{"runId":"luna6-jev-compaction-v1","baselineRunId":"luna6-compaction-v2","updatedAt":"2026-09-29T11:59:54.565Z","runState":"STOPPED","phase":"Deadline reached","completedTrials":96,"plannedTrials":96,"totals":{"passes":57,"scored":95,"errors":1,"running":0,"openaiCostUsd":4.749827059999999,"jevCostUsd":0.05548435199999997,"compactingTrials":53,"compactions":217},"mechanics":{"trials":95,"meanCompactions":2.28,"meanRequests":39.2,"meanTotalTokens":1422095,"meanCostUsd":0.0489,"medianDurationSec":492,"medianResidualTokens":24790,"meanDroppedCalls":32.61,"meanTruncatedResults":3.79,"timedOut":6},"groups":{"primary":{"tasks":12,"jevMean":0.583,"comparisons":{"TextualFixed50kPi":{"label":"Pi textual","matchedTasks":12,"jevMean":0.583,"baselineMean":0.569,"effect":{"meanPp":1.4,"lowPp":-12.5,"highPp":13.9,"tasks":12}},"Native50kPi":{"label":"OpenAI encrypted","matchedTasks":12,"jevMean":0.583,"baselineMean":0.535,"effect":{"meanPp":4.9,"lowPp":-6.3,"highPp":17.4,"tasks":12}}}},"all":{"tasks":24,"jevMean":0.594,"comparisons":{"TextualFixed50kPi":{"label":"Pi textual","matchedTasks":24,"jevMean":0.594,"baselineMean":0.618,"effect":{"meanPp":-2.4,"lowPp":-9.7,"highPp":4.5,"tasks":24}},"Native50kPi":{"label":"OpenAI encrypted","matchedTasks":24,"jevMean":0.594,"baselineMean":0.601,"effect":{"meanPp":-0.7,"lowPp":-8.3,"highPp":6.9,"tasks":24}}}},"placebo":{"tasks":6,"jevMean":0.75,"comparisons":{"TextualFixed50kPi":{"label":"Pi textual","matchedTasks":6,"jevMean":0.75,"baselineMean":0.792,"effect":{"meanPp":-4.2,"lowPp":-12.5,"highPp":0,"tasks":6}},"Native50kPi":{"label":"OpenAI encrypted","matchedTasks":6,"jevMean":0.75,"baselineMean":0.833,"effect":{"meanPp":-8.3,"lowPp":-25,"highPp":0,"tasks":6}}}}},"tasks":[{"task":"make-mips-interpreter","group":"primary","baselineCompactionRate":1,"passes":2,"scored":4,"errors":0,"running":0,"queued":0,"passRate":0.5,"compactionRate":1,"trials":[{"task":"make-mips-interpreter","round":0,"trial":"make-mips-interpreter__ezmifGz","status":"PASS","timedOut":false,"exception":null,"qualifiedCompactions":1,"compactions":1,"droppedCalls":20,"truncatedResults":1,"medianResidualTokens":17990,"requests":28,"inputTokens":707264,"outputTokens":21012,"totalTokens":728276,"openaiCostUsd":0.026764925,"jevCostUsd":0.00023583000000000002,"durationSec":248.288,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-28T22:32:10.462896Z","finishedAt":"2026-09-28T22:36:18.750386Z"},{"task":"make-mips-interpreter","round":1,"trial":"make-mips-interpreter__nR2VWiy","status":"FAIL","timedOut":false,"exception":null,"qualifiedCompactions":9,"compactions":9,"droppedCalls":156,"truncatedResults":19,"medianResidualTokens":40563,"requests":140,"inputTokens":5146260,"outputTokens":64850,"totalTokens":5211110,"openaiCostUsd":0.13930031500000004,"jevCostUsd":0.0022720320000000002,"durationSec":791.209,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-29T02:08:46.117531Z","finishedAt":"2026-09-29T02:21:57.326837Z"},{"task":"make-mips-interpreter","round":2,"trial":"make-mips-interpreter__WMJQcDr","status":"FAIL","timedOut":false,"exception":null,"qualifiedCompactions":4,"compactions":4,"droppedCalls":54,"truncatedResults":6,"medianResidualTokens":26194.5,"requests":58,"inputTokens":1892287,"outputTokens":42754,"totalTokens":1935041,"openaiCostUsd":0.06797717,"jevCostUsd":0.0008287860000000001,"durationSec":463.142,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-29T02:18:48.484472Z","finishedAt":"2026-09-29T02:26:31.626802Z"},{"task":"make-mips-interpreter","round":3,"trial":"make-mips-interpreter__fxVvqZW","status":"PASS","timedOut":false,"exception":null,"qualifiedCompactions":6,"compactions":6,"droppedCalls":98,"truncatedResults":12,"medianResidualTokens":20040.5,"requests":91,"inputTokens":3183138,"outputTokens":49965,"totalTokens":3233103,"openaiCostUsd":0.09471737999999998,"jevCostUsd":0.001356684,"durationSec":754.387,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-29T05:37:48.440431Z","finishedAt":"2026-09-29T05:50:22.827372Z"}]},{"task":"fix-ocaml-gc","group":"primary","baselineCompactionRate":0.875,"passes":4,"scored":4,"errors":0,"running":0,"queued":0,"passRate":1,"compactionRate":1,"trials":[{"task":"fix-ocaml-gc","round":0,"trial":"fix-ocaml-gc__yNM5JJZ","status":"PASS","timedOut":false,"exception":null,"qualifiedCompactions":1,"compactions":1,"droppedCalls":13,"truncatedResults":0,"medianResidualTokens":24790,"requests":18,"inputTokens":417073,"outputTokens":4296,"totalTokens":421369,"openaiCostUsd":0.013836655000000003,"jevCostUsd":0.00014645400000000002,"durationSec":1313.338,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-28T22:32:10.461348Z","finishedAt":"2026-09-28T22:54:03.799494Z"},{"task":"fix-ocaml-gc","round":1,"trial":"fix-ocaml-gc__9Prw7Dr","status":"PASS","timedOut":false,"exception":null,"qualifiedCompactions":2,"compactions":2,"droppedCalls":22,"truncatedResults":2,"medianResidualTokens":20644,"requests":28,"inputTokens":788752,"outputTokens":3789,"totalTokens":792541,"openaiCostUsd":0.02495325,"jevCostUsd":0.000284802,"durationSec":1418.321,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-29T01:56:54.198522Z","finishedAt":"2026-09-29T02:20:32.519072Z"},{"task":"fix-ocaml-gc","round":2,"trial":"fix-ocaml-gc__kFt4kwK","status":"PASS","timedOut":false,"exception":null,"qualifiedCompactions":2,"compactions":2,"droppedCalls":34,"truncatedResults":2,"medianResidualTokens":17034,"requests":29,"inputTokens":820196,"outputTokens":7529,"totalTokens":827725,"openaiCostUsd":0.024334144999999998,"jevCostUsd":0.00039240600000000004,"durationSec":1333.106,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-29T02:20:35.173641Z","finishedAt":"2026-09-29T02:42:48.279798Z"},{"task":"fix-ocaml-gc","round":3,"trial":"fix-ocaml-gc__jkHkstu","status":"PASS","timedOut":false,"exception":null,"qualifiedCompactions":2,"compactions":2,"droppedCalls":22,"truncatedResults":1,"medianResidualTokens":26571.5,"requests":26,"inputTokens":886758,"outputTokens":7415,"totalTokens":894173,"openaiCostUsd":0.03131192,"jevCostUsd":0.00027917400000000003,"durationSec":1462.359,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-29T05:25:55.632330Z","finishedAt":"2026-09-29T05:50:17.991319Z"}]},{"task":"make-doom-for-mips","group":"primary","baselineCompactionRate":1,"passes":0,"scored":3,"errors":1,"running":0,"queued":0,"passRate":0,"compactionRate":1,"trials":[{"task":"make-doom-for-mips","round":0,"trial":"make-doom-for-mips__pJavxbL","status":"FAIL","timedOut":false,"exception":null,"qualifiedCompactions":4,"compactions":4,"droppedCalls":101,"truncatedResults":23,"medianResidualTokens":25131,"requests":106,"inputTokens":3469958,"outputTokens":38499,"totalTokens":3508457,"openaiCostUsd":0.08077867999999999,"jevCostUsd":0.001535352,"durationSec":589.434,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-28T22:32:10.461147Z","finishedAt":"2026-09-28T22:41:59.895729Z"},{"task":"make-doom-for-mips","round":1,"trial":"make-doom-for-mips__JTe5RKH","status":"FAIL","timedOut":false,"exception":null,"qualifiedCompactions":12,"compactions":12,"droppedCalls":160,"truncatedResults":86,"medianResidualTokens":35553,"requests":136,"inputTokens":5204200,"outputTokens":63095,"totalTokens":5267295,"openaiCostUsd":0.15658336999999994,"jevCostUsd":0.0035216579999999996,"durationSec":858.489,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-29T01:54:24.908495Z","finishedAt":"2026-09-29T02:08:43.397483Z"},{"task":"make-doom-for-mips","round":2,"trial":"make-doom-for-mips__qbtE45e","status":"ERROR","timedOut":false,"exception":"NonZeroAgentExitCodeError","qualifiedCompactions":11,"compactions":11,"droppedCalls":167,"truncatedResults":27,"medianResidualTokens":41628,"requests":137,"inputTokens":5344712,"outputTokens":71676,"totalTokens":5416388,"openaiCostUsd":0.15954984999999997,"jevCostUsd":0.00279951,"durationSec":842.328,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-29T02:21:59.947871Z","finishedAt":"2026-09-29T02:36:02.275370Z"},{"task":"make-doom-for-mips","round":3,"trial":"make-doom-for-mips__mB7htDS","status":"FAIL","timedOut":false,"exception":null,"qualifiedCompactions":11,"compactions":11,"droppedCalls":170,"truncatedResults":67,"medianResidualTokens":40121,"requests":158,"inputTokens":6032542,"outputTokens":64227,"totalTokens":6096769,"openaiCostUsd":0.16016770500000002,"jevCostUsd":0.003242568,"durationSec":842.646,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-29T05:11:49.963690Z","finishedAt":"2026-09-29T05:25:52.609614Z"}]},{"task":"caffe-cifar-10","group":"primary","baselineCompactionRate":1,"passes":2,"scored":4,"errors":0,"running":0,"queued":0,"passRate":0.5,"compactionRate":1,"trials":[{"task":"caffe-cifar-10","round":0,"trial":"caffe-cifar-10__3Z4hrCi","status":"PASS","timedOut":false,"exception":null,"qualifiedCompactions":3,"compactions":3,"droppedCalls":54,"truncatedResults":10,"medianResidualTokens":11625,"requests":45,"inputTokens":1367341,"outputTokens":15889,"totalTokens":1383230,"openaiCostUsd":0.04331583999999999,"jevCostUsd":0.000724794,"durationSec":2505.963,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-28T22:36:21.263847Z","finishedAt":"2026-09-28T23:18:07.226953Z"},{"task":"caffe-cifar-10","round":1,"trial":"caffe-cifar-10__nF5iowJ","status":"FAIL","timedOut":false,"exception":null,"qualifiedCompactions":3,"compactions":3,"droppedCalls":60,"truncatedResults":6,"medianResidualTokens":22582,"requests":52,"inputTokens":1517124,"outputTokens":25479,"totalTokens":1542603,"openaiCostUsd":0.046503144999999996,"jevCostUsd":0.000789222,"durationSec":1523.731,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-29T01:53:22.105437Z","finishedAt":"2026-09-29T02:18:45.836371Z"},{"task":"caffe-cifar-10","round":2,"trial":"caffe-cifar-10__SEx3YhQ","status":"PASS","timedOut":false,"exception":null,"qualifiedCompactions":2,"compactions":2,"droppedCalls":48,"truncatedResults":4,"medianResidualTokens":17179.5,"requests":54,"inputTokens":1622003,"outputTokens":17284,"totalTokens":1639287,"openaiCostUsd":0.039803034999999994,"jevCostUsd":0.0005546100000000001,"durationSec":1732.581,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-29T02:26:34.239402Z","finishedAt":"2026-09-29T02:55:26.820039Z"},{"task":"caffe-cifar-10","round":3,"trial":"caffe-cifar-10__KPnsbQD","status":"FAIL","timedOut":true,"exception":null,"qualifiedCompactions":1,"compactions":1,"droppedCalls":16,"truncatedResults":1,"medianResidualTokens":13667,"requests":22,"inputTokens":521681,"outputTokens":4271,"totalTokens":525952,"openaiCostUsd":0.016851845,"jevCostUsd":0.000190512,"durationSec":3645.997,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-29T05:07:09.820655Z","finishedAt":"2026-09-29T06:07:55.817691Z"}]},{"task":"path-tracing-reverse","group":"primary","baselineCompactionRate":1,"passes":4,"scored":4,"errors":0,"running":0,"queued":0,"passRate":1,"compactionRate":1,"trials":[{"task":"path-tracing-reverse","round":0,"trial":"path-tracing-reverse__q9nnHdf","status":"PASS","timedOut":false,"exception":null,"qualifiedCompactions":6,"compactions":6,"droppedCalls":64,"truncatedResults":7,"medianResidualTokens":25668.5,"requests":73,"inputTokens":2631080,"outputTokens":46217,"totalTokens":2677297,"openaiCostUsd":0.09198843500000001,"jevCostUsd":0.0011229120000000002,"durationSec":555.585,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-28T22:42:02.583883Z","finishedAt":"2026-09-28T22:51:18.168057Z"},{"task":"path-tracing-reverse","round":1,"trial":"path-tracing-reverse__4Z7J9oJ","status":"PASS","timedOut":false,"exception":null,"qualifiedCompactions":7,"compactions":7,"droppedCalls":91,"truncatedResults":9,"medianResidualTokens":42189,"requests":83,"inputTokens":3099366,"outputTokens":53641,"totalTokens":3153007,"openaiCostUsd":0.10532927000000002,"jevCostUsd":0.001373904,"durationSec":597.853,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-29T01:46:53.748336Z","finishedAt":"2026-09-29T01:56:51.601654Z"},{"task":"path-tracing-reverse","round":2,"trial":"path-tracing-reverse__vWsyVNv","status":"PASS","timedOut":false,"exception":null,"qualifiedCompactions":5,"compactions":5,"droppedCalls":65,"truncatedResults":7,"medianResidualTokens":29273,"requests":67,"inputTokens":2285920,"outputTokens":39571,"totalTokens":2325491,"openaiCostUsd":0.07579647500000002,"jevCostUsd":0.000987588,"durationSec":447.536,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-29T02:36:04.922880Z","finishedAt":"2026-09-29T02:43:32.458222Z"},{"task":"path-tracing-reverse","round":3,"trial":"path-tracing-reverse__6jUDdLk","status":"PASS","timedOut":false,"exception":null,"qualifiedCompactions":3,"compactions":3,"droppedCalls":36,"truncatedResults":2,"medianResidualTokens":26352,"requests":33,"inputTokens":883787,"outputTokens":26554,"totalTokens":910341,"openaiCostUsd":0.04303008999999999,"jevCostUsd":0.000549612,"durationSec":311.128,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-29T05:06:35.656258Z","finishedAt":"2026-09-29T05:11:46.784096Z"}]},{"task":"compile-compcert","group":"primary","baselineCompactionRate":1,"passes":4,"scored":4,"errors":0,"running":0,"queued":0,"passRate":1,"compactionRate":0.75,"trials":[{"task":"compile-compcert","round":0,"trial":"compile-compcert__FrRZbhU","status":"PASS","timedOut":false,"exception":null,"qualifiedCompactions":2,"compactions":2,"droppedCalls":37,"truncatedResults":3,"medianResidualTokens":17128,"requests":36,"inputTokens":949238,"outputTokens":8159,"totalTokens":957397,"openaiCostUsd":0.026321184999999997,"jevCostUsd":0.00040782000000000004,"durationSec":1181.7,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-28T22:51:20.711563Z","finishedAt":"2026-09-28T23:11:02.411447Z"},{"task":"compile-compcert","round":1,"trial":"compile-compcert__xbKe9rf","status":"PASS","timedOut":false,"exception":null,"qualifiedCompactions":1,"compactions":1,"droppedCalls":16,"truncatedResults":1,"medianResidualTokens":13996,"requests":27,"inputTokens":605604,"outputTokens":8219,"totalTokens":613823,"openaiCostUsd":0.018655920000000003,"jevCostUsd":0.00017766000000000003,"durationSec":1145.759,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-29T01:35:16.565498Z","finishedAt":"2026-09-29T01:54:22.324036Z"},{"task":"compile-compcert","round":2,"trial":"compile-compcert__TrM9NDW","status":"PASS","timedOut":false,"exception":null,"qualifiedCompactions":0,"compactions":0,"droppedCalls":0,"truncatedResults":0,"medianResidualTokens":null,"requests":31,"inputTokens":908603,"outputTokens":7644,"totalTokens":916247,"openaiCostUsd":0.018662259999999996,"jevCostUsd":0,"durationSec":908.945,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-29T02:42:50.913656Z","finishedAt":"2026-09-29T02:57:59.858195Z"},{"task":"compile-compcert","round":3,"trial":"compile-compcert__unBke26","status":"PASS","timedOut":false,"exception":null,"qualifiedCompactions":1,"compactions":1,"droppedCalls":20,"truncatedResults":2,"medianResidualTokens":8285,"requests":42,"inputTokens":1108895,"outputTokens":10100,"totalTokens":1118995,"openaiCostUsd":0.025534289999999998,"jevCostUsd":0.00023121,"durationSec":2134.574,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-29T05:02:11.115369Z","finishedAt":"2026-09-29T05:37:45.689497Z"}]},{"task":"regex-chess","group":"primary","baselineCompactionRate":0.7142857142857143,"passes":2,"scored":4,"errors":0,"running":0,"queued":0,"passRate":0.5,"compactionRate":0.75,"trials":[{"task":"regex-chess","round":0,"trial":"regex-chess__hokxsLD","status":"FAIL","timedOut":false,"exception":null,"qualifiedCompactions":0,"compactions":0,"droppedCalls":0,"truncatedResults":0,"medianResidualTokens":null,"requests":30,"inputTokens":996880,"outputTokens":32534,"totalTokens":1029414,"openaiCostUsd":0.031952154999999996,"jevCostUsd":0,"durationSec":596.633,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-28T22:54:06.345342Z","finishedAt":"2026-09-28T23:04:02.978950Z"},{"task":"regex-chess","round":1,"trial":"regex-chess__UAiXZgE","status":"PASS","timedOut":false,"exception":null,"qualifiedCompactions":1,"compactions":1,"droppedCalls":26,"truncatedResults":4,"medianResidualTokens":30491,"requests":39,"inputTokens":1328405,"outputTokens":33983,"totalTokens":1362388,"openaiCostUsd":0.04066023,"jevCostUsd":0.000401184,"durationSec":763.677,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-29T01:34:06.925349Z","finishedAt":"2026-09-29T01:46:50.602189Z"},{"task":"regex-chess","round":2,"trial":"regex-chess__mLAnQDN","status":"FAIL","timedOut":false,"exception":null,"qualifiedCompactions":2,"compactions":2,"droppedCalls":42,"truncatedResults":5,"medianResidualTokens":30734.5,"requests":54,"inputTokens":1942456,"outputTokens":40302,"totalTokens":1982758,"openaiCostUsd":0.05618199500000002,"jevCostUsd":0.0007912800000000001,"durationSec":695.966,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-29T02:43:35.101719Z","finishedAt":"2026-09-29T02:55:11.067360Z"},{"task":"regex-chess","round":3,"trial":"regex-chess__eUYpCUB","status":"PASS","timedOut":false,"exception":null,"qualifiedCompactions":3,"compactions":3,"droppedCalls":28,"truncatedResults":2,"medianResidualTokens":53030,"requests":40,"inputTokens":1548872,"outputTokens":32815,"totalTokens":1581687,"openaiCostUsd":0.05948459500000001,"jevCostUsd":0.000621978,"durationSec":613.799,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-29T04:56:19.012856Z","finishedAt":"2026-09-29T05:06:32.811790Z"}]},{"task":"gpt2-codegolf","group":"other","baselineCompactionRate":0.14285714285714285,"passes":0,"scored":4,"errors":0,"running":0,"queued":0,"passRate":0,"compactionRate":0,"trials":[{"task":"gpt2-codegolf","round":0,"trial":"gpt2-codegolf__9jbdfdk","status":"FAIL","timedOut":false,"exception":null,"qualifiedCompactions":0,"compactions":0,"droppedCalls":0,"truncatedResults":0,"medianResidualTokens":null,"requests":9,"inputTokens":30573,"outputTokens":7238,"totalTokens":37811,"openaiCostUsd":0.00488097,"jevCostUsd":0,"durationSec":127.893,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-28T23:04:05.866791Z","finishedAt":"2026-09-28T23:06:13.759475Z"},{"task":"gpt2-codegolf","round":1,"trial":"gpt2-codegolf__dqbHKh2","status":"FAIL","timedOut":false,"exception":null,"qualifiedCompactions":0,"compactions":0,"droppedCalls":0,"truncatedResults":0,"medianResidualTokens":null,"requests":33,"inputTokens":788181,"outputTokens":36904,"totalTokens":825085,"openaiCostUsd":0.03161983999999999,"jevCostUsd":0,"durationSec":396.722,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-29T01:28:37.125568Z","finishedAt":"2026-09-29T01:35:13.847603Z"},{"task":"gpt2-codegolf","round":2,"trial":"gpt2-codegolf__i2WJAJ3","status":"FAIL","timedOut":false,"exception":null,"qualifiedCompactions":0,"compactions":0,"droppedCalls":0,"truncatedResults":0,"medianResidualTokens":null,"requests":33,"inputTokens":630803,"outputTokens":29402,"totalTokens":660205,"openaiCostUsd":0.025410940000000003,"jevCostUsd":0,"durationSec":315.662,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-29T02:55:13.996796Z","finishedAt":"2026-09-29T03:00:29.658830Z"},{"task":"gpt2-codegolf","round":3,"trial":"gpt2-codegolf__CpeVNtM","status":"FAIL","timedOut":false,"exception":null,"qualifiedCompactions":0,"compactions":0,"droppedCalls":0,"truncatedResults":0,"medianResidualTokens":null,"requests":8,"inputTokens":30762,"outputTokens":7073,"totalTokens":37835,"openaiCostUsd":0.004640125,"jevCostUsd":0,"durationSec":99.226,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-29T04:54:36.891399Z","finishedAt":"2026-09-29T04:56:16.117696Z"}]},{"task":"path-tracing","group":"primary","baselineCompactionRate":0.7142857142857143,"passes":4,"scored":4,"errors":0,"running":0,"queued":0,"passRate":1,"compactionRate":1,"trials":[{"task":"path-tracing","round":0,"trial":"path-tracing__UeuvStE","status":"PASS","timedOut":false,"exception":null,"qualifiedCompactions":6,"compactions":6,"droppedCalls":69,"truncatedResults":3,"medianResidualTokens":41692,"requests":76,"inputTokens":2837279,"outputTokens":60034,"totalTokens":2897313,"openaiCostUsd":0.09943115499999998,"jevCostUsd":0.001461474,"durationSec":1145.025,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-28T23:06:16.652634Z","finishedAt":"2026-09-28T23:25:21.677751Z"},{"task":"path-tracing","round":1,"trial":"path-tracing__dSytmGr","status":"PASS","timedOut":false,"exception":null,"qualifiedCompactions":9,"compactions":9,"droppedCalls":82,"truncatedResults":3,"medianResidualTokens":55155,"requests":86,"inputTokens":3964482,"outputTokens":89428,"totalTokens":4053910,"openaiCostUsd":0.15293216000000004,"jevCostUsd":0.0019824000000000005,"durationSec":1396.523,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-29T01:10:47.707257Z","finishedAt":"2026-09-29T01:34:04.230598Z"},{"task":"path-tracing","round":2,"trial":"path-tracing__PaYVihG","status":"PASS","timedOut":false,"exception":null,"qualifiedCompactions":11,"compactions":11,"droppedCalls":84,"truncatedResults":12,"medianResidualTokens":51192,"requests":86,"inputTokens":4098746,"outputTokens":97046,"totalTokens":4195792,"openaiCostUsd":0.17165920499999998,"jevCostUsd":0.00264936,"durationSec":1543.065,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-29T02:55:29.773754Z","finishedAt":"2026-09-29T03:21:12.838734Z"},{"task":"path-tracing","round":3,"trial":"path-tracing__cg2BAov","status":"PASS","timedOut":false,"exception":null,"qualifiedCompactions":7,"compactions":7,"droppedCalls":61,"truncatedResults":8,"medianResidualTokens":44552,"requests":69,"inputTokens":2816436,"outputTokens":60971,"totalTokens":2877407,"openaiCostUsd":0.10374480999999998,"jevCostUsd":0.00152313,"durationSec":865.27,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-29T04:52:41.732042Z","finishedAt":"2026-09-29T05:07:07.002188Z"}]},{"task":"build-pov-ray","group":"primary","baselineCompactionRate":1,"passes":4,"scored":4,"errors":0,"running":0,"queued":0,"passRate":1,"compactionRate":0.75,"trials":[{"task":"build-pov-ray","round":0,"trial":"build-pov-ray__Su5ifKc","status":"PASS","timedOut":false,"exception":null,"qualifiedCompactions":1,"compactions":1,"droppedCalls":47,"truncatedResults":4,"medianResidualTokens":9600,"requests":36,"inputTokens":932316,"outputTokens":11025,"totalTokens":943341,"openaiCostUsd":0.022444005,"jevCostUsd":0.000574224,"durationSec":264.978,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-28T23:11:04.929170Z","finishedAt":"2026-09-28T23:15:29.907160Z"},{"task":"build-pov-ray","round":1,"trial":"build-pov-ray__mGjb5kd","status":"PASS","timedOut":false,"exception":null,"qualifiedCompactions":0,"compactions":0,"droppedCalls":0,"truncatedResults":0,"medianResidualTokens":null,"requests":41,"inputTokens":1087032,"outputTokens":7880,"totalTokens":1094912,"openaiCostUsd":0.020204310000000003,"jevCostUsd":0,"durationSec":196.44,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-29T01:07:28.632762Z","finishedAt":"2026-09-29T01:10:45.072645Z"},{"task":"build-pov-ray","round":2,"trial":"build-pov-ray__Q6Nx8ko","status":"PASS","timedOut":false,"exception":null,"qualifiedCompactions":2,"compactions":2,"droppedCalls":70,"truncatedResults":3,"medianResidualTokens":14046,"requests":45,"inputTokens":877815,"outputTokens":11506,"totalTokens":889321,"openaiCostUsd":0.027402370000000002,"jevCostUsd":0.0007717500000000001,"durationSec":278.48,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-29T02:58:02.498642Z","finishedAt":"2026-09-29T03:02:40.978127Z"},{"task":"build-pov-ray","round":3,"trial":"build-pov-ray__6tjqMo5","status":"PASS","timedOut":false,"exception":null,"qualifiedCompactions":2,"compactions":2,"droppedCalls":59,"truncatedResults":0,"medianResidualTokens":22490.5,"requests":24,"inputTokens":603166,"outputTokens":7813,"totalTokens":610979,"openaiCostUsd":0.021067324999999998,"jevCostUsd":0.0006479760000000001,"durationSec":207.574,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-29T04:49:11.237393Z","finishedAt":"2026-09-29T04:52:38.811039Z"}]},{"task":"mcmc-sampling-stan","group":"primary","baselineCompactionRate":0.875,"passes":0,"scored":4,"errors":0,"running":0,"queued":0,"passRate":0,"compactionRate":1,"trials":[{"task":"mcmc-sampling-stan","round":0,"trial":"mcmc-sampling-stan__dipDkpb","status":"FAIL","timedOut":false,"exception":null,"qualifiedCompactions":1,"compactions":1,"droppedCalls":16,"truncatedResults":0,"medianResidualTokens":6660,"requests":19,"inputTokens":432667,"outputTokens":6755,"totalTokens":439422,"openaiCostUsd":0.014159190000000002,"jevCostUsd":0.00023515800000000001,"durationSec":936.006,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-28T23:15:32.472378Z","finishedAt":"2026-09-28T23:31:08.478503Z"},{"task":"mcmc-sampling-stan","round":1,"trial":"mcmc-sampling-stan__pVAjatE","status":"FAIL","timedOut":false,"exception":null,"qualifiedCompactions":2,"compactions":2,"droppedCalls":22,"truncatedResults":3,"medianResidualTokens":21023,"requests":23,"inputTokens":577490,"outputTokens":8229,"totalTokens":585719,"openaiCostUsd":0.024336620000000003,"jevCostUsd":0.000357378,"durationSec":1551.871,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-29T01:02:42.559196Z","finishedAt":"2026-09-29T01:28:34.430220Z"},{"task":"mcmc-sampling-stan","round":2,"trial":"mcmc-sampling-stan__qqZqp6w","status":"FAIL","timedOut":false,"exception":null,"qualifiedCompactions":1,"compactions":1,"droppedCalls":16,"truncatedResults":0,"medianResidualTokens":15631,"requests":17,"inputTokens":280575,"outputTokens":7010,"totalTokens":287585,"openaiCostUsd":0.014179730000000001,"jevCostUsd":0.00022919400000000003,"durationSec":646.23,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-29T03:00:32.323538Z","finishedAt":"2026-09-29T03:11:18.553023Z"},{"task":"mcmc-sampling-stan","round":3,"trial":"mcmc-sampling-stan__3AmUS9X","status":"FAIL","timedOut":false,"exception":null,"qualifiedCompactions":1,"compactions":1,"droppedCalls":11,"truncatedResults":0,"medianResidualTokens":5116,"requests":11,"inputTokens":183828,"outputTokens":5694,"totalTokens":189522,"openaiCostUsd":0.011028775000000001,"jevCostUsd":0.00017052000000000001,"durationSec":824.613,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-29T04:40:49.447074Z","finishedAt":"2026-09-29T04:54:34.060291Z"}]},{"task":"rstan-to-pystan","group":"placebo","baselineCompactionRate":0,"passes":4,"scored":4,"errors":0,"running":0,"queued":0,"passRate":1,"compactionRate":0,"trials":[{"task":"rstan-to-pystan","round":0,"trial":"rstan-to-pystan__aFYDPbv","status":"PASS","timedOut":false,"exception":null,"qualifiedCompactions":0,"compactions":0,"droppedCalls":0,"truncatedResults":0,"medianResidualTokens":null,"requests":22,"inputTokens":529095,"outputTokens":7466,"totalTokens":536561,"openaiCostUsd":0.013763174999999999,"jevCostUsd":0,"durationSec":828.158,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-28T23:18:09.800559Z","finishedAt":"2026-09-28T23:31:57.958520Z"},{"task":"rstan-to-pystan","round":1,"trial":"rstan-to-pystan__AhnsQsC","status":"PASS","timedOut":false,"exception":null,"qualifiedCompactions":0,"compactions":0,"droppedCalls":0,"truncatedResults":0,"medianResidualTokens":null,"requests":19,"inputTokens":275990,"outputTokens":7275,"totalTokens":283265,"openaiCostUsd":0.01078886,"jevCostUsd":0,"durationSec":522.186,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-29T00:58:43.640652Z","finishedAt":"2026-09-29T01:07:25.826423Z"},{"task":"rstan-to-pystan","round":2,"trial":"rstan-to-pystan__cKh3864","status":"PASS","timedOut":false,"exception":null,"qualifiedCompactions":0,"compactions":0,"droppedCalls":0,"truncatedResults":0,"medianResidualTokens":null,"requests":22,"inputTokens":490370,"outputTokens":6621,"totalTokens":496991,"openaiCostUsd":0.012989190000000001,"jevCostUsd":0,"durationSec":526.335,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-29T03:02:43.749445Z","finishedAt":"2026-09-29T03:11:30.084060Z"},{"task":"rstan-to-pystan","round":3,"trial":"rstan-to-pystan__mMGZwJC","status":"PASS","timedOut":false,"exception":null,"qualifiedCompactions":0,"compactions":0,"droppedCalls":0,"truncatedResults":0,"medianResidualTokens":null,"requests":23,"inputTokens":335682,"outputTokens":6369,"totalTokens":342051,"openaiCostUsd":0.011110845,"jevCostUsd":0,"durationSec":526.699,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-29T04:40:21.562297Z","finishedAt":"2026-09-29T04:49:08.261684Z"}]},{"task":"distribution-search","group":"placebo","baselineCompactionRate":0,"passes":4,"scored":4,"errors":0,"running":0,"queued":0,"passRate":1,"compactionRate":0,"trials":[{"task":"distribution-search","round":0,"trial":"distribution-search__E2jv4ZK","status":"PASS","timedOut":false,"exception":null,"qualifiedCompactions":0,"compactions":0,"droppedCalls":0,"truncatedResults":0,"medianResidualTokens":null,"requests":7,"inputTokens":33841,"outputTokens":5355,"totalTokens":39196,"openaiCostUsd":0.003907669999999999,"jevCostUsd":0,"durationSec":91.684,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-28T23:25:24.473046Z","finishedAt":"2026-09-28T23:26:56.157108Z"},{"task":"distribution-search","round":1,"trial":"distribution-search__nvbcFvt","status":"PASS","timedOut":false,"exception":null,"qualifiedCompactions":0,"compactions":0,"droppedCalls":0,"truncatedResults":0,"medianResidualTokens":null,"requests":5,"inputTokens":17114,"outputTokens":3538,"totalTokens":20652,"openaiCostUsd":0.00253443,"jevCostUsd":0,"durationSec":63.521,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-29T00:57:37.429850Z","finishedAt":"2026-09-29T00:58:40.950419Z"},{"task":"distribution-search","round":2,"trial":"distribution-search__8JsSMLH","status":"PASS","timedOut":false,"exception":null,"qualifiedCompactions":0,"compactions":0,"droppedCalls":0,"truncatedResults":0,"medianResidualTokens":null,"requests":5,"inputTokens":25500,"outputTokens":5182,"totalTokens":30682,"openaiCostUsd":0.0036351000000000005,"jevCostUsd":0,"durationSec":81.186,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-29T03:11:21.178367Z","finishedAt":"2026-09-29T03:12:42.364483Z"},{"task":"distribution-search","round":3,"trial":"distribution-search__GecKgnR","status":"PASS","timedOut":false,"exception":null,"qualifiedCompactions":0,"compactions":0,"droppedCalls":0,"truncatedResults":0,"medianResidualTokens":null,"requests":5,"inputTokens":17435,"outputTokens":3652,"totalTokens":21087,"openaiCostUsd":0.002633855,"jevCostUsd":0,"durationSec":66.75,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-29T04:39:39.830751Z","finishedAt":"2026-09-29T04:40:46.580840Z"}]},{"task":"mteb-leaderboard","group":"primary","baselineCompactionRate":0.875,"passes":2,"scored":4,"errors":0,"running":0,"queued":0,"passRate":0.5,"compactionRate":0.75,"trials":[{"task":"mteb-leaderboard","round":0,"trial":"mteb-leaderboard__b6znmdo","status":"PASS","timedOut":false,"exception":null,"qualifiedCompactions":3,"compactions":3,"droppedCalls":109,"truncatedResults":0,"medianResidualTokens":15762,"requests":124,"inputTokens":3172646,"outputTokens":25833,"totalTokens":3198479,"openaiCostUsd":0.06319339499999999,"jevCostUsd":0.001229928,"durationSec":910.298,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-28T23:27:02.109347Z","finishedAt":"2026-09-28T23:42:12.407272Z"},{"task":"mteb-leaderboard","round":1,"trial":"mteb-leaderboard__BaMYYH5","status":"FAIL","timedOut":false,"exception":null,"qualifiedCompactions":1,"compactions":1,"droppedCalls":34,"truncatedResults":0,"medianResidualTokens":11580,"requests":46,"inputTokens":1136882,"outputTokens":14355,"totalTokens":1151237,"openaiCostUsd":0.028434595000000007,"jevCostUsd":0.000448266,"durationSec":329.56,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-29T00:57:07.402382Z","finishedAt":"2026-09-29T01:02:36.962984Z"},{"task":"mteb-leaderboard","round":2,"trial":"mteb-leaderboard__rrmwzL3","status":"FAIL","timedOut":false,"exception":null,"qualifiedCompactions":2,"compactions":2,"droppedCalls":30,"truncatedResults":0,"medianResidualTokens":16850.5,"requests":50,"inputTokens":1301695,"outputTokens":13641,"totalTokens":1315336,"openaiCostUsd":0.03536353000000001,"jevCostUsd":0.00046053,"durationSec":340.751,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-29T03:11:32.730755Z","finishedAt":"2026-09-29T03:17:13.481710Z"},{"task":"mteb-leaderboard","round":3,"trial":"mteb-leaderboard__eXZFMTA","status":"PASS","timedOut":false,"exception":null,"qualifiedCompactions":0,"compactions":0,"droppedCalls":0,"truncatedResults":0,"medianResidualTokens":null,"requests":25,"inputTokens":257462,"outputTokens":4842,"totalTokens":262304,"openaiCostUsd":0.00751466,"jevCostUsd":0,"durationSec":123.792,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-29T04:38:14.992723Z","finishedAt":"2026-09-29T04:40:18.784519Z"}]},{"task":"portfolio-optimization","group":"placebo","baselineCompactionRate":0,"passes":4,"scored":4,"errors":0,"running":0,"queued":0,"passRate":1,"compactionRate":0,"trials":[{"task":"portfolio-optimization","round":0,"trial":"portfolio-optimization__vdgX3dE","status":"PASS","timedOut":false,"exception":null,"qualifiedCompactions":0,"compactions":0,"droppedCalls":0,"truncatedResults":0,"medianResidualTokens":null,"requests":7,"inputTokens":38385,"outputTokens":3589,"totalTokens":41974,"openaiCostUsd":0.00304757,"jevCostUsd":0,"durationSec":176.498,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-28T23:31:11.096489Z","finishedAt":"2026-09-28T23:34:07.594874Z"},{"task":"portfolio-optimization","round":1,"trial":"portfolio-optimization__T7cEJuq","status":"PASS","timedOut":false,"exception":null,"qualifiedCompactions":0,"compactions":0,"droppedCalls":0,"truncatedResults":0,"medianResidualTokens":null,"requests":8,"inputTokens":46811,"outputTokens":4736,"totalTokens":51547,"openaiCostUsd":0.0038809749999999996,"jevCostUsd":0,"durationSec":195.576,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-29T00:54:19.071046Z","finishedAt":"2026-09-29T00:57:34.647670Z"},{"task":"portfolio-optimization","round":2,"trial":"portfolio-optimization__8howwT9","status":"PASS","timedOut":false,"exception":null,"qualifiedCompactions":0,"compactions":0,"droppedCalls":0,"truncatedResults":0,"medianResidualTokens":null,"requests":15,"inputTokens":133175,"outputTokens":8527,"totalTokens":141702,"openaiCostUsd":0.007132594999999999,"jevCostUsd":0,"durationSec":236.946,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-29T03:12:45.029465Z","finishedAt":"2026-09-29T03:16:41.975107Z"},{"task":"portfolio-optimization","round":3,"trial":"portfolio-optimization__kaPfdjM","status":"PASS","timedOut":false,"exception":null,"qualifiedCompactions":0,"compactions":0,"droppedCalls":0,"truncatedResults":0,"medianResidualTokens":null,"requests":8,"inputTokens":44772,"outputTokens":3992,"totalTokens":48764,"openaiCostUsd":0.00338083,"jevCostUsd":0,"durationSec":192.519,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-29T04:36:24.564204Z","finishedAt":"2026-09-29T04:39:37.083420Z"}]},{"task":"reshard-c4-data","group":"other","baselineCompactionRate":0.125,"passes":4,"scored":4,"errors":0,"running":0,"queued":0,"passRate":1,"compactionRate":0,"trials":[{"task":"reshard-c4-data","round":0,"trial":"reshard-c4-data__ZjEgw6z","status":"PASS","timedOut":false,"exception":null,"qualifiedCompactions":0,"compactions":0,"droppedCalls":0,"truncatedResults":0,"medianResidualTokens":null,"requests":21,"inputTokens":405179,"outputTokens":20538,"totalTokens":425717,"openaiCostUsd":0.017318185,"jevCostUsd":0,"durationSec":285.127,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-28T23:32:00.569030Z","finishedAt":"2026-09-28T23:36:45.696450Z"},{"task":"reshard-c4-data","round":1,"trial":"reshard-c4-data__aSDsfrE","status":"PASS","timedOut":false,"exception":null,"qualifiedCompactions":0,"compactions":0,"droppedCalls":0,"truncatedResults":0,"medianResidualTokens":null,"requests":14,"inputTokens":293970,"outputTokens":26709,"totalTokens":320679,"openaiCostUsd":0.019781330000000003,"jevCostUsd":0,"durationSec":323.478,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-29T00:48:52.845426Z","finishedAt":"2026-09-29T00:54:16.323431Z"},{"task":"reshard-c4-data","round":2,"trial":"reshard-c4-data__D9YocFS","status":"PASS","timedOut":false,"exception":null,"qualifiedCompactions":0,"compactions":0,"droppedCalls":0,"truncatedResults":0,"medianResidualTokens":null,"requests":14,"inputTokens":299071,"outputTokens":20779,"totalTokens":319850,"openaiCostUsd":0.01671945,"jevCostUsd":0,"durationSec":296.351,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-29T03:16:44.645490Z","finishedAt":"2026-09-29T03:21:40.996279Z"},{"task":"reshard-c4-data","round":3,"trial":"reshard-c4-data__R5T4tnQ","status":"PASS","timedOut":false,"exception":null,"qualifiedCompactions":0,"compactions":0,"droppedCalls":0,"truncatedResults":0,"medianResidualTokens":null,"requests":19,"inputTokens":325701,"outputTokens":20192,"totalTokens":345893,"openaiCostUsd":0.016094565,"jevCostUsd":0,"durationSec":310.875,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-29T04:33:01.347095Z","finishedAt":"2026-09-29T04:38:12.222804Z"}]},{"task":"sam-cell-seg","group":"placebo","baselineCompactionRate":0,"passes":2,"scored":4,"errors":0,"running":0,"queued":0,"passRate":0.5,"compactionRate":0,"trials":[{"task":"sam-cell-seg","round":0,"trial":"sam-cell-seg__PSfWmGB","status":"PASS","timedOut":false,"exception":null,"qualifiedCompactions":0,"compactions":0,"droppedCalls":0,"truncatedResults":0,"medianResidualTokens":null,"requests":9,"inputTokens":135499,"outputTokens":15952,"totalTokens":151451,"openaiCostUsd":0.012041095,"jevCostUsd":0,"durationSec":240.938,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-28T23:34:10.233146Z","finishedAt":"2026-09-28T23:38:11.171969Z"},{"task":"sam-cell-seg","round":1,"trial":"sam-cell-seg__irfaUJN","status":"PASS","timedOut":false,"exception":null,"qualifiedCompactions":0,"compactions":0,"droppedCalls":0,"truncatedResults":0,"medianResidualTokens":null,"requests":12,"inputTokens":252218,"outputTokens":21414,"totalTokens":273632,"openaiCostUsd":0.016906325,"jevCostUsd":0,"durationSec":309.992,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-29T00:43:40.130177Z","finishedAt":"2026-09-29T00:48:50.122228Z"},{"task":"sam-cell-seg","round":2,"trial":"sam-cell-seg__rVrYU8P","status":"FAIL","timedOut":false,"exception":null,"qualifiedCompactions":0,"compactions":0,"droppedCalls":0,"truncatedResults":0,"medianResidualTokens":null,"requests":5,"inputTokens":45879,"outputTokens":8739,"totalTokens":54618,"openaiCostUsd":0.006375125000000001,"jevCostUsd":0,"durationSec":174.146,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-29T03:17:16.096678Z","finishedAt":"2026-09-29T03:20:10.242721Z"},{"task":"sam-cell-seg","round":3,"trial":"sam-cell-seg__EtK4rg4","status":"FAIL","timedOut":false,"exception":null,"qualifiedCompactions":0,"compactions":0,"droppedCalls":0,"truncatedResults":0,"medianResidualTokens":null,"requests":9,"inputTokens":117547,"outputTokens":15044,"totalTokens":132591,"openaiCostUsd":0.011113060000000001,"jevCostUsd":0,"durationSec":243.571,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-29T04:28:54.966386Z","finishedAt":"2026-09-29T04:32:58.537975Z"}]},{"task":"train-fasttext","group":"other","baselineCompactionRate":0.375,"passes":0,"scored":4,"errors":0,"running":0,"queued":0,"passRate":0,"compactionRate":0,"trials":[{"task":"train-fasttext","round":0,"trial":"train-fasttext__wXrQ3vp","status":"FAIL","timedOut":true,"exception":null,"qualifiedCompactions":0,"compactions":0,"droppedCalls":0,"truncatedResults":0,"medianResidualTokens":null,"requests":13,"inputTokens":124760,"outputTokens":4071,"totalTokens":128831,"openaiCostUsd":0.007319775000000001,"jevCostUsd":0,"durationSec":4009.133,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-28T23:36:48.226278Z","finishedAt":"2026-09-29T00:43:37.359516Z"},{"task":"train-fasttext","round":1,"trial":"train-fasttext__wXt2iDY","status":"FAIL","timedOut":true,"exception":null,"qualifiedCompactions":0,"compactions":0,"droppedCalls":0,"truncatedResults":0,"medianResidualTokens":null,"requests":14,"inputTokens":299258,"outputTokens":7975,"totalTokens":307233,"openaiCostUsd":0.01218669,"jevCostUsd":0,"durationSec":4576.869,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-29T00:37:02.588314Z","finishedAt":"2026-09-29T01:53:19.457898Z"},{"task":"train-fasttext","round":2,"trial":"train-fasttext__mPzNTJE","status":"FAIL","timedOut":true,"exception":null,"qualifiedCompactions":0,"compactions":0,"droppedCalls":0,"truncatedResults":0,"medianResidualTokens":null,"requests":21,"inputTokens":544446,"outputTokens":7173,"totalTokens":551619,"openaiCostUsd":0.014318695000000001,"jevCostUsd":0,"durationSec":4119.118,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-29T03:20:12.925462Z","finishedAt":"2026-09-29T04:28:52.043705Z"},{"task":"train-fasttext","round":3,"trial":"train-fasttext__dZFxMjA","status":"FAIL","timedOut":true,"exception":null,"qualifiedCompactions":0,"compactions":0,"droppedCalls":0,"truncatedResults":0,"medianResidualTokens":null,"requests":17,"inputTokens":366799,"outputTokens":7694,"totalTokens":374493,"openaiCostUsd":0.01313664,"jevCostUsd":0,"durationSec":4080.464,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-29T03:54:07.952371Z","finishedAt":"2026-09-29T05:02:08.416016Z"}]},{"task":"winning-avg-corewars","group":"other","baselineCompactionRate":0.375,"passes":3,"scored":4,"errors":0,"running":0,"queued":0,"passRate":0.75,"compactionRate":1,"trials":[{"task":"winning-avg-corewars","round":0,"trial":"winning-avg-corewars__hoLCRZE","status":"PASS","timedOut":false,"exception":null,"qualifiedCompactions":1,"compactions":1,"droppedCalls":47,"truncatedResults":0,"medianResidualTokens":26626,"requests":46,"inputTokens":1252656,"outputTokens":30536,"totalTokens":1283192,"openaiCostUsd":0.03658861000000001,"jevCostUsd":0.000666792,"durationSec":613.096,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-28T23:38:13.757183Z","finishedAt":"2026-09-28T23:48:26.853531Z"},{"task":"winning-avg-corewars","round":1,"trial":"winning-avg-corewars__rxmF3zk","status":"PASS","timedOut":false,"exception":null,"qualifiedCompactions":43,"compactions":43,"droppedCalls":424,"truncatedResults":22,"medianResidualTokens":129997,"requests":275,"inputTokens":27275011,"outputTokens":228512,"totalTokens":27503523,"openaiCostUsd":1.0163666850000004,"jevCostUsd":0.008044848000000002,"durationSec":2842.009,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-29T00:09:42.674154Z","finishedAt":"2026-09-29T00:57:04.683992Z"},{"task":"winning-avg-corewars","round":2,"trial":"winning-avg-corewars__SCYN8LB","status":"PASS","timedOut":false,"exception":null,"qualifiedCompactions":1,"compactions":1,"droppedCalls":67,"truncatedResults":2,"medianResidualTokens":25500,"requests":68,"inputTokens":1780466,"outputTokens":31254,"totalTokens":1811720,"openaiCostUsd":0.04244095000000001,"jevCostUsd":0.000713832,"durationSec":453.269,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-29T03:21:15.491862Z","finishedAt":"2026-09-29T03:28:48.760983Z"},{"task":"winning-avg-corewars","round":3,"trial":"winning-avg-corewars__GgCd9Si","status":"FAIL","timedOut":false,"exception":null,"qualifiedCompactions":17,"compactions":17,"droppedCalls":149,"truncatedResults":2,"medianResidualTokens":86651,"requests":145,"inputTokens":10553732,"outputTokens":208847,"totalTokens":10762579,"openaiCostUsd":0.41936057499999996,"jevCostUsd":0.002689554,"durationSec":2634.906,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-29T03:52:26.873280Z","finishedAt":"2026-09-29T04:36:21.779060Z"}]},{"task":"dna-assembly","group":"placebo","baselineCompactionRate":0,"passes":0,"scored":4,"errors":0,"running":0,"queued":0,"passRate":0,"compactionRate":0.75,"trials":[{"task":"dna-assembly","round":0,"trial":"dna-assembly__XFBk6va","status":"FAIL","timedOut":false,"exception":null,"qualifiedCompactions":1,"compactions":1,"droppedCalls":19,"truncatedResults":0,"medianResidualTokens":27318,"requests":25,"inputTokens":532340,"outputTokens":30049,"totalTokens":562389,"openaiCostUsd":0.029948065000000003,"jevCostUsd":0.000280812,"durationSec":382.348,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-28T23:42:15.058116Z","finishedAt":"2026-09-28T23:48:37.406459Z"},{"task":"dna-assembly","round":1,"trial":"dna-assembly__6KiNkaN","status":"FAIL","timedOut":true,"exception":null,"qualifiedCompactions":0,"compactions":0,"droppedCalls":0,"truncatedResults":0,"medianResidualTokens":null,"requests":10,"inputTokens":64640,"outputTokens":3128,"totalTokens":67768,"openaiCostUsd":0.0032366,"jevCostUsd":0,"durationSec":1837.393,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-29T00:06:22.388917Z","finishedAt":"2026-09-29T00:36:59.781350Z"},{"task":"dna-assembly","round":2,"trial":"dna-assembly__uvfL873","status":"FAIL","timedOut":false,"exception":null,"qualifiedCompactions":1,"compactions":1,"droppedCalls":18,"truncatedResults":0,"medianResidualTokens":14634,"requests":24,"inputTokens":443928,"outputTokens":24657,"totalTokens":468585,"openaiCostUsd":0.025256545,"jevCostUsd":0.000296184,"durationSec":279.432,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-29T03:21:43.697265Z","finishedAt":"2026-09-29T03:26:23.129255Z"},{"task":"dna-assembly","round":3,"trial":"dna-assembly__spDetTA","status":"FAIL","timedOut":false,"exception":null,"qualifiedCompactions":1,"compactions":1,"droppedCalls":22,"truncatedResults":1,"medianResidualTokens":35483,"requests":31,"inputTokens":671844,"outputTokens":40301,"totalTokens":712145,"openaiCostUsd":0.037080455000000005,"jevCostUsd":0.000389298,"durationSec":427.036,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-29T03:46:58.133322Z","finishedAt":"2026-09-29T03:54:05.169506Z"}]},{"task":"dna-insert","group":"other","baselineCompactionRate":0.125,"passes":0,"scored":4,"errors":0,"running":0,"queued":0,"passRate":0,"compactionRate":0,"trials":[{"task":"dna-insert","round":0,"trial":"dna-insert__BYnPtfN","status":"FAIL","timedOut":false,"exception":null,"qualifiedCompactions":0,"compactions":0,"droppedCalls":0,"truncatedResults":0,"medianResidualTokens":null,"requests":24,"inputTokens":264423,"outputTokens":9579,"totalTokens":274002,"openaiCostUsd":0.009746075000000002,"jevCostUsd":0,"durationSec":155.542,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-28T23:48:29.491604Z","finishedAt":"2026-09-28T23:51:05.033963Z"},{"task":"dna-insert","round":1,"trial":"dna-insert__CSrSfNm","status":"FAIL","timedOut":false,"exception":null,"qualifiedCompactions":0,"compactions":0,"droppedCalls":0,"truncatedResults":0,"medianResidualTokens":null,"requests":22,"inputTokens":207907,"outputTokens":10129,"totalTokens":218036,"openaiCostUsd":0.00915373,"jevCostUsd":0,"durationSec":152.451,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-29T00:03:47.235970Z","finishedAt":"2026-09-29T00:06:19.686494Z"},{"task":"dna-insert","round":2,"trial":"dna-insert__g2GwNgM","status":"FAIL","timedOut":false,"exception":null,"qualifiedCompactions":0,"compactions":0,"droppedCalls":0,"truncatedResults":0,"medianResidualTokens":null,"requests":24,"inputTokens":288876,"outputTokens":14759,"totalTokens":303635,"openaiCostUsd":0.012957,"jevCostUsd":0,"durationSec":189.665,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-29T03:26:25.887700Z","finishedAt":"2026-09-29T03:29:35.552064Z"},{"task":"dna-insert","round":3,"trial":"dna-insert__539yuML","status":"FAIL","timedOut":false,"exception":null,"qualifiedCompactions":0,"compactions":0,"droppedCalls":0,"truncatedResults":0,"medianResidualTokens":null,"requests":15,"inputTokens":110821,"outputTokens":6406,"totalTokens":117227,"openaiCostUsd":0.005880870000000001,"jevCostUsd":0,"durationSec":111.533,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-29T03:45:03.699884Z","finishedAt":"2026-09-29T03:46:55.232202Z"}]},{"task":"llm-inference-batching-scheduler","group":"other","baselineCompactionRate":0.125,"passes":4,"scored":4,"errors":0,"running":0,"queued":0,"passRate":1,"compactionRate":0.75,"trials":[{"task":"llm-inference-batching-scheduler","round":0,"trial":"llm-inference-batching-scheduler__Sqw5kjh","status":"PASS","timedOut":false,"exception":null,"qualifiedCompactions":0,"compactions":0,"droppedCalls":0,"truncatedResults":0,"medianResidualTokens":null,"requests":12,"inputTokens":268071,"outputTokens":10537,"totalTokens":278608,"openaiCostUsd":0.011940305,"jevCostUsd":0,"durationSec":133.502,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-28T23:48:40.087790Z","finishedAt":"2026-09-28T23:50:53.589574Z"},{"task":"llm-inference-batching-scheduler","round":1,"trial":"llm-inference-batching-scheduler__EgRysrp","status":"PASS","timedOut":false,"exception":null,"qualifiedCompactions":1,"compactions":1,"droppedCalls":22,"truncatedResults":1,"medianResidualTokens":22368,"requests":29,"inputTokens":741005,"outputTokens":31373,"totalTokens":772378,"openaiCostUsd":0.03156838,"jevCostUsd":0.000501942,"durationSec":491.9,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-29T00:01:28.036254Z","finishedAt":"2026-09-29T00:09:39.936421Z"},{"task":"llm-inference-batching-scheduler","round":2,"trial":"llm-inference-batching-scheduler__5jqCFkM","status":"PASS","timedOut":false,"exception":null,"qualifiedCompactions":1,"compactions":1,"droppedCalls":12,"truncatedResults":0,"medianResidualTokens":19329,"requests":15,"inputTokens":331953,"outputTokens":17508,"totalTokens":349461,"openaiCostUsd":0.019680575,"jevCostUsd":0.00030416400000000005,"durationSec":435.108,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-29T03:28:51.509059Z","finishedAt":"2026-09-29T03:36:06.617585Z"},{"task":"llm-inference-batching-scheduler","round":3,"trial":"llm-inference-batching-scheduler__9u3KP3e","status":"PASS","timedOut":false,"exception":null,"qualifiedCompactions":1,"compactions":1,"droppedCalls":21,"truncatedResults":0,"medianResidualTokens":15145,"requests":22,"inputTokens":522494,"outputTokens":22385,"totalTokens":544879,"openaiCostUsd":0.02418358,"jevCostUsd":0.00045595200000000003,"durationSec":539.782,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-29T03:43:24.325264Z","finishedAt":"2026-09-29T03:52:24.107699Z"}]},{"task":"mteb-retrieve","group":"placebo","baselineCompactionRate":0,"passes":4,"scored":4,"errors":0,"running":0,"queued":0,"passRate":1,"compactionRate":0,"trials":[{"task":"mteb-retrieve","round":0,"trial":"mteb-retrieve__36NhPha","status":"PASS","timedOut":false,"exception":null,"qualifiedCompactions":0,"compactions":0,"droppedCalls":0,"truncatedResults":0,"medianResidualTokens":null,"requests":19,"inputTokens":100259,"outputTokens":3482,"totalTokens":103741,"openaiCostUsd":0.003780155,"jevCostUsd":0,"durationSec":222.802,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-28T23:50:56.240699Z","finishedAt":"2026-09-28T23:54:39.042198Z"},{"task":"mteb-retrieve","round":1,"trial":"mteb-retrieve__kQ57cQr","status":"PASS","timedOut":false,"exception":null,"qualifiedCompactions":0,"compactions":0,"droppedCalls":0,"truncatedResults":0,"medianResidualTokens":null,"requests":13,"inputTokens":51128,"outputTokens":2429,"totalTokens":53557,"openaiCostUsd":0.002523825,"jevCostUsd":0,"durationSec":158.214,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-28T23:58:47.085193Z","finishedAt":"2026-09-29T00:01:25.299523Z"},{"task":"mteb-retrieve","round":2,"trial":"mteb-retrieve__yNuKDxw","status":"PASS","timedOut":false,"exception":null,"qualifiedCompactions":0,"compactions":0,"droppedCalls":0,"truncatedResults":0,"medianResidualTokens":null,"requests":13,"inputTokens":53724,"outputTokens":2185,"totalTokens":55909,"openaiCostUsd":0.0024325,"jevCostUsd":0,"durationSec":167.78,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-29T03:29:38.327942Z","finishedAt":"2026-09-29T03:32:26.107528Z"},{"task":"mteb-retrieve","round":3,"trial":"mteb-retrieve__hhyukaU","status":"PASS","timedOut":false,"exception":null,"qualifiedCompactions":0,"compactions":0,"droppedCalls":0,"truncatedResults":0,"medianResidualTokens":null,"requests":12,"inputTokens":55953,"outputTokens":2615,"totalTokens":58568,"openaiCostUsd":0.0028184449999999997,"jevCostUsd":0,"durationSec":167.961,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-29T03:42:12.988913Z","finishedAt":"2026-09-29T03:45:00.949790Z"}]},{"task":"protein-assembly","group":"primary","baselineCompactionRate":0.5,"passes":0,"scored":4,"errors":0,"running":0,"queued":0,"passRate":0,"compactionRate":1,"trials":[{"task":"protein-assembly","round":0,"trial":"protein-assembly__wcbKdx7","status":"FAIL","timedOut":false,"exception":null,"qualifiedCompactions":2,"compactions":2,"droppedCalls":39,"truncatedResults":4,"medianResidualTokens":27151,"requests":43,"inputTokens":1222472,"outputTokens":36291,"totalTokens":1258763,"openaiCostUsd":0.04468921,"jevCostUsd":0.00073479,"durationSec":456.616,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-28T23:51:07.790430Z","finishedAt":"2026-09-28T23:58:44.406281Z"},{"task":"protein-assembly","round":1,"trial":"protein-assembly__doiPw3q","status":"FAIL","timedOut":false,"exception":null,"qualifiedCompactions":1,"compactions":1,"droppedCalls":29,"truncatedResults":4,"medianResidualTokens":19074,"requests":33,"inputTokens":792045,"outputTokens":26223,"totalTokens":818268,"openaiCostUsd":0.02957892,"jevCostUsd":0.00047880000000000004,"durationSec":542.829,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-28T23:54:41.733478Z","finishedAt":"2026-09-29T00:03:44.562620Z"},{"task":"protein-assembly","round":2,"trial":"protein-assembly__P5qwSsd","status":"FAIL","timedOut":false,"exception":null,"qualifiedCompactions":2,"compactions":2,"droppedCalls":43,"truncatedResults":4,"medianResidualTokens":28810,"requests":45,"inputTokens":1191767,"outputTokens":37064,"totalTokens":1228831,"openaiCostUsd":0.04475896500000001,"jevCostUsd":0.0007222320000000001,"durationSec":581.361,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-29T03:32:28.923548Z","finishedAt":"2026-09-29T03:42:10.284183Z"},{"task":"protein-assembly","round":3,"trial":"protein-assembly__i6wyN7F","status":"FAIL","timedOut":false,"exception":null,"qualifiedCompactions":1,"compactions":1,"droppedCalls":23,"truncatedResults":2,"medianResidualTokens":28576,"requests":34,"inputTokens":822471,"outputTokens":38423,"totalTokens":860894,"openaiCostUsd":0.03774617000000001,"jevCostUsd":0.00040110000000000005,"durationSec":432.193,"actualModels":["gpt-6-luna"],"startedAt":"2026-09-29T03:36:09.325493Z","finishedAt":"2026-09-29T03:43:21.518796Z"}]}],"audit":{"ok":false,"errors":["Unknown Jev trial smoke__SdXsb4Y","Unknown Jev trial smoke__SdXsb4Y","Unknown Jev trial smoke__SdXsb4Y"]}}