8b4df3a9", "tools/start_demo.py": "c597e6cad28d245b3191654bb3e2801fa9dd2364e2acb25561923613717b615f", "tools/supplemental_acceptance.py": "7327277143d80a531e4c254ac74a9fc0e0d5c76572d53b8469e0a580eda17d65", "tools/sync_sources.py": "b51e889b0f41f9f63bfb19a09fb96d3777693d6b1d76fe0132bdd2a15e155898", "tools/validate_community_pr.py": "796b896dfade07b4529af2088a4b9b9d23484148b3bc0732b3fb837b75c9844b", "tools/verify_official_assessment_mapping.py": "daeb448a016940d5b6b1285979a56e5b9014bd91db40acb131445e4a83a23059", "tools/verify_task_package.py": "9e1e6105f6b5e4e78b36aa57f00117a9fbc8948ab53983c32ab56da88d23ccc4", "profiles/agents.json": "af9c492c08d13b3044aa6b6952589ed6a0a07d5258d8ff72bb18185b3eaebdc5", "profiles/ai-exam-execution-policy.json": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "profiles/bsl-analyzer-0.3.2-macos.json": "83537abdbf38c41ce665e4d0f24128bb51b62e971e0e0f368695f1326a7d2ffb", "profiles/bsl-analyzer-0.3.2-portable.json": "d6ba732e6778e256df34d6bc548593128820a70430c35b279796843606ee40a8", "profiles/bsl-ls-1.1.0-rc.6-macos.json": "245fc10747197e6911b2b4c77cdb15e6fa4eb7bc7c3758b63e768c5adf1df180", "profiles/bsl-ls-1.1.0-rc.6-portable.json": "9f10660881f2ec84794f7d584556b8f75c7e14b3555464af0ed0e60c4c892d86", "profiles/code-index-1.9.0-macos.json": "63a919523ce62ecec274f4c139bc7ad49a75dd4c339568b822cbc695b4e30408", "profiles/code-index-1.9.0-portable.json": "81106cee8f424ffd8a9dc46ecd8e4f57598fc1d49661a83c77b1f0507993fbdc", "profiles/codex-probe-plan.json": "166e41aad5fb3b27d9050bc6de952c6cba363cc6e804d4080568cc71a2a4d289", "profiles/machine.linux.example.json": "408304fd0581098d5d8110dc67dfeab353bc4d4030e32d37e6acf98d2b1aedfd", "profiles/machine.macos.example.json": "52e9f9d17797cb520b9d8955d6806fd550b899bed4da241ebf096dcb6a21a942", "profiles/machine.windows.example.json": "63accac9a2f81d47d03447efbabffd4760aee325193f02f46b9b29a28d50d2d8", "profiles/mcp-toolkit-1.9.0-macos.json": "1d3f9cde5ffa20589a840d01fdae03aa0fc2f412c929f064f203919c4129625b", "profiles/mcp-toolkit-1.9.0-portable.json": "8e370eebe773eef0e08045ee9c6d5be1451f769f65be0710834b262a4336e054", "profiles/none-macos.json": "b1401d9c48159aed3559006c7f6ace6ef4571224d5cf0bb76d1a823505a10056", "profiles/none-portable.json": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "profiles/rlm-tools-bsl-1.43.0-macos.json": "9354421052640ab60bc3e6aa98ff2e7ba9ca2318b0f4026c137487449242cbd2", "profiles/rlm-tools-bsl-1.43.0-portable.json": "2599e5645e0a7d4e44cb2934bc2b272cae79a9bf7ea74a23cd48aacea64bc424", "profiles/rlm-tools-bsl-1.43.0-posix-requirements.txt": "4fdf9a1bd994bf0272e65d231daf76cf19b0a34dad0ae6b50ec4f11a2ce4c330", "profiles/rlm-tools-bsl-1.43.0-windows-requirements.txt": "3730cb46c81cda5181ecd4485e98b11933104632358bc86f8c0eb1a612a8954f", "profiles/shirokov-skills-macos.json": "84f3e89091676884a802035c707e912762a1179425fb8e3faff25be736873cdb", "profiles/shirokov-skills-portable.json": "2b0a461e06602f1456410e70f02ceaa5ac32c6549c486660bcb5ace0c2f87b15", "profiles/shirokov-skills-windows-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/unica-0.12.3-macos.json": "2c39fbb591cf2c2c6e056373823615485397ea83651b7926c6f25a5fe6a0aae6", "profiles/unica-0.13.0-macos.json": "b76b5c8a4dd33f571c4a90993f1a2da5f7223b4f0f8e1042c282e21a66121052", "profiles/unica-0.14.0-rc.1-portable.json": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "rules/1c-specialist-platform/chistov.json": "7a42ef723a1f5f03f02c387cd3ca95725f7364c2e11ebdfc988a02919ab22c37", "rules/1c-specialist-platform/decisions.json": "f622107423ce3c188c063318d7ab4f7718ceb38e443130677d8987f386641c09", "rules/1c-specialist-platform/examiner.json": "30353aa2a1b6545496b070d9066e9ffba0c3779e5b53ef70a4fd2cee375b18c0", "rules/1c-specialist-platform/ledger.json": "f167c10db2b5799dd9a1ea6a37cd2d7d186810dadf5ea2f50f26ae723c676882", "rules/1c-specialist-platform/rules.json": "1d320a4f8e1bf4701496388931f492315549bd3dce574b17285dd1d7f8652007", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" } } }, "conditions": { "client": "codex", "model": "gpt-6.1-sol", "client_version": "0.164.0", "reasoning_effort": "medium", "harness": "ai-rules-1c-3f909dc", "billing_channel": "subscription", "solve_timeout_seconds": 7200, "time_series": null, "delegation": "native_disabled", "network_profile": "open-book_shell", "deadline_disclosed": true, "statement_sha256": "8a6ccb3e673826d1f8220fda53eb310e3ec18c136d87ce8f4cebb2a08614e7e5", "starter_dt_sha256": "f40d084818b0d1cfe503fc7653a6a13f1a8e47fcd1688dad6245b12744eb4638", "profile_sha256": "8c5dd51ff06982703b86f733da56d172dd452f3db00b2c9a00296e8176fee580", "execution_policy_sha256": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "calibration_sha256": "fb1dcb74e6b2bd4731d30b0ffc4bd84053cebd2ed4006d67be20b878b4bc7fd4", "started_at": "2026-10-25T19:30:10.853392+00:00", "timing": { "prepare_ms": 27420, "solve_ms": 6874394, "grade_ms": null }, "original_submission_valid": true, "model_provenance": "requested_only", "tokens": { "input": 62582144, "cached_input": 62026624, "fresh_input": 555520, "output": 218385, "reasoning_output": 89058, "total": 62800529, "coverage": "reported_completed_root_turns" }, "tools": { "mcp_calls": 277, "unica_calls": 0, "failed_calls": 11 }, "process": { "status": "completed", "exit_code": 0, "stop_confirmed": true } }, "verification": "contributor_reported", "download": "community-downloads/demo-20261025T192940Z-5ea870/solution.zip", "source_context": "community-downloads/demo-20261025T192940Z-5ea870/source-context.json", "regrade_required": [ { "id": "grader_changed", "files": [ "assessment.py", "bp.py", "calcwrite.py", "calibrate.py", "calibration_periodicity.py", "calibration_query.py", "claude.py", "codescan.py", "codex.py", "common.py", "docx_text.py", "examiner.py", "harness.py", "interpretations.py", "locking.py", "materials.py", "mcp_toolkit.py", "ou.py", "penalties.py", "portable_harnesses.py", "pr.py", "preflight.py", "queries.py", "queryschema.py", "querytypes.py", "replay_calibration.py", "rules/1c-specialist-platform/chistov.json", "rules/1c-specialist-platform/examiner.json", "rules/1c-specialist-platform/rules.json", "rules/1c-specialist-platform/standards.json", "smoke_check.py", "starters/carcass-8.3.25.1445/starter.json", "stdio_harnesses.py", "tasks/1c-platform-official-sample/checks.json", "tasks/1c-platform-official-sample/private/official-assessment-mapping.json", "tasks/1c-platform-official-sample/private/owner-scoring-policy.json", "telemetry.py" ] } ], "grader_revision_sha256": "855d4f66db31ec9f50ebfc18f596c0d1d157e53e2830c51f853c1338f628e49c", "archive_sha256": "b8f9c9deab0ccdc09862224ac9d4521aa14e795a61436f2f56b381d23dc6d09e" } ] }, { "id": "demo-20261026T070850Z-84a3a7--owner-2026-10-26T223352692405-0000", "run_id": "demo-20261026T070850Z-84a3a7", "result": { "run_id": "demo-20261026T070850Z-84a3a7", "created_at": "2026-10-26T22:33:52.692405+00:00", "model": "claude-opus-5-5", "harness": "ai-rules-1c-3f909dc", "solve_seconds": 2726, "platform": "8.3.27.1688", "counts": { "pass": 63, "fail": 2 }, "rules": [ { "id": "BU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU01.selected_fixture" }, { "id": "BU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU04.selected_fixture" }, { "id": "BU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU05.selected_fixture" }, { "id": "BU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU16.selected_fixture" }, { "id": "BU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU17.selected_fixture" }, { "id": "BU02", "verdict": "pass", "reason": null, "coverage": "partial", "assertion_id": "BU02.posting_cost_and_balance" }, { "id": "BU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU10.selected_fixture" }, { "id": "BU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU12.selected_fixture" }, { "id": "BU03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU03.selected_fixture" }, { "id": "BU06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU06.selected_fixture" }, { "id": "BU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU07.selected_fixture" }, { "id": "BU08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU08.selected_fixture" }, { "id": "BU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU09.selected_fixture" }, { "id": "BU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU11.selected_fixture" }, { "id": "BU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU14.selected_fixture" }, { "id": "BU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU15.selected_fixture" }, { "id": "BU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU13.selected_fixture" }, { "id": "OU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU15.selected_fixture" }, { "id": "OU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU16.selected_fixture" }, { "id": "OU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU17.selected_fixture" }, { "id": "OU02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU02.selected_fixture" }, { "id": "OU18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU18.selected_fixture" }, { "id": "OU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU14.selected_fixture" }, { "id": "OU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU01.selected_fixture" }, { "id": "OU03", "verdict": "pass", "reason": "История и годовая периодичность регистра подтверждены.", "coverage": "history_and_periodicity", "assertion_id": "OU03.selected_fixture" }, { "id": "OU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU05.selected_fixture" }, { "id": "OU06", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "OU06.selected_fixture" }, { "id": "OU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU07.selected_fixture" }, { "id": "OU08", "verdict": "pass", "reason": "История и дневная периодичность подтверждены; ограничение одной версии в неделю отдельно не проверяется.", "coverage": "history_and_periodicity", "assertion_id": "OU08.selected_fixture" }, { "id": "OU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU09.selected_fixture" }, { "id": "OU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU10.selected_fixture" }, { "id": "OU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU11.selected_fixture" }, { "id": "OU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU12.selected_fixture" }, { "id": "OU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU13.selected_fixture" }, { "id": "OU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU04.selected_fixture" }, { "id": "OU19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU19.selected_fixture" }, { "id": "OU20", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU20.selected_fixture" }, { "id": "OU21", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU21.selected_fixture" }, { "id": "PR01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR01.selected_fixture" }, { "id": "PR02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR02.selected_fixture" }, { "id": "PR03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR03.selected_fixture" }, { "id": "PR04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR04.selected_fixture" }, { "id": "PR05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR05.selected_fixture" }, { "id": "PR06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR06.selected_fixture" }, { "id": "PR07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR07.selected_fixture" }, { "id": "PR08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR08.selected_fixture" }, { "id": "PR09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR09.selected_fixture" }, { "id": "PR10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR10.selected_fixture" }, { "id": "PR11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR11.selected_fixture" }, { "id": "PR12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR12.selected_fixture" }, { "id": "PR13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR13.selected_fixture" }, { "id": "PR14", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "PR14.selected_fixture" }, { "id": "PR15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR15.selected_fixture" }, { "id": "PR16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR16.selected_fixture" }, { "id": "PR17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR17.selected_fixture" }, { "id": "PR18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR18.selected_fixture" }, { "id": "PR19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR19.selected_fixture" }, { "id": "F01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F01.selected_fixture" }, { "id": "F02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F02.selected_fixture" }, { "id": "F03", "verdict": "fail", "reason": "list attribute type [], expected a reference to the chart ВидыДополнительныхСведений", "coverage": "selected_fixture", "assertion_id": "F03.selected_fixture" }, { "id": "F04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F04.selected_fixture" }, { "id": "F05", "verdict": "fail", "reason": "typed ['C1', 'C2'], written True, stored []", "coverage": "selected_fixture", "assertion_id": "F05.selected_fixture" }, { "id": "G01", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G01.static_sources" }, { "id": "G02", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G02.static_sources" }, { "id": "G03", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G03.static_sources" } ], "charges": [ { "id": "F1C-GEN01", "points": "0.5", "reason": "не выполнено требование: F03 — list attribute type [], expected a reference to the chart ВидыДополнительныхСведений" }, { "id": "F1C-GEN01", "points": "0.5", "reason": "не выполнено требование: F05 — typed ['C1', 'C2'], written True, stored []" }, { "id": "F1C-GEN12", "points": "0.25", "reason": "текст запроса не разбирается платформой: DataProcessors/ЗаполнениеГрафика/Ext/ObjectModule.bsl:19 — Поле не найдено \"Подразделения.ЭтоГруппа\"" }, { "id": "F1C-GEN22", "points": "1.0", "reason": "CommonModules/УчетСервер/Ext/Module.bsl:65 — поле присоединённой таблицы Политика в выражении без ЕСТЬNULL: ВЫБОР\n\tКОГДА Политика.МетодСписания = &ЛИФО\n\t\tТОГДА -1\n\tИНАЧЕ 1\nКОНЕЦ * РАЗНОСТЬДАТ(ДАТАВРЕМЯ(2000, 1, 1), ЕСТЬNULL(Парт" }, { "id": "F1C-GEN29", "points": "1.5", "reason": "проведение читает остатки регистров до записи их движений, а управляемой блокировки этих регистров нет нигде: ОстаткиТоваров, ПартииТоваров" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "проводимые документы в режиме «Записывать модифицированные»: Операция" }, { "id": "F1C-GEN01", "points": "0.5", "reason": "из каркаса удалены объекты: AccumulationRegisters/ОстаткиНоменклатуры" }, { "id": "F1C-PR14", "points": "0.5", "reason": "после расчёта набор с периодом действия перезаписывается целиком, с пересчётом фактического периода действия (нужно Записать(, Истина)): Documents/НачислениеЗарплаты/Ext/ObjectModule.bsl:159 Набор.Записать(); Documents/НачислениеЗарплаты/Ext/ObjectModule.bsl:242 Набор.Записать(); Documents/НачислениеЗарплаты/Ext/ObjectModule.bsl:291 Набор.Записать()" }, { "id": "F1C-BU07", "points": "1.0", "reason": "признак учёта субконто Суммовой заведён в плане счетов, но не указан ни у одного ресурса регистра — не действует" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "оперативное проведение разрешено у документов с движениями по регистрам расчёта: НачислениеЗарплаты" }, { "id": "F1C-GEN01", "points": "0.5", "reason": "расчёт только в модулях объектов: Documents/НачислениеЗарплаты/Ext/ObjectModule.bsl" } ], "score_upper_bound": "-3.25", "score": null, "grade": "unsatisfactory", "deductions": "8.25", "not_assessed": 13, "gates": { "starter_origin": "passed", "load": "loaded", "clients": "compiles", "demo_data": "present" }, "infrastructure_errors": false, "comparison_eligible": false, "binding_compatibility": null }, "measurement": { "operator": { "name": "Vasiliy", "github": "Gh0sTspp" }, "environment": { "captured_at": "2026-10-26T07:08:52.108249+00:00", "capture_timing": "before_run", "hardware": { "cpu": "Intel(R) Core(TM) i7-5820K CPU @ 3.30GHz", "logical_cpus": 12, "ram_bytes": 34189709312 }, "os": { "system": "Windows", "release": "10", "version": "10.0.19045", "architecture": "AMD64" }, "python": "3.13.12", "platform_version": "8.3.27.1688", "isolation": "dedicated-host", "network_profile": "open-book_shell", "unsafe_action_protection_observed_in_user_config": true, "git_revision": "4a5af75e72de6dafa32f07df84375c1b2ea9488a", "implementation_files": { "exam_bench/__init__.py": "ad5bf6f05dc6765f40b78bd186870ca2c49be113cfa33f8aa76f4926f2cb2c1e", "exam_bench/assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "exam_bench/bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "exam_bench/calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "exam_bench/calibrate.py": "78b5185cb0888c0c0ac3de95ffc3a80154a6de9ae66fc461f79d012e5a58e1db", "exam_bench/calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "exam_bench/calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "exam_bench/calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "exam_bench/calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "exam_bench/calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "exam_bench/claude.py": "7df8c92365863665b74379044eefa3bc84009c9a639225465a667ac294cd286a", "exam_bench/cli.py": "1a37ce645633d761f7897dffc9c45e6b8b9600cd7bd233b1cbf78f49d26b099a", "exam_bench/codescan.py": "751e38001b6e65727a31e28172a0623f0bf34bc092a958037c286aa991a197ed", "exam_bench/codex.py": "c3f89d72af11f312d851c73a1610d92e79acadf336be9ccedd1f94ede3b3ccb0", "exam_bench/common.py": "8682603b519063e655eae3574a02a49efee63bde21f582ccee20ddd623fca96d", "exam_bench/docker_services.py": "3cd9d78070856ae3f8bf4f1e50aee90f627ec20e5150e8b8c0c57b6dacae7323", "exam_bench/docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "exam_bench/examiner.py": "d7294fdd23ed1732216cafebf0a8cf2c24cce4259859aeb7149f62b7607d087d", "exam_bench/finalize.py": "4034f1c63896a940afdb1a83d541cf47fc75c8b5061e3f839047109c04beb620", "exam_bench/forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "exam_bench/gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "exam_bench/grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "exam_bench/harness.py": "3040f6daaf1dc6e6583219f4d925151f8ba7851b2d5417d7f14645892b485ddf", "exam_bench/interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "exam_bench/interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "exam_bench/isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "exam_bench/ledger.py": "7e851523580e22d8490e75f9b6026c07f2c355007e0d11d0b252671f56bef654", "exam_bench/locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "exam_bench/materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "exam_bench/mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "exam_bench/observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "exam_bench/ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "exam_bench/penalties.py": "0d79e2e46102657dca00609b6abbfc0bf7d11fad41429564f876c82bc6b33269", "exam_bench/platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "exam_bench/portable.py": "cad56968ff407983608f5bdbc9ce7234128d7a4580b096ecea8e0e7b4edb9070", "exam_bench/portable_harnesses.py": "6fc286cb7b35c9f869a92fd08c95ed5ac3f90d6ba21ba32034ea4de73275bd69", "exam_bench/pr.py": "6a3a20caf0e10c0cc94410511a72d62c9fcda785f3abab1be2ad616d4ee16836", "exam_bench/preflight.py": "5619be0131d8641925f3ce2a3c8e5234d42aa5635d95676138ca81536d95cd29", "exam_bench/process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "exam_bench/queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "exam_bench/queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "exam_bench/replay_calibration.py": "e2d79cb508f2d5e3846d6dad36c3898d41dec1c573c1a1b7d8a2ec43e33c8c08", "exam_bench/report.py": "5e4c0757e1c7f189953f9a5302593ab726551835856baed25efd93dad6e8bfcd", "exam_bench/runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "exam_bench/smoke_check.py": "f36922a0027429ead0b414048dcc14bbe67f2f0e79a70d03dffbe1447d253545", "exam_bench/stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "exam_bench/submission.py": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "exam_bench/telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "exam_bench/windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "exam_bench/workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tools/build_public_site.py": "9682ed696f5ac9e9a82b65a45c0dece556ec7e49eeb20dcd616882cc534a8258", "tools/build_result_site.py": "3294e1d2ec1486058e208735264d61e349a68a4ae2fa2ec7a723c70e3263b496", "tools/check_native_harnesses.py": "ff9aabf660569eb5a20dd9ce4cfa235c313a42e10cd0c89e571fcafe95bb94c8", "tools/check_native_toolkit.py": "0272794617121f2932828e5e4e9ae20095183c443666cf3ba466b44fbe875095", "tools/community_results.py": "3f4c0067088353ec5bba8ea32decba5e205c3f7993cc305d07693b54c7039a23", "tools/community_service.py": "c374480dbd88d656c0b9054fa04a8e1c6698c69e2f9cf475e82498a2dff61d84", "tools/community_setup.py": "5d7d126ed7d4dd48e1d79f57b99647a92ffcc8c9f80d90915e458888cdd76bf7", "tools/compare_harness_runs.py": "f274df5f3f804cb02504491aec946943833e12fbce6e62d281e12beb8508fc4e", "tools/create_run_plan.py": "871cd81b1eda231c0fba8805f63d2668926be9fc641559e6ddf320e2f47cd37a", "tools/demo_runner.py": "96c099c95b019ac30df5b2900991d0161ca73af6bdfa73a74e4172ba9c1deb00", "tools/installers.py": "9a2742780936b17500869e7c89202c1a2549e37d53a42ad9a50a0abbf78bbe09", "tools/machine_bundle.py": "8aa8346f99f537e81ceca6fb6ab9530e844954bab8eff87bf33d3602f81f8a30", "tools/prepare_native_harnesses.py": "b1909332ea4426acdb262685a7a9f4f02feaebc09421af613dc1333ce53529d8", "tools/prepare_official_statement.py": "6b7028c78e90e798d6ef1a93b76520cc61a308c354fb9b87f7fad18b99800fad", "tools/prepare_open_exam_requirements.py": "544f4e378b9be5f166186f8788f8d454afdac2deb99d91d98421e39d01ba6d03", "tools/probe_harness.py": "1ed8ef93420d1484cbbfd151b7efc31b9a201ceb942dd05e3103efa22ffa7f27", "tools/probe_native_mcp.py": "989a2b1d30bf91f42e5512e60c1597c7e32534bdd46b4e2654c665a59a3acf4b", "tools/readiness.py": "0b71ab667e6b2d9979fb3e5a769ebb8a453edec80a71090fb0b21b45af7986ce", "tools/recheck_community.py": "f0843d7d677f90da31e22bde0b1c86584dd46c022f1532d43d042619e426b230", "tools/regrade_runs.py": "011775afb06d3aac67a4aa81117a368c75896b0fcbe1e6f27ccc6237612fbf59", "tools/render_statement_text.py": "dabc0716a3612c288c671bc20e17fd4986691d732768e1e957d6dddddbea92a3", "tools/replay_calibration.py": "801f5004926c438c21ed3668fe2a4ddf45312b3e75320165a3839aae034eee9b", "tools/run_exam_campaign.py": "2c450d57a1cd0a2682838f5ec7c0a4ffb3aed0f1730d34c408e912d59cab6efd", "tools/serve_result_site.py": "86badfac863cd4ad1fc894a14110c75b28470513f0133eeae9d2799b8b4df3a9", "tools/start_demo.py": "c597e6cad28d245b3191654bb3e2801fa9dd2364e2acb25561923613717b615f", "tools/supplemental_acceptance.py": "7327277143d80a531e4c254ac74a9fc0e0d5c76572d53b8469e0a580eda17d65", "tools/sync_sources.py": "b51e889b0f41f9f63bfb19a09fb96d3777693d6b1d76fe0132bdd2a15e155898", "tools/validate_community_pr.py": "796b896dfade07b4529af2088a4b9b9d23484148b3bc0732b3fb837b75c9844b", "tools/verify_official_assessment_mapping.py": "daeb448a016940d5b6b1285979a56e5b9014bd91db40acb131445e4a83a23059", "tools/verify_task_package.py": "9e1e6105f6b5e4e78b36aa57f00117a9fbc8948ab53983c32ab56da88d23ccc4", "profiles/agents.json": "af9c492c08d13b3044aa6b6952589ed6a0a07d5258d8ff72bb18185b3eaebdc5", "profiles/ai-exam-execution-policy.json": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "profiles/bsl-analyzer-0.3.2-macos.json": "83537abdbf38c41ce665e4d0f24128bb51b62e971e0e0f368695f1326a7d2ffb", "profiles/bsl-analyzer-0.3.2-portable.json": "d6ba732e6778e256df34d6bc548593128820a70430c35b279796843606ee40a8", "profiles/bsl-ls-1.1.0-rc.6-macos.json": "245fc10747197e6911b2b4c77cdb15e6fa4eb7bc7c3758b63e768c5adf1df180", "profiles/bsl-ls-1.1.0-rc.6-portable.json": "9f10660881f2ec84794f7d584556b8f75c7e14b3555464af0ed0e60c4c892d86", "profiles/code-index-1.9.0-macos.json": "63a919523ce62ecec274f4c139bc7ad49a75dd4c339568b822cbc695b4e30408", "profiles/code-index-1.9.0-portable.json": "81106cee8f424ffd8a9dc46ecd8e4f57598fc1d49661a83c77b1f0507993fbdc", "profiles/codex-probe-plan.json": "166e41aad5fb3b27d9050bc6de952c6cba363cc6e804d4080568cc71a2a4d289", "profiles/machine.linux.example.json": "408304fd0581098d5d8110dc67dfeab353bc4d4030e32d37e6acf98d2b1aedfd", "profiles/machine.macos.example.json": "52e9f9d17797cb520b9d8955d6806fd550b899bed4da241ebf096dcb6a21a942", "profiles/machine.windows.example.json": "63accac9a2f81d47d03447efbabffd4760aee325193f02f46b9b29a28d50d2d8", "profiles/mcp-toolkit-1.9.0-macos.json": "1d3f9cde5ffa20589a840d01fdae03aa0fc2f412c929f064f203919c4129625b", "profiles/mcp-toolkit-1.9.0-portable.json": "8e370eebe773eef0e08045ee9c6d5be1451f769f65be0710834b262a4336e054", "profiles/none-macos.json": "b1401d9c48159aed3559006c7f6ace6ef4571224d5cf0bb76d1a823505a10056", "profiles/none-portable.json": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "profiles/rlm-tools-bsl-1.43.0-macos.json": "9354421052640ab60bc3e6aa98ff2e7ba9ca2318b0f4026c137487449242cbd2", "profiles/rlm-tools-bsl-1.43.0-portable.json": "2599e5645e0a7d4e44cb2934bc2b272cae79a9bf7ea74a23cd48aacea64bc424", "profiles/rlm-tools-bsl-1.43.0-posix-requirements.txt": "4fdf9a1bd994bf0272e65d231daf76cf19b0a34dad0ae6b50ec4f11a2ce4c330", "profiles/rlm-tools-bsl-1.43.0-windows-requirements.txt": "3730cb46c81cda5181ecd4485e98b11933104632358bc86f8c0eb1a612a8954f", "profiles/shirokov-skills-macos.json": "84f3e89091676884a802035c707e912762a1179425fb8e3faff25be736873cdb", "profiles/shirokov-skills-portable.json": "2b0a461e06602f1456410e70f02ceaa5ac32c6549c486660bcb5ace0c2f87b15", "profiles/shirokov-skills-windows-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/unica-0.12.3-macos.json": "2c39fbb591cf2c2c6e056373823615485397ea83651b7926c6f25a5fe6a0aae6", "profiles/unica-0.13.0-macos.json": "b76b5c8a4dd33f571c4a90993f1a2da5f7223b4f0f8e1042c282e21a66121052", "profiles/unica-0.14.0-rc.1-portable.json": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "rules/1c-specialist-platform/chistov.json": "7a42ef723a1f5f03f02c387cd3ca95725f7364c2e11ebdfc988a02919ab22c37", "rules/1c-specialist-platform/decisions.json": "f622107423ce3c188c063318d7ab4f7718ceb38e443130677d8987f386641c09", "rules/1c-specialist-platform/examiner.json": "30353aa2a1b6545496b070d9066e9ffba0c3779e5b53ef70a4fd2cee375b18c0", "rules/1c-specialist-platform/ledger.json": "f167c10db2b5799dd9a1ea6a37cd2d7d186810dadf5ea2f50f26ae723c676882", "rules/1c-specialist-platform/rules.json": "1d320a4f8e1bf4701496388931f492315549bd3dce574b17285dd1d7f8652007", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" } } }, "conditions": { "client": "claude", "model": "claude-opus-5-5", "client_version": "2.1.310", "reasoning_effort": "medium", "harness": "ai-rules-1c-3f909dc", "billing_channel": "subscription", "solve_timeout_seconds": 10800, "time_series": null, "delegation": "native_disabled", "network_profile": "open-book_shell", "deadline_disclosed": true, "statement_sha256": "8a6ccb3e673826d1f8220fda53eb310e3ec18c136d87ce8f4cebb2a08614e7e5", "starter_dt_sha256": "f40d084818b0d1cfe503fc7653a6a13f1a8e47fcd1688dad6245b12744eb4638", "profile_sha256": "8c5dd51ff06982703b86f733da56d172dd452f3db00b2c9a00296e8176fee580", "execution_policy_sha256": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "calibration_sha256": "fb1dcb74e6b2bd4731d30b0ffc4bd84053cebd2ed4006d67be20b878b4bc7fd4", "started_at": "2026-10-26T07:09:28.758105+00:00", "timing": { "prepare_ms": 32963, "solve_ms": 2725971, "grade_ms": null }, "original_submission_valid": true, "model_provenance": "client_reported", "tokens": { "input": 42023364, "cached_input": 41639627, "fresh_input": 383737, "output": 192780, "reasoning_output": null, "total": 42216144, "coverage": "final_result_model_usage" }, "tools": { "mcp_calls": 46, "unica_calls": 0, "failed_calls": 5 }, "process": { "status": "completed", "exit_code": 0, "stop_confirmed": true } }, "verification": "repository_owner", "download": "community-downloads/demo-20261026T070850Z-84a3a7--owner-2026-10-26T223352692405-0000/solution.zip", "source_context": "community-downloads/demo-20261026T070850Z-84a3a7--owner-2026-10-26T223352692405-0000/source-context.json", "regrade_required": [], "grader_revision_sha256": "9aee1ffe0e1d04f9158fbbbeed3a403a5f0550ad8a590d7a6394977590760e1a", "archive_sha256": "983ff1958287b64d91650e168ed06028155f8dd24fe420eb3946f427bca0242e", "owner_verification": { "kind": "repository_owner", "repository": "zeegin/1c-agent-exam-benchmark", "operator": { "name": "Ingvar Vilkman", "github": "zeegin" }, "started_at": "2026-10-26T22:33:52.537446+00:00", "server": { "name": "Owner Windows stand", "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "hardware": { "cpu": "AMD Ryzen 7 5800X 8-Core Processor ", "logical_cpus": 4, "ram_bytes": 17109000192 }, "isolation": "dedicated-host" }, "platform_version": "8.3.27.2342", "grader": { "profile": "technical-v8", "commit": "e15c8ea80263c0b38baa3a1fc19611983270e8a7", "working_tree_dirty": false, "fingerprint": { "assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "calibrate.py": "aac127e03744907fd52ef149b88aa6d88a54a2b7497d56084484ee1b99e0da99", "calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "calibration_periodicity.py": "0b1953d7781e236467897cd2ed66705b75d9719353a2de60b36f2bbdfe799108", "calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "calibration_query.py": "3555b103cde8ea0519955cf52358d09223f5ab183a9df00533bdb48c89237a8c", "claude.py": "5bae98af6e2021e2718afa3a71ed04bee812deaae31a43d4e7324814139ccc82", "codescan.py": "6d8375210cef1fd768fc2d98d630d880b2993a9724f01ae25f33b4ea5aa9631d", "codex.py": "904e75503cd35f16cbb052f66806b3879fe25bfc9f99e33b93c889d862c46324", "common.py": "739b39e2bb9bdd4a571fc69df5843190cddcad094ef7e68964061bc1266b20dc", "docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "examiner.py": "8cdffcdd52f043c905f896697403380af95bf485dd4a5edca24f7956e7795ffe", "forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "harness.py": "3cbb90fd3187e700b5df32e5daafb20313d49bb5721c826e3033cbc6aa6e3825", "interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "ou.py": "f62784b54a3f85576a078a2ff1908c9395f3159e55f6bb5b1a3c564392241abe", "penalties.py": "ae388cb8953ecca1f2370a7c4cb1db3b6cc8318fc2a7563a4db15f9f5b057429", "platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "pr.py": "2b6bfea0634703469605ce114f9274716b485852d9a55d9185c39893b14e4726", "preflight.py": "448c3120ab64b625abae3891be686c7a214ce4211f7cf651fd90e12c0b298433", "process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "queries.py": "1ef57e292db3e8967a733948371ecc542f743b811890d4fc509df17303b9c4ac", "queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "querytypes.py": "b645f489a2abc27762b4a9bbf4917e72f7b46dc053a74c0dca4a8fc46491b3ef", "replay_calibration.py": "e0e3d5ca6416934715b9735aa516046b8d19ad4ae690220eeacd96b198a5f86c", "runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "smoke_check.py": "7837e980986bcb54dc8bc1dfb5d0003deef11e05f6e11df3910fa509e1f74c8d", "stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "submission.py": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tasks/1c-platform-official-sample/checks.json": "7447a9b42d3e348d29d07f001cfb6bd269acd953b7117eba7cca2ce9f5a9a60d", "tasks/1c-platform-official-sample/private/official-assessment-mapping.json": "303587c0dabe77c1eeebb2017fe85539e3370b17c9090435e6e0325a66bd0644", "tasks/1c-platform-official-sample/private/owner-scoring-policy.json": "d26d534bb838ab1b5facb7bc033ca8ec40912133baadcdbad83b27fc577905f5", "starters/carcass-8.3.25.1445/starter.json": "0f7a7060885ba99a19402bfc6e63cc8fe979b0f491b040d3a01d5d21b304b3a6", "rules/1c-specialist-platform/rules.json": "ea75e34ace5de11ba3de403c63cd2c026db81d1d991f8531e4a779d4ce9788e7", "rules/1c-specialist-platform/examiner.json": "1247486ddd412d600db88d9c1db4ba501fc1994afd1dc2ebe85402fcc332f4c8", "rules/1c-specialist-platform/chistov.json": "800da27601a3f1c7ec1df64482fd4ad035e559ba0b390a274ed5031128487d3d", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" }, "sha256": "9aee1ffe0e1d04f9158fbbbeed3a403a5f0550ad8a590d7a6394977590760e1a" }, "method": "saved_platform_observations", "outcome": "complete", "completed_at": "2026-10-26T22:33:52.692405+00:00" }, "previous_evaluations": [ { "id": "demo-20261026T070850Z-84a3a7--owner-2026-10-26T214433831904-0000", "run_id": "demo-20261026T070850Z-84a3a7", "result": { "run_id": "demo-20261026T070850Z-84a3a7", "created_at": "2026-10-26T21:44:33.831904+00:00", "model": "claude-opus-5-5", "harness": "ai-rules-1c-3f909dc", "solve_seconds": 2726, "platform": "8.3.27.1688", "counts": { "pass": 63, "fail": 2 }, "rules": [ { "id": "BU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU01.selected_fixture" }, { "id": "BU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU04.selected_fixture" }, { "id": "BU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU05.selected_fixture" }, { "id": "BU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU16.selected_fixture" }, { "id": "BU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU17.selected_fixture" }, { "id": "BU02", "verdict": "pass", "reason": null, "coverage": "partial", "assertion_id": "BU02.posting_cost_and_balance" }, { "id": "BU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU10.selected_fixture" }, { "id": "BU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU12.selected_fixture" }, { "id": "BU03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU03.selected_fixture" }, { "id": "BU06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU06.selected_fixture" }, { "id": "BU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU07.selected_fixture" }, { "id": "BU08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU08.selected_fixture" }, { "id": "BU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU09.selected_fixture" }, { "id": "BU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU11.selected_fixture" }, { "id": "BU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU14.selected_fixture" }, { "id": "BU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU15.selected_fixture" }, { "id": "BU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU13.selected_fixture" }, { "id": "OU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU15.selected_fixture" }, { "id": "OU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU16.selected_fixture" }, { "id": "OU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU17.selected_fixture" }, { "id": "OU02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU02.selected_fixture" }, { "id": "OU18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU18.selected_fixture" }, { "id": "OU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU14.selected_fixture" }, { "id": "OU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU01.selected_fixture" }, { "id": "OU03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU03.selected_fixture" }, { "id": "OU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU05.selected_fixture" }, { "id": "OU06", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "OU06.selected_fixture" }, { "id": "OU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU07.selected_fixture" }, { "id": "OU08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU08.selected_fixture" }, { "id": "OU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU09.selected_fixture" }, { "id": "OU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU10.selected_fixture" }, { "id": "OU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU11.selected_fixture" }, { "id": "OU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU12.selected_fixture" }, { "id": "OU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU13.selected_fixture" }, { "id": "OU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU04.selected_fixture" }, { "id": "OU19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU19.selected_fixture" }, { "id": "OU20", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU20.selected_fixture" }, { "id": "OU21", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU21.selected_fixture" }, { "id": "PR01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR01.selected_fixture" }, { "id": "PR02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR02.selected_fixture" }, { "id": "PR03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR03.selected_fixture" }, { "id": "PR04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR04.selected_fixture" }, { "id": "PR05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR05.selected_fixture" }, { "id": "PR06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR06.selected_fixture" }, { "id": "PR07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR07.selected_fixture" }, { "id": "PR08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR08.selected_fixture" }, { "id": "PR09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR09.selected_fixture" }, { "id": "PR10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR10.selected_fixture" }, { "id": "PR11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR11.selected_fixture" }, { "id": "PR12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR12.selected_fixture" }, { "id": "PR13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR13.selected_fixture" }, { "id": "PR14", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "PR14.selected_fixture" }, { "id": "PR15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR15.selected_fixture" }, { "id": "PR16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR16.selected_fixture" }, { "id": "PR17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR17.selected_fixture" }, { "id": "PR18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR18.selected_fixture" }, { "id": "PR19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR19.selected_fixture" }, { "id": "F01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F01.selected_fixture" }, { "id": "F02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F02.selected_fixture" }, { "id": "F03", "verdict": "fail", "reason": "list attribute type [], expected a reference to the chart ВидыДополнительныхСведений", "coverage": "selected_fixture", "assertion_id": "F03.selected_fixture" }, { "id": "F04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F04.selected_fixture" }, { "id": "F05", "verdict": "fail", "reason": "typed ['C1', 'C2'], written True, stored []", "coverage": "selected_fixture", "assertion_id": "F05.selected_fixture" }, { "id": "G01", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G01.static_sources" }, { "id": "G02", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G02.static_sources" }, { "id": "G03", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G03.static_sources" } ], "charges": [ { "id": "F1C-GEN01", "points": "0.5", "reason": "не выполнено требование: F03 — list attribute type [], expected a reference to the chart ВидыДополнительныхСведений" }, { "id": "F1C-GEN01", "points": "0.5", "reason": "не выполнено требование: F05 — typed ['C1', 'C2'], written True, stored []" }, { "id": "F1C-GEN12", "points": "0.25", "reason": "текст запроса не разбирается платформой: DataProcessors/ЗаполнениеГрафика/Ext/ObjectModule.bsl:19 — Поле не найдено \"Подразделения.ЭтоГруппа\"" }, { "id": "F1C-GEN22", "points": "1.0", "reason": "CommonModules/УчетСервер/Ext/Module.bsl:65 — поле присоединённой таблицы Политика в выражении без ЕСТЬNULL: ВЫБОР\n\tКОГДА Политика.МетодСписания = &ЛИФО\n\t\tТОГДА -1\n\tИНАЧЕ 1\nКОНЕЦ * РАЗНОСТЬДАТ(ДАТАВРЕМЯ(2000, 1, 1), ЕСТЬNULL(Парт" }, { "id": "F1C-GEN29", "points": "1.5", "reason": "проведение читает остатки регистров до записи их движений, а управляемой блокировки этих регистров нет нигде: ОстаткиТоваров, ПартииТоваров" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "проводимые документы в режиме «Записывать модифицированные»: Операция" }, { "id": "F1C-GEN01", "points": "0.5", "reason": "из каркаса удалены объекты: AccumulationRegisters/ОстаткиНоменклатуры" }, { "id": "F1C-PR14", "points": "0.5", "reason": "после расчёта набор с периодом действия перезаписывается целиком, с пересчётом фактического периода действия (нужно Записать(, Истина)): Documents/НачислениеЗарплаты/Ext/ObjectModule.bsl:159 Набор.Записать(); Documents/НачислениеЗарплаты/Ext/ObjectModule.bsl:242 Набор.Записать(); Documents/НачислениеЗарплаты/Ext/ObjectModule.bsl:291 Набор.Записать()" }, { "id": "F1C-BU07", "points": "1.0", "reason": "признак учёта субконто Суммовой заведён в плане счетов, но не указан ни у одного ресурса регистра — не действует" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "оперативное проведение разрешено у документов с движениями по регистрам расчёта: НачислениеЗарплаты" }, { "id": "F1C-GEN01", "points": "0.5", "reason": "расчёт только в модулях объектов: Documents/НачислениеЗарплаты/Ext/ObjectModule.bsl" } ], "score_upper_bound": "-3.25", "score": null, "grade": "unsatisfactory", "deductions": "8.25", "not_assessed": 13, "gates": { "starter_origin": "passed", "load": "loaded", "clients": "compiles", "demo_data": "present" }, "infrastructure_errors": false, "comparison_eligible": false, "binding_compatibility": null }, "measurement": { "operator": { "name": "Vasiliy", "github": "Gh0sTspp" }, "environment": { "captured_at": "2026-10-26T07:08:52.108249+00:00", "capture_timing": "before_run", "hardware": { "cpu": "Intel(R) Core(TM) i7-5820K CPU @ 3.30GHz", "logical_cpus": 12, "ram_bytes": 34189709312 }, "os": { "system": "Windows", "release": "10", "version": "10.0.19045", "architecture": "AMD64" }, "python": "3.13.12", "platform_version": "8.3.27.1688", "isolation": "dedicated-host", "network_profile": "open-book_shell", "unsafe_action_protection_observed_in_user_config": true, "git_revision": "4a5af75e72de6dafa32f07df84375c1b2ea9488a", "implementation_files": { "exam_bench/__init__.py": "ad5bf6f05dc6765f40b78bd186870ca2c49be113cfa33f8aa76f4926f2cb2c1e", "exam_bench/assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "exam_bench/bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "exam_bench/calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "exam_bench/calibrate.py": "78b5185cb0888c0c0ac3de95ffc3a80154a6de9ae66fc461f79d012e5a58e1db", "exam_bench/calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "exam_bench/calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "exam_bench/calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "exam_bench/calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "exam_bench/calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "exam_bench/claude.py": "7df8c92365863665b74379044eefa3bc84009c9a639225465a667ac294cd286a", "exam_bench/cli.py": "1a37ce645633d761f7897dffc9c45e6b8b9600cd7bd233b1cbf78f49d26b099a", "exam_bench/codescan.py": "751e38001b6e65727a31e28172a0623f0bf34bc092a958037c286aa991a197ed", "exam_bench/codex.py": "c3f89d72af11f312d851c73a1610d92e79acadf336be9ccedd1f94ede3b3ccb0", "exam_bench/common.py": "8682603b519063e655eae3574a02a49efee63bde21f582ccee20ddd623fca96d", "exam_bench/docker_services.py": "3cd9d78070856ae3f8bf4f1e50aee90f627ec20e5150e8b8c0c57b6dacae7323", "exam_bench/docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "exam_bench/examiner.py": "d7294fdd23ed1732216cafebf0a8cf2c24cce4259859aeb7149f62b7607d087d", "exam_bench/finalize.py": "4034f1c63896a940afdb1a83d541cf47fc75c8b5061e3f839047109c04beb620", "exam_bench/forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "exam_bench/gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "exam_bench/grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "exam_bench/harness.py": "3040f6daaf1dc6e6583219f4d925151f8ba7851b2d5417d7f14645892b485ddf", "exam_bench/interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "exam_bench/interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "exam_bench/isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "exam_bench/ledger.py": "7e851523580e22d8490e75f9b6026c07f2c355007e0d11d0b252671f56bef654", "exam_bench/locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "exam_bench/materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "exam_bench/mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "exam_bench/observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "exam_bench/ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "exam_bench/penalties.py": "0d79e2e46102657dca00609b6abbfc0bf7d11fad41429564f876c82bc6b33269", "exam_bench/platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "exam_bench/portable.py": "cad56968ff407983608f5bdbc9ce7234128d7a4580b096ecea8e0e7b4edb9070", "exam_bench/portable_harnesses.py": "6fc286cb7b35c9f869a92fd08c95ed5ac3f90d6ba21ba32034ea4de73275bd69", "exam_bench/pr.py": "6a3a20caf0e10c0cc94410511a72d62c9fcda785f3abab1be2ad616d4ee16836", "exam_bench/preflight.py": "5619be0131d8641925f3ce2a3c8e5234d42aa5635d95676138ca81536d95cd29", "exam_bench/process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "exam_bench/queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "exam_bench/queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "exam_bench/replay_calibration.py": "e2d79cb508f2d5e3846d6dad36c3898d41dec1c573c1a1b7d8a2ec43e33c8c08", "exam_bench/report.py": "5e4c0757e1c7f189953f9a5302593ab726551835856baed25efd93dad6e8bfcd", "exam_bench/runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "exam_bench/smoke_check.py": "f36922a0027429ead0b414048dcc14bbe67f2f0e79a70d03dffbe1447d253545", "exam_bench/stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "exam_bench/submission.py": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "exam_bench/telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "exam_bench/windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "exam_bench/workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tools/build_public_site.py": "9682ed696f5ac9e9a82b65a45c0dece556ec7e49eeb20dcd616882cc534a8258", "tools/build_result_site.py": "3294e1d2ec1486058e208735264d61e349a68a4ae2fa2ec7a723c70e3263b496", "tools/check_native_harnesses.py": "ff9aabf660569eb5a20dd9ce4cfa235c313a42e10cd0c89e571fcafe95bb94c8", "tools/check_native_toolkit.py": "0272794617121f2932828e5e4e9ae20095183c443666cf3ba466b44fbe875095", "tools/community_results.py": "3f4c0067088353ec5bba8ea32decba5e205c3f7993cc305d07693b54c7039a23", "tools/community_service.py": "c374480dbd88d656c0b9054fa04a8e1c6698c69e2f9cf475e82498a2dff61d84", "tools/community_setup.py": "5d7d126ed7d4dd48e1d79f57b99647a92ffcc8c9f80d90915e458888cdd76bf7", "tools/compare_harness_runs.py": "f274df5f3f804cb02504491aec946943833e12fbce6e62d281e12beb8508fc4e", "tools/create_run_plan.py": "871cd81b1eda231c0fba8805f63d2668926be9fc641559e6ddf320e2f47cd37a", "tools/demo_runner.py": "96c099c95b019ac30df5b2900991d0161ca73af6bdfa73a74e4172ba9c1deb00", "tools/installers.py": "9a2742780936b17500869e7c89202c1a2549e37d53a42ad9a50a0abbf78bbe09", "tools/machine_bundle.py": "8aa8346f99f537e81ceca6fb6ab9530e844954bab8eff87bf33d3602f81f8a30", "tools/prepare_native_harnesses.py": "b1909332ea4426acdb262685a7a9f4f02feaebc09421af613dc1333ce53529d8", "tools/prepare_official_statement.py": "6b7028c78e90e798d6ef1a93b76520cc61a308c354fb9b87f7fad18b99800fad", "tools/prepare_open_exam_requirements.py": "544f4e378b9be5f166186f8788f8d454afdac2deb99d91d98421e39d01ba6d03", "tools/probe_harness.py": "1ed8ef93420d1484cbbfd151b7efc31b9a201ceb942dd05e3103efa22ffa7f27", "tools/probe_native_mcp.py": "989a2b1d30bf91f42e5512e60c1597c7e32534bdd46b4e2654c665a59a3acf4b", "tools/readiness.py": "0b71ab667e6b2d9979fb3e5a769ebb8a453edec80a71090fb0b21b45af7986ce", "tools/recheck_community.py": "f0843d7d677f90da31e22bde0b1c86584dd46c022f1532d43d042619e426b230", "tools/regrade_runs.py": "011775afb06d3aac67a4aa81117a368c75896b0fcbe1e6f27ccc6237612fbf59", "tools/render_statement_text.py": "dabc0716a3612c288c671bc20e17fd4986691d732768e1e957d6dddddbea92a3", "tools/replay_calibration.py": "801f5004926c438c21ed3668fe2a4ddf45312b3e75320165a3839aae034eee9b", "tools/run_exam_campaign.py": "2c450d57a1cd0a2682838f5ec7c0a4ffb3aed0f1730d34c408e912d59cab6efd", "tools/serve_result_site.py": "86badfac863cd4ad1fc894a14110c75b28470513f0133eeae9d2799b8b4df3a9", "tools/start_demo.py": "c597e6cad28d245b3191654bb3e2801fa9dd2364e2acb25561923613717b615f", "tools/supplemental_acceptance.py": "7327277143d80a531e4c254ac74a9fc0e0d5c76572d53b8469e0a580eda17d65", "tools/sync_sources.py": "b51e889b0f41f9f63bfb19a09fb96d3777693d6b1d76fe0132bdd2a15e155898", "tools/validate_community_pr.py": "796b896dfade07b4529af2088a4b9b9d23484148b3bc0732b3fb837b75c9844b", "tools/verify_official_assessment_mapping.py": "daeb448a016940d5b6b1285979a56e5b9014bd91db40acb131445e4a83a23059", "tools/verify_task_package.py": "9e1e6105f6b5e4e78b36aa57f00117a9fbc8948ab53983c32ab56da88d23ccc4", "profiles/agents.json": "af9c492c08d13b3044aa6b6952589ed6a0a07d5258d8ff72bb18185b3eaebdc5", "profiles/ai-exam-execution-policy.json": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "profiles/bsl-analyzer-0.3.2-macos.json": "83537abdbf38c41ce665e4d0f24128bb51b62e971e0e0f368695f1326a7d2ffb", "profiles/bsl-analyzer-0.3.2-portable.json": "d6ba732e6778e256df34d6bc548593128820a70430c35b279796843606ee40a8", "profiles/bsl-ls-1.1.0-rc.6-macos.json": "245fc10747197e6911b2b4c77cdb15e6fa4eb7bc7c3758b63e768c5adf1df180", "profiles/bsl-ls-1.1.0-rc.6-portable.json": "9f10660881f2ec84794f7d584556b8f75c7e14b3555464af0ed0e60c4c892d86", "profiles/code-index-1.9.0-macos.json": "63a919523ce62ecec274f4c139bc7ad49a75dd4c339568b822cbc695b4e30408", "profiles/code-index-1.9.0-portable.json": "81106cee8f424ffd8a9dc46ecd8e4f57598fc1d49661a83c77b1f0507993fbdc", "profiles/codex-probe-plan.json": "166e41aad5fb3b27d9050bc6de952c6cba363cc6e804d4080568cc71a2a4d289", "profiles/machine.linux.example.json": "408304fd0581098d5d8110dc67dfeab353bc4d4030e32d37e6acf98d2b1aedfd", "profiles/machine.macos.example.json": "52e9f9d17797cb520b9d8955d6806fd550b899bed4da241ebf096dcb6a21a942", "profiles/machine.windows.example.json": "63accac9a2f81d47d03447efbabffd4760aee325193f02f46b9b29a28d50d2d8", "profiles/mcp-toolkit-1.9.0-macos.json": "1d3f9cde5ffa20589a840d01fdae03aa0fc2f412c929f064f203919c4129625b", "profiles/mcp-toolkit-1.9.0-portable.json": "8e370eebe773eef0e08045ee9c6d5be1451f769f65be0710834b262a4336e054", "profiles/none-macos.json": "b1401d9c48159aed3559006c7f6ace6ef4571224d5cf0bb76d1a823505a10056", "profiles/none-portable.json": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "profiles/rlm-tools-bsl-1.43.0-macos.json": "9354421052640ab60bc3e6aa98ff2e7ba9ca2318b0f4026c137487449242cbd2", "profiles/rlm-tools-bsl-1.43.0-portable.json": "2599e5645e0a7d4e44cb2934bc2b272cae79a9bf7ea74a23cd48aacea64bc424", "profiles/rlm-tools-bsl-1.43.0-posix-requirements.txt": "4fdf9a1bd994bf0272e65d231daf76cf19b0a34dad0ae6b50ec4f11a2ce4c330", "profiles/rlm-tools-bsl-1.43.0-windows-requirements.txt": "3730cb46c81cda5181ecd4485e98b11933104632358bc86f8c0eb1a612a8954f", "profiles/shirokov-skills-macos.json": "84f3e89091676884a802035c707e912762a1179425fb8e3faff25be736873cdb", "profiles/shirokov-skills-portable.json": "2b0a461e06602f1456410e70f02ceaa5ac32c6549c486660bcb5ace0c2f87b15", "profiles/shirokov-skills-windows-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/unica-0.12.3-macos.json": "2c39fbb591cf2c2c6e056373823615485397ea83651b7926c6f25a5fe6a0aae6", "profiles/unica-0.13.0-macos.json": "b76b5c8a4dd33f571c4a90993f1a2da5f7223b4f0f8e1042c282e21a66121052", "profiles/unica-0.14.0-rc.1-portable.json": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "rules/1c-specialist-platform/chistov.json": "7a42ef723a1f5f03f02c387cd3ca95725f7364c2e11ebdfc988a02919ab22c37", "rules/1c-specialist-platform/decisions.json": "f622107423ce3c188c063318d7ab4f7718ceb38e443130677d8987f386641c09", "rules/1c-specialist-platform/examiner.json": "30353aa2a1b6545496b070d9066e9ffba0c3779e5b53ef70a4fd2cee375b18c0", "rules/1c-specialist-platform/ledger.json": "f167c10db2b5799dd9a1ea6a37cd2d7d186810dadf5ea2f50f26ae723c676882", "rules/1c-specialist-platform/rules.json": "1d320a4f8e1bf4701496388931f492315549bd3dce574b17285dd1d7f8652007", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" } } }, "conditions": { "client": "claude", "model": "claude-opus-5-5", "client_version": "2.1.310", "reasoning_effort": "medium", "harness": "ai-rules-1c-3f909dc", "billing_channel": "subscription", "solve_timeout_seconds": 10800, "time_series": null, "delegation": "native_disabled", "network_profile": "open-book_shell", "deadline_disclosed": true, "statement_sha256": "8a6ccb3e673826d1f8220fda53eb310e3ec18c136d87ce8f4cebb2a08614e7e5", "starter_dt_sha256": "f40d084818b0d1cfe503fc7653a6a13f1a8e47fcd1688dad6245b12744eb4638", "profile_sha256": "8c5dd51ff06982703b86f733da56d172dd452f3db00b2c9a00296e8176fee580", "execution_policy_sha256": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "calibration_sha256": "fb1dcb74e6b2bd4731d30b0ffc4bd84053cebd2ed4006d67be20b878b4bc7fd4", "started_at": "2026-10-26T07:09:28.758105+00:00", "timing": { "prepare_ms": 32963, "solve_ms": 2725971, "grade_ms": null }, "original_submission_valid": true, "model_provenance": "client_reported", "tokens": { "input": 42023364, "cached_input": 41639627, "fresh_input": 383737, "output": 192780, "reasoning_output": null, "total": 42216144, "coverage": "final_result_model_usage" }, "tools": { "mcp_calls": 46, "unica_calls": 0, "failed_calls": 5 }, "process": { "status": "completed", "exit_code": 0, "stop_confirmed": true } }, "verification": "repository_owner", "download": "community-downloads/demo-20261026T070850Z-84a3a7--owner-2026-10-26T214433831904-0000/solution.zip", "source_context": "community-downloads/demo-20261026T070850Z-84a3a7--owner-2026-10-26T214433831904-0000/source-context.json", "regrade_required": [ { "id": "grader_changed", "files": [ "calibrate.py", "calibration_periodicity.py", "common.py", "ou.py", "replay_calibration.py", "smoke_check.py", "tasks/1c-platform-official-sample/checks.json" ] } ], "grader_revision_sha256": "349d87e0c7f531acbe35dd2b39c35722d8a877fedde97575b49e8466ab763c1d", "archive_sha256": "b85bec4419b8a5d6f4ba6d61455669fb4b5ed1af2c33de96805b3642200be228", "owner_verification": { "kind": "repository_owner", "repository": "zeegin/1c-agent-exam-benchmark", "operator": { "name": "Ingvar Vilkman", "github": "zeegin" }, "started_at": "2026-10-26T21:44:33.653260+00:00", "server": { "name": "Owner Windows stand", "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "hardware": { "cpu": "AMD Ryzen 7 5800X 8-Core Processor ", "logical_cpus": 4, "ram_bytes": 17109000192 }, "isolation": "dedicated-host" }, "platform_version": "8.3.27.2342", "grader": { "profile": "technical-v8", "commit": "e8fd8ced03a85b549c5472fbbda29225749f54d1", "working_tree_dirty": false, "fingerprint": { "assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "calibrate.py": "3162d431f3cab5e7976aa39f665d6286dce45499cf362d85109b7123fa8403a2", "calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "calibration_query.py": "3555b103cde8ea0519955cf52358d09223f5ab183a9df00533bdb48c89237a8c", "claude.py": "eedabc75fca0faa434f40a1624b71419ec7dc22e2854a0886cf84b4911db8372", "codescan.py": "6d8375210cef1fd768fc2d98d630d880b2993a9724f01ae25f33b4ea5aa9631d", "codex.py": "904e75503cd35f16cbb052f66806b3879fe25bfc9f99e33b93c889d862c46324", "common.py": "52825cf5c29f3536d6e046a89e789d5ef9c83aacd7f2f5a07f4f53e77b5229cc", "docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "examiner.py": "8cdffcdd52f043c905f896697403380af95bf485dd4a5edca24f7956e7795ffe", "forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "harness.py": "3cbb90fd3187e700b5df32e5daafb20313d49bb5721c826e3033cbc6aa6e3825", "interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "penalties.py": "ae388cb8953ecca1f2370a7c4cb1db3b6cc8318fc2a7563a4db15f9f5b057429", "platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "pr.py": "2b6bfea0634703469605ce114f9274716b485852d9a55d9185c39893b14e4726", "preflight.py": "448c3120ab64b625abae3891be686c7a214ce4211f7cf651fd90e12c0b298433", "process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "queries.py": "1ef57e292db3e8967a733948371ecc542f743b811890d4fc509df17303b9c4ac", "queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "querytypes.py": "b645f489a2abc27762b4a9bbf4917e72f7b46dc053a74c0dca4a8fc46491b3ef", "replay_calibration.py": "0a4d9b84a9908944c5a945878eb6f5eeda5a4e42ffff4f55c04a680742803d80", "runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "smoke_check.py": "66caf1a01f7aa18432293abe3567ac228ac837a660b08c3dc7bb093f7bd51628", "stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "submission.py": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tasks/1c-platform-official-sample/checks.json": "17a6fcc0c14410829650623eb1443ce99796e000cdfd19905ac0287988b73a00", "tasks/1c-platform-official-sample/private/official-assessment-mapping.json": "303587c0dabe77c1eeebb2017fe85539e3370b17c9090435e6e0325a66bd0644", "tasks/1c-platform-official-sample/private/owner-scoring-policy.json": "d26d534bb838ab1b5facb7bc033ca8ec40912133baadcdbad83b27fc577905f5", "starters/carcass-8.3.25.1445/starter.json": "0f7a7060885ba99a19402bfc6e63cc8fe979b0f491b040d3a01d5d21b304b3a6", "rules/1c-specialist-platform/rules.json": "ea75e34ace5de11ba3de403c63cd2c026db81d1d991f8531e4a779d4ce9788e7", "rules/1c-specialist-platform/examiner.json": "1247486ddd412d600db88d9c1db4ba501fc1994afd1dc2ebe85402fcc332f4c8", "rules/1c-specialist-platform/chistov.json": "800da27601a3f1c7ec1df64482fd4ad035e559ba0b390a274ed5031128487d3d", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" }, "sha256": "349d87e0c7f531acbe35dd2b39c35722d8a877fedde97575b49e8466ab763c1d" }, "method": "saved_platform_observations", "outcome": "complete", "completed_at": "2026-10-26T21:44:33.831904+00:00" } }, { "id": "demo-20261026T070850Z-84a3a7--owner-2026-10-26T192820411322-0000", "run_id": "demo-20261026T070850Z-84a3a7", "result": { "run_id": "demo-20261026T070850Z-84a3a7", "created_at": "2026-10-26T19:28:20.411322+00:00", "model": "claude-opus-5-5", "harness": "ai-rules-1c-3f909dc", "solve_seconds": 2726, "platform": "8.3.27.1688", "counts": { "pass": 63, "fail": 2 }, "rules": [ { "id": "BU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU01.selected_fixture" }, { "id": "BU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU04.selected_fixture" }, { "id": "BU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU05.selected_fixture" }, { "id": "BU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU16.selected_fixture" }, { "id": "BU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU17.selected_fixture" }, { "id": "BU02", "verdict": "pass", "reason": null, "coverage": "partial", "assertion_id": "BU02.posting_cost_and_balance" }, { "id": "BU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU10.selected_fixture" }, { "id": "BU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU12.selected_fixture" }, { "id": "BU03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU03.selected_fixture" }, { "id": "BU06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU06.selected_fixture" }, { "id": "BU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU07.selected_fixture" }, { "id": "BU08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU08.selected_fixture" }, { "id": "BU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU09.selected_fixture" }, { "id": "BU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU11.selected_fixture" }, { "id": "BU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU14.selected_fixture" }, { "id": "BU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU15.selected_fixture" }, { "id": "BU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU13.selected_fixture" }, { "id": "OU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU15.selected_fixture" }, { "id": "OU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU16.selected_fixture" }, { "id": "OU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU17.selected_fixture" }, { "id": "OU02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU02.selected_fixture" }, { "id": "OU18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU18.selected_fixture" }, { "id": "OU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU14.selected_fixture" }, { "id": "OU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU01.selected_fixture" }, { "id": "OU03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU03.selected_fixture" }, { "id": "OU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU05.selected_fixture" }, { "id": "OU06", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "OU06.selected_fixture" }, { "id": "OU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU07.selected_fixture" }, { "id": "OU08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU08.selected_fixture" }, { "id": "OU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU09.selected_fixture" }, { "id": "OU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU10.selected_fixture" }, { "id": "OU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU11.selected_fixture" }, { "id": "OU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU12.selected_fixture" }, { "id": "OU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU13.selected_fixture" }, { "id": "OU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU04.selected_fixture" }, { "id": "OU19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU19.selected_fixture" }, { "id": "OU20", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU20.selected_fixture" }, { "id": "OU21", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU21.selected_fixture" }, { "id": "PR01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR01.selected_fixture" }, { "id": "PR02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR02.selected_fixture" }, { "id": "PR03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR03.selected_fixture" }, { "id": "PR04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR04.selected_fixture" }, { "id": "PR05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR05.selected_fixture" }, { "id": "PR06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR06.selected_fixture" }, { "id": "PR07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR07.selected_fixture" }, { "id": "PR08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR08.selected_fixture" }, { "id": "PR09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR09.selected_fixture" }, { "id": "PR10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR10.selected_fixture" }, { "id": "PR11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR11.selected_fixture" }, { "id": "PR12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR12.selected_fixture" }, { "id": "PR13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR13.selected_fixture" }, { "id": "PR14", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "PR14.selected_fixture" }, { "id": "PR15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR15.selected_fixture" }, { "id": "PR16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR16.selected_fixture" }, { "id": "PR17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR17.selected_fixture" }, { "id": "PR18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR18.selected_fixture" }, { "id": "PR19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR19.selected_fixture" }, { "id": "F01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F01.selected_fixture" }, { "id": "F02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F02.selected_fixture" }, { "id": "F03", "verdict": "fail", "reason": "list attribute type [], expected a reference to the chart ВидыДополнительныхСведений", "coverage": "selected_fixture", "assertion_id": "F03.selected_fixture" }, { "id": "F04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F04.selected_fixture" }, { "id": "F05", "verdict": "fail", "reason": "typed ['C1', 'C2'], written True, stored []", "coverage": "selected_fixture", "assertion_id": "F05.selected_fixture" }, { "id": "G01", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G01.static_sources" }, { "id": "G02", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G02.static_sources" }, { "id": "G03", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G03.static_sources" } ], "charges": [ { "id": "F1C-GEN01", "points": "0.5", "reason": "не выполнено требование: F03 — list attribute type [], expected a reference to the chart ВидыДополнительныхСведений" }, { "id": "F1C-GEN01", "points": "0.5", "reason": "не выполнено требование: F05 — typed ['C1', 'C2'], written True, stored []" }, { "id": "F1C-GEN12", "points": "0.25", "reason": "текст запроса не разбирается платформой: DataProcessors/ЗаполнениеГрафика/Ext/ObjectModule.bsl:19 — Поле не найдено \"Подразделения.ЭтоГруппа\"" }, { "id": "F1C-GEN22", "points": "1.0", "reason": "CommonModules/УчетСервер/Ext/Module.bsl:65 — поле присоединённой таблицы Политика в выражении без ЕСТЬNULL: ВЫБОР\n\tКОГДА Политика.МетодСписания = &ЛИФО\n\t\tТОГДА -1\n\tИНАЧЕ 1\nКОНЕЦ * РАЗНОСТЬДАТ(ДАТАВРЕМЯ(2000, 1, 1), ЕСТЬNULL(Парт" }, { "id": "F1C-GEN29", "points": "1.5", "reason": "проведение читает остатки регистров до записи их движений, а управляемой блокировки этих регистров нет нигде: ОстаткиТоваров, ПартииТоваров" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "проводимые документы в режиме «Записывать модифицированные»: Операция" }, { "id": "F1C-GEN01", "points": "0.5", "reason": "из каркаса удалены объекты: AccumulationRegisters/ОстаткиНоменклатуры" }, { "id": "F1C-PR14", "points": "0.5", "reason": "после расчёта набор с периодом действия перезаписывается целиком, с пересчётом фактического периода действия (нужно Записать(, Истина)): Documents/НачислениеЗарплаты/Ext/ObjectModule.bsl:159 Набор.Записать(); Documents/НачислениеЗарплаты/Ext/ObjectModule.bsl:242 Набор.Записать(); Documents/НачислениеЗарплаты/Ext/ObjectModule.bsl:291 Набор.Записать()" }, { "id": "F1C-BU07", "points": "1.0", "reason": "признак учёта субконто Суммовой заведён в плане счетов, но не указан ни у одного ресурса регистра — не действует" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "оперативное проведение разрешено у документов с движениями по регистрам расчёта: НачислениеЗарплаты" }, { "id": "F1C-GEN01", "points": "0.5", "reason": "расчёт только в модулях объектов: Documents/НачислениеЗарплаты/Ext/ObjectModule.bsl" } ], "score_upper_bound": "-3.25", "score": null, "grade": "unsatisfactory", "deductions": "8.25", "not_assessed": 13, "gates": { "starter_origin": "passed", "load": "loaded", "clients": "compiles", "demo_data": "present" }, "infrastructure_errors": false, "comparison_eligible": false, "binding_compatibility": null }, "measurement": { "operator": { "name": "Vasiliy", "github": "Gh0sTspp" }, "environment": { "captured_at": "2026-10-26T07:08:52.108249+00:00", "capture_timing": "before_run", "hardware": { "cpu": "Intel(R) Core(TM) i7-5820K CPU @ 3.30GHz", "logical_cpus": 12, "ram_bytes": 34189709312 }, "os": { "system": "Windows", "release": "10", "version": "10.0.19045", "architecture": "AMD64" }, "python": "3.13.12", "platform_version": "8.3.27.1688", "isolation": "dedicated-host", "network_profile": "open-book_shell", "unsafe_action_protection_observed_in_user_config": true, "git_revision": "4a5af75e72de6dafa32f07df84375c1b2ea9488a", "implementation_files": { "exam_bench/__init__.py": "ad5bf6f05dc6765f40b78bd186870ca2c49be113cfa33f8aa76f4926f2cb2c1e", "exam_bench/assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "exam_bench/bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "exam_bench/calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "exam_bench/calibrate.py": "78b5185cb0888c0c0ac3de95ffc3a80154a6de9ae66fc461f79d012e5a58e1db", "exam_bench/calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "exam_bench/calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "exam_bench/calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "exam_bench/calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "exam_bench/calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "exam_bench/claude.py": "7df8c92365863665b74379044eefa3bc84009c9a639225465a667ac294cd286a", "exam_bench/cli.py": "1a37ce645633d761f7897dffc9c45e6b8b9600cd7bd233b1cbf78f49d26b099a", "exam_bench/codescan.py": "751e38001b6e65727a31e28172a0623f0bf34bc092a958037c286aa991a197ed", "exam_bench/codex.py": "c3f89d72af11f312d851c73a1610d92e79acadf336be9ccedd1f94ede3b3ccb0", "exam_bench/common.py": "8682603b519063e655eae3574a02a49efee63bde21f582ccee20ddd623fca96d", "exam_bench/docker_services.py": "3cd9d78070856ae3f8bf4f1e50aee90f627ec20e5150e8b8c0c57b6dacae7323", "exam_bench/docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "exam_bench/examiner.py": "d7294fdd23ed1732216cafebf0a8cf2c24cce4259859aeb7149f62b7607d087d", "exam_bench/finalize.py": "4034f1c63896a940afdb1a83d541cf47fc75c8b5061e3f839047109c04beb620", "exam_bench/forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "exam_bench/gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "exam_bench/grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "exam_bench/harness.py": "3040f6daaf1dc6e6583219f4d925151f8ba7851b2d5417d7f14645892b485ddf", "exam_bench/interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "exam_bench/interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "exam_bench/isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "exam_bench/ledger.py": "7e851523580e22d8490e75f9b6026c07f2c355007e0d11d0b252671f56bef654", "exam_bench/locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "exam_bench/materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "exam_bench/mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "exam_bench/observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "exam_bench/ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "exam_bench/penalties.py": "0d79e2e46102657dca00609b6abbfc0bf7d11fad41429564f876c82bc6b33269", "exam_bench/platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "exam_bench/portable.py": "cad56968ff407983608f5bdbc9ce7234128d7a4580b096ecea8e0e7b4edb9070", "exam_bench/portable_harnesses.py": "6fc286cb7b35c9f869a92fd08c95ed5ac3f90d6ba21ba32034ea4de73275bd69", "exam_bench/pr.py": "6a3a20caf0e10c0cc94410511a72d62c9fcda785f3abab1be2ad616d4ee16836", "exam_bench/preflight.py": "5619be0131d8641925f3ce2a3c8e5234d42aa5635d95676138ca81536d95cd29", "exam_bench/process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "exam_bench/queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "exam_bench/queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "exam_bench/replay_calibration.py": "e2d79cb508f2d5e3846d6dad36c3898d41dec1c573c1a1b7d8a2ec43e33c8c08", "exam_bench/report.py": "5e4c0757e1c7f189953f9a5302593ab726551835856baed25efd93dad6e8bfcd", "exam_bench/runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "exam_bench/smoke_check.py": "f36922a0027429ead0b414048dcc14bbe67f2f0e79a70d03dffbe1447d253545", "exam_bench/stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "exam_bench/submission.py": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "exam_bench/telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "exam_bench/windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "exam_bench/workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tools/build_public_site.py": "9682ed696f5ac9e9a82b65a45c0dece556ec7e49eeb20dcd616882cc534a8258", "tools/build_result_site.py": "3294e1d2ec1486058e208735264d61e349a68a4ae2fa2ec7a723c70e3263b496", "tools/check_native_harnesses.py": "ff9aabf660569eb5a20dd9ce4cfa235c313a42e10cd0c89e571fcafe95bb94c8", "tools/check_native_toolkit.py": "0272794617121f2932828e5e4e9ae20095183c443666cf3ba466b44fbe875095", "tools/community_results.py": "3f4c0067088353ec5bba8ea32decba5e205c3f7993cc305d07693b54c7039a23", "tools/community_service.py": "c374480dbd88d656c0b9054fa04a8e1c6698c69e2f9cf475e82498a2dff61d84", "tools/community_setup.py": "5d7d126ed7d4dd48e1d79f57b99647a92ffcc8c9f80d90915e458888cdd76bf7", "tools/compare_harness_runs.py": "f274df5f3f804cb02504491aec946943833e12fbce6e62d281e12beb8508fc4e", "tools/create_run_plan.py": "871cd81b1eda231c0fba8805f63d2668926be9fc641559e6ddf320e2f47cd37a", "tools/demo_runner.py": "96c099c95b019ac30df5b2900991d0161ca73af6bdfa73a74e4172ba9c1deb00", "tools/installers.py": "9a2742780936b17500869e7c89202c1a2549e37d53a42ad9a50a0abbf78bbe09", "tools/machine_bundle.py": "8aa8346f99f537e81ceca6fb6ab9530e844954bab8eff87bf33d3602f81f8a30", "tools/prepare_native_harnesses.py": "b1909332ea4426acdb262685a7a9f4f02feaebc09421af613dc1333ce53529d8", "tools/prepare_official_statement.py": "6b7028c78e90e798d6ef1a93b76520cc61a308c354fb9b87f7fad18b99800fad", "tools/prepare_open_exam_requirements.py": "544f4e378b9be5f166186f8788f8d454afdac2deb99d91d98421e39d01ba6d03", "tools/probe_harness.py": "1ed8ef93420d1484cbbfd151b7efc31b9a201ceb942dd05e3103efa22ffa7f27", "tools/probe_native_mcp.py": "989a2b1d30bf91f42e5512e60c1597c7e32534bdd46b4e2654c665a59a3acf4b", "tools/readiness.py": "0b71ab667e6b2d9979fb3e5a769ebb8a453edec80a71090fb0b21b45af7986ce", "tools/recheck_community.py": "f0843d7d677f90da31e22bde0b1c86584dd46c022f1532d43d042619e426b230", "tools/regrade_runs.py": "011775afb06d3aac67a4aa81117a368c75896b0fcbe1e6f27ccc6237612fbf59", "tools/render_statement_text.py": "dabc0716a3612c288c671bc20e17fd4986691d732768e1e957d6dddddbea92a3", "tools/replay_calibration.py": "801f5004926c438c21ed3668fe2a4ddf45312b3e75320165a3839aae034eee9b", "tools/run_exam_campaign.py": "2c450d57a1cd0a2682838f5ec7c0a4ffb3aed0f1730d34c408e912d59cab6efd", "tools/serve_result_site.py": "86badfac863cd4ad1fc894a14110c75b28470513f0133eeae9d2799b8b4df3a9", "tools/start_demo.py": "c597e6cad28d245b3191654bb3e2801fa9dd2364e2acb25561923613717b615f", "tools/supplemental_acceptance.py": "7327277143d80a531e4c254ac74a9fc0e0d5c76572d53b8469e0a580eda17d65", "tools/sync_sources.py": "b51e889b0f41f9f63bfb19a09fb96d3777693d6b1d76fe0132bdd2a15e155898", "tools/validate_community_pr.py": "796b896dfade07b4529af2088a4b9b9d23484148b3bc0732b3fb837b75c9844b", "tools/verify_official_assessment_mapping.py": "daeb448a016940d5b6b1285979a56e5b9014bd91db40acb131445e4a83a23059", "tools/verify_task_package.py": "9e1e6105f6b5e4e78b36aa57f00117a9fbc8948ab53983c32ab56da88d23ccc4", "profiles/agents.json": "af9c492c08d13b3044aa6b6952589ed6a0a07d5258d8ff72bb18185b3eaebdc5", "profiles/ai-exam-execution-policy.json": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "profiles/bsl-analyzer-0.3.2-macos.json": "83537abdbf38c41ce665e4d0f24128bb51b62e971e0e0f368695f1326a7d2ffb", "profiles/bsl-analyzer-0.3.2-portable.json": "d6ba732e6778e256df34d6bc548593128820a70430c35b279796843606ee40a8", "profiles/bsl-ls-1.1.0-rc.6-macos.json": "245fc10747197e6911b2b4c77cdb15e6fa4eb7bc7c3758b63e768c5adf1df180", "profiles/bsl-ls-1.1.0-rc.6-portable.json": "9f10660881f2ec84794f7d584556b8f75c7e14b3555464af0ed0e60c4c892d86", "profiles/code-index-1.9.0-macos.json": "63a919523ce62ecec274f4c139bc7ad49a75dd4c339568b822cbc695b4e30408", "profiles/code-index-1.9.0-portable.json": "81106cee8f424ffd8a9dc46ecd8e4f57598fc1d49661a83c77b1f0507993fbdc", "profiles/codex-probe-plan.json": "166e41aad5fb3b27d9050bc6de952c6cba363cc6e804d4080568cc71a2a4d289", "profiles/machine.linux.example.json": "408304fd0581098d5d8110dc67dfeab353bc4d4030e32d37e6acf98d2b1aedfd", "profiles/machine.macos.example.json": "52e9f9d17797cb520b9d8955d6806fd550b899bed4da241ebf096dcb6a21a942", "profiles/machine.windows.example.json": "63accac9a2f81d47d03447efbabffd4760aee325193f02f46b9b29a28d50d2d8", "profiles/mcp-toolkit-1.9.0-macos.json": "1d3f9cde5ffa20589a840d01fdae03aa0fc2f412c929f064f203919c4129625b", "profiles/mcp-toolkit-1.9.0-portable.json": "8e370eebe773eef0e08045ee9c6d5be1451f769f65be0710834b262a4336e054", "profiles/none-macos.json": "b1401d9c48159aed3559006c7f6ace6ef4571224d5cf0bb76d1a823505a10056", "profiles/none-portable.json": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "profiles/rlm-tools-bsl-1.43.0-macos.json": "9354421052640ab60bc3e6aa98ff2e7ba9ca2318b0f4026c137487449242cbd2", "profiles/rlm-tools-bsl-1.43.0-portable.json": "2599e5645e0a7d4e44cb2934bc2b272cae79a9bf7ea74a23cd48aacea64bc424", "profiles/rlm-tools-bsl-1.43.0-posix-requirements.txt": "4fdf9a1bd994bf0272e65d231daf76cf19b0a34dad0ae6b50ec4f11a2ce4c330", "profiles/rlm-tools-bsl-1.43.0-windows-requirements.txt": "3730cb46c81cda5181ecd4485e98b11933104632358bc86f8c0eb1a612a8954f", "profiles/shirokov-skills-macos.json": "84f3e89091676884a802035c707e912762a1179425fb8e3faff25be736873cdb", "profiles/shirokov-skills-portable.json": "2b0a461e06602f1456410e70f02ceaa5ac32c6549c486660bcb5ace0c2f87b15", "profiles/shirokov-skills-windows-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/unica-0.12.3-macos.json": "2c39fbb591cf2c2c6e056373823615485397ea83651b7926c6f25a5fe6a0aae6", "profiles/unica-0.13.0-macos.json": "b76b5c8a4dd33f571c4a90993f1a2da5f7223b4f0f8e1042c282e21a66121052", "profiles/unica-0.14.0-rc.1-portable.json": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "rules/1c-specialist-platform/chistov.json": "7a42ef723a1f5f03f02c387cd3ca95725f7364c2e11ebdfc988a02919ab22c37", "rules/1c-specialist-platform/decisions.json": "f622107423ce3c188c063318d7ab4f7718ceb38e443130677d8987f386641c09", "rules/1c-specialist-platform/examiner.json": "30353aa2a1b6545496b070d9066e9ffba0c3779e5b53ef70a4fd2cee375b18c0", "rules/1c-specialist-platform/ledger.json": "f167c10db2b5799dd9a1ea6a37cd2d7d186810dadf5ea2f50f26ae723c676882", "rules/1c-specialist-platform/rules.json": "1d320a4f8e1bf4701496388931f492315549bd3dce574b17285dd1d7f8652007", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" } } }, "conditions": { "client": "claude", "model": "claude-opus-5-5", "client_version": "2.1.310", "reasoning_effort": "medium", "harness": "ai-rules-1c-3f909dc", "billing_channel": "subscription", "solve_timeout_seconds": 10800, "time_series": null, "delegation": "native_disabled", "network_profile": "open-book_shell", "deadline_disclosed": true, "statement_sha256": "8a6ccb3e673826d1f8220fda53eb310e3ec18c136d87ce8f4cebb2a08614e7e5", "starter_dt_sha256": "f40d084818b0d1cfe503fc7653a6a13f1a8e47fcd1688dad6245b12744eb4638", "profile_sha256": "8c5dd51ff06982703b86f733da56d172dd452f3db00b2c9a00296e8176fee580", "execution_policy_sha256": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "calibration_sha256": "fb1dcb74e6b2bd4731d30b0ffc4bd84053cebd2ed4006d67be20b878b4bc7fd4", "started_at": "2026-10-26T07:09:28.758105+00:00", "timing": { "prepare_ms": 32963, "solve_ms": 2725971, "grade_ms": null }, "original_submission_valid": true, "model_provenance": "client_reported", "tokens": { "input": 42023364, "cached_input": 41639627, "fresh_input": 383737, "output": 192780, "reasoning_output": null, "total": 42216144, "coverage": "final_result_model_usage" }, "tools": { "mcp_calls": 46, "unica_calls": 0, "failed_calls": 5 }, "process": { "status": "completed", "exit_code": 0, "stop_confirmed": true } }, "verification": "repository_owner", "download": "community-downloads/demo-20261026T070850Z-84a3a7--owner-2026-10-26T192820411322-0000/solution.zip", "source_context": "community-downloads/demo-20261026T070850Z-84a3a7--owner-2026-10-26T192820411322-0000/source-context.json", "regrade_required": [ { "id": "grader_changed", "files": [ "calibrate.py", "calibration_periodicity.py", "calibration_query.py", "common.py", "ou.py", "penalties.py", "queries.py", "replay_calibration.py", "rules/1c-specialist-platform/rules.json", "smoke_check.py", "tasks/1c-platform-official-sample/checks.json" ] } ], "grader_revision_sha256": "4a12b62d2c10085e1fc710f377f84903abdf2fb787dda19628d944da990a86b2", "archive_sha256": "256c0397693bdbe675265d772afd867efd478b8c8c1b1f8312f6940ceba043c0", "owner_verification": { "kind": "repository_owner", "repository": "zeegin/1c-agent-exam-benchmark", "operator": { "name": "Ingvar Vilkman", "github": "zeegin" }, "started_at": "2026-10-26T19:25:15.655186+00:00", "server": { "name": "Owner Windows stand", "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "hardware": { "cpu": "AMD Ryzen 7 5800X 8-Core Processor ", "logical_cpus": 4, "ram_bytes": 17109000192 }, "isolation": "dedicated-host" }, "platform_version": "8.3.27.2342", "grader": { "profile": "technical-v8", "commit": "5b6a28372b253e81e22b83f8559df897297e28ff", "working_tree_dirty": true, "fingerprint": { "assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "calibrate.py": "1c844971b4977fdcc3b30aebe8aad40fbd45e6828955b8deb043ac8573d61731", "calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "claude.py": "eedabc75fca0faa434f40a1624b71419ec7dc22e2854a0886cf84b4911db8372", "codescan.py": "6d8375210cef1fd768fc2d98d630d880b2993a9724f01ae25f33b4ea5aa9631d", "codex.py": "904e75503cd35f16cbb052f66806b3879fe25bfc9f99e33b93c889d862c46324", "common.py": "7696116dd1a796666518b4c5d2aa3cafa04ee974593d3636333cbe5385bd6ccb", "docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "examiner.py": "8cdffcdd52f043c905f896697403380af95bf485dd4a5edca24f7956e7795ffe", "forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "harness.py": "3cbb90fd3187e700b5df32e5daafb20313d49bb5721c826e3033cbc6aa6e3825", "interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "penalties.py": "b82704e7f47d3dfdf6e501452d7e0abca1f9da63307093d2e257e32358be0489", "platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "pr.py": "2b6bfea0634703469605ce114f9274716b485852d9a55d9185c39893b14e4726", "preflight.py": "448c3120ab64b625abae3891be686c7a214ce4211f7cf651fd90e12c0b298433", "process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "querytypes.py": "b645f489a2abc27762b4a9bbf4917e72f7b46dc053a74c0dca4a8fc46491b3ef", "replay_calibration.py": "3b6f3a289cc8a7f5e458f62bfa2c6cc534cc9076ba3f22d1e4bd8a5f9e175317", "runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "smoke_check.py": "bd6266367e6b769a95258eb383239b89a22deae406d64f6e142c77396f4639ba", "stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "submission.py": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tasks/1c-platform-official-sample/checks.json": "17a6fcc0c14410829650623eb1443ce99796e000cdfd19905ac0287988b73a00", "tasks/1c-platform-official-sample/private/official-assessment-mapping.json": "303587c0dabe77c1eeebb2017fe85539e3370b17c9090435e6e0325a66bd0644", "tasks/1c-platform-official-sample/private/owner-scoring-policy.json": "d26d534bb838ab1b5facb7bc033ca8ec40912133baadcdbad83b27fc577905f5", "starters/carcass-8.3.25.1445/starter.json": "0f7a7060885ba99a19402bfc6e63cc8fe979b0f491b040d3a01d5d21b304b3a6", "rules/1c-specialist-platform/rules.json": "7ec895a7751ef17f4a50cc80b5f7fa986e1e04360ab0b4ce9aa29115195df03c", "rules/1c-specialist-platform/examiner.json": "1247486ddd412d600db88d9c1db4ba501fc1994afd1dc2ebe85402fcc332f4c8", "rules/1c-specialist-platform/chistov.json": "800da27601a3f1c7ec1df64482fd4ad035e559ba0b390a274ed5031128487d3d", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" }, "sha256": "4a12b62d2c10085e1fc710f377f84903abdf2fb787dda19628d944da990a86b2" }, "identity_verified_at": "2026-10-26T18:44:22.364471+00:00", "identity_session_sha256": "950670ab9a82059c65525d0d6e5b8a00f0dc292581edea3eb087c4ecadeaab09", "completed_at": "2026-10-26T19:28:20.411322+00:00" } }, { "id": "demo-20261026T070850Z-84a3a7", "run_id": "demo-20261026T070850Z-84a3a7", "result": { "run_id": "demo-20261026T070850Z-84a3a7", "created_at": "2026-10-26T08:08:05.393142+00:00", "model": "claude-opus-5-5", "harness": "ai-rules-1c-3f909dc", "solve_seconds": 2726, "platform": "8.3.27.1688", "counts": { "pass": 63, "fail": 2 }, "rules": [ { "id": "BU01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU16", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU17", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU02", "verdict": "pass", "coverage": "partial", "reason": null }, { "id": "BU10", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU12", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU06", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU07", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU08", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU09", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU11", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU14", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU15", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU13", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU15", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU16", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU17", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU02", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU18", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU14", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU06", "verdict": "pass", "coverage": "no_violation_found", "reason": null }, { "id": "OU07", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU08", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU09", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU10", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU11", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU12", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU13", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU19", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU20", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU21", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR02", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR06", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR07", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR08", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR09", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR10", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR11", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR12", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR13", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR14", "verdict": "pass", "coverage": "no_violation_found", "reason": null }, { "id": "PR15", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR16", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR17", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR18", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR19", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F02", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F03", "verdict": "fail", "coverage": "selected_fixture", "reason": null }, { "id": "F04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F05", "verdict": "fail", "coverage": "selected_fixture", "reason": null }, { "id": "G01", "verdict": "pass", "coverage": "static_sources", "reason": null }, { "id": "G02", "verdict": "pass", "coverage": "static_sources", "reason": null }, { "id": "G03", "verdict": "pass", "coverage": "static_sources", "reason": null } ], "charges": [ { "id": "F1C-GEN01", "points": "0.5", "reason": "не выполнено требование: F03 — list attribute type [], expected a reference to the chart ВидыДополнительныхСведений" }, { "id": "F1C-GEN01", "points": "0.5", "reason": "не выполнено требование: F05 — typed ['C1', 'C2'], written True, stored []" }, { "id": "F1C-GEN12", "points": "0.25", "reason": "текст запроса не разбирается платформой: DataProcessors/ЗаполнениеГрафика/Ext/ObjectModule.bsl:19 — Поле не найдено \"Подразделения.ЭтоГруппа\"" }, { "id": "F1C-GEN22", "points": "1.0", "reason": "CommonModules/УчетСервер/Ext/Module.bsl:65 — поле присоединённой таблицы Политика в выражении без ЕСТЬNULL: ВЫБОР\n\tКОГДА Политика.МетодСписания = &ЛИФО\n\t\tТОГДА -1\n\tИНАЧЕ 1\nКОНЕЦ * РАЗНОСТЬДАТ(ДАТАВРЕМЯ(2000, 1, 1), ЕСТЬNULL(Парт" }, { "id": "F1C-GEN04", "points": "1.0", "reason": "не соблюдён механизм, предписанный билетом: F03" }, { "id": "F1C-GEN29", "points": "1.5", "reason": "проведение читает остатки регистров до записи их движений, а управляемой блокировки этих регистров нет нигде: ОстаткиТоваров, ПартииТоваров" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "проводимые документы в режиме «Записывать модифицированные»: Операция" }, { "id": "F1C-GEN01", "points": "0.5", "reason": "из каркаса удалены объекты: AccumulationRegisters/ОстаткиНоменклатуры" }, { "id": "F1C-PR14", "points": "0.5", "reason": "после расчёта набор с периодом действия перезаписывается целиком, с пересчётом фактического периода действия (нужно Записать(, Истина)): Documents/НачислениеЗарплаты/Ext/ObjectModule.bsl:159 Набор.Записать(); Documents/НачислениеЗарплаты/Ext/ObjectModule.bsl:242 Набор.Записать(); Documents/НачислениеЗарплаты/Ext/ObjectModule.bsl:291 Набор.Записать()" }, { "id": "F1C-BU07", "points": "1.0", "reason": "признак учёта субконто Суммовой заведён в плане счетов, но не указан ни у одного ресурса регистра — не действует" }, { "id": "F1C-GEN28", "points": "1.0", "reason": "оперативное проведение разрешено у документов с движениями по регистрам расчёта: НачислениеЗарплаты" }, { "id": "F1C-GEN01", "points": "0.5", "reason": "расчёт только в модулях объектов: Documents/НачислениеЗарплаты/Ext/ObjectModule.bsl" } ], "score_upper_bound": "-4.25", "score": null, "grade": "unsatisfactory", "deductions": "9.25", "not_assessed": 13, "gates": { "starter_origin": "passed", "load": "loaded", "clients": "compiles", "demo_data": "present" }, "infrastructure_errors": false, "comparison_eligible": false, "binding_compatibility": null, "evaluation_sha256": "3ce1ae30440e00e1bd552ce5d9a65f22a95aa8e3632732205ae5ff3b922602dc", "downloads": [] }, "measurement": { "operator": { "name": "Vasiliy", "github": "Gh0sTspp" }, "environment": { "captured_at": "2026-10-26T07:08:52.108249+00:00", "capture_timing": "before_run", "hardware": { "cpu": "Intel(R) Core(TM) i7-5820K CPU @ 3.30GHz", "logical_cpus": 12, "ram_bytes": 34189709312 }, "os": { "system": "Windows", "release": "10", "version": "10.0.19045", "architecture": "AMD64" }, "python": "3.13.12", "platform_version": "8.3.27.1688", "isolation": "dedicated-host", "network_profile": "open-book_shell", "unsafe_action_protection_observed_in_user_config": true, "git_revision": "4a5af75e72de6dafa32f07df84375c1b2ea9488a", "implementation_files": { "exam_bench/__init__.py": "ad5bf6f05dc6765f40b78bd186870ca2c49be113cfa33f8aa76f4926f2cb2c1e", "exam_bench/assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "exam_bench/bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "exam_bench/calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "exam_bench/calibrate.py": "78b5185cb0888c0c0ac3de95ffc3a80154a6de9ae66fc461f79d012e5a58e1db", "exam_bench/calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "exam_bench/calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "exam_bench/calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "exam_bench/calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "exam_bench/calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "exam_bench/claude.py": "7df8c92365863665b74379044eefa3bc84009c9a639225465a667ac294cd286a", "exam_bench/cli.py": "1a37ce645633d761f7897dffc9c45e6b8b9600cd7bd233b1cbf78f49d26b099a", "exam_bench/codescan.py": "751e38001b6e65727a31e28172a0623f0bf34bc092a958037c286aa991a197ed", "exam_bench/codex.py": "c3f89d72af11f312d851c73a1610d92e79acadf336be9ccedd1f94ede3b3ccb0", "exam_bench/common.py": "8682603b519063e655eae3574a02a49efee63bde21f582ccee20ddd623fca96d", "exam_bench/docker_services.py": "3cd9d78070856ae3f8bf4f1e50aee90f627ec20e5150e8b8c0c57b6dacae7323", "exam_bench/docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "exam_bench/examiner.py": "d7294fdd23ed1732216cafebf0a8cf2c24cce4259859aeb7149f62b7607d087d", "exam_bench/finalize.py": "4034f1c63896a940afdb1a83d541cf47fc75c8b5061e3f839047109c04beb620", "exam_bench/forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "exam_bench/gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "exam_bench/grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "exam_bench/harness.py": "3040f6daaf1dc6e6583219f4d925151f8ba7851b2d5417d7f14645892b485ddf", "exam_bench/interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "exam_bench/interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "exam_bench/isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "exam_bench/ledger.py": "7e851523580e22d8490e75f9b6026c07f2c355007e0d11d0b252671f56bef654", "exam_bench/locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "exam_bench/materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "exam_bench/mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "exam_bench/observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "exam_bench/ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "exam_bench/penalties.py": "0d79e2e46102657dca00609b6abbfc0bf7d11fad41429564f876c82bc6b33269", "exam_bench/platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "exam_bench/portable.py": "cad56968ff407983608f5bdbc9ce7234128d7a4580b096ecea8e0e7b4edb9070", "exam_bench/portable_harnesses.py": "6fc286cb7b35c9f869a92fd08c95ed5ac3f90d6ba21ba32034ea4de73275bd69", "exam_bench/pr.py": "6a3a20caf0e10c0cc94410511a72d62c9fcda785f3abab1be2ad616d4ee16836", "exam_bench/preflight.py": "5619be0131d8641925f3ce2a3c8e5234d42aa5635d95676138ca81536d95cd29", "exam_bench/process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "exam_bench/queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "exam_bench/queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "exam_bench/replay_calibration.py": "e2d79cb508f2d5e3846d6dad36c3898d41dec1c573c1a1b7d8a2ec43e33c8c08", "exam_bench/report.py": "5e4c0757e1c7f189953f9a5302593ab726551835856baed25efd93dad6e8bfcd", "exam_bench/runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "exam_bench/smoke_check.py": "f36922a0027429ead0b414048dcc14bbe67f2f0e79a70d03dffbe1447d253545", "exam_bench/stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "exam_bench/submission.py": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "exam_bench/telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "exam_bench/windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "exam_bench/workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tools/build_public_site.py": "9682ed696f5ac9e9a82b65a45c0dece556ec7e49eeb20dcd616882cc534a8258", "tools/build_result_site.py": "3294e1d2ec1486058e208735264d61e349a68a4ae2fa2ec7a723c70e3263b496", "tools/check_native_harnesses.py": "ff9aabf660569eb5a20dd9ce4cfa235c313a42e10cd0c89e571fcafe95bb94c8", "tools/check_native_toolkit.py": "0272794617121f2932828e5e4e9ae20095183c443666cf3ba466b44fbe875095", "tools/community_results.py": "3f4c0067088353ec5bba8ea32decba5e205c3f7993cc305d07693b54c7039a23", "tools/community_service.py": "c374480dbd88d656c0b9054fa04a8e1c6698c69e2f9cf475e82498a2dff61d84", "tools/community_setup.py": "5d7d126ed7d4dd48e1d79f57b99647a92ffcc8c9f80d90915e458888cdd76bf7", "tools/compare_harness_runs.py": "f274df5f3f804cb02504491aec946943833e12fbce6e62d281e12beb8508fc4e", "tools/create_run_plan.py": "871cd81b1eda231c0fba8805f63d2668926be9fc641559e6ddf320e2f47cd37a", "tools/demo_runner.py": "96c099c95b019ac30df5b2900991d0161ca73af6bdfa73a74e4172ba9c1deb00", "tools/installers.py": "9a2742780936b17500869e7c89202c1a2549e37d53a42ad9a50a0abbf78bbe09", "tools/machine_bundle.py": "8aa8346f99f537e81ceca6fb6ab9530e844954bab8eff87bf33d3602f81f8a30", "tools/prepare_native_harnesses.py": "b1909332ea4426acdb262685a7a9f4f02feaebc09421af613dc1333ce53529d8", "tools/prepare_official_statement.py": "6b7028c78e90e798d6ef1a93b76520cc61a308c354fb9b87f7fad18b99800fad", "tools/prepare_open_exam_requirements.py": "544f4e378b9be5f166186f8788f8d454afdac2deb99d91d98421e39d01ba6d03", "tools/probe_harness.py": "1ed8ef93420d1484cbbfd151b7efc31b9a201ceb942dd05e3103efa22ffa7f27", "tools/probe_native_mcp.py": "989a2b1d30bf91f42e5512e60c1597c7e32534bdd46b4e2654c665a59a3acf4b", "tools/readiness.py": "0b71ab667e6b2d9979fb3e5a769ebb8a453edec80a71090fb0b21b45af7986ce", "tools/recheck_community.py": "f0843d7d677f90da31e22bde0b1c86584dd46c022f1532d43d042619e426b230", "tools/regrade_runs.py": "011775afb06d3aac67a4aa81117a368c75896b0fcbe1e6f27ccc6237612fbf59", "tools/render_statement_text.py": "dabc0716a3612c288c671bc20e17fd4986691d732768e1e957d6dddddbea92a3", "tools/replay_calibration.py": "801f5004926c438c21ed3668fe2a4ddf45312b3e75320165a3839aae034eee9b", "tools/run_exam_campaign.py": "2c450d57a1cd0a2682838f5ec7c0a4ffb3aed0f1730d34c408e912d59cab6efd", "tools/serve_result_site.py": "86badfac863cd4ad1fc894a14110c75b28470513f0133eeae9d2799b8b4df3a9", "tools/start_demo.py": "c597e6cad28d245b3191654bb3e2801fa9dd2364e2acb25561923613717b615f", "tools/supplemental_acceptance.py": "7327277143d80a531e4c254ac74a9fc0e0d5c76572d53b8469e0a580eda17d65", "tools/sync_sources.py": "b51e889b0f41f9f63bfb19a09fb96d3777693d6b1d76fe0132bdd2a15e155898", "tools/validate_community_pr.py": "796b896dfade07b4529af2088a4b9b9d23484148b3bc0732b3fb837b75c9844b", "tools/verify_official_assessment_mapping.py": "daeb448a016940d5b6b1285979a56e5b9014bd91db40acb131445e4a83a23059", "tools/verify_task_package.py": "9e1e6105f6b5e4e78b36aa57f00117a9fbc8948ab53983c32ab56da88d23ccc4", "profiles/agents.json": "af9c492c08d13b3044aa6b6952589ed6a0a07d5258d8ff72bb18185b3eaebdc5", "profiles/ai-exam-execution-policy.json": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "profiles/bsl-analyzer-0.3.2-macos.json": "83537abdbf38c41ce665e4d0f24128bb51b62e971e0e0f368695f1326a7d2ffb", "profiles/bsl-analyzer-0.3.2-portable.json": "d6ba732e6778e256df34d6bc548593128820a70430c35b279796843606ee40a8", "profiles/bsl-ls-1.1.0-rc.6-macos.json": "245fc10747197e6911b2b4c77cdb15e6fa4eb7bc7c3758b63e768c5adf1df180", "profiles/bsl-ls-1.1.0-rc.6-portable.json": "9f10660881f2ec84794f7d584556b8f75c7e14b3555464af0ed0e60c4c892d86", "profiles/code-index-1.9.0-macos.json": "63a919523ce62ecec274f4c139bc7ad49a75dd4c339568b822cbc695b4e30408", "profiles/code-index-1.9.0-portable.json": "81106cee8f424ffd8a9dc46ecd8e4f57598fc1d49661a83c77b1f0507993fbdc", "profiles/codex-probe-plan.json": "166e41aad5fb3b27d9050bc6de952c6cba363cc6e804d4080568cc71a2a4d289", "profiles/machine.linux.example.json": "408304fd0581098d5d8110dc67dfeab353bc4d4030e32d37e6acf98d2b1aedfd", "profiles/machine.macos.example.json": "52e9f9d17797cb520b9d8955d6806fd550b899bed4da241ebf096dcb6a21a942", "profiles/machine.windows.example.json": "63accac9a2f81d47d03447efbabffd4760aee325193f02f46b9b29a28d50d2d8", "profiles/mcp-toolkit-1.9.0-macos.json": "1d3f9cde5ffa20589a840d01fdae03aa0fc2f412c929f064f203919c4129625b", "profiles/mcp-toolkit-1.9.0-portable.json": "8e370eebe773eef0e08045ee9c6d5be1451f769f65be0710834b262a4336e054", "profiles/none-macos.json": "b1401d9c48159aed3559006c7f6ace6ef4571224d5cf0bb76d1a823505a10056", "profiles/none-portable.json": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "profiles/rlm-tools-bsl-1.43.0-macos.json": "9354421052640ab60bc3e6aa98ff2e7ba9ca2318b0f4026c137487449242cbd2", "profiles/rlm-tools-bsl-1.43.0-portable.json": "2599e5645e0a7d4e44cb2934bc2b272cae79a9bf7ea74a23cd48aacea64bc424", "profiles/rlm-tools-bsl-1.43.0-posix-requirements.txt": "4fdf9a1bd994bf0272e65d231daf76cf19b0a34dad0ae6b50ec4f11a2ce4c330", "profiles/rlm-tools-bsl-1.43.0-windows-requirements.txt": "3730cb46c81cda5181ecd4485e98b11933104632358bc86f8c0eb1a612a8954f", "profiles/shirokov-skills-macos.json": "84f3e89091676884a802035c707e912762a1179425fb8e3faff25be736873cdb", "profiles/shirokov-skills-portable.json": "2b0a461e06602f1456410e70f02ceaa5ac32c6549c486660bcb5ace0c2f87b15", "profiles/shirokov-skills-windows-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/unica-0.12.3-macos.json": "2c39fbb591cf2c2c6e056373823615485397ea83651b7926c6f25a5fe6a0aae6", "profiles/unica-0.13.0-macos.json": "b76b5c8a4dd33f571c4a90993f1a2da5f7223b4f0f8e1042c282e21a66121052", "profiles/unica-0.14.0-rc.1-portable.json": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "rules/1c-specialist-platform/chistov.json": "7a42ef723a1f5f03f02c387cd3ca95725f7364c2e11ebdfc988a02919ab22c37", "rules/1c-specialist-platform/decisions.json": "f622107423ce3c188c063318d7ab4f7718ceb38e443130677d8987f386641c09", "rules/1c-specialist-platform/examiner.json": "30353aa2a1b6545496b070d9066e9ffba0c3779e5b53ef70a4fd2cee375b18c0", "rules/1c-specialist-platform/ledger.json": "f167c10db2b5799dd9a1ea6a37cd2d7d186810dadf5ea2f50f26ae723c676882", "rules/1c-specialist-platform/rules.json": "1d320a4f8e1bf4701496388931f492315549bd3dce574b17285dd1d7f8652007", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" } } }, "conditions": { "client": "claude", "model": "claude-opus-5-5", "client_version": "2.1.310", "reasoning_effort": "medium", "harness": "ai-rules-1c-3f909dc", "billing_channel": "subscription", "solve_timeout_seconds": 10800, "time_series": null, "delegation": "native_disabled", "network_profile": "open-book_shell", "deadline_disclosed": true, "statement_sha256": "8a6ccb3e673826d1f8220fda53eb310e3ec18c136d87ce8f4cebb2a08614e7e5", "starter_dt_sha256": "f40d084818b0d1cfe503fc7653a6a13f1a8e47fcd1688dad6245b12744eb4638", "profile_sha256": "8c5dd51ff06982703b86f733da56d172dd452f3db00b2c9a00296e8176fee580", "execution_policy_sha256": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "calibration_sha256": "fb1dcb74e6b2bd4731d30b0ffc4bd84053cebd2ed4006d67be20b878b4bc7fd4", "started_at": "2026-10-26T07:09:28.758105+00:00", "timing": { "prepare_ms": 32963, "solve_ms": 2725971, "grade_ms": null }, "original_submission_valid": true, "model_provenance": "client_reported", "tokens": { "input": 42023364, "cached_input": 41639627, "fresh_input": 383737, "output": 192780, "reasoning_output": null, "total": 42216144, "coverage": "final_result_model_usage" }, "tools": { "mcp_calls": 46, "unica_calls": 0, "failed_calls": 5 }, "process": { "status": "completed", "exit_code": 0, "stop_confirmed": true } }, "verification": "contributor_reported", "download": "community-downloads/demo-20261026T070850Z-84a3a7/solution.zip", "source_context": "community-downloads/demo-20261026T070850Z-84a3a7/source-context.json", "regrade_required": [ { "id": "grader_changed", "files": [ "assessment.py", "bp.py", "calcwrite.py", "calibrate.py", "calibration_periodicity.py", "calibration_query.py", "claude.py", "codescan.py", "codex.py", "common.py", "docx_text.py", "examiner.py", "harness.py", "interpretations.py", "locking.py", "materials.py", "mcp_toolkit.py", "ou.py", "penalties.py", "portable_harnesses.py", "pr.py", "preflight.py", "queries.py", "queryschema.py", "querytypes.py", "replay_calibration.py", "rules/1c-specialist-platform/chistov.json", "rules/1c-specialist-platform/examiner.json", "rules/1c-specialist-platform/rules.json", "rules/1c-specialist-platform/standards.json", "smoke_check.py", "starters/carcass-8.3.25.1445/starter.json", "stdio_harnesses.py", "tasks/1c-platform-official-sample/checks.json", "tasks/1c-platform-official-sample/private/official-assessment-mapping.json", "tasks/1c-platform-official-sample/private/owner-scoring-policy.json", "telemetry.py" ] } ], "grader_revision_sha256": "855d4f66db31ec9f50ebfc18f596c0d1d157e53e2830c51f853c1338f628e49c", "archive_sha256": "0e60e86c6dc5be08e71ac8fced22548febd7f5832d98897023f56612b213972b" } ] }, { "id": "demo-20261026T113637Z-010c79--owner-2026-10-26T223359597004-0000", "run_id": "demo-20261026T113637Z-010c79", "result": { "run_id": "demo-20261026T113637Z-010c79", "created_at": "2026-10-26T22:33:59.597004+00:00", "model": "gpt-6.1-sol", "harness": "none", "solve_seconds": 4563, "platform": "8.3.27.2342", "counts": { "pass": 64, "fail": 1 }, "rules": [ { "id": "BU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU01.selected_fixture" }, { "id": "BU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU04.selected_fixture" }, { "id": "BU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU05.selected_fixture" }, { "id": "BU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU16.selected_fixture" }, { "id": "BU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU17.selected_fixture" }, { "id": "BU02", "verdict": "pass", "reason": null, "coverage": "partial", "assertion_id": "BU02.posting_cost_and_balance" }, { "id": "BU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU10.selected_fixture" }, { "id": "BU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU12.selected_fixture" }, { "id": "BU03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU03.selected_fixture" }, { "id": "BU06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU06.selected_fixture" }, { "id": "BU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU07.selected_fixture" }, { "id": "BU08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU08.selected_fixture" }, { "id": "BU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU09.selected_fixture" }, { "id": "BU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU11.selected_fixture" }, { "id": "BU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU14.selected_fixture" }, { "id": "BU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU15.selected_fixture" }, { "id": "BU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU13.selected_fixture" }, { "id": "OU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU15.selected_fixture" }, { "id": "OU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU16.selected_fixture" }, { "id": "OU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU17.selected_fixture" }, { "id": "OU02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU02.selected_fixture" }, { "id": "OU18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU18.selected_fixture" }, { "id": "OU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU14.selected_fixture" }, { "id": "OU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU01.selected_fixture" }, { "id": "OU03", "verdict": "pass", "reason": "История и годовая периодичность регистра подтверждены.", "coverage": "history_and_periodicity", "assertion_id": "OU03.selected_fixture" }, { "id": "OU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU05.selected_fixture" }, { "id": "OU06", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "OU06.selected_fixture" }, { "id": "OU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU07.selected_fixture" }, { "id": "OU08", "verdict": "pass", "reason": "История и дневная периодичность подтверждены; ограничение одной версии в неделю отдельно не проверяется.", "coverage": "history_and_periodicity", "assertion_id": "OU08.selected_fixture" }, { "id": "OU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU09.selected_fixture" }, { "id": "OU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU10.selected_fixture" }, { "id": "OU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU11.selected_fixture" }, { "id": "OU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU12.selected_fixture" }, { "id": "OU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU13.selected_fixture" }, { "id": "OU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU04.selected_fixture" }, { "id": "OU19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU19.selected_fixture" }, { "id": "OU20", "verdict": "fail", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU20.selected_fixture" }, { "id": "OU21", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU21.selected_fixture" }, { "id": "PR01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR01.selected_fixture" }, { "id": "PR02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR02.selected_fixture" }, { "id": "PR03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR03.selected_fixture" }, { "id": "PR04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR04.selected_fixture" }, { "id": "PR05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR05.selected_fixture" }, { "id": "PR06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR06.selected_fixture" }, { "id": "PR07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR07.selected_fixture" }, { "id": "PR08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR08.selected_fixture" }, { "id": "PR09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR09.selected_fixture" }, { "id": "PR10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR10.selected_fixture" }, { "id": "PR11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR11.selected_fixture" }, { "id": "PR12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR12.selected_fixture" }, { "id": "PR13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR13.selected_fixture" }, { "id": "PR14", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "PR14.selected_fixture" }, { "id": "PR15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR15.selected_fixture" }, { "id": "PR16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR16.selected_fixture" }, { "id": "PR17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR17.selected_fixture" }, { "id": "PR18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR18.selected_fixture" }, { "id": "PR19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR19.selected_fixture" }, { "id": "F01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F01.selected_fixture" }, { "id": "F02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F02.selected_fixture" }, { "id": "F03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F03.selected_fixture" }, { "id": "F04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F04.selected_fixture" }, { "id": "F05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F05.selected_fixture" }, { "id": "G01", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G01.static_sources" }, { "id": "G02", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G02.static_sources" }, { "id": "G03", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G03.static_sources" } ], "charges": [ { "id": "F1C-GEN03", "points": "0.5", "reason": "отчёт не соответствует заданию: OU20" }, { "id": "F1C-PR14", "points": "0.5", "reason": "после расчёта набор с периодом действия перезаписывается целиком, с пересчётом фактического периода действия (нужно Записать(, Истина)): CommonModules/РасчетЗарплаты/Ext/Module.bsl:110 Набор.Записать(Истина, Ложь, Истина, Ложь)" }, { "id": "F1C-BU06", "points": "1.5", "reason": "у счёта товаров 01.02 не включён признак учёта КоличественныйУчет" }, { "id": "F1C-GEN20", "points": "2.0", "reason": "данные базы читаются в цикле по записям: CommonModules/УчетСервер/Ext/Module.bsl:368; CommonModules/УчетСервер/Ext/Module.bsl:368" } ], "score_upper_bound": "0.5", "score": null, "grade": "unsatisfactory", "deductions": "4.5", "not_assessed": 15, "gates": { "starter_origin": "passed", "load": "loaded", "clients": "compiles", "demo_data": "present" }, "infrastructure_errors": false, "comparison_eligible": false, "binding_compatibility": null }, "measurement": { "operator": { "name": "Виктор Мурашкин", "github": "VictorMurashkin" }, "environment": { "captured_at": "2026-10-26T11:36:38.784331+00:00", "capture_timing": "before_run", "hardware": { "cpu": "12th Gen Intel(R) Core(TM) i5-12600KF", "logical_cpus": 16, "ram_bytes": 68500021248 }, "os": { "system": "Windows", "release": "11", "version": "10.0.26100", "architecture": "AMD64" }, "python": "3.14.6", "platform_version": "8.3.27.2342", "isolation": "dedicated-host", "network_profile": "open-book_shell", "unsafe_action_protection_observed_in_user_config": true, "git_revision": "4431a896acdc1e09f964b8afb3468fc045118372", "implementation_files": { "exam_bench/__init__.py": "ad5bf6f05dc6765f40b78bd186870ca2c49be113cfa33f8aa76f4926f2cb2c1e", "exam_bench/assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "exam_bench/bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "exam_bench/calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "exam_bench/calibrate.py": "78b5185cb0888c0c0ac3de95ffc3a80154a6de9ae66fc461f79d012e5a58e1db", "exam_bench/calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "exam_bench/calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "exam_bench/calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "exam_bench/calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "exam_bench/calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "exam_bench/claude.py": "687602f4654ece014891d13e1503e2e90788a67e4cc0bde7eb6287bd7cf48b17", "exam_bench/cli.py": "a1a83be1f53924705576ed06b2a2c20868067fd0c5d3da839192e7b13c37540b", "exam_bench/codescan.py": "751e38001b6e65727a31e28172a0623f0bf34bc092a958037c286aa991a197ed", "exam_bench/codex.py": "904e75503cd35f16cbb052f66806b3879fe25bfc9f99e33b93c889d862c46324", "exam_bench/common.py": "8682603b519063e655eae3574a02a49efee63bde21f582ccee20ddd623fca96d", "exam_bench/cursor.py": "4ba6ac1ee1120e40c7e6429fd95959fd0d1ca7364471944b056870be93c86dc8", "exam_bench/cursor_bsl.py": "753f02ebed60e5b8bbefba0933adbdf28477ef916353d70e3c68c817ce6c42e0", "exam_bench/cursor_execution.py": "f495154ccf22013224716ce0f178956e5ef55a4191b1aa5f13a90a95cea3d35b", "exam_bench/cursor_harnesses.py": "9b1fe8386c4440eab5cfe080ee362d185f87fc4d9907037be7892e9dcb31166b", "exam_bench/cursor_load.py": "195e9f3334927f1052ea415ae6c7b7c02f5b9df061b8965bfdfb2866cb2208f8", "exam_bench/docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "exam_bench/examiner.py": "d7294fdd23ed1732216cafebf0a8cf2c24cce4259859aeb7149f62b7607d087d", "exam_bench/finalize.py": "4034f1c63896a940afdb1a83d541cf47fc75c8b5061e3f839047109c04beb620", "exam_bench/forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "exam_bench/gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "exam_bench/grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "exam_bench/harness.py": "3040f6daaf1dc6e6583219f4d925151f8ba7851b2d5417d7f14645892b485ddf", "exam_bench/interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "exam_bench/interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "exam_bench/isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "exam_bench/ledger.py": "7e851523580e22d8490e75f9b6026c07f2c355007e0d11d0b252671f56bef654", "exam_bench/locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "exam_bench/materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "exam_bench/mcp_toolkit.py": "f4c3ea8d9ce542645960a0234ddb61712a047793c58d4e2a0691fc9a45961383", "exam_bench/observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "exam_bench/ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "exam_bench/penalties.py": "0d79e2e46102657dca00609b6abbfc0bf7d11fad41429564f876c82bc6b33269", "exam_bench/platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "exam_bench/portable.py": "cad56968ff407983608f5bdbc9ce7234128d7a4580b096ecea8e0e7b4edb9070", "exam_bench/portable_harnesses.py": "686c46a4231067625b3a20f0b22639d14bcaeb26fab3493e06f92b53dfead05a", "exam_bench/pr.py": "6a3a20caf0e10c0cc94410511a72d62c9fcda785f3abab1be2ad616d4ee16836", "exam_bench/preflight.py": "fbce47aa201c1f5acdbc80b241655dce443df35f9d14d3260c2325f875d6f6e4", "exam_bench/process.py": "263c065a9be9d0586d5467a478e9d34c44035697b7d69781ef38a997bf90596f", "exam_bench/queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "exam_bench/queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "exam_bench/replay_calibration.py": "e2d79cb508f2d5e3846d6dad36c3898d41dec1c573c1a1b7d8a2ec43e33c8c08", "exam_bench/report.py": "5e4c0757e1c7f189953f9a5302593ab726551835856baed25efd93dad6e8bfcd", "exam_bench/runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "exam_bench/smoke_check.py": "f36922a0027429ead0b414048dcc14bbe67f2f0e79a70d03dffbe1447d253545", "exam_bench/stdio_harnesses.py": "0bbfd791fb244a934c6cda3a4e63fbe9ce515e4af64729bb923ce86645057288", "exam_bench/submission.py": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "exam_bench/telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "exam_bench/windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "exam_bench/workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tools/build_public_site.py": "788ec78558bf5391a2143d8602fc3659d4d45a914b8a5f476f42aef33e51771e", "tools/build_result_site.py": "2cdf8ca026e40fb41a4697bb4a267e5d28535cdd11ff7db8ee0e4dc864f95c33", "tools/check_native_harnesses.py": "1fdde7b8eeb76f94341592ddbf1cac61306a65779d7b871ecabd053ab70c1e80", "tools/check_native_toolkit.py": "0272794617121f2932828e5e4e9ae20095183c443666cf3ba466b44fbe875095", "tools/community_results.py": "897bc6b845e707458164c395075e659be9dbbb98898677359870578dee78a938", "tools/community_service.py": "493186a0718c81c8afa356c1c160d42b2c1d77dfedf1b70c8eb8c6aad84a73dc", "tools/community_setup.py": "5d7d126ed7d4dd48e1d79f57b99647a92ffcc8c9f80d90915e458888cdd76bf7", "tools/compare_harness_runs.py": "f274df5f3f804cb02504491aec946943833e12fbce6e62d281e12beb8508fc4e", "tools/create_run_plan.py": "694f1b376f5b78de23705b8df3ec943def516eda93f96e7afaa3942729a1240c", "tools/demo_runner.py": "dda8e6dc8931eead20766a8aff06eec40c1100587dfb265f4dccc20f3c04d4c0", "tools/installers.py": "9a2742780936b17500869e7c89202c1a2549e37d53a42ad9a50a0abbf78bbe09", "tools/load_diagnostics.py": "6673122a8c32bf3a33cb292f514d4d79f2b62d4d72a859d7356b24312440f2dd", "tools/machine_bundle.py": "8aa8346f99f537e81ceca6fb6ab9530e844954bab8eff87bf33d3602f81f8a30", "tools/prepare_native_harnesses.py": "fba3fd78b1fdd400196e086c5f463aec5ecefe41e81cd6875d87c76a3126a877", "tools/prepare_official_statement.py": "6b7028c78e90e798d6ef1a93b76520cc61a308c354fb9b87f7fad18b99800fad", "tools/prepare_open_exam_requirements.py": "544f4e378b9be5f166186f8788f8d454afdac2deb99d91d98421e39d01ba6d03", "tools/probe_cursor_harnesses.py": "19952ea409c934ed89cf2589dbb7dcf8d52fad5e01ca256c7df552578d28addc", "tools/probe_harness.py": "1ed8ef93420d1484cbbfd151b7efc31b9a201ceb942dd05e3103efa22ffa7f27", "tools/probe_http_mcp.py": "2667e191fb831b1cbc9cbbbbefdfad16241e17d620a1a42a43405ab0b8139ac4", "tools/probe_native_mcp.py": "9918d324129cba898993e07f8f8b6dbcbaf369398ebf28d464f9f1f00abdb254", "tools/readiness.py": "3c5404be17a7a0a2f72d7cef5714f7d1d6bde7da0d8eb698da4cc65d0b0dd3f3", "tools/recheck_community.py": "f0843d7d677f90da31e22bde0b1c86584dd46c022f1532d43d042619e426b230", "tools/regrade_runs.py": "011775afb06d3aac67a4aa81117a368c75896b0fcbe1e6f27ccc6237612fbf59", "tools/render_statement_text.py": "dabc0716a3612c288c671bc20e17fd4986691d732768e1e957d6dddddbea92a3", "tools/replay_calibration.py": "801f5004926c438c21ed3668fe2a4ddf45312b3e75320165a3839aae034eee9b", "tools/run_exam_campaign.py": "2c450d57a1cd0a2682838f5ec7c0a4ffb3aed0f1730d34c408e912d59cab6efd", "tools/serve_result_site.py": "07ffdd3bc63227523c1a589a996b5027f357a139d53d3835dfb77f9817a7e09d", "tools/start_demo.py": "c597e6cad28d245b3191654bb3e2801fa9dd2364e2acb25561923613717b615f", "tools/supplemental_acceptance.py": "7327277143d80a531e4c254ac74a9fc0e0d5c76572d53b8469e0a580eda17d65", "tools/sync_sources.py": "b51e889b0f41f9f63bfb19a09fb96d3777693d6b1d76fe0132bdd2a15e155898", "tools/validate_community_pr.py": "796b896dfade07b4529af2088a4b9b9d23484148b3bc0732b3fb837b75c9844b", "tools/verify_official_assessment_mapping.py": "daeb448a016940d5b6b1285979a56e5b9014bd91db40acb131445e4a83a23059", "tools/verify_task_package.py": "9e1e6105f6b5e4e78b36aa57f00117a9fbc8948ab53983c32ab56da88d23ccc4", "profiles/1c-ai-rules-2026-10-23-requirements.txt": "fd7ada214e0977776eb350794bb492d97824d96810eb7b158e46cf5cd72c8e65", "profiles/agents.json": "af9c492c08d13b3044aa6b6952589ed6a0a07d5258d8ff72bb18185b3eaebdc5", "profiles/ai-exam-execution-policy.json": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "profiles/bsl-analyzer-0.3.2-macos.json": "83537abdbf38c41ce665e4d0f24128bb51b62e971e0e0f368695f1326a7d2ffb", "profiles/bsl-analyzer-0.3.2-portable.json": "d6ba732e6778e256df34d6bc548593128820a70430c35b279796843606ee40a8", "profiles/bsl-ls-1.1.0-rc.6-macos.json": "245fc10747197e6911b2b4c77cdb15e6fa4eb7bc7c3758b63e768c5adf1df180", "profiles/bsl-ls-1.1.0-rc.6-portable.json": "9f10660881f2ec84794f7d584556b8f75c7e14b3555464af0ed0e60c4c892d86", "profiles/claude-code-skills-1c-1.12.0-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/code-index-1.9.0-macos.json": "63a919523ce62ecec274f4c139bc7ad49a75dd4c339568b822cbc695b4e30408", "profiles/code-index-1.9.0-portable.json": "81106cee8f424ffd8a9dc46ecd8e4f57598fc1d49661a83c77b1f0507993fbdc", "profiles/codex-probe-plan.json": "166e41aad5fb3b27d9050bc6de952c6cba363cc6e804d4080568cc71a2a4d289", "profiles/cursor-1c-skills-1.12.0-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/machine.linux.example.json": "408304fd0581098d5d8110dc67dfeab353bc4d4030e32d37e6acf98d2b1aedfd", "profiles/machine.macos.example.json": "52e9f9d17797cb520b9d8955d6806fd550b899bed4da241ebf096dcb6a21a942", "profiles/machine.windows.example.json": "63accac9a2f81d47d03447efbabffd4760aee325193f02f46b9b29a28d50d2d8", "profiles/mcp-toolkit-1.9.0-macos.json": "1d3f9cde5ffa20589a840d01fdae03aa0fc2f412c929f064f203919c4129625b", "profiles/mcp-toolkit-1.9.0-portable.json": "8e370eebe773eef0e08045ee9c6d5be1451f769f65be0710834b262a4336e054", "profiles/none-macos.json": "b1401d9c48159aed3559006c7f6ace6ef4571224d5cf0bb76d1a823505a10056", "profiles/none-portable.json": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "profiles/rlm-tools-bsl-1.43.0-macos.json": "9354421052640ab60bc3e6aa98ff2e7ba9ca2318b0f4026c137487449242cbd2", "profiles/rlm-tools-bsl-1.43.0-portable.json": "2599e5645e0a7d4e44cb2934bc2b272cae79a9bf7ea74a23cd48aacea64bc424", "profiles/rlm-tools-bsl-1.43.0-posix-requirements.txt": "4fdf9a1bd994bf0272e65d231daf76cf19b0a34dad0ae6b50ec4f11a2ce4c330", "profiles/rlm-tools-bsl-1.43.0-windows-requirements.txt": "3730cb46c81cda5181ecd4485e98b11933104632358bc86f8c0eb1a612a8954f", "profiles/shirokov-skills-macos.json": "84f3e89091676884a802035c707e912762a1179425fb8e3faff25be736873cdb", "profiles/shirokov-skills-portable.json": "2b0a461e06602f1456410e70f02ceaa5ac32c6549c486660bcb5ace0c2f87b15", "profiles/shirokov-skills-windows-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/unica-0.12.3-macos.json": "2c39fbb591cf2c2c6e056373823615485397ea83651b7926c6f25a5fe6a0aae6", "profiles/unica-0.13.0-macos.json": "b76b5c8a4dd33f571c4a90993f1a2da5f7223b4f0f8e1042c282e21a66121052", "profiles/unica-0.14.0-rc.1-portable.json": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "rules/1c-specialist-platform/chistov.json": "7a42ef723a1f5f03f02c387cd3ca95725f7364c2e11ebdfc988a02919ab22c37", "rules/1c-specialist-platform/decisions.json": "f622107423ce3c188c063318d7ab4f7718ceb38e443130677d8987f386641c09", "rules/1c-specialist-platform/examiner.json": "30353aa2a1b6545496b070d9066e9ffba0c3779e5b53ef70a4fd2cee375b18c0", "rules/1c-specialist-platform/ledger.json": "f167c10db2b5799dd9a1ea6a37cd2d7d186810dadf5ea2f50f26ae723c676882", "rules/1c-specialist-platform/rules.json": "1d320a4f8e1bf4701496388931f492315549bd3dce574b17285dd1d7f8652007", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" } } }, "conditions": { "client": "codex", "model": "gpt-6.1-sol", "client_version": "0.163.0", "reasoning_effort": "medium", "harness": "none", "billing_channel": "subscription", "solve_timeout_seconds": 18000, "time_series": "exam", "delegation": "native_disabled", "network_profile": "open-book_shell", "deadline_disclosed": true, "statement_sha256": "8a6ccb3e673826d1f8220fda53eb310e3ec18c136d87ce8f4cebb2a08614e7e5", "starter_dt_sha256": "f40d084818b0d1cfe503fc7653a6a13f1a8e47fcd1688dad6245b12744eb4638", "profile_sha256": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "execution_policy_sha256": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "calibration_sha256": "6fde5ca6242bb0895fda9c18ff5c5357a1762042d1c6d704032ee8f355eeb0a9", "started_at": "2026-10-26T11:36:57.347327+00:00", "timing": { "prepare_ms": 12600, "solve_ms": 4562988, "grade_ms": null }, "original_submission_valid": true, "model_provenance": "requested_only", "tokens": { "input": 21616270, "cached_input": 21442048, "fresh_input": 174222, "output": 134247, "reasoning_output": 50708, "total": 21750517, "coverage": "reported_completed_root_turns" }, "tools": { "mcp_calls": 0, "unica_calls": 0, "failed_calls": 0 }, "process": { "status": "completed", "exit_code": 0, "stop_confirmed": true } }, "verification": "repository_owner", "download": "community-downloads/demo-20261026T113637Z-010c79--owner-2026-10-26T223359597004-0000/solution.zip", "source_context": "community-downloads/demo-20261026T113637Z-010c79--owner-2026-10-26T223359597004-0000/source-context.json", "regrade_required": [], "grader_revision_sha256": "9aee1ffe0e1d04f9158fbbbeed3a403a5f0550ad8a590d7a6394977590760e1a", "archive_sha256": "2f4fb87d17984f71c6a9d19f3b1c36e2affbe6636950261d4a6d0db84081d8d2", "owner_verification": { "kind": "repository_owner", "repository": "zeegin/1c-agent-exam-benchmark", "operator": { "name": "Ingvar Vilkman", "github": "zeegin" }, "started_at": "2026-10-26T22:33:59.437134+00:00", "server": { "name": "Owner Windows stand", "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "hardware": { "cpu": "AMD Ryzen 7 5800X 8-Core Processor ", "logical_cpus": 4, "ram_bytes": 17109000192 }, "isolation": "dedicated-host" }, "platform_version": "8.3.27.2342", "grader": { "profile": "technical-v8", "commit": "e15c8ea80263c0b38baa3a1fc19611983270e8a7", "working_tree_dirty": false, "fingerprint": { "assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "calibrate.py": "aac127e03744907fd52ef149b88aa6d88a54a2b7497d56084484ee1b99e0da99", "calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "calibration_periodicity.py": "0b1953d7781e236467897cd2ed66705b75d9719353a2de60b36f2bbdfe799108", "calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "calibration_query.py": "3555b103cde8ea0519955cf52358d09223f5ab183a9df00533bdb48c89237a8c", "claude.py": "5bae98af6e2021e2718afa3a71ed04bee812deaae31a43d4e7324814139ccc82", "codescan.py": "6d8375210cef1fd768fc2d98d630d880b2993a9724f01ae25f33b4ea5aa9631d", "codex.py": "904e75503cd35f16cbb052f66806b3879fe25bfc9f99e33b93c889d862c46324", "common.py": "739b39e2bb9bdd4a571fc69df5843190cddcad094ef7e68964061bc1266b20dc", "docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "examiner.py": "8cdffcdd52f043c905f896697403380af95bf485dd4a5edca24f7956e7795ffe", "forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "harness.py": "3cbb90fd3187e700b5df32e5daafb20313d49bb5721c826e3033cbc6aa6e3825", "interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "ou.py": "f62784b54a3f85576a078a2ff1908c9395f3159e55f6bb5b1a3c564392241abe", "penalties.py": "ae388cb8953ecca1f2370a7c4cb1db3b6cc8318fc2a7563a4db15f9f5b057429", "platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "pr.py": "2b6bfea0634703469605ce114f9274716b485852d9a55d9185c39893b14e4726", "preflight.py": "448c3120ab64b625abae3891be686c7a214ce4211f7cf651fd90e12c0b298433", "process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "queries.py": "1ef57e292db3e8967a733948371ecc542f743b811890d4fc509df17303b9c4ac", "queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "querytypes.py": "b645f489a2abc27762b4a9bbf4917e72f7b46dc053a74c0dca4a8fc46491b3ef", "replay_calibration.py": "e0e3d5ca6416934715b9735aa516046b8d19ad4ae690220eeacd96b198a5f86c", "runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "smoke_check.py": "7837e980986bcb54dc8bc1dfb5d0003deef11e05f6e11df3910fa509e1f74c8d", "stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "submission.py": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tasks/1c-platform-official-sample/checks.json": "7447a9b42d3e348d29d07f001cfb6bd269acd953b7117eba7cca2ce9f5a9a60d", "tasks/1c-platform-official-sample/private/official-assessment-mapping.json": "303587c0dabe77c1eeebb2017fe85539e3370b17c9090435e6e0325a66bd0644", "tasks/1c-platform-official-sample/private/owner-scoring-policy.json": "d26d534bb838ab1b5facb7bc033ca8ec40912133baadcdbad83b27fc577905f5", "starters/carcass-8.3.25.1445/starter.json": "0f7a7060885ba99a19402bfc6e63cc8fe979b0f491b040d3a01d5d21b304b3a6", "rules/1c-specialist-platform/rules.json": "ea75e34ace5de11ba3de403c63cd2c026db81d1d991f8531e4a779d4ce9788e7", "rules/1c-specialist-platform/examiner.json": "1247486ddd412d600db88d9c1db4ba501fc1994afd1dc2ebe85402fcc332f4c8", "rules/1c-specialist-platform/chistov.json": "800da27601a3f1c7ec1df64482fd4ad035e559ba0b390a274ed5031128487d3d", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" }, "sha256": "9aee1ffe0e1d04f9158fbbbeed3a403a5f0550ad8a590d7a6394977590760e1a" }, "method": "saved_platform_observations", "outcome": "complete", "completed_at": "2026-10-26T22:33:59.597004+00:00" }, "previous_evaluations": [ { "id": "demo-20261026T113637Z-010c79--owner-2026-10-26T214441318235-0000", "run_id": "demo-20261026T113637Z-010c79", "result": { "run_id": "demo-20261026T113637Z-010c79", "created_at": "2026-10-26T21:44:41.318235+00:00", "model": "gpt-6.1-sol", "harness": "none", "solve_seconds": 4563, "platform": "8.3.27.2342", "counts": { "pass": 64, "fail": 1 }, "rules": [ { "id": "BU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU01.selected_fixture" }, { "id": "BU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU04.selected_fixture" }, { "id": "BU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU05.selected_fixture" }, { "id": "BU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU16.selected_fixture" }, { "id": "BU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU17.selected_fixture" }, { "id": "BU02", "verdict": "pass", "reason": null, "coverage": "partial", "assertion_id": "BU02.posting_cost_and_balance" }, { "id": "BU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU10.selected_fixture" }, { "id": "BU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU12.selected_fixture" }, { "id": "BU03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU03.selected_fixture" }, { "id": "BU06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU06.selected_fixture" }, { "id": "BU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU07.selected_fixture" }, { "id": "BU08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU08.selected_fixture" }, { "id": "BU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU09.selected_fixture" }, { "id": "BU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU11.selected_fixture" }, { "id": "BU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU14.selected_fixture" }, { "id": "BU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU15.selected_fixture" }, { "id": "BU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU13.selected_fixture" }, { "id": "OU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU15.selected_fixture" }, { "id": "OU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU16.selected_fixture" }, { "id": "OU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU17.selected_fixture" }, { "id": "OU02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU02.selected_fixture" }, { "id": "OU18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU18.selected_fixture" }, { "id": "OU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU14.selected_fixture" }, { "id": "OU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU01.selected_fixture" }, { "id": "OU03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU03.selected_fixture" }, { "id": "OU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU05.selected_fixture" }, { "id": "OU06", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "OU06.selected_fixture" }, { "id": "OU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU07.selected_fixture" }, { "id": "OU08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU08.selected_fixture" }, { "id": "OU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU09.selected_fixture" }, { "id": "OU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU10.selected_fixture" }, { "id": "OU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU11.selected_fixture" }, { "id": "OU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU12.selected_fixture" }, { "id": "OU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU13.selected_fixture" }, { "id": "OU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU04.selected_fixture" }, { "id": "OU19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU19.selected_fixture" }, { "id": "OU20", "verdict": "fail", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU20.selected_fixture" }, { "id": "OU21", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU21.selected_fixture" }, { "id": "PR01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR01.selected_fixture" }, { "id": "PR02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR02.selected_fixture" }, { "id": "PR03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR03.selected_fixture" }, { "id": "PR04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR04.selected_fixture" }, { "id": "PR05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR05.selected_fixture" }, { "id": "PR06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR06.selected_fixture" }, { "id": "PR07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR07.selected_fixture" }, { "id": "PR08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR08.selected_fixture" }, { "id": "PR09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR09.selected_fixture" }, { "id": "PR10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR10.selected_fixture" }, { "id": "PR11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR11.selected_fixture" }, { "id": "PR12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR12.selected_fixture" }, { "id": "PR13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR13.selected_fixture" }, { "id": "PR14", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "PR14.selected_fixture" }, { "id": "PR15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR15.selected_fixture" }, { "id": "PR16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR16.selected_fixture" }, { "id": "PR17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR17.selected_fixture" }, { "id": "PR18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR18.selected_fixture" }, { "id": "PR19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR19.selected_fixture" }, { "id": "F01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F01.selected_fixture" }, { "id": "F02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F02.selected_fixture" }, { "id": "F03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F03.selected_fixture" }, { "id": "F04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F04.selected_fixture" }, { "id": "F05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F05.selected_fixture" }, { "id": "G01", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G01.static_sources" }, { "id": "G02", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G02.static_sources" }, { "id": "G03", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G03.static_sources" } ], "charges": [ { "id": "F1C-GEN03", "points": "0.5", "reason": "отчёт не соответствует заданию: OU20" }, { "id": "F1C-PR14", "points": "0.5", "reason": "после расчёта набор с периодом действия перезаписывается целиком, с пересчётом фактического периода действия (нужно Записать(, Истина)): CommonModules/РасчетЗарплаты/Ext/Module.bsl:110 Набор.Записать(Истина, Ложь, Истина, Ложь)" }, { "id": "F1C-BU06", "points": "1.5", "reason": "у счёта товаров 01.02 не включён признак учёта КоличественныйУчет" }, { "id": "F1C-GEN20", "points": "2.0", "reason": "данные базы читаются в цикле по записям: CommonModules/УчетСервер/Ext/Module.bsl:368; CommonModules/УчетСервер/Ext/Module.bsl:368" } ], "score_upper_bound": "0.5", "score": null, "grade": "unsatisfactory", "deductions": "4.5", "not_assessed": 15, "gates": { "starter_origin": "passed", "load": "loaded", "clients": "compiles", "demo_data": "present" }, "infrastructure_errors": false, "comparison_eligible": false, "binding_compatibility": null }, "measurement": { "operator": { "name": "Виктор Мурашкин", "github": "VictorMurashkin" }, "environment": { "captured_at": "2026-10-26T11:36:38.784331+00:00", "capture_timing": "before_run", "hardware": { "cpu": "12th Gen Intel(R) Core(TM) i5-12600KF", "logical_cpus": 16, "ram_bytes": 68500021248 }, "os": { "system": "Windows", "release": "11", "version": "10.0.26100", "architecture": "AMD64" }, "python": "3.14.6", "platform_version": "8.3.27.2342", "isolation": "dedicated-host", "network_profile": "open-book_shell", "unsafe_action_protection_observed_in_user_config": true, "git_revision": "4431a896acdc1e09f964b8afb3468fc045118372", "implementation_files": { "exam_bench/__init__.py": "ad5bf6f05dc6765f40b78bd186870ca2c49be113cfa33f8aa76f4926f2cb2c1e", "exam_bench/assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "exam_bench/bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "exam_bench/calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "exam_bench/calibrate.py": "78b5185cb0888c0c0ac3de95ffc3a80154a6de9ae66fc461f79d012e5a58e1db", "exam_bench/calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "exam_bench/calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "exam_bench/calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "exam_bench/calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "exam_bench/calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "exam_bench/claude.py": "687602f4654ece014891d13e1503e2e90788a67e4cc0bde7eb6287bd7cf48b17", "exam_bench/cli.py": "a1a83be1f53924705576ed06b2a2c20868067fd0c5d3da839192e7b13c37540b", "exam_bench/codescan.py": "751e38001b6e65727a31e28172a0623f0bf34bc092a958037c286aa991a197ed", "exam_bench/codex.py": "904e75503cd35f16cbb052f66806b3879fe25bfc9f99e33b93c889d862c46324", "exam_bench/common.py": "8682603b519063e655eae3574a02a49efee63bde21f582ccee20ddd623fca96d", "exam_bench/cursor.py": "4ba6ac1ee1120e40c7e6429fd95959fd0d1ca7364471944b056870be93c86dc8", "exam_bench/cursor_bsl.py": "753f02ebed60e5b8bbefba0933adbdf28477ef916353d70e3c68c817ce6c42e0", "exam_bench/cursor_execution.py": "f495154ccf22013224716ce0f178956e5ef55a4191b1aa5f13a90a95cea3d35b", "exam_bench/cursor_harnesses.py": "9b1fe8386c4440eab5cfe080ee362d185f87fc4d9907037be7892e9dcb31166b", "exam_bench/cursor_load.py": "195e9f3334927f1052ea415ae6c7b7c02f5b9df061b8965bfdfb2866cb2208f8", "exam_bench/docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "exam_bench/examiner.py": "d7294fdd23ed1732216cafebf0a8cf2c24cce4259859aeb7149f62b7607d087d", "exam_bench/finalize.py": "4034f1c63896a940afdb1a83d541cf47fc75c8b5061e3f839047109c04beb620", "exam_bench/forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "exam_bench/gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "exam_bench/grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "exam_bench/harness.py": "3040f6daaf1dc6e6583219f4d925151f8ba7851b2d5417d7f14645892b485ddf", "exam_bench/interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "exam_bench/interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "exam_bench/isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "exam_bench/ledger.py": "7e851523580e22d8490e75f9b6026c07f2c355007e0d11d0b252671f56bef654", "exam_bench/locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "exam_bench/materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "exam_bench/mcp_toolkit.py": "f4c3ea8d9ce542645960a0234ddb61712a047793c58d4e2a0691fc9a45961383", "exam_bench/observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "exam_bench/ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "exam_bench/penalties.py": "0d79e2e46102657dca00609b6abbfc0bf7d11fad41429564f876c82bc6b33269", "exam_bench/platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "exam_bench/portable.py": "cad56968ff407983608f5bdbc9ce7234128d7a4580b096ecea8e0e7b4edb9070", "exam_bench/portable_harnesses.py": "686c46a4231067625b3a20f0b22639d14bcaeb26fab3493e06f92b53dfead05a", "exam_bench/pr.py": "6a3a20caf0e10c0cc94410511a72d62c9fcda785f3abab1be2ad616d4ee16836", "exam_bench/preflight.py": "fbce47aa201c1f5acdbc80b241655dce443df35f9d14d3260c2325f875d6f6e4", "exam_bench/process.py": "263c065a9be9d0586d5467a478e9d34c44035697b7d69781ef38a997bf90596f", "exam_bench/queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "exam_bench/queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "exam_bench/replay_calibration.py": "e2d79cb508f2d5e3846d6dad36c3898d41dec1c573c1a1b7d8a2ec43e33c8c08", "exam_bench/report.py": "5e4c0757e1c7f189953f9a5302593ab726551835856baed25efd93dad6e8bfcd", "exam_bench/runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "exam_bench/smoke_check.py": "f36922a0027429ead0b414048dcc14bbe67f2f0e79a70d03dffbe1447d253545", "exam_bench/stdio_harnesses.py": "0bbfd791fb244a934c6cda3a4e63fbe9ce515e4af64729bb923ce86645057288", "exam_bench/submission.py": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "exam_bench/telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "exam_bench/windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "exam_bench/workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tools/build_public_site.py": "788ec78558bf5391a2143d8602fc3659d4d45a914b8a5f476f42aef33e51771e", "tools/build_result_site.py": "2cdf8ca026e40fb41a4697bb4a267e5d28535cdd11ff7db8ee0e4dc864f95c33", "tools/check_native_harnesses.py": "1fdde7b8eeb76f94341592ddbf1cac61306a65779d7b871ecabd053ab70c1e80", "tools/check_native_toolkit.py": "0272794617121f2932828e5e4e9ae20095183c443666cf3ba466b44fbe875095", "tools/community_results.py": "897bc6b845e707458164c395075e659be9dbbb98898677359870578dee78a938", "tools/community_service.py": "493186a0718c81c8afa356c1c160d42b2c1d77dfedf1b70c8eb8c6aad84a73dc", "tools/community_setup.py": "5d7d126ed7d4dd48e1d79f57b99647a92ffcc8c9f80d90915e458888cdd76bf7", "tools/compare_harness_runs.py": "f274df5f3f804cb02504491aec946943833e12fbce6e62d281e12beb8508fc4e", "tools/create_run_plan.py": "694f1b376f5b78de23705b8df3ec943def516eda93f96e7afaa3942729a1240c", "tools/demo_runner.py": "dda8e6dc8931eead20766a8aff06eec40c1100587dfb265f4dccc20f3c04d4c0", "tools/installers.py": "9a2742780936b17500869e7c89202c1a2549e37d53a42ad9a50a0abbf78bbe09", "tools/load_diagnostics.py": "6673122a8c32bf3a33cb292f514d4d79f2b62d4d72a859d7356b24312440f2dd", "tools/machine_bundle.py": "8aa8346f99f537e81ceca6fb6ab9530e844954bab8eff87bf33d3602f81f8a30", "tools/prepare_native_harnesses.py": "fba3fd78b1fdd400196e086c5f463aec5ecefe41e81cd6875d87c76a3126a877", "tools/prepare_official_statement.py": "6b7028c78e90e798d6ef1a93b76520cc61a308c354fb9b87f7fad18b99800fad", "tools/prepare_open_exam_requirements.py": "544f4e378b9be5f166186f8788f8d454afdac2deb99d91d98421e39d01ba6d03", "tools/probe_cursor_harnesses.py": "19952ea409c934ed89cf2589dbb7dcf8d52fad5e01ca256c7df552578d28addc", "tools/probe_harness.py": "1ed8ef93420d1484cbbfd151b7efc31b9a201ceb942dd05e3103efa22ffa7f27", "tools/probe_http_mcp.py": "2667e191fb831b1cbc9cbbbbefdfad16241e17d620a1a42a43405ab0b8139ac4", "tools/probe_native_mcp.py": "9918d324129cba898993e07f8f8b6dbcbaf369398ebf28d464f9f1f00abdb254", "tools/readiness.py": "3c5404be17a7a0a2f72d7cef5714f7d1d6bde7da0d8eb698da4cc65d0b0dd3f3", "tools/recheck_community.py": "f0843d7d677f90da31e22bde0b1c86584dd46c022f1532d43d042619e426b230", "tools/regrade_runs.py": "011775afb06d3aac67a4aa81117a368c75896b0fcbe1e6f27ccc6237612fbf59", "tools/render_statement_text.py": "dabc0716a3612c288c671bc20e17fd4986691d732768e1e957d6dddddbea92a3", "tools/replay_calibration.py": "801f5004926c438c21ed3668fe2a4ddf45312b3e75320165a3839aae034eee9b", "tools/run_exam_campaign.py": "2c450d57a1cd0a2682838f5ec7c0a4ffb3aed0f1730d34c408e912d59cab6efd", "tools/serve_result_site.py": "07ffdd3bc63227523c1a589a996b5027f357a139d53d3835dfb77f9817a7e09d", "tools/start_demo.py": "c597e6cad28d245b3191654bb3e2801fa9dd2364e2acb25561923613717b615f", "tools/supplemental_acceptance.py": "7327277143d80a531e4c254ac74a9fc0e0d5c76572d53b8469e0a580eda17d65", "tools/sync_sources.py": "b51e889b0f41f9f63bfb19a09fb96d3777693d6b1d76fe0132bdd2a15e155898", "tools/validate_community_pr.py": "796b896dfade07b4529af2088a4b9b9d23484148b3bc0732b3fb837b75c9844b", "tools/verify_official_assessment_mapping.py": "daeb448a016940d5b6b1285979a56e5b9014bd91db40acb131445e4a83a23059", "tools/verify_task_package.py": "9e1e6105f6b5e4e78b36aa57f00117a9fbc8948ab53983c32ab56da88d23ccc4", "profiles/1c-ai-rules-2026-10-23-requirements.txt": "fd7ada214e0977776eb350794bb492d97824d96810eb7b158e46cf5cd72c8e65", "profiles/agents.json": "af9c492c08d13b3044aa6b6952589ed6a0a07d5258d8ff72bb18185b3eaebdc5", "profiles/ai-exam-execution-policy.json": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "profiles/bsl-analyzer-0.3.2-macos.json": "83537abdbf38c41ce665e4d0f24128bb51b62e971e0e0f368695f1326a7d2ffb", "profiles/bsl-analyzer-0.3.2-portable.json": "d6ba732e6778e256df34d6bc548593128820a70430c35b279796843606ee40a8", "profiles/bsl-ls-1.1.0-rc.6-macos.json": "245fc10747197e6911b2b4c77cdb15e6fa4eb7bc7c3758b63e768c5adf1df180", "profiles/bsl-ls-1.1.0-rc.6-portable.json": "9f10660881f2ec84794f7d584556b8f75c7e14b3555464af0ed0e60c4c892d86", "profiles/claude-code-skills-1c-1.12.0-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/code-index-1.9.0-macos.json": "63a919523ce62ecec274f4c139bc7ad49a75dd4c339568b822cbc695b4e30408", "profiles/code-index-1.9.0-portable.json": "81106cee8f424ffd8a9dc46ecd8e4f57598fc1d49661a83c77b1f0507993fbdc", "profiles/codex-probe-plan.json": "166e41aad5fb3b27d9050bc6de952c6cba363cc6e804d4080568cc71a2a4d289", "profiles/cursor-1c-skills-1.12.0-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/machine.linux.example.json": "408304fd0581098d5d8110dc67dfeab353bc4d4030e32d37e6acf98d2b1aedfd", "profiles/machine.macos.example.json": "52e9f9d17797cb520b9d8955d6806fd550b899bed4da241ebf096dcb6a21a942", "profiles/machine.windows.example.json": "63accac9a2f81d47d03447efbabffd4760aee325193f02f46b9b29a28d50d2d8", "profiles/mcp-toolkit-1.9.0-macos.json": "1d3f9cde5ffa20589a840d01fdae03aa0fc2f412c929f064f203919c4129625b", "profiles/mcp-toolkit-1.9.0-portable.json": "8e370eebe773eef0e08045ee9c6d5be1451f769f65be0710834b262a4336e054", "profiles/none-macos.json": "b1401d9c48159aed3559006c7f6ace6ef4571224d5cf0bb76d1a823505a10056", "profiles/none-portable.json": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "profiles/rlm-tools-bsl-1.43.0-macos.json": "9354421052640ab60bc3e6aa98ff2e7ba9ca2318b0f4026c137487449242cbd2", "profiles/rlm-tools-bsl-1.43.0-portable.json": "2599e5645e0a7d4e44cb2934bc2b272cae79a9bf7ea74a23cd48aacea64bc424", "profiles/rlm-tools-bsl-1.43.0-posix-requirements.txt": "4fdf9a1bd994bf0272e65d231daf76cf19b0a34dad0ae6b50ec4f11a2ce4c330", "profiles/rlm-tools-bsl-1.43.0-windows-requirements.txt": "3730cb46c81cda5181ecd4485e98b11933104632358bc86f8c0eb1a612a8954f", "profiles/shirokov-skills-macos.json": "84f3e89091676884a802035c707e912762a1179425fb8e3faff25be736873cdb", "profiles/shirokov-skills-portable.json": "2b0a461e06602f1456410e70f02ceaa5ac32c6549c486660bcb5ace0c2f87b15", "profiles/shirokov-skills-windows-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/unica-0.12.3-macos.json": "2c39fbb591cf2c2c6e056373823615485397ea83651b7926c6f25a5fe6a0aae6", "profiles/unica-0.13.0-macos.json": "b76b5c8a4dd33f571c4a90993f1a2da5f7223b4f0f8e1042c282e21a66121052", "profiles/unica-0.14.0-rc.1-portable.json": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "rules/1c-specialist-platform/chistov.json": "7a42ef723a1f5f03f02c387cd3ca95725f7364c2e11ebdfc988a02919ab22c37", "rules/1c-specialist-platform/decisions.json": "f622107423ce3c188c063318d7ab4f7718ceb38e443130677d8987f386641c09", "rules/1c-specialist-platform/examiner.json": "30353aa2a1b6545496b070d9066e9ffba0c3779e5b53ef70a4fd2cee375b18c0", "rules/1c-specialist-platform/ledger.json": "f167c10db2b5799dd9a1ea6a37cd2d7d186810dadf5ea2f50f26ae723c676882", "rules/1c-specialist-platform/rules.json": "1d320a4f8e1bf4701496388931f492315549bd3dce574b17285dd1d7f8652007", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" } } }, "conditions": { "client": "codex", "model": "gpt-6.1-sol", "client_version": "0.163.0", "reasoning_effort": "medium", "harness": "none", "billing_channel": "subscription", "solve_timeout_seconds": 18000, "time_series": "exam", "delegation": "native_disabled", "network_profile": "open-book_shell", "deadline_disclosed": true, "statement_sha256": "8a6ccb3e673826d1f8220fda53eb310e3ec18c136d87ce8f4cebb2a08614e7e5", "starter_dt_sha256": "f40d084818b0d1cfe503fc7653a6a13f1a8e47fcd1688dad6245b12744eb4638", "profile_sha256": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "execution_policy_sha256": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "calibration_sha256": "6fde5ca6242bb0895fda9c18ff5c5357a1762042d1c6d704032ee8f355eeb0a9", "started_at": "2026-10-26T11:36:57.347327+00:00", "timing": { "prepare_ms": 12600, "solve_ms": 4562988, "grade_ms": null }, "original_submission_valid": true, "model_provenance": "requested_only", "tokens": { "input": 21616270, "cached_input": 21442048, "fresh_input": 174222, "output": 134247, "reasoning_output": 50708, "total": 21750517, "coverage": "reported_completed_root_turns" }, "tools": { "mcp_calls": 0, "unica_calls": 0, "failed_calls": 0 }, "process": { "status": "completed", "exit_code": 0, "stop_confirmed": true } }, "verification": "repository_owner", "download": "community-downloads/demo-20261026T113637Z-010c79--owner-2026-10-26T214441318235-0000/solution.zip", "source_context": "community-downloads/demo-20261026T113637Z-010c79--owner-2026-10-26T214441318235-0000/source-context.json", "regrade_required": [ { "id": "grader_changed", "files": [ "calibrate.py", "calibration_periodicity.py", "common.py", "ou.py", "replay_calibration.py", "smoke_check.py", "tasks/1c-platform-official-sample/checks.json" ] } ], "grader_revision_sha256": "349d87e0c7f531acbe35dd2b39c35722d8a877fedde97575b49e8466ab763c1d", "archive_sha256": "e184d2ad29b4195649755dc04a25bbc949ded9f62e64de91f932be876dc5fee7", "owner_verification": { "kind": "repository_owner", "repository": "zeegin/1c-agent-exam-benchmark", "operator": { "name": "Ingvar Vilkman", "github": "zeegin" }, "started_at": "2026-10-26T21:44:41.153095+00:00", "server": { "name": "Owner Windows stand", "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "hardware": { "cpu": "AMD Ryzen 7 5800X 8-Core Processor ", "logical_cpus": 4, "ram_bytes": 17109000192 }, "isolation": "dedicated-host" }, "platform_version": "8.3.27.2342", "grader": { "profile": "technical-v8", "commit": "e8fd8ced03a85b549c5472fbbda29225749f54d1", "working_tree_dirty": false, "fingerprint": { "assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "calibrate.py": "3162d431f3cab5e7976aa39f665d6286dce45499cf362d85109b7123fa8403a2", "calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "calibration_query.py": "3555b103cde8ea0519955cf52358d09223f5ab183a9df00533bdb48c89237a8c", "claude.py": "eedabc75fca0faa434f40a1624b71419ec7dc22e2854a0886cf84b4911db8372", "codescan.py": "6d8375210cef1fd768fc2d98d630d880b2993a9724f01ae25f33b4ea5aa9631d", "codex.py": "904e75503cd35f16cbb052f66806b3879fe25bfc9f99e33b93c889d862c46324", "common.py": "52825cf5c29f3536d6e046a89e789d5ef9c83aacd7f2f5a07f4f53e77b5229cc", "docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "examiner.py": "8cdffcdd52f043c905f896697403380af95bf485dd4a5edca24f7956e7795ffe", "forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "harness.py": "3cbb90fd3187e700b5df32e5daafb20313d49bb5721c826e3033cbc6aa6e3825", "interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "penalties.py": "ae388cb8953ecca1f2370a7c4cb1db3b6cc8318fc2a7563a4db15f9f5b057429", "platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "pr.py": "2b6bfea0634703469605ce114f9274716b485852d9a55d9185c39893b14e4726", "preflight.py": "448c3120ab64b625abae3891be686c7a214ce4211f7cf651fd90e12c0b298433", "process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "queries.py": "1ef57e292db3e8967a733948371ecc542f743b811890d4fc509df17303b9c4ac", "queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "querytypes.py": "b645f489a2abc27762b4a9bbf4917e72f7b46dc053a74c0dca4a8fc46491b3ef", "replay_calibration.py": "0a4d9b84a9908944c5a945878eb6f5eeda5a4e42ffff4f55c04a680742803d80", "runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "smoke_check.py": "66caf1a01f7aa18432293abe3567ac228ac837a660b08c3dc7bb093f7bd51628", "stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "submission.py": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tasks/1c-platform-official-sample/checks.json": "17a6fcc0c14410829650623eb1443ce99796e000cdfd19905ac0287988b73a00", "tasks/1c-platform-official-sample/private/official-assessment-mapping.json": "303587c0dabe77c1eeebb2017fe85539e3370b17c9090435e6e0325a66bd0644", "tasks/1c-platform-official-sample/private/owner-scoring-policy.json": "d26d534bb838ab1b5facb7bc033ca8ec40912133baadcdbad83b27fc577905f5", "starters/carcass-8.3.25.1445/starter.json": "0f7a7060885ba99a19402bfc6e63cc8fe979b0f491b040d3a01d5d21b304b3a6", "rules/1c-specialist-platform/rules.json": "ea75e34ace5de11ba3de403c63cd2c026db81d1d991f8531e4a779d4ce9788e7", "rules/1c-specialist-platform/examiner.json": "1247486ddd412d600db88d9c1db4ba501fc1994afd1dc2ebe85402fcc332f4c8", "rules/1c-specialist-platform/chistov.json": "800da27601a3f1c7ec1df64482fd4ad035e559ba0b390a274ed5031128487d3d", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" }, "sha256": "349d87e0c7f531acbe35dd2b39c35722d8a877fedde97575b49e8466ab763c1d" }, "method": "saved_platform_observations", "outcome": "complete", "completed_at": "2026-10-26T21:44:41.318235+00:00" } }, { "id": "demo-20261026T113637Z-010c79--owner-2026-10-26T193109254386-0000", "run_id": "demo-20261026T113637Z-010c79", "result": { "run_id": "demo-20261026T113637Z-010c79", "created_at": "2026-10-26T19:31:09.254386+00:00", "model": "gpt-6.1-sol", "harness": "none", "solve_seconds": 4563, "platform": "8.3.27.2342", "counts": { "pass": 64, "fail": 1 }, "rules": [ { "id": "BU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU01.selected_fixture" }, { "id": "BU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU04.selected_fixture" }, { "id": "BU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU05.selected_fixture" }, { "id": "BU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU16.selected_fixture" }, { "id": "BU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU17.selected_fixture" }, { "id": "BU02", "verdict": "pass", "reason": null, "coverage": "partial", "assertion_id": "BU02.posting_cost_and_balance" }, { "id": "BU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU10.selected_fixture" }, { "id": "BU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU12.selected_fixture" }, { "id": "BU03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU03.selected_fixture" }, { "id": "BU06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU06.selected_fixture" }, { "id": "BU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU07.selected_fixture" }, { "id": "BU08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU08.selected_fixture" }, { "id": "BU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU09.selected_fixture" }, { "id": "BU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU11.selected_fixture" }, { "id": "BU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU14.selected_fixture" }, { "id": "BU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU15.selected_fixture" }, { "id": "BU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "BU13.selected_fixture" }, { "id": "OU15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU15.selected_fixture" }, { "id": "OU16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU16.selected_fixture" }, { "id": "OU17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU17.selected_fixture" }, { "id": "OU02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU02.selected_fixture" }, { "id": "OU18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU18.selected_fixture" }, { "id": "OU14", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU14.selected_fixture" }, { "id": "OU01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU01.selected_fixture" }, { "id": "OU03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU03.selected_fixture" }, { "id": "OU05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU05.selected_fixture" }, { "id": "OU06", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "OU06.selected_fixture" }, { "id": "OU07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU07.selected_fixture" }, { "id": "OU08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU08.selected_fixture" }, { "id": "OU09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU09.selected_fixture" }, { "id": "OU10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU10.selected_fixture" }, { "id": "OU11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU11.selected_fixture" }, { "id": "OU12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU12.selected_fixture" }, { "id": "OU13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU13.selected_fixture" }, { "id": "OU04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU04.selected_fixture" }, { "id": "OU19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU19.selected_fixture" }, { "id": "OU20", "verdict": "fail", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU20.selected_fixture" }, { "id": "OU21", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "OU21.selected_fixture" }, { "id": "PR01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR01.selected_fixture" }, { "id": "PR02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR02.selected_fixture" }, { "id": "PR03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR03.selected_fixture" }, { "id": "PR04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR04.selected_fixture" }, { "id": "PR05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR05.selected_fixture" }, { "id": "PR06", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR06.selected_fixture" }, { "id": "PR07", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR07.selected_fixture" }, { "id": "PR08", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR08.selected_fixture" }, { "id": "PR09", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR09.selected_fixture" }, { "id": "PR10", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR10.selected_fixture" }, { "id": "PR11", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR11.selected_fixture" }, { "id": "PR12", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR12.selected_fixture" }, { "id": "PR13", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR13.selected_fixture" }, { "id": "PR14", "verdict": "pass", "reason": null, "coverage": "no_violation_found", "assertion_id": "PR14.selected_fixture" }, { "id": "PR15", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR15.selected_fixture" }, { "id": "PR16", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR16.selected_fixture" }, { "id": "PR17", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR17.selected_fixture" }, { "id": "PR18", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR18.selected_fixture" }, { "id": "PR19", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "PR19.selected_fixture" }, { "id": "F01", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F01.selected_fixture" }, { "id": "F02", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F02.selected_fixture" }, { "id": "F03", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F03.selected_fixture" }, { "id": "F04", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F04.selected_fixture" }, { "id": "F05", "verdict": "pass", "reason": null, "coverage": "selected_fixture", "assertion_id": "F05.selected_fixture" }, { "id": "G01", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G01.static_sources" }, { "id": "G02", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G02.static_sources" }, { "id": "G03", "verdict": "pass", "reason": null, "coverage": "static_sources", "assertion_id": "G03.static_sources" } ], "charges": [ { "id": "F1C-GEN03", "points": "0.5", "reason": "отчёт не соответствует заданию: OU20" }, { "id": "F1C-PR14", "points": "0.5", "reason": "после расчёта набор с периодом действия перезаписывается целиком, с пересчётом фактического периода действия (нужно Записать(, Истина)): CommonModules/РасчетЗарплаты/Ext/Module.bsl:110 Набор.Записать(Истина, Ложь, Истина, Ложь)" }, { "id": "F1C-BU06", "points": "1.5", "reason": "у счёта товаров 01.02 не включён признак учёта КоличественныйУчет" }, { "id": "F1C-GEN20", "points": "2.0", "reason": "данные базы читаются в цикле по записям: CommonModules/УчетСервер/Ext/Module.bsl:368; CommonModules/УчетСервер/Ext/Module.bsl:368" } ], "score_upper_bound": "0.5", "score": null, "grade": "unsatisfactory", "deductions": "4.5", "not_assessed": 15, "gates": { "starter_origin": "passed", "load": "loaded", "clients": "compiles", "demo_data": "present" }, "infrastructure_errors": false, "comparison_eligible": false, "binding_compatibility": null }, "measurement": { "operator": { "name": "Виктор Мурашкин", "github": "VictorMurashkin" }, "environment": { "captured_at": "2026-10-26T11:36:38.784331+00:00", "capture_timing": "before_run", "hardware": { "cpu": "12th Gen Intel(R) Core(TM) i5-12600KF", "logical_cpus": 16, "ram_bytes": 68500021248 }, "os": { "system": "Windows", "release": "11", "version": "10.0.26100", "architecture": "AMD64" }, "python": "3.14.6", "platform_version": "8.3.27.2342", "isolation": "dedicated-host", "network_profile": "open-book_shell", "unsafe_action_protection_observed_in_user_config": true, "git_revision": "4431a896acdc1e09f964b8afb3468fc045118372", "implementation_files": { "exam_bench/__init__.py": "ad5bf6f05dc6765f40b78bd186870ca2c49be113cfa33f8aa76f4926f2cb2c1e", "exam_bench/assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "exam_bench/bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "exam_bench/calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "exam_bench/calibrate.py": "78b5185cb0888c0c0ac3de95ffc3a80154a6de9ae66fc461f79d012e5a58e1db", "exam_bench/calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "exam_bench/calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "exam_bench/calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "exam_bench/calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "exam_bench/calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "exam_bench/claude.py": "687602f4654ece014891d13e1503e2e90788a67e4cc0bde7eb6287bd7cf48b17", "exam_bench/cli.py": "a1a83be1f53924705576ed06b2a2c20868067fd0c5d3da839192e7b13c37540b", "exam_bench/codescan.py": "751e38001b6e65727a31e28172a0623f0bf34bc092a958037c286aa991a197ed", "exam_bench/codex.py": "904e75503cd35f16cbb052f66806b3879fe25bfc9f99e33b93c889d862c46324", "exam_bench/common.py": "8682603b519063e655eae3574a02a49efee63bde21f582ccee20ddd623fca96d", "exam_bench/cursor.py": "4ba6ac1ee1120e40c7e6429fd95959fd0d1ca7364471944b056870be93c86dc8", "exam_bench/cursor_bsl.py": "753f02ebed60e5b8bbefba0933adbdf28477ef916353d70e3c68c817ce6c42e0", "exam_bench/cursor_execution.py": "f495154ccf22013224716ce0f178956e5ef55a4191b1aa5f13a90a95cea3d35b", "exam_bench/cursor_harnesses.py": "9b1fe8386c4440eab5cfe080ee362d185f87fc4d9907037be7892e9dcb31166b", "exam_bench/cursor_load.py": "195e9f3334927f1052ea415ae6c7b7c02f5b9df061b8965bfdfb2866cb2208f8", "exam_bench/docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "exam_bench/examiner.py": "d7294fdd23ed1732216cafebf0a8cf2c24cce4259859aeb7149f62b7607d087d", "exam_bench/finalize.py": "4034f1c63896a940afdb1a83d541cf47fc75c8b5061e3f839047109c04beb620", "exam_bench/forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "exam_bench/gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "exam_bench/grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "exam_bench/harness.py": "3040f6daaf1dc6e6583219f4d925151f8ba7851b2d5417d7f14645892b485ddf", "exam_bench/interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "exam_bench/interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "exam_bench/isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "exam_bench/ledger.py": "7e851523580e22d8490e75f9b6026c07f2c355007e0d11d0b252671f56bef654", "exam_bench/locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "exam_bench/materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "exam_bench/mcp_toolkit.py": "f4c3ea8d9ce542645960a0234ddb61712a047793c58d4e2a0691fc9a45961383", "exam_bench/observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "exam_bench/ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "exam_bench/penalties.py": "0d79e2e46102657dca00609b6abbfc0bf7d11fad41429564f876c82bc6b33269", "exam_bench/platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "exam_bench/portable.py": "cad56968ff407983608f5bdbc9ce7234128d7a4580b096ecea8e0e7b4edb9070", "exam_bench/portable_harnesses.py": "686c46a4231067625b3a20f0b22639d14bcaeb26fab3493e06f92b53dfead05a", "exam_bench/pr.py": "6a3a20caf0e10c0cc94410511a72d62c9fcda785f3abab1be2ad616d4ee16836", "exam_bench/preflight.py": "fbce47aa201c1f5acdbc80b241655dce443df35f9d14d3260c2325f875d6f6e4", "exam_bench/process.py": "263c065a9be9d0586d5467a478e9d34c44035697b7d69781ef38a997bf90596f", "exam_bench/queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "exam_bench/queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "exam_bench/replay_calibration.py": "e2d79cb508f2d5e3846d6dad36c3898d41dec1c573c1a1b7d8a2ec43e33c8c08", "exam_bench/report.py": "5e4c0757e1c7f189953f9a5302593ab726551835856baed25efd93dad6e8bfcd", "exam_bench/runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "exam_bench/smoke_check.py": "f36922a0027429ead0b414048dcc14bbe67f2f0e79a70d03dffbe1447d253545", "exam_bench/stdio_harnesses.py": "0bbfd791fb244a934c6cda3a4e63fbe9ce515e4af64729bb923ce86645057288", "exam_bench/submission.py": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "exam_bench/telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "exam_bench/windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "exam_bench/workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tools/build_public_site.py": "788ec78558bf5391a2143d8602fc3659d4d45a914b8a5f476f42aef33e51771e", "tools/build_result_site.py": "2cdf8ca026e40fb41a4697bb4a267e5d28535cdd11ff7db8ee0e4dc864f95c33", "tools/check_native_harnesses.py": "1fdde7b8eeb76f94341592ddbf1cac61306a65779d7b871ecabd053ab70c1e80", "tools/check_native_toolkit.py": "0272794617121f2932828e5e4e9ae20095183c443666cf3ba466b44fbe875095", "tools/community_results.py": "897bc6b845e707458164c395075e659be9dbbb98898677359870578dee78a938", "tools/community_service.py": "493186a0718c81c8afa356c1c160d42b2c1d77dfedf1b70c8eb8c6aad84a73dc", "tools/community_setup.py": "5d7d126ed7d4dd48e1d79f57b99647a92ffcc8c9f80d90915e458888cdd76bf7", "tools/compare_harness_runs.py": "f274df5f3f804cb02504491aec946943833e12fbce6e62d281e12beb8508fc4e", "tools/create_run_plan.py": "694f1b376f5b78de23705b8df3ec943def516eda93f96e7afaa3942729a1240c", "tools/demo_runner.py": "dda8e6dc8931eead20766a8aff06eec40c1100587dfb265f4dccc20f3c04d4c0", "tools/installers.py": "9a2742780936b17500869e7c89202c1a2549e37d53a42ad9a50a0abbf78bbe09", "tools/load_diagnostics.py": "6673122a8c32bf3a33cb292f514d4d79f2b62d4d72a859d7356b24312440f2dd", "tools/machine_bundle.py": "8aa8346f99f537e81ceca6fb6ab9530e844954bab8eff87bf33d3602f81f8a30", "tools/prepare_native_harnesses.py": "fba3fd78b1fdd400196e086c5f463aec5ecefe41e81cd6875d87c76a3126a877", "tools/prepare_official_statement.py": "6b7028c78e90e798d6ef1a93b76520cc61a308c354fb9b87f7fad18b99800fad", "tools/prepare_open_exam_requirements.py": "544f4e378b9be5f166186f8788f8d454afdac2deb99d91d98421e39d01ba6d03", "tools/probe_cursor_harnesses.py": "19952ea409c934ed89cf2589dbb7dcf8d52fad5e01ca256c7df552578d28addc", "tools/probe_harness.py": "1ed8ef93420d1484cbbfd151b7efc31b9a201ceb942dd05e3103efa22ffa7f27", "tools/probe_http_mcp.py": "2667e191fb831b1cbc9cbbbbefdfad16241e17d620a1a42a43405ab0b8139ac4", "tools/probe_native_mcp.py": "9918d324129cba898993e07f8f8b6dbcbaf369398ebf28d464f9f1f00abdb254", "tools/readiness.py": "3c5404be17a7a0a2f72d7cef5714f7d1d6bde7da0d8eb698da4cc65d0b0dd3f3", "tools/recheck_community.py": "f0843d7d677f90da31e22bde0b1c86584dd46c022f1532d43d042619e426b230", "tools/regrade_runs.py": "011775afb06d3aac67a4aa81117a368c75896b0fcbe1e6f27ccc6237612fbf59", "tools/render_statement_text.py": "dabc0716a3612c288c671bc20e17fd4986691d732768e1e957d6dddddbea92a3", "tools/replay_calibration.py": "801f5004926c438c21ed3668fe2a4ddf45312b3e75320165a3839aae034eee9b", "tools/run_exam_campaign.py": "2c450d57a1cd0a2682838f5ec7c0a4ffb3aed0f1730d34c408e912d59cab6efd", "tools/serve_result_site.py": "07ffdd3bc63227523c1a589a996b5027f357a139d53d3835dfb77f9817a7e09d", "tools/start_demo.py": "c597e6cad28d245b3191654bb3e2801fa9dd2364e2acb25561923613717b615f", "tools/supplemental_acceptance.py": "7327277143d80a531e4c254ac74a9fc0e0d5c76572d53b8469e0a580eda17d65", "tools/sync_sources.py": "b51e889b0f41f9f63bfb19a09fb96d3777693d6b1d76fe0132bdd2a15e155898", "tools/validate_community_pr.py": "796b896dfade07b4529af2088a4b9b9d23484148b3bc0732b3fb837b75c9844b", "tools/verify_official_assessment_mapping.py": "daeb448a016940d5b6b1285979a56e5b9014bd91db40acb131445e4a83a23059", "tools/verify_task_package.py": "9e1e6105f6b5e4e78b36aa57f00117a9fbc8948ab53983c32ab56da88d23ccc4", "profiles/1c-ai-rules-2026-10-23-requirements.txt": "fd7ada214e0977776eb350794bb492d97824d96810eb7b158e46cf5cd72c8e65", "profiles/agents.json": "af9c492c08d13b3044aa6b6952589ed6a0a07d5258d8ff72bb18185b3eaebdc5", "profiles/ai-exam-execution-policy.json": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "profiles/bsl-analyzer-0.3.2-macos.json": "83537abdbf38c41ce665e4d0f24128bb51b62e971e0e0f368695f1326a7d2ffb", "profiles/bsl-analyzer-0.3.2-portable.json": "d6ba732e6778e256df34d6bc548593128820a70430c35b279796843606ee40a8", "profiles/bsl-ls-1.1.0-rc.6-macos.json": "245fc10747197e6911b2b4c77cdb15e6fa4eb7bc7c3758b63e768c5adf1df180", "profiles/bsl-ls-1.1.0-rc.6-portable.json": "9f10660881f2ec84794f7d584556b8f75c7e14b3555464af0ed0e60c4c892d86", "profiles/claude-code-skills-1c-1.12.0-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/code-index-1.9.0-macos.json": "63a919523ce62ecec274f4c139bc7ad49a75dd4c339568b822cbc695b4e30408", "profiles/code-index-1.9.0-portable.json": "81106cee8f424ffd8a9dc46ecd8e4f57598fc1d49661a83c77b1f0507993fbdc", "profiles/codex-probe-plan.json": "166e41aad5fb3b27d9050bc6de952c6cba363cc6e804d4080568cc71a2a4d289", "profiles/cursor-1c-skills-1.12.0-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/machine.linux.example.json": "408304fd0581098d5d8110dc67dfeab353bc4d4030e32d37e6acf98d2b1aedfd", "profiles/machine.macos.example.json": "52e9f9d17797cb520b9d8955d6806fd550b899bed4da241ebf096dcb6a21a942", "profiles/machine.windows.example.json": "63accac9a2f81d47d03447efbabffd4760aee325193f02f46b9b29a28d50d2d8", "profiles/mcp-toolkit-1.9.0-macos.json": "1d3f9cde5ffa20589a840d01fdae03aa0fc2f412c929f064f203919c4129625b", "profiles/mcp-toolkit-1.9.0-portable.json": "8e370eebe773eef0e08045ee9c6d5be1451f769f65be0710834b262a4336e054", "profiles/none-macos.json": "b1401d9c48159aed3559006c7f6ace6ef4571224d5cf0bb76d1a823505a10056", "profiles/none-portable.json": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "profiles/rlm-tools-bsl-1.43.0-macos.json": "9354421052640ab60bc3e6aa98ff2e7ba9ca2318b0f4026c137487449242cbd2", "profiles/rlm-tools-bsl-1.43.0-portable.json": "2599e5645e0a7d4e44cb2934bc2b272cae79a9bf7ea74a23cd48aacea64bc424", "profiles/rlm-tools-bsl-1.43.0-posix-requirements.txt": "4fdf9a1bd994bf0272e65d231daf76cf19b0a34dad0ae6b50ec4f11a2ce4c330", "profiles/rlm-tools-bsl-1.43.0-windows-requirements.txt": "3730cb46c81cda5181ecd4485e98b11933104632358bc86f8c0eb1a612a8954f", "profiles/shirokov-skills-macos.json": "84f3e89091676884a802035c707e912762a1179425fb8e3faff25be736873cdb", "profiles/shirokov-skills-portable.json": "2b0a461e06602f1456410e70f02ceaa5ac32c6549c486660bcb5ace0c2f87b15", "profiles/shirokov-skills-windows-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/unica-0.12.3-macos.json": "2c39fbb591cf2c2c6e056373823615485397ea83651b7926c6f25a5fe6a0aae6", "profiles/unica-0.13.0-macos.json": "b76b5c8a4dd33f571c4a90993f1a2da5f7223b4f0f8e1042c282e21a66121052", "profiles/unica-0.14.0-rc.1-portable.json": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "rules/1c-specialist-platform/chistov.json": "7a42ef723a1f5f03f02c387cd3ca95725f7364c2e11ebdfc988a02919ab22c37", "rules/1c-specialist-platform/decisions.json": "f622107423ce3c188c063318d7ab4f7718ceb38e443130677d8987f386641c09", "rules/1c-specialist-platform/examiner.json": "30353aa2a1b6545496b070d9066e9ffba0c3779e5b53ef70a4fd2cee375b18c0", "rules/1c-specialist-platform/ledger.json": "f167c10db2b5799dd9a1ea6a37cd2d7d186810dadf5ea2f50f26ae723c676882", "rules/1c-specialist-platform/rules.json": "1d320a4f8e1bf4701496388931f492315549bd3dce574b17285dd1d7f8652007", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" } } }, "conditions": { "client": "codex", "model": "gpt-6.1-sol", "client_version": "0.163.0", "reasoning_effort": "medium", "harness": "none", "billing_channel": "subscription", "solve_timeout_seconds": 18000, "time_series": "exam", "delegation": "native_disabled", "network_profile": "open-book_shell", "deadline_disclosed": true, "statement_sha256": "8a6ccb3e673826d1f8220fda53eb310e3ec18c136d87ce8f4cebb2a08614e7e5", "starter_dt_sha256": "f40d084818b0d1cfe503fc7653a6a13f1a8e47fcd1688dad6245b12744eb4638", "profile_sha256": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "execution_policy_sha256": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "calibration_sha256": "6fde5ca6242bb0895fda9c18ff5c5357a1762042d1c6d704032ee8f355eeb0a9", "started_at": "2026-10-26T11:36:57.347327+00:00", "timing": { "prepare_ms": 12600, "solve_ms": 4562988, "grade_ms": null }, "original_submission_valid": true, "model_provenance": "requested_only", "tokens": { "input": 21616270, "cached_input": 21442048, "fresh_input": 174222, "output": 134247, "reasoning_output": 50708, "total": 21750517, "coverage": "reported_completed_root_turns" }, "tools": { "mcp_calls": 0, "unica_calls": 0, "failed_calls": 0 }, "process": { "status": "completed", "exit_code": 0, "stop_confirmed": true } }, "verification": "repository_owner", "download": "community-downloads/demo-20261026T113637Z-010c79--owner-2026-10-26T193109254386-0000/solution.zip", "source_context": "community-downloads/demo-20261026T113637Z-010c79--owner-2026-10-26T193109254386-0000/source-context.json", "regrade_required": [ { "id": "grader_changed", "files": [ "calibrate.py", "calibration_periodicity.py", "calibration_query.py", "common.py", "ou.py", "penalties.py", "queries.py", "replay_calibration.py", "rules/1c-specialist-platform/rules.json", "smoke_check.py", "tasks/1c-platform-official-sample/checks.json" ] } ], "grader_revision_sha256": "4a12b62d2c10085e1fc710f377f84903abdf2fb787dda19628d944da990a86b2", "archive_sha256": "cd45a272c51a7eb4098d3a56959caccd579b73a02fbb71df0dc4ba4258618888", "owner_verification": { "kind": "repository_owner", "repository": "zeegin/1c-agent-exam-benchmark", "operator": { "name": "Ingvar Vilkman", "github": "zeegin" }, "started_at": "2026-10-26T19:28:20.862646+00:00", "server": { "name": "Owner Windows stand", "os": { "system": "Windows", "release": "11", "version": "10.0.26300", "architecture": "AMD64" }, "hardware": { "cpu": "AMD Ryzen 7 5800X 8-Core Processor ", "logical_cpus": 4, "ram_bytes": 17109000192 }, "isolation": "dedicated-host" }, "platform_version": "8.3.27.2342", "grader": { "profile": "technical-v8", "commit": "5b6a28372b253e81e22b83f8559df897297e28ff", "working_tree_dirty": true, "fingerprint": { "assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "calibrate.py": "1c844971b4977fdcc3b30aebe8aad40fbd45e6828955b8deb043ac8573d61731", "calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "claude.py": "eedabc75fca0faa434f40a1624b71419ec7dc22e2854a0886cf84b4911db8372", "codescan.py": "6d8375210cef1fd768fc2d98d630d880b2993a9724f01ae25f33b4ea5aa9631d", "codex.py": "904e75503cd35f16cbb052f66806b3879fe25bfc9f99e33b93c889d862c46324", "common.py": "7696116dd1a796666518b4c5d2aa3cafa04ee974593d3636333cbe5385bd6ccb", "docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "examiner.py": "8cdffcdd52f043c905f896697403380af95bf485dd4a5edca24f7956e7795ffe", "forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "harness.py": "3cbb90fd3187e700b5df32e5daafb20313d49bb5721c826e3033cbc6aa6e3825", "interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "mcp_toolkit.py": "400e25973f39059e24071e88630095e2a52c6472dc29040a57cfc4518b8862b7", "observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "penalties.py": "b82704e7f47d3dfdf6e501452d7e0abca1f9da63307093d2e257e32358be0489", "platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "portable_harnesses.py": "b7855982f5191e23ff98ca07eec12262123ce06efe23e12afa52ad88595ece83", "pr.py": "2b6bfea0634703469605ce114f9274716b485852d9a55d9185c39893b14e4726", "preflight.py": "448c3120ab64b625abae3891be686c7a214ce4211f7cf651fd90e12c0b298433", "process.py": "9bd42380092692109d822ba6ff13bd1801c2b6f301743ef77415cfba2158cedd", "queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "querytypes.py": "b645f489a2abc27762b4a9bbf4917e72f7b46dc053a74c0dca4a8fc46491b3ef", "replay_calibration.py": "3b6f3a289cc8a7f5e458f62bfa2c6cc534cc9076ba3f22d1e4bd8a5f9e175317", "runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "smoke_check.py": "bd6266367e6b769a95258eb383239b89a22deae406d64f6e142c77396f4639ba", "stdio_harnesses.py": "a977ac241c8eaab388c08a85aaa674dbb8506c07f3e10325b243429cc07177a7", "submission.py": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tasks/1c-platform-official-sample/checks.json": "17a6fcc0c14410829650623eb1443ce99796e000cdfd19905ac0287988b73a00", "tasks/1c-platform-official-sample/private/official-assessment-mapping.json": "303587c0dabe77c1eeebb2017fe85539e3370b17c9090435e6e0325a66bd0644", "tasks/1c-platform-official-sample/private/owner-scoring-policy.json": "d26d534bb838ab1b5facb7bc033ca8ec40912133baadcdbad83b27fc577905f5", "starters/carcass-8.3.25.1445/starter.json": "0f7a7060885ba99a19402bfc6e63cc8fe979b0f491b040d3a01d5d21b304b3a6", "rules/1c-specialist-platform/rules.json": "7ec895a7751ef17f4a50cc80b5f7fa986e1e04360ab0b4ce9aa29115195df03c", "rules/1c-specialist-platform/examiner.json": "1247486ddd412d600db88d9c1db4ba501fc1994afd1dc2ebe85402fcc332f4c8", "rules/1c-specialist-platform/chistov.json": "800da27601a3f1c7ec1df64482fd4ad035e559ba0b390a274ed5031128487d3d", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" }, "sha256": "4a12b62d2c10085e1fc710f377f84903abdf2fb787dda19628d944da990a86b2" }, "identity_verified_at": "2026-10-26T18:44:22.364471+00:00", "identity_session_sha256": "950670ab9a82059c65525d0d6e5b8a00f0dc292581edea3eb087c4ecadeaab09", "completed_at": "2026-10-26T19:31:09.254386+00:00" } }, { "id": "demo-20261026T113637Z-010c79", "run_id": "demo-20261026T113637Z-010c79", "result": { "run_id": "demo-20261026T113637Z-010c79", "created_at": "2026-10-26T12:56:39.941570+00:00", "model": "gpt-6.1-sol", "harness": "none", "solve_seconds": 4563, "platform": "8.3.27.2342", "counts": { "pass": 64, "fail": 1 }, "rules": [ { "id": "BU01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU16", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU17", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU02", "verdict": "pass", "coverage": "partial", "reason": null }, { "id": "BU10", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU12", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU06", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU07", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU08", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU09", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU11", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU14", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU15", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "BU13", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU15", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU16", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU17", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU02", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU18", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU14", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU06", "verdict": "pass", "coverage": "no_violation_found", "reason": null }, { "id": "OU07", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU08", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU09", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU10", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU11", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU12", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU13", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU19", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "OU20", "verdict": "fail", "coverage": "selected_fixture", "reason": "Ведомость не прошла проверку группировки по значениям характеристик." }, { "id": "OU21", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR02", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR06", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR07", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR08", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR09", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR10", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR11", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR12", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR13", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR14", "verdict": "pass", "coverage": "no_violation_found", "reason": null }, { "id": "PR15", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR16", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR17", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR18", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "PR19", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F01", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F02", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F03", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F04", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "F05", "verdict": "pass", "coverage": "selected_fixture", "reason": null }, { "id": "G01", "verdict": "pass", "coverage": "static_sources", "reason": null }, { "id": "G02", "verdict": "pass", "coverage": "static_sources", "reason": null }, { "id": "G03", "verdict": "pass", "coverage": "static_sources", "reason": null } ], "charges": [ { "id": "F1C-GEN03", "points": "0.5", "reason": "Ведомость не прошла проверку группировки по значениям характеристик." }, { "id": "F1C-PR14", "points": "0.5", "reason": "после расчёта набор с периодом действия перезаписывается целиком, с пересчётом фактического периода действия (нужно Записать(, Истина)): CommonModules/РасчетЗарплаты/Ext/Module.bsl:110 Набор.Записать(Истина, Ложь, Истина, Ложь)" }, { "id": "F1C-BU06", "points": "1.5", "reason": "у счёта товаров 01.02 не включён признак учёта КоличественныйУчет" }, { "id": "F1C-GEN20", "points": "2.0", "reason": "данные базы читаются в цикле по записям: CommonModules/РасчетЗарплаты/Ext/Module.bsl:152; CommonModules/РасчетЗарплаты/Ext/Module.bsl:152; CommonModules/РасчетЗарплаты/Ext/Module.bsl:160 и ещё 9" }, { "id": "F1C-GEN21", "points": "2.0", "reason": "параметры виртуальной таблицы не заданы или заменены условием ГДЕ: CommonModules/Испытания/Ext/Module.bsl:28 РегистрНакопления.ОстаткиНоменклатуры.Остатки(,; CommonModules/Испытания/Ext/Module.bsl:100 РегистрБухгалтерии.Хозрасчетный.Остатки(," } ], "score_upper_bound": "-1.5", "score": null, "grade": "unsatisfactory", "deductions": "6.5", "not_assessed": 15, "gates": { "starter_origin": "passed", "load": "loaded", "clients": "compiles", "demo_data": "present" }, "infrastructure_errors": false, "comparison_eligible": false, "binding_compatibility": null, "evaluation_sha256": "864b59ceec1c2c8e29fb1a6288ea9df7ebbfa41fa5f682b10013dfd76ab2127a", "downloads": [] }, "measurement": { "operator": { "name": "Виктор Мурашкин", "github": "VictorMurashkin" }, "environment": { "captured_at": "2026-10-26T11:36:38.784331+00:00", "capture_timing": "before_run", "hardware": { "cpu": "12th Gen Intel(R) Core(TM) i5-12600KF", "logical_cpus": 16, "ram_bytes": 68500021248 }, "os": { "system": "Windows", "release": "11", "version": "10.0.26100", "architecture": "AMD64" }, "python": "3.14.6", "platform_version": "8.3.27.2342", "isolation": "dedicated-host", "network_profile": "open-book_shell", "unsafe_action_protection_observed_in_user_config": true, "git_revision": "4431a896acdc1e09f964b8afb3468fc045118372", "implementation_files": { "exam_bench/__init__.py": "ad5bf6f05dc6765f40b78bd186870ca2c49be113cfa33f8aa76f4926f2cb2c1e", "exam_bench/assessment.py": "d78e2b1ae097234ec7ab6a3ca89c39e1a861492eb761bc03cfdf9177125a35ea", "exam_bench/bp.py": "400a2b3761ea0e4e73d3779861def780c84f942a2986023455d1d25b740967ec", "exam_bench/calcwrite.py": "5cfe385d8579c86ccf9ff101bb81d27caadde108e405c75bd7b6fe87ffe03509", "exam_bench/calibrate.py": "78b5185cb0888c0c0ac3de95ffc3a80154a6de9ae66fc461f79d012e5a58e1db", "exam_bench/calibration.py": "478823112d10e26ebae086166031cad575b736e80540165b771e95e9e913245c", "exam_bench/calibration_forms.py": "d9580fa73a9ebf609187450c7ba2f765cf98eedf7455234c2dd64802397fc014", "exam_bench/calibration_interface.py": "9585b07b6638835fbc184a2b3faad2184e1f88e3dbd915766aaf7d8e0b5f3c1c", "exam_bench/calibration_ou.py": "a17bbacecb7f3990126387cefa65ca5b31aa99560c934e6a32dd8d9ffd6ca47d", "exam_bench/calibration_pr.py": "403ee5cb14adb1020b723eae4396a7f48b83dbf8350f85c122e12a8c8df6d5f4", "exam_bench/claude.py": "687602f4654ece014891d13e1503e2e90788a67e4cc0bde7eb6287bd7cf48b17", "exam_bench/cli.py": "a1a83be1f53924705576ed06b2a2c20868067fd0c5d3da839192e7b13c37540b", "exam_bench/codescan.py": "751e38001b6e65727a31e28172a0623f0bf34bc092a958037c286aa991a197ed", "exam_bench/codex.py": "904e75503cd35f16cbb052f66806b3879fe25bfc9f99e33b93c889d862c46324", "exam_bench/common.py": "8682603b519063e655eae3574a02a49efee63bde21f582ccee20ddd623fca96d", "exam_bench/cursor.py": "4ba6ac1ee1120e40c7e6429fd95959fd0d1ca7364471944b056870be93c86dc8", "exam_bench/cursor_bsl.py": "753f02ebed60e5b8bbefba0933adbdf28477ef916353d70e3c68c817ce6c42e0", "exam_bench/cursor_execution.py": "f495154ccf22013224716ce0f178956e5ef55a4191b1aa5f13a90a95cea3d35b", "exam_bench/cursor_harnesses.py": "9b1fe8386c4440eab5cfe080ee362d185f87fc4d9907037be7892e9dcb31166b", "exam_bench/cursor_load.py": "195e9f3334927f1052ea415ae6c7b7c02f5b9df061b8965bfdfb2866cb2208f8", "exam_bench/docx_text.py": "556f636b574f898a8c1a404d33515ed272655af325510a2a2ea196932ba43840", "exam_bench/examiner.py": "d7294fdd23ed1732216cafebf0a8cf2c24cce4259859aeb7149f62b7607d087d", "exam_bench/finalize.py": "4034f1c63896a940afdb1a83d541cf47fc75c8b5061e3f839047109c04beb620", "exam_bench/forms.py": "65045a46965ad51a227258eca8fe8d04b120dcd96a7aaa6e92ff55a365a043cf", "exam_bench/gates.py": "0512fc16c20ab6632ab763044007cd805fb17147ace38109004994d6ad62b0b3", "exam_bench/grader.py": "de63485213673a55cea4020c22c42b232f44d3d3dd491d0ce986652d02637355", "exam_bench/harness.py": "3040f6daaf1dc6e6583219f4d925151f8ba7851b2d5417d7f14645892b485ddf", "exam_bench/interface.py": "b12121013e915c912550a3582a09e47e2e930f4b3995f1047eb63888561396dc", "exam_bench/interpretations.py": "d1c8e1d43f9cd89eb17afdd63f4a961b85dca39622e4f8150bf85d2274e45836", "exam_bench/isolation.py": "cfc12a0595622a930662457aa88c778d11f12b112e5340293a8452b8791fbcd7", "exam_bench/ledger.py": "7e851523580e22d8490e75f9b6026c07f2c355007e0d11d0b252671f56bef654", "exam_bench/locking.py": "98aa0cfb3f65adaed674f9c70f3f18be57d8d0481240de46b54ef06a390d09b9", "exam_bench/materials.py": "ee1691579ce68e2ddf9e952cf7f412ffafda2dfefacf51b7b295ae681c5d476b", "exam_bench/mcp_toolkit.py": "f4c3ea8d9ce542645960a0234ddb61712a047793c58d4e2a0691fc9a45961383", "exam_bench/observer.py": "f0c92a814a495ef876259b310b78c408a92b8f0935de3a6b14f3b959fe442d2d", "exam_bench/ou.py": "c55aa22c7b31af5289be067290406fb1f93a3fab0dffbcd248f62e27c892db84", "exam_bench/penalties.py": "0d79e2e46102657dca00609b6abbfc0bf7d11fad41429564f876c82bc6b33269", "exam_bench/platform.py": "c8eafb66348ff505565956d97c1dfbb54ba6a91bd99f1f3ca40a2fb57ba5c2d7", "exam_bench/portable.py": "cad56968ff407983608f5bdbc9ce7234128d7a4580b096ecea8e0e7b4edb9070", "exam_bench/portable_harnesses.py": "686c46a4231067625b3a20f0b22639d14bcaeb26fab3493e06f92b53dfead05a", "exam_bench/pr.py": "6a3a20caf0e10c0cc94410511a72d62c9fcda785f3abab1be2ad616d4ee16836", "exam_bench/preflight.py": "fbce47aa201c1f5acdbc80b241655dce443df35f9d14d3260c2325f875d6f6e4", "exam_bench/process.py": "263c065a9be9d0586d5467a478e9d34c44035697b7d69781ef38a997bf90596f", "exam_bench/queries.py": "5665073c03640f2aecaf8b82434834498d9576d4427988797ad5238aa1281fdf", "exam_bench/queryschema.py": "5f6fce7f25da3cfa27486f6c35d903c06337439bcb2789cee9a8ca525319a2db", "exam_bench/replay_calibration.py": "e2d79cb508f2d5e3846d6dad36c3898d41dec1c573c1a1b7d8a2ec43e33c8c08", "exam_bench/report.py": "5e4c0757e1c7f189953f9a5302593ab726551835856baed25efd93dad6e8bfcd", "exam_bench/runtime.py": "bf63004e76749719d6c9b790d1ca6dc7536be1b5e42ef564a0b9f7c18c4c6edf", "exam_bench/smoke_check.py": "f36922a0027429ead0b414048dcc14bbe67f2f0e79a70d03dffbe1447d253545", "exam_bench/stdio_harnesses.py": "0bbfd791fb244a934c6cda3a4e63fbe9ce515e4af64729bb923ce86645057288", "exam_bench/submission.py": "caffc29276c5d562e33ddb73f7d3575b6bf8605e699fe198617dc75fcb8253a1", "exam_bench/telemetry.py": "e79aa598ddf51260ce99bf2e45f00f2c5120aa8455690d15dd33e4a2076933ea", "exam_bench/windows_job.py": "c5ee52e2413c4faee8d6c92064c2138a755124a3299c283d19c8e94fe9ead790", "exam_bench/workspaces.py": "96f988b42492d7d7b62b9e809c788e6c39debc285a6d0b8cbc01aa51616e85af", "tools/build_public_site.py": "788ec78558bf5391a2143d8602fc3659d4d45a914b8a5f476f42aef33e51771e", "tools/build_result_site.py": "2cdf8ca026e40fb41a4697bb4a267e5d28535cdd11ff7db8ee0e4dc864f95c33", "tools/check_native_harnesses.py": "1fdde7b8eeb76f94341592ddbf1cac61306a65779d7b871ecabd053ab70c1e80", "tools/check_native_toolkit.py": "0272794617121f2932828e5e4e9ae20095183c443666cf3ba466b44fbe875095", "tools/community_results.py": "897bc6b845e707458164c395075e659be9dbbb98898677359870578dee78a938", "tools/community_service.py": "493186a0718c81c8afa356c1c160d42b2c1d77dfedf1b70c8eb8c6aad84a73dc", "tools/community_setup.py": "5d7d126ed7d4dd48e1d79f57b99647a92ffcc8c9f80d90915e458888cdd76bf7", "tools/compare_harness_runs.py": "f274df5f3f804cb02504491aec946943833e12fbce6e62d281e12beb8508fc4e", "tools/create_run_plan.py": "694f1b376f5b78de23705b8df3ec943def516eda93f96e7afaa3942729a1240c", "tools/demo_runner.py": "dda8e6dc8931eead20766a8aff06eec40c1100587dfb265f4dccc20f3c04d4c0", "tools/installers.py": "9a2742780936b17500869e7c89202c1a2549e37d53a42ad9a50a0abbf78bbe09", "tools/load_diagnostics.py": "6673122a8c32bf3a33cb292f514d4d79f2b62d4d72a859d7356b24312440f2dd", "tools/machine_bundle.py": "8aa8346f99f537e81ceca6fb6ab9530e844954bab8eff87bf33d3602f81f8a30", "tools/prepare_native_harnesses.py": "fba3fd78b1fdd400196e086c5f463aec5ecefe41e81cd6875d87c76a3126a877", "tools/prepare_official_statement.py": "6b7028c78e90e798d6ef1a93b76520cc61a308c354fb9b87f7fad18b99800fad", "tools/prepare_open_exam_requirements.py": "544f4e378b9be5f166186f8788f8d454afdac2deb99d91d98421e39d01ba6d03", "tools/probe_cursor_harnesses.py": "19952ea409c934ed89cf2589dbb7dcf8d52fad5e01ca256c7df552578d28addc", "tools/probe_harness.py": "1ed8ef93420d1484cbbfd151b7efc31b9a201ceb942dd05e3103efa22ffa7f27", "tools/probe_http_mcp.py": "2667e191fb831b1cbc9cbbbbefdfad16241e17d620a1a42a43405ab0b8139ac4", "tools/probe_native_mcp.py": "9918d324129cba898993e07f8f8b6dbcbaf369398ebf28d464f9f1f00abdb254", "tools/readiness.py": "3c5404be17a7a0a2f72d7cef5714f7d1d6bde7da0d8eb698da4cc65d0b0dd3f3", "tools/recheck_community.py": "f0843d7d677f90da31e22bde0b1c86584dd46c022f1532d43d042619e426b230", "tools/regrade_runs.py": "011775afb06d3aac67a4aa81117a368c75896b0fcbe1e6f27ccc6237612fbf59", "tools/render_statement_text.py": "dabc0716a3612c288c671bc20e17fd4986691d732768e1e957d6dddddbea92a3", "tools/replay_calibration.py": "801f5004926c438c21ed3668fe2a4ddf45312b3e75320165a3839aae034eee9b", "tools/run_exam_campaign.py": "2c450d57a1cd0a2682838f5ec7c0a4ffb3aed0f1730d34c408e912d59cab6efd", "tools/serve_result_site.py": "07ffdd3bc63227523c1a589a996b5027f357a139d53d3835dfb77f9817a7e09d", "tools/start_demo.py": "c597e6cad28d245b3191654bb3e2801fa9dd2364e2acb25561923613717b615f", "tools/supplemental_acceptance.py": "7327277143d80a531e4c254ac74a9fc0e0d5c76572d53b8469e0a580eda17d65", "tools/sync_sources.py": "b51e889b0f41f9f63bfb19a09fb96d3777693d6b1d76fe0132bdd2a15e155898", "tools/validate_community_pr.py": "796b896dfade07b4529af2088a4b9b9d23484148b3bc0732b3fb837b75c9844b", "tools/verify_official_assessment_mapping.py": "daeb448a016940d5b6b1285979a56e5b9014bd91db40acb131445e4a83a23059", "tools/verify_task_package.py": "9e1e6105f6b5e4e78b36aa57f00117a9fbc8948ab53983c32ab56da88d23ccc4", "profiles/1c-ai-rules-2026-10-23-requirements.txt": "fd7ada214e0977776eb350794bb492d97824d96810eb7b158e46cf5cd72c8e65", "profiles/agents.json": "af9c492c08d13b3044aa6b6952589ed6a0a07d5258d8ff72bb18185b3eaebdc5", "profiles/ai-exam-execution-policy.json": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "profiles/bsl-analyzer-0.3.2-macos.json": "83537abdbf38c41ce665e4d0f24128bb51b62e971e0e0f368695f1326a7d2ffb", "profiles/bsl-analyzer-0.3.2-portable.json": "d6ba732e6778e256df34d6bc548593128820a70430c35b279796843606ee40a8", "profiles/bsl-ls-1.1.0-rc.6-macos.json": "245fc10747197e6911b2b4c77cdb15e6fa4eb7bc7c3758b63e768c5adf1df180", "profiles/bsl-ls-1.1.0-rc.6-portable.json": "9f10660881f2ec84794f7d584556b8f75c7e14b3555464af0ed0e60c4c892d86", "profiles/claude-code-skills-1c-1.12.0-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/code-index-1.9.0-macos.json": "63a919523ce62ecec274f4c139bc7ad49a75dd4c339568b822cbc695b4e30408", "profiles/code-index-1.9.0-portable.json": "81106cee8f424ffd8a9dc46ecd8e4f57598fc1d49661a83c77b1f0507993fbdc", "profiles/codex-probe-plan.json": "166e41aad5fb3b27d9050bc6de952c6cba363cc6e804d4080568cc71a2a4d289", "profiles/cursor-1c-skills-1.12.0-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/machine.linux.example.json": "408304fd0581098d5d8110dc67dfeab353bc4d4030e32d37e6acf98d2b1aedfd", "profiles/machine.macos.example.json": "52e9f9d17797cb520b9d8955d6806fd550b899bed4da241ebf096dcb6a21a942", "profiles/machine.windows.example.json": "63accac9a2f81d47d03447efbabffd4760aee325193f02f46b9b29a28d50d2d8", "profiles/mcp-toolkit-1.9.0-macos.json": "1d3f9cde5ffa20589a840d01fdae03aa0fc2f412c929f064f203919c4129625b", "profiles/mcp-toolkit-1.9.0-portable.json": "8e370eebe773eef0e08045ee9c6d5be1451f769f65be0710834b262a4336e054", "profiles/none-macos.json": "b1401d9c48159aed3559006c7f6ace6ef4571224d5cf0bb76d1a823505a10056", "profiles/none-portable.json": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "profiles/rlm-tools-bsl-1.43.0-macos.json": "9354421052640ab60bc3e6aa98ff2e7ba9ca2318b0f4026c137487449242cbd2", "profiles/rlm-tools-bsl-1.43.0-portable.json": "2599e5645e0a7d4e44cb2934bc2b272cae79a9bf7ea74a23cd48aacea64bc424", "profiles/rlm-tools-bsl-1.43.0-posix-requirements.txt": "4fdf9a1bd994bf0272e65d231daf76cf19b0a34dad0ae6b50ec4f11a2ce4c330", "profiles/rlm-tools-bsl-1.43.0-windows-requirements.txt": "3730cb46c81cda5181ecd4485e98b11933104632358bc86f8c0eb1a612a8954f", "profiles/shirokov-skills-macos.json": "84f3e89091676884a802035c707e912762a1179425fb8e3faff25be736873cdb", "profiles/shirokov-skills-portable.json": "2b0a461e06602f1456410e70f02ceaa5ac32c6549c486660bcb5ace0c2f87b15", "profiles/shirokov-skills-windows-requirements.txt": "6190feb8adb0945a55fad28ab242621c7321b93fd8557c4b19e4a481688d08d8", "profiles/unica-0.12.3-macos.json": "2c39fbb591cf2c2c6e056373823615485397ea83651b7926c6f25a5fe6a0aae6", "profiles/unica-0.13.0-macos.json": "b76b5c8a4dd33f571c4a90993f1a2da5f7223b4f0f8e1042c282e21a66121052", "profiles/unica-0.14.0-rc.1-portable.json": "7679e744c1fd0a428d02ab240795a01098b42102d4f5cb4fc217fada2ed91a77", "rules/1c-specialist-platform/chistov.json": "7a42ef723a1f5f03f02c387cd3ca95725f7364c2e11ebdfc988a02919ab22c37", "rules/1c-specialist-platform/decisions.json": "f622107423ce3c188c063318d7ab4f7718ceb38e443130677d8987f386641c09", "rules/1c-specialist-platform/examiner.json": "30353aa2a1b6545496b070d9066e9ffba0c3779e5b53ef70a4fd2cee375b18c0", "rules/1c-specialist-platform/ledger.json": "f167c10db2b5799dd9a1ea6a37cd2d7d186810dadf5ea2f50f26ae723c676882", "rules/1c-specialist-platform/rules.json": "1d320a4f8e1bf4701496388931f492315549bd3dce574b17285dd1d7f8652007", "rules/1c-specialist-platform/standards.json": "ed8af01d02edc604885530a3084d06ebe32b4cc8c4ae47e0798b79adb6ae6a26" } } }, "conditions": { "client": "codex", "model": "gpt-6.1-sol", "client_version": "0.163.0", "reasoning_effort": "medium", "harness": "none", "billing_channel": "subscription", "solve_timeout_seconds": 18000, "time_series": "exam", "delegation": "native_disabled", "network_profile": "open-book_shell", "deadline_disclosed": true, "statement_sha256": "8a6ccb3e673826d1f8220fda53eb310e3ec18c136d87ce8f4cebb2a08614e7e5", "starter_dt_sha256": "f40d084818b0d1cfe503fc7653a6a13f1a8e47fcd1688dad6245b12744eb4638", "profile_sha256": "7ccb3ce209cd8fe3586084914b2e201edf921d75e28b4d7415276587424765dd", "execution_policy_sha256": "fd2cd554bb1eff56e5a09f817ecf5eaa2f4d29851499d98c9a0a1675fd07aa4b", "calibration_sha256": "6fde5ca6242bb0895fda9c18ff5c5357a1762042d1c6d704032ee8f355eeb0a9", "started_at": "2026-10-26T11:36:57.347327+00:00", "timing": { "prepare_ms": 12600, "solve_ms": 4562988, "grade_ms": null }, "original_submission_valid": true, "model_provenance": "requested_only", "tokens": { "input": 21616270, "cached_input": 21442048, "fresh_input": 174222, "output": 134247, "reasoning_output": 50708, "total": 21750517, "coverage": "reported_completed_root_turns" }, "tools": { "mcp_calls": 0, "unica_calls": 0, "failed_calls": 0 }, "process": { "status": "completed", "exit_code": 0, "stop_confirmed": true } }, "verification": "contributor_reported", "download": "community-downloads/demo-20261026T113637Z-010c79/solution.zip", "source_context": "community-downloads/demo-20261026T113637Z-010c79/source-context.json", "regrade_required": [ { "id": "grader_changed", "files": [ "assessment.py", "bp.py", "calcwrite.py", "calibrate.py", "calibration_periodicity.py", "calibration_query.py", "claude.py", "codescan.py", "codex.py", "common.py", "docx_text.py", "examiner.py", "harness.py", "interpretations.py", "locking.py", "materials.py", "mcp_toolkit.py", "ou.py", "penalties.py", "portable_harnesses.py", "pr.py", "preflight.py", "process.py", "queries.py", "queryschema.py", "querytypes.py", "replay_calibration.py", "rules/1c-specialist-platform/chistov.json", "rules/1c-specialist-platform/examiner.json", "rules/1c-specialist-platform/rules.json", "rules/1c-specialist-platform/standards.json", "smoke_check.py", "starters/carcass-8.3.25.1445/starter.json", "stdio_harnesses.py", "tasks/1c-platform-official-sample/checks.json", "tasks/1c-platform-official-sample/private/official-assessment-mapping.json", "tasks/1c-platform-official-sample/private/owner-scoring-policy.json", "telemetry.py" ] } ], "grader_revision_sha256": "509a4f0a3280bc35f7bcdcdca59d70e507a14c9fa51e07c8ed244b5560318b7b", "archive_sha256": "1d4f69ecee5058bd8d86dd3f154dd00a4aff7d7533058b3bd19a6d79ef9c98de" } ] } ], "repository": "https://github.com/zeegin/1c-agent-exam-benchmark" }