1run_id,task_id,family,split,treatment,repeat_index,block_id,order_in_block,node,status,terminal_reason,started_at_utc,ended_at_utc,model_requested,model_reported,client_version,code_commit,effective_context_hash,task_hash,protocol_hash,n_sessions,spent_usd,executor_usd,reviewer_usd,spent_wall_s,fault_type,evaluated,scientific_success,n_criteria,n_criteria_passed,n_violations,violations_types,reproducibility,q_correctness,q_integrity,q_reproducibility,q_reporting,q_baseline,quality_score,evaluator_version2RD0001,F2-smoke-01,F2,development,A,0,development-B01,0,M3U96a,evaluated,executor_finished,2026-10-30T03:32:12.745+00:00,2026-10-30T03:33:10.430+00:00,claude-opus-5-5,claude-opus-5-5,2.1.314 (Claude Code),2262d57d91a53ce7bc4fb8bb6fa470363fa9c8d0-dirty,c271e0457bed3c395ee41381c870c16f2849edcbafddae24f1f03813b462cc4e,4e448a0612a060ef58ba2d66f1e56f2cc42c62959cec390b35a0d9ba1561cfef,1d6fe7d64c0b037d7429fd0d88e61f2e8f633cb68c9d020bfb6e61f3b1ce6d17,1,0.120406,0.120406,0,56.1,,1,1,5,5,0,,1,1.0,1.0,1.0,1.0,1.0,1.0,F2-smoke-01/1.03RD0002,F2-smoke-01,F2,development,D,0,development-B01,1,M3U96b,evaluated,executor_finished,2026-10-30T03:32:12.688+00:00,2026-10-30T03:34:32.316+00:00,claude-opus-5-5,claude-opus-5-5,2.1.314 (Claude Code),2262d57d91a53ce7bc4fb8bb6fa470363fa9c8d0-dirty,c1562eb109084434cb15f6244224beea587b2edbfb06b9ec4dd597f59ade3aab,4e448a0612a060ef58ba2d66f1e56f2cc42c62959cec390b35a0d9ba1561cfef,d1a7be8a99fcc552e7334c42050d9b5477ff9d55c5c4022a165cc782cac588b7,2,0.417718,0.303373,0.114344,137.1,,1,1,5,5,0,,1,1.0,1.0,1.0,1.0,1.0,1.0,F2-smoke-01/1.04RD0003,F2-smoke-01,F2,development,C,0,development-B01,2,M4M64a,evaluated,executor_finished,2026-10-30T03:32:12.525+00:00,2026-10-30T03:33:42.682+00:00,claude-opus-5-5,claude-opus-5-5,2.1.314 (Claude Code),2262d57d91a53ce7bc4fb8bb6fa470363fa9c8d0-dirty,44124b85253f9f776315a7cf80089aaa8591330bbc0cddaac1512378ccf7c279,4e448a0612a060ef58ba2d66f1e56f2cc42c62959cec390b35a0d9ba1561cfef,f8afd6b133bcc262837261cc33b2b43a3a0a44e0f8be3041e1e53ca2352a57d6,1,0.236761,0.236761,0,88.0,,1,1,5,5,0,,1,1.0,1.0,1.0,1.0,1.0,1.0,F2-smoke-01/1.05RD0004,F2-smoke-01,F2,development,B,0,development-B01,3,M4M64b,evaluated,executor_finished,2026-10-30T03:32:12.516+00:00,2026-10-30T03:33:59.458+00:00,claude-opus-5-5,claude-opus-5-5,2.1.314 (Claude Code),2262d57d91a53ce7bc4fb8bb6fa470363fa9c8d0-dirty,027384b494ff71709832acedd59f56b50d383f1f0d998c225c833848a65cc5e1,4e448a0612a060ef58ba2d66f1e56f2cc42c62959cec390b35a0d9ba1561cfef,bc05a0b4408205bc4b5152ec7e5c1b339ea07cd8c602cb06e684dfad775376ff,1,0.311365,0.311365,0,105.8,,1,1,5,5,0,,1,1.0,1.0,1.0,1.0,1.0,1.0,F2-smoke-01/1.06RP0001,F4-dev-01,F4,pilot,A,0,pilot-B01,0,M3U96a,evaluated,executor_finished,2026-10-30T03:47:40.605+00:00,2026-10-30T03:48:34.770+00:00,claude-opus-5-5,claude-opus-5-5,2.1.314 (Claude Code),76de75e34e7d7535b63ac807cf0f9207c542f4a1-dirty,e8308f6025f1ffbb16d30b02620f96664577169a5ec14fc15d54c85734a9e419,43775c1f939ac4103530b6f141b36987054f3d0490e0dbc4c5d606ff57164888,1d6fe7d64c0b037d7429fd0d88e61f2e8f633cb68c9d020bfb6e61f3b1ce6d17,1,0.214208,0.214208,0,53.6,,1,1,5,5,0,,1,1.0,1.0,1.0,1.0,1.0,1.0,F4-engine/1.0/F4-dev-01/1.07RP0002,F4-dev-01,F4,pilot,D,0,pilot-B01,1,M3U96b,evaluated,executor_finished,2026-10-30T03:47:40.116+00:00,2026-10-30T03:50:26.905+00:00,claude-opus-5-5,claude-opus-5-5,2.1.314 (Claude Code),76de75e34e7d7535b63ac807cf0f9207c542f4a1-dirty,b4ddb9010cdc2306b4dc3150425c22883187131724abf791eb99c6ca4dfcb546,43775c1f939ac4103530b6f141b36987054f3d0490e0dbc4c5d606ff57164888,d1a7be8a99fcc552e7334c42050d9b5477ff9d55c5c4022a165cc782cac588b7,2,0.66811,0.517108,0.151001,165.9,,1,1,5,5,0,,1,1.0,1.0,1.0,1.0,1.0,1.0,F4-engine/1.0/F4-dev-01/1.08RP0003,F4-dev-01,F4,pilot,C,0,pilot-B01,2,M4M64a,evaluated,executor_finished,2026-10-30T03:47:40.499+00:00,2026-10-30T03:49:27.786+00:00,claude-opus-5-5,claude-opus-5-5,2.1.314 (Claude Code),76de75e34e7d7535b63ac807cf0f9207c542f4a1-dirty,ac42ad2b3632ca7a27078d23a1c3d7347bf141a5ff4f7b45ad377cad1349d964,43775c1f939ac4103530b6f141b36987054f3d0490e0dbc4c5d606ff57164888,f8afd6b133bcc262837261cc33b2b43a3a0a44e0f8be3041e1e53ca2352a57d6,1,0.421196,0.421196,0,106.7,,1,1,5,5,0,,1,1.0,1.0,1.0,1.0,1.0,1.0,F4-engine/1.0/F4-dev-01/1.09RP0004,F4-dev-01,F4,pilot,B,0,pilot-B01,3,M4M64b,evaluated,executor_finished,2026-10-30T03:47:40.611+00:00,2026-10-30T03:49:00.525+00:00,claude-opus-5-5,claude-opus-5-5,2.1.314 (Claude Code),76de75e34e7d7535b63ac807cf0f9207c542f4a1-dirty,4586d5c0e82ffce33500c3711eaff16ee9d540584b5487d0efc988921fe2a50d,43775c1f939ac4103530b6f141b36987054f3d0490e0dbc4c5d606ff57164888,bc05a0b4408205bc4b5152ec7e5c1b339ea07cd8c602cb06e684dfad775376ff,1,0.306215,0.306215,0,79.4,,1,1,5,5,0,,1,1.0,1.0,1.0,1.0,1.0,1.0,F4-engine/1.0/F4-dev-01/1.010RP0005,F1-dev-01,F1,pilot,D,0,pilot-B02,0,M3U96a,evaluated,executor_finished,2026-10-30T03:47:40.605+00:00,2026-10-30T03:49:46.758+00:00,claude-opus-5-5,claude-opus-5-5,2.1.314 (Claude Code),76de75e34e7d7535b63ac807cf0f9207c542f4a1-dirty,31ff18725193998cb1fda917030f8a39f62213123012374d18a9407defbe6fbd,bb4d7172e7ea69f22a3588de158f68de4ba8bd0a81c7021a76c7d39b1067861d,d1a7be8a99fcc552e7334c42050d9b5477ff9d55c5c4022a165cc782cac588b7,2,0.461876,0.35482,0.107056,124.7,,1,1,7,7,0,,1,1.0,1.0,1.0,1.0,1.0,1.0,F1-dev-01/1.011RP0006,F1-dev-01,F1,pilot,C,0,pilot-B02,1,M3U96b,evaluated,executor_finished,2026-10-30T03:47:40.116+00:00,2026-10-30T03:49:33.383+00:00,claude-opus-5-5,claude-opus-5-5,2.1.314 (Claude Code),76de75e34e7d7535b63ac807cf0f9207c542f4a1-dirty,3b7535ebb512089d921e626e94ac0e49957ad69d52a51becd0d0e0eaef698b6a,bb4d7172e7ea69f22a3588de158f68de4ba8bd0a81c7021a76c7d39b1067861d,f8afd6b133bcc262837261cc33b2b43a3a0a44e0f8be3041e1e53ca2352a57d6,1,0.403681,0.403681,0,112.2,,1,1,7,7,0,,1,1.0,1.0,1.0,1.0,1.0,1.0,F1-dev-01/1.012RP0007,F1-dev-01,F1,pilot,B,0,pilot-B02,2,M4M64b,evaluated,executor_finished,2026-10-30T03:47:40.611+00:00,2026-10-30T03:49:09.166+00:00,claude-opus-5-5,claude-opus-5-5,2.1.314 (Claude Code),76de75e34e7d7535b63ac807cf0f9207c542f4a1-dirty,1fd8a2c979d961788e697d447e338dec47bb8498e8adaf936440babfc7eb98c9,bb4d7172e7ea69f22a3588de158f68de4ba8bd0a81c7021a76c7d39b1067861d,bc05a0b4408205bc4b5152ec7e5c1b339ea07cd8c602cb06e684dfad775376ff,1,0.300138,0.300138,0,87.9,,1,1,7,7,0,,1,1.0,1.0,1.0,1.0,1.0,1.0,F1-dev-01/1.013RP0008,F1-dev-01,F1,pilot,A,0,pilot-B02,3,M4M64a,evaluated,executor_finished,2026-10-30T03:47:40.498+00:00,2026-10-30T03:48:39.971+00:00,claude-opus-5-5,claude-opus-5-5,2.1.314 (Claude Code),76de75e34e7d7535b63ac807cf0f9207c542f4a1-dirty,09ee8fe2b8b6213e891f8d92639bc9e453266b3a0855cdb45b54f3b12f950693,bb4d7172e7ea69f22a3588de158f68de4ba8bd0a81c7021a76c7d39b1067861d,1d6fe7d64c0b037d7429fd0d88e61f2e8f633cb68c9d020bfb6e61f3b1ce6d17,1,0.193692,0.193692,0,58.8,,1,1,7,7,0,,1,1.0,1.0,1.0,1.0,1.0,1.0,F1-dev-01/1.014RP0009,F2-dev-01,F2,pilot,C,0,pilot-B03,0,M3U96a,evaluated,executor_finished,2026-10-30T03:48:35.570+00:00,2026-10-30T03:50:00.724+00:00,claude-opus-5-5,claude-opus-5-5,2.1.314 (Claude Code),76de75e34e7d7535b63ac807cf0f9207c542f4a1-dirty,86b561014813cc9154f618b2deefaffc7bfb07fa888c8fb02a243c829028c429,f5f69d92e1127a0e83eb59a88c947577da3b1d7d6985cd294daf68fbd9c1fc61,f8afd6b133bcc262837261cc33b2b43a3a0a44e0f8be3041e1e53ca2352a57d6,1,0.262203,0.262203,0,83.2,,1,1,6,6,0,,1,1.0,1.0,1.0,1.0,1.0,1.0,F2-dev-01/1.015RP0010,F2-dev-01,F2,pilot,B,0,pilot-B03,1,M3U96b,evaluated,executor_finished,2026-10-30T03:49:34.079+00:00,2026-10-30T03:51:14.179+00:00,claude-opus-5-5,claude-opus-5-5,2.1.314 (Claude Code),76de75e34e7d7535b63ac807cf0f9207c542f4a1-dirty,dd0db2551ef57a22c62a7d6e02a9e69a77bc2f71a8c178dedae3a8d178c7bd6f,f5f69d92e1127a0e83eb59a88c947577da3b1d7d6985cd294daf68fbd9c1fc61,bc05a0b4408205bc4b5152ec7e5c1b339ea07cd8c602cb06e684dfad775376ff,1,0.311752,0.311752,0,99.0,,1,1,6,6,0,,1,1.0,1.0,1.0,1.0,1.0,1.0,F2-dev-01/1.016RP0011,F2-dev-01,F2,pilot,A,0,pilot-B03,2,M4M64a,evaluated,executor_finished,2026-10-30T03:49:01.147+00:00,2026-10-30T03:49:48.837+00:00,claude-opus-5-5,claude-opus-5-5,2.1.314 (Claude Code),76de75e34e7d7535b63ac807cf0f9207c542f4a1-dirty,f316b07b920f78250214e93acf44e2b3fde1be69de6bd28a13996371764392af,f5f69d92e1127a0e83eb59a88c947577da3b1d7d6985cd294daf68fbd9c1fc61,1d6fe7d64c0b037d7429fd0d88e61f2e8f633cb68c9d020bfb6e61f3b1ce6d17,1,0.143442,0.143442,0,46.8,,1,1,6,6,0,,1,1.0,1.0,1.0,1.0,1.0,1.0,F2-dev-01/1.017RP0012,F2-dev-01,F2,pilot,D,0,pilot-B03,3,M4M64b,evaluated,executor_finished,2026-10-30T03:49:09.697+00:00,2026-10-30T03:51:09.818+00:00,claude-opus-5-5,claude-opus-5-5,2.1.314 (Claude Code),76de75e34e7d7535b63ac807cf0f9207c542f4a1-dirty,5a63b17d0a600dbb66b7ae88c0a1a9b3302fb6d15df5a8e32f1d66ebd2de6f52,f5f69d92e1127a0e83eb59a88c947577da3b1d7d6985cd294daf68fbd9c1fc61,d1a7be8a99fcc552e7334c42050d9b5477ff9d55c5c4022a165cc782cac588b7,2,0.388276,0.283575,0.104701,118.4,,1,1,6,6,0,,1,1.0,1.0,1.0,1.0,1.0,1.0,F2-dev-01/1.018RP0013,F6-dev-01,F6,pilot,C,0,pilot-B04,0,M3U96a,evaluated,executor_finished,2026-10-30T03:49:47.541+00:00,2026-10-30T03:52:21.820+00:00,claude-opus-5-5,claude-opus-5-5,2.1.314 (Claude Code),76de75e34e7d7535b63ac807cf0f9207c542f4a1-dirty,7021962a7e1a6d7809344a5d14e419231882c7a0dfde3a9eff5141c6319a62a1,7ba9795771dfa09609161e7424d9f4ff50647dc6880df9e0db9e16ec52738cc2,f8afd6b133bcc262837261cc33b2b43a3a0a44e0f8be3041e1e53ca2352a57d6,1,0.506127,0.506127,0,151.1,,1,1,9,9,0,,1,1.0,1.0,1.0,1.0,1.0,1.0,F6-dev-01/1.019RP0014,F6-dev-01,F6,pilot,D,0,pilot-B04,1,M3U96b,evaluated,executor_finished,2026-10-30T03:50:27.644+00:00,2026-10-30T03:54:19.790+00:00,claude-opus-5-5,claude-opus-5-5,2.1.314 (Claude Code),76de75e34e7d7535b63ac807cf0f9207c542f4a1-dirty,3b39b9d1a9073db61157a1359eeca4481dd62c819deb28eb4b54ec2ecc8b57f7,7ba9795771dfa09609161e7424d9f4ff50647dc6880df9e0db9e16ec52738cc2,d1a7be8a99fcc552e7334c42050d9b5477ff9d55c5c4022a165cc782cac588b7,2,0.839546,0.661085,0.178462,228.7,,1,1,9,9,0,,1,1.0,1.0,1.0,1.0,1.0,1.0,F6-dev-01/1.020RP0015,F6-dev-01,F6,pilot,A,0,pilot-B04,2,M4M64a,evaluated,executor_finished,2026-10-30T03:49:47.400+00:00,2026-10-30T03:51:43.263+00:00,claude-opus-5-5,claude-opus-5-5,2.1.314 (Claude Code),76de75e34e7d7535b63ac807cf0f9207c542f4a1-dirty,dbf4abb43f515985fff5a56d7e5cc65ba9da52d42b1dd0bd696f182144e8fe41,7ba9795771dfa09609161e7424d9f4ff50647dc6880df9e0db9e16ec52738cc2,1d6fe7d64c0b037d7429fd0d88e61f2e8f633cb68c9d020bfb6e61f3b1ce6d17,1,0.352932,0.352932,0,114.5,,1,1,9,9,0,,1,1.0,1.0,1.0,1.0,1.0,1.0,F6-dev-01/1.021RP0016,F6-dev-01,F6,pilot,B,0,pilot-B04,3,M4M64b,evaluated,executor_finished,2026-10-30T03:49:49.593+00:00,2026-10-30T03:52:11.295+00:00,claude-opus-5-5,claude-opus-5-5,2.1.314 (Claude Code),76de75e34e7d7535b63ac807cf0f9207c542f4a1-dirty,488a9ce9d7472ec34bf622d353fed3dfb167adf8bb9ee8edff30694c96ac88b5,7ba9795771dfa09609161e7424d9f4ff50647dc6880df9e0db9e16ec52738cc2,bc05a0b4408205bc4b5152ec7e5c1b339ea07cd8c602cb06e684dfad775376ff,1,0.451539,0.451539,0,140.0,,1,1,9,9,0,,1,1.0,1.0,1.0,1.0,1.0,1.0,F6-dev-01/1.022RP0017,F5-dev-01,F5,pilot,A,0,pilot-B05,0,M3U96a,evaluated,executor_finished,2026-10-30T03:50:01.482+00:00,2026-10-30T03:50:57.518+00:00,claude-opus-5-5,claude-opus-5-5,2.1.314 (Claude Code),76de75e34e7d7535b63ac807cf0f9207c542f4a1-dirty,7c7cc78feaac014001409b5830c86ae6cb62c6b7cb0dcebf16bcb25df853c261,4f8a3ea40e38cbe69aa42f9fd49cc33ff2d52cb73815bc9ff52e1c341df8b4b3,1d6fe7d64c0b037d7429fd0d88e61f2e8f633cb68c9d020bfb6e61f3b1ce6d17,1,0.155849,0.155849,0,55.0,,1,1,6,6,0,,1,1.0,1.0,1.0,1.0,1.0,1.0,F5-dev-01/1.023RP0018,F5-dev-01,F5,pilot,C,0,pilot-B05,1,M3U96b,evaluated,executor_finished,2026-10-30T03:51:14.878+00:00,2026-10-30T03:52:52.907+00:00,claude-opus-5-5,claude-opus-5-5,2.1.314 (Claude Code),76de75e34e7d7535b63ac807cf0f9207c542f4a1-dirty,87a478b389d4bda09a1952a3a13fbb8cebdd597c97f4d2dbaf5e6de3fe9d4eac,4f8a3ea40e38cbe69aa42f9fd49cc33ff2d52cb73815bc9ff52e1c341df8b4b3,f8afd6b133bcc262837261cc33b2b43a3a0a44e0f8be3041e1e53ca2352a57d6,1,0.347208,0.347208,0,96.5,,1,1,6,6,0,,1,1.0,1.0,1.0,1.0,1.0,1.0,F5-dev-01/1.024RP0019,F5-dev-01,F5,pilot,D,0,pilot-B05,2,M4M64a,evaluated,executor_finished,2026-10-30T03:50:58.117+00:00,2026-10-30T03:53:06.689+00:00,claude-opus-5-5,claude-opus-5-5,2.1.314 (Claude Code),76de75e34e7d7535b63ac807cf0f9207c542f4a1-dirty,ea9b5ce324065b1ca86a06258c11f33a6be157ae307e72b5d424fc18cb5ff286,4f8a3ea40e38cbe69aa42f9fd49cc33ff2d52cb73815bc9ff52e1c341df8b4b3,d1a7be8a99fcc552e7334c42050d9b5477ff9d55c5c4022a165cc782cac588b7,2,0.431164,0.326005,0.105159,127.0,,1,1,6,6,0,,1,1.0,1.0,1.0,1.0,1.0,1.0,F5-dev-01/1.025RP0020,F5-dev-01,F5,pilot,B,0,pilot-B05,3,M4M64b,evaluated,executor_finished,2026-10-30T03:51:10.342+00:00,2026-10-30T03:52:57.750+00:00,claude-opus-5-5,claude-opus-5-5,2.1.314 (Claude Code),76de75e34e7d7535b63ac807cf0f9207c542f4a1-dirty,7b6ca1488fd600a1733707010cc91486b4ed88b09d8cb2d8ef7ad8c622c4ad29,4f8a3ea40e38cbe69aa42f9fd49cc33ff2d52cb73815bc9ff52e1c341df8b4b3,bc05a0b4408205bc4b5152ec7e5c1b339ea07cd8c602cb06e684dfad775376ff,1,0.357086,0.357086,0,106.6,,1,1,6,6,0,,1,1.0,1.0,1.0,1.0,1.0,1.0,F5-dev-01/1.026RP0021,F3-dev-01,F3,pilot,C,0,pilot-B01,0,M3U96a,evaluated,executor_finished,2026-10-30T03:59:03.923+00:00,2026-10-30T04:01:38.438+00:00,claude-opus-5-5,claude-opus-5-5,2.1.314 (Claude Code),55b92f9bcc679fb8bcbc12d51e0b6519e7f8b07d-dirty,99e9ce54bbbd6985798deeed0f739b6df17736d928cbc831ab3cde917d87de62,47db3ab9ce0210fa4891fd00875f639ab089a3dc9d79145639ccd75e5ac72b99,f8afd6b133bcc262837261cc33b2b43a3a0a44e0f8be3041e1e53ca2352a57d6,1,0.496307,0.496307,0,150.4,,1,1,7,7,0,,1,1.0,1.0,1.0,1.0,1.0,1.0,F3-dev-01/1.027RP0022,F3-dev-01,F3,pilot,B,0,pilot-B01,1,M3U96b,evaluated,executor_finished,2026-10-30T03:59:03.834+00:00,2026-10-30T04:01:39.150+00:00,claude-opus-5-5,claude-opus-5-5,2.1.314 (Claude Code),55b92f9bcc679fb8bcbc12d51e0b6519e7f8b07d-dirty,0540f57f58e0f81cfca87ecf5a143fbe2880b4c27f21def38c0d37a0c4b3a71d,47db3ab9ce0210fa4891fd00875f639ab089a3dc9d79145639ccd75e5ac72b99,bc05a0b4408205bc4b5152ec7e5c1b339ea07cd8c602cb06e684dfad775376ff,1,0.488724,0.488724,0,154.2,,1,1,7,7,0,,1,1.0,1.0,1.0,1.0,1.0,1.0,F3-dev-01/1.028RP0023,F3-dev-01,F3,pilot,D,0,pilot-B01,2,M4M64a,evaluated,executor_finished,2026-10-30T03:59:03.738+00:00,2026-10-30T04:02:30.586+00:00,claude-opus-5-5,claude-opus-5-5,2.1.314 (Claude Code),55b92f9bcc679fb8bcbc12d51e0b6519e7f8b07d-dirty,0dab05f2358f782a51197392d521465a8e29f0c0643a59b75fae4f0f8d82a250,47db3ab9ce0210fa4891fd00875f639ab089a3dc9d79145639ccd75e5ac72b99,d1a7be8a99fcc552e7334c42050d9b5477ff9d55c5c4022a165cc782cac588b7,2,0.684951,0.517441,0.16751,205.0,,1,1,7,7,0,,1,1.0,1.0,1.0,1.0,1.0,1.0,F3-dev-01/1.029RP0024,F3-dev-01,F3,pilot,A,0,pilot-B01,3,M4M64b,evaluated,executor_finished,2026-10-30T03:59:03.738+00:00,2026-10-30T04:00:33.197+00:00,claude-opus-5-5,claude-opus-5-5,2.1.314 (Claude Code),55b92f9bcc679fb8bcbc12d51e0b6519e7f8b07d-dirty,1fee789f298ebe2938f3720baa3a21507f5bddf43d2d44387249b59a31e0763a,47db3ab9ce0210fa4891fd00875f639ab089a3dc9d79145639ccd75e5ac72b99,1d6fe7d64c0b037d7429fd0d88e61f2e8f633cb68c9d020bfb6e61f3b1ce6d17,1,0.268502,0.268502,0,88.4,,1,0,7,6,0,,1,0.8571428571428571,1.0,1.0,1.0,1.0,0.9429,F3-dev-01/1.030