{"experiment":"rmsnorm","model":"jev","arm":"baseline","run":1,"concurrency":1,"request_count":74,"source_file":"analysis/baseline-measured-1.jsonl","source_sha256":"8d6f228adbfa70b989f7c543a34f3a8910867f26ea8575e25c59d822c571a21c","response_semantics_sha256":"487c9568dd218821352340c14bf4816157b94c55b95a78c3077de168c1799638","request_ids":["original-policy-01-0","original-policy-01-1","original-policy-02-0","original-policy-02-1","original-policy-03-0","original-policy-03-1","original-policy-04-0","original-policy-04-1","original-policy-05-0","original-policy-05-1","original-policy-06-0","original-policy-06-1","original-adequacy-01-0","original-adequacy-01-1","original-adequacy-02-0","original-adequacy-02-1","original-adequacy-03-0","original-adequacy-03-1","original-adequacy-04-0","original-adequacy-04-1","original-adequacy-05-0","original-adequacy-05-1","original-adequacy-06-0","original-adequacy-06-1","easy-fact-00","easy-fact-01","easy-fact-02","easy-fact-03","easy-fact-04","easy-fact-05","easy-fact-06","easy-fact-07","easy-fact-08","easy-fact-09","easy-fact-10","easy-fact-11","hard-opus-a-long_policy-11","hard-opus-a-long_policy-13","hard-opus-a-long_policy-19","hard-opus-a-probability-03","hard-opus-a-probability-08","hard-opus-a-temporal_numeric-03","hard-opus-a-temporal_numeric-06","hard-opus-a-temporal_numeric-09","hard-opus-b-multi_hop-08","hard-opus-b-probability-03","hard-opus-b-tradeoff-06","hard-opus-b-tradeoff-08","hard-opus-c-long_policy-04","hard-opus-c-long_policy-11","hard-opus-c-temporal_numeric-02","hard-sol-a-adversarial-06","hard-sol-a-adversarial-08","hard-sol-a-trap-02","hard-sol-a-trap-04","hard-sol-a-trap-13","hard-sol-a-trap-15","hard-sol-b-judge_hard-01","hard-sol-b-judge_hard-02","hard-sol-b-judge_hard-05","hard-sol-b-judge_hard-08","hard-sol-b-judge_hard-10","hard-sol-b-judge_hard-14","hard-sol-b-judge_hard-15","hard-sol-b-judge_hard-18","hard-sol-c-judge_hard-03","hard-sol-c-judge_hard-05","hard-sol-c-judge_hard-07","hard-sol-c-judge_hard-08","hard-sol-c-judge_hard-09","hard-sol-c-judge_hard-10","hard-sol-c-judge_hard-11","hard-sol-c-judge_hard-13","hard-sol-c-judge_hard-15"],"latency_ms":[22.550443187355995,22.57355023175478,22.05026615411043,21.960693411529064,22.104816511273384,22.04967848956585,21.966337226331234,22.055563516914845,21.9927616417408,21.973651833832264,22.017567418515682,22.00317569077015,21.69207390397787,21.502649411559105,21.78722247481346,21.749623119831085,21.753624081611633,21.762026473879814,21.74820937216282,21.734653040766716,21.437586285173893,21.436615847051144,22.078536450862885,21.918626502156258,21.631679497659206,21.493985317647457,21.757766604423523,21.88530657440424,21.523226983845234,21.616529673337936,21.909558214247227,21.561549976468086,21.38364687561989,21.374786272644997,21.730429492890835,21.68256975710392,229.2622486129403,233.51096734404564,233.36888197809458,49.664667807519436,45.60447670519352,54.61445916444063,61.251248233020306,59.05677750706673,233.04652143269777,123.8057417795062,80.55753726512194,63.13684117048979,327.1439913660288,344.0404273569584,95.39987985044718,31.197931617498398,30.29031492769718,35.11637914925814,27.819251641631126,27.957139536738396,35.08949466049671,35.31597927212715,29.029392637312412,30.740151181817055,28.841327875852585,30.854313634335995,30.434577725827694,28.550710529088974,26.051878929138184,44.15357764810324,41.75232816487551,39.59122858941555,35.85896175354719,40.792860090732574,42.82085597515106,40.41191656142473,39.62675388902426,35.34944076091051],"mean_ms":51.44003272761364,"response_timing_field_excluded":true}
{"experiment":"rmsnorm","model":"jev","arm":"baseline","run":2,"concurrency":1,"request_count":74,"source_file":"analysis/baseline-measured-2.jsonl","source_sha256":"77a4383b14d0d292a7395985391e3ea499e2a7431234df1e58d8a490c1e287e8","response_semantics_sha256":"487c9568dd218821352340c14bf4816157b94c55b95a78c3077de168c1799638","request_ids":["original-policy-01-0","original-policy-01-1","original-policy-02-0","original-policy-02-1","original-policy-03-0","original-policy-03-1","original-policy-04-0","original-policy-04-1","original-policy-05-0","original-policy-05-1","original-policy-06-0","original-policy-06-1","original-adequacy-01-0","original-adequacy-01-1","original-adequacy-02-0","original-adequacy-02-1","original-adequacy-03-0","original-adequacy-03-1","original-adequacy-04-0","original-adequacy-04-1","original-adequacy-05-0","original-adequacy-05-1","original-adequacy-06-0","original-adequacy-06-1","easy-fact-00","easy-fact-01","easy-fact-02","easy-fact-03","easy-fact-04","easy-fact-05","easy-fact-06","easy-fact-07","easy-fact-08","easy-fact-09","easy-fact-10","easy-fact-11","hard-opus-a-long_policy-11","hard-opus-a-long_policy-13","hard-opus-a-long_policy-19","hard-opus-a-probability-03","hard-opus-a-probability-08","hard-opus-a-temporal_numeric-03","hard-opus-a-temporal_numeric-06","hard-opus-a-temporal_numeric-09","hard-opus-b-multi_hop-08","hard-opus-b-probability-03","hard-opus-b-tradeoff-06","hard-opus-b-tradeoff-08","hard-opus-c-long_policy-04","hard-opus-c-long_policy-11","hard-opus-c-temporal_numeric-02","hard-sol-a-adversarial-06","hard-sol-a-adversarial-08","hard-sol-a-trap-02","hard-sol-a-trap-04","hard-sol-a-trap-13","hard-sol-a-trap-15","hard-sol-b-judge_hard-01","hard-sol-b-judge_hard-02","hard-sol-b-judge_hard-05","hard-sol-b-judge_hard-08","hard-sol-b-judge_hard-10","hard-sol-b-judge_hard-14","hard-sol-b-judge_hard-15","hard-sol-b-judge_hard-18","hard-sol-c-judge_hard-03","hard-sol-c-judge_hard-05","hard-sol-c-judge_hard-07","hard-sol-c-judge_hard-08","hard-sol-c-judge_hard-09","hard-sol-c-judge_hard-10","hard-sol-c-judge_hard-11","hard-sol-c-judge_hard-13","hard-sol-c-judge_hard-15"],"latency_ms":[22.549262270331383,22.148014046251774,21.90800942480564,21.866681054234505,21.957652643322945,21.925142966210842,21.852818317711353,21.957439370453358,21.927526220679283,21.903389133512974,21.916769444942474,21.946407854557037,21.627850830554962,21.53055928647518,21.565732546150684,21.582315675914288,21.673675626516342,21.654250100255013,21.63053210824728,21.56413346529007,21.40044793486595,21.41034137457609,21.933715790510178,21.902029402554035,21.549725905060768,21.316953003406525,21.63050975650549,21.79111074656248,21.399080753326416,21.78551536053419,21.908029913902283,21.382948383688927,21.350552327930927,21.416256204247475,21.69600035995245,21.72859199345112,227.94059664011002,234.7526466473937,237.5948578119278,51.11287534236908,45.385763980448246,52.290456369519234,56.54949601739645,57.953229174017906,230.058123357594,121.32741045206785,80.7015597820282,62.83534038811922,332.5284142047167,344.24311574548483,96.72489855438471,31.303866766393185,30.41829727590084,35.16266029328108,27.876372449100018,28.099052608013153,35.23244522511959,34.886266104876995,29.389151372015476,30.865751206874847,29.102607630193233,30.800985172390938,30.6920288130641,29.160120524466038,26.488889940083027,44.979133643209934,41.729168966412544,39.02485128492117,35.6387123465538,41.44123289734125,43.14829781651497,40.336509235203266,39.53375015407801,34.64641608297825],"mean_ms":51.40872059289266,"response_timing_field_excluded":true}
{"experiment":"rmsnorm","model":"jev","arm":"candidate","run":1,"concurrency":1,"request_count":74,"source_file":"analysis/optimized-measured-1.jsonl","source_sha256":"8f68c6e95b33f35a54082a79d20b1b693a05223ab76f6f7f46827e62602b9cab","response_semantics_sha256":"487c9568dd218821352340c14bf4816157b94c55b95a78c3077de168c1799638","request_ids":["original-policy-01-0","original-policy-01-1","original-policy-02-0","original-policy-02-1","original-policy-03-0","original-policy-03-1","original-policy-04-0","original-policy-04-1","original-policy-05-0","original-policy-05-1","original-policy-06-0","original-policy-06-1","original-adequacy-01-0","original-adequacy-01-1","original-adequacy-02-0","original-adequacy-02-1","original-adequacy-03-0","original-adequacy-03-1","original-adequacy-04-0","original-adequacy-04-1","original-adequacy-05-0","original-adequacy-05-1","original-adequacy-06-0","original-adequacy-06-1","easy-fact-00","easy-fact-01","easy-fact-02","easy-fact-03","easy-fact-04","easy-fact-05","easy-fact-06","easy-fact-07","easy-fact-08","easy-fact-09","easy-fact-10","easy-fact-11","hard-opus-a-long_policy-11","hard-opus-a-long_policy-13","hard-opus-a-long_policy-19","hard-opus-a-probability-03","hard-opus-a-probability-08","hard-opus-a-temporal_numeric-03","hard-opus-a-temporal_numeric-06","hard-opus-a-temporal_numeric-09","hard-opus-b-multi_hop-08","hard-opus-b-probability-03","hard-opus-b-tradeoff-06","hard-opus-b-tradeoff-08","hard-opus-c-long_policy-04","hard-opus-c-long_policy-11","hard-opus-c-temporal_numeric-02","hard-sol-a-adversarial-06","hard-sol-a-adversarial-08","hard-sol-a-trap-02","hard-sol-a-trap-04","hard-sol-a-trap-13","hard-sol-a-trap-15","hard-sol-b-judge_hard-01","hard-sol-b-judge_hard-02","hard-sol-b-judge_hard-05","hard-sol-b-judge_hard-08","hard-sol-b-judge_hard-10","hard-sol-b-judge_hard-14","hard-sol-b-judge_hard-15","hard-sol-b-judge_hard-18","hard-sol-c-judge_hard-03","hard-sol-c-judge_hard-05","hard-sol-c-judge_hard-07","hard-sol-c-judge_hard-08","hard-sol-c-judge_hard-09","hard-sol-c-judge_hard-10","hard-sol-c-judge_hard-11","hard-sol-c-judge_hard-13","hard-sol-c-judge_hard-15"],"latency_ms":[20.81037499010563,20.597987808287144,20.507074892520905,20.409698598086834,20.610284991562366,20.484156906604767,20.354212261736393,20.52628993988037,20.40107175707817,20.612834952771664,20.596270449459553,20.71868907660246,20.28927579522133,20.091164857149124,20.36096155643463,20.339504815638065,20.35195752978325,20.463191904127598,20.40405012667179,20.323216915130615,20.072510465979576,20.08679136633873,20.58762963861227,20.532569848001003,20.36317065358162,20.129093900322914,20.34686040133238,20.48654295504093,20.07984835654497,20.246810279786587,20.471857860684395,20.04512958228588,20.00327594578266,19.978757947683334,20.238916389644146,20.231468603014946,223.81260804831982,233.8371817022562,240.3019294142723,49.681090749800205,44.53705437481403,55.108568631112576,60.90494617819786,56.32263422012329,226.77118331193924,119.0495090559125,79.38409131020308,62.09476292133331,326.57469157129526,341.5787937119603,95.568279735744,29.859883710741997,29.146372340619564,34.279752522706985,26.558639481663704,27.410095557570457,35.10752134025097,34.47604551911354,27.740408666431904,29.21851444989443,27.396857738494873,29.156194999814034,29.1593661531806,27.990938164293766,25.116700679063797,43.48696395754814,40.23561533540487,38.093858398497105,34.811326302587986,40.03981780260801,41.61683563143015,39.18017819523811,38.157012313604355,33.75796973705292],"mean_ms":50.14429321965656,"response_timing_field_excluded":true}
{"experiment":"rmsnorm","model":"jev","arm":"candidate","run":2,"concurrency":1,"request_count":74,"source_file":"analysis/optimized-measured-2.jsonl","source_sha256":"df4574a967b8aeeac041f73936c60afd863d3d10ba4b7f6b001be312f6a0c895","response_semantics_sha256":"487c9568dd218821352340c14bf4816157b94c55b95a78c3077de168c1799638","request_ids":["original-policy-01-0","original-policy-01-1","original-policy-02-0","original-policy-02-1","original-policy-03-0","original-policy-03-1","original-policy-04-0","original-policy-04-1","original-policy-05-0","original-policy-05-1","original-policy-06-0","original-policy-06-1","original-adequacy-01-0","original-adequacy-01-1","original-adequacy-02-0","original-adequacy-02-1","original-adequacy-03-0","original-adequacy-03-1","original-adequacy-04-0","original-adequacy-04-1","original-adequacy-05-0","original-adequacy-05-1","original-adequacy-06-0","original-adequacy-06-1","easy-fact-00","easy-fact-01","easy-fact-02","easy-fact-03","easy-fact-04","easy-fact-05","easy-fact-06","easy-fact-07","easy-fact-08","easy-fact-09","easy-fact-10","easy-fact-11","hard-opus-a-long_policy-11","hard-opus-a-long_policy-13","hard-opus-a-long_policy-19","hard-opus-a-probability-03","hard-opus-a-probability-08","hard-opus-a-temporal_numeric-03","hard-opus-a-temporal_numeric-06","hard-opus-a-temporal_numeric-09","hard-opus-b-multi_hop-08","hard-opus-b-probability-03","hard-opus-b-tradeoff-06","hard-opus-b-tradeoff-08","hard-opus-c-long_policy-04","hard-opus-c-long_policy-11","hard-opus-c-temporal_numeric-02","hard-sol-a-adversarial-06","hard-sol-a-adversarial-08","hard-sol-a-trap-02","hard-sol-a-trap-04","hard-sol-a-trap-13","hard-sol-a-trap-15","hard-sol-b-judge_hard-01","hard-sol-b-judge_hard-02","hard-sol-b-judge_hard-05","hard-sol-b-judge_hard-08","hard-sol-b-judge_hard-10","hard-sol-b-judge_hard-14","hard-sol-b-judge_hard-15","hard-sol-b-judge_hard-18","hard-sol-c-judge_hard-03","hard-sol-c-judge_hard-05","hard-sol-c-judge_hard-07","hard-sol-c-judge_hard-08","hard-sol-c-judge_hard-09","hard-sol-c-judge_hard-10","hard-sol-c-judge_hard-11","hard-sol-c-judge_hard-13","hard-sol-c-judge_hard-15"],"latency_ms":[21.18902187794447,20.672762766480446,20.53896151483059,20.45206632465124,20.422015339136124,20.410846918821335,20.358551293611526,20.561478100717068,20.472154952585697,20.564699545502663,20.487754605710506,20.48312220722437,20.195587538182735,19.998304545879364,20.121527835726738,20.130555145442486,20.207829773426056,20.24931740015745,20.30235156416893,20.236508920788765,20.039906725287437,19.993607886135578,20.45094035565853,20.538137294352055,20.362415350973606,20.064279437065125,20.26920672506094,20.37948090583086,19.96788941323757,20.047281868755817,20.316701382398605,20.083592273294926,20.31446062028408,20.07845602929592,20.28787788003683,20.375662483274937,227.61831618845463,233.95180888473988,234.62636023759842,50.72354804724455,46.322804875671864,52.84037720412016,56.00420944392681,56.900786235928535,227.24405489861965,121.14803120493889,80.47511242330074,62.19134386628866,325.4081951454282,340.7330382615328,94.38356664031744,29.853585176169872,29.10258248448372,34.293996170163155,26.698987931013107,27.434314601123333,35.059007816016674,34.74660310894251,27.47450303286314,29.122534207999706,27.593419887125492,29.36122566461563,28.759358450770378,27.317806147038937,24.830413050949574,43.47401112318039,40.732513181865215,38.285053335130215,34.872498363256454,39.44845963269472,41.27979837357998,39.45902269333601,38.70315104722977,33.524892292916775],"mean_ms":50.0489811639528,"response_timing_field_excluded":true}
{"experiment":"silu","model":"jev","arm":"baseline","run":1,"concurrency":1,"request_count":74,"source_file":"analysis/baseline-measured-1.jsonl","source_sha256":"e137811ad3b32721ae19ac7b2f16bfcec2e55d8cdef60b21770903ac53240cdd","response_semantics_sha256":"487c9568dd218821352340c14bf4816157b94c55b95a78c3077de168c1799638","request_ids":["original-policy-01-0","original-policy-01-1","original-policy-02-0","original-policy-02-1","original-policy-03-0","original-policy-03-1","original-policy-04-0","original-policy-04-1","original-policy-05-0","original-policy-05-1","original-policy-06-0","original-policy-06-1","original-adequacy-01-0","original-adequacy-01-1","original-adequacy-02-0","original-adequacy-02-1","original-adequacy-03-0","original-adequacy-03-1","original-adequacy-04-0","original-adequacy-04-1","original-adequacy-05-0","original-adequacy-05-1","original-adequacy-06-0","original-adequacy-06-1","easy-fact-00","easy-fact-01","easy-fact-02","easy-fact-03","easy-fact-04","easy-fact-05","easy-fact-06","easy-fact-07","easy-fact-08","easy-fact-09","easy-fact-10","easy-fact-11","hard-opus-a-long_policy-11","hard-opus-a-long_policy-13","hard-opus-a-long_policy-19","hard-opus-a-probability-03","hard-opus-a-probability-08","hard-opus-a-temporal_numeric-03","hard-opus-a-temporal_numeric-06","hard-opus-a-temporal_numeric-09","hard-opus-b-multi_hop-08","hard-opus-b-probability-03","hard-opus-b-tradeoff-06","hard-opus-b-tradeoff-08","hard-opus-c-long_policy-04","hard-opus-c-long_policy-11","hard-opus-c-temporal_numeric-02","hard-sol-a-adversarial-06","hard-sol-a-adversarial-08","hard-sol-a-trap-02","hard-sol-a-trap-04","hard-sol-a-trap-13","hard-sol-a-trap-15","hard-sol-b-judge_hard-01","hard-sol-b-judge_hard-02","hard-sol-b-judge_hard-05","hard-sol-b-judge_hard-08","hard-sol-b-judge_hard-10","hard-sol-b-judge_hard-14","hard-sol-b-judge_hard-15","hard-sol-b-judge_hard-18","hard-sol-c-judge_hard-03","hard-sol-c-judge_hard-05","hard-sol-c-judge_hard-07","hard-sol-c-judge_hard-08","hard-sol-c-judge_hard-09","hard-sol-c-judge_hard-10","hard-sol-c-judge_hard-11","hard-sol-c-judge_hard-13","hard-sol-c-judge_hard-15"],"latency_ms":[20.768767222762108,20.525015890598297,20.380519330501556,20.343700423836708,20.390053279697895,20.30345145612955,20.356975495815277,20.35581599920988,20.18461935222149,20.30801586806774,20.26470936834812,20.440975204110146,20.097249187529087,19.877268001437187,19.97488271445036,19.961503334343433,20.003083162009716,20.112432539463043,20.103994756937027,20.209183916449547,19.922894425690174,19.83689609915018,20.28487902134657,20.286329090595245,20.069241523742676,19.967242144048214,20.150328055024147,20.30836045742035,19.898340106010437,20.02938650548458,20.216546952724457,19.75176203995943,19.83456127345562,19.73074860870838,19.969922490417957,20.004721358418465,224.73667841404676,234.05119124799967,234.76052284240723,48.44121169298887,43.53929590433836,50.25783181190491,59.312271885573864,56.667886674404144,223.3167951926589,118.92954166978598,82.27406162768602,62.40553129464388,325.01672487705946,330.76132368296385,94.4781955331564,29.39265128225088,28.41243799775839,33.55369716882706,26.33191365748644,26.723486371338367,34.56277213990688,32.94462710618973,27.2988248616457,28.886640444397926,27.496696449816227,29.61828652769327,29.55637127161026,27.527890168130398,24.536719545722008,42.91986767202616,40.646241046488285,39.09295331686735,34.51939485967159,39.56619184464216,41.07059072703123,38.41704409569502,37.57733106613159,32.86017384380102],"mean_ms":49.56332762801164,"response_timing_field_excluded":true}
{"experiment":"silu","model":"jev","arm":"baseline","run":2,"concurrency":1,"request_count":74,"source_file":"analysis/baseline-measured-2.jsonl","source_sha256":"89720961a61ba7449da64e25ab463fd4d890482cda0c1ec53b42a676ddbb24ad","response_semantics_sha256":"487c9568dd218821352340c14bf4816157b94c55b95a78c3077de168c1799638","request_ids":["original-policy-01-0","original-policy-01-1","original-policy-02-0","original-policy-02-1","original-policy-03-0","original-policy-03-1","original-policy-04-0","original-policy-04-1","original-policy-05-0","original-policy-05-1","original-policy-06-0","original-policy-06-1","original-adequacy-01-0","original-adequacy-01-1","original-adequacy-02-0","original-adequacy-02-1","original-adequacy-03-0","original-adequacy-03-1","original-adequacy-04-0","original-adequacy-04-1","original-adequacy-05-0","original-adequacy-05-1","original-adequacy-06-0","original-adequacy-06-1","easy-fact-00","easy-fact-01","easy-fact-02","easy-fact-03","easy-fact-04","easy-fact-05","easy-fact-06","easy-fact-07","easy-fact-08","easy-fact-09","easy-fact-10","easy-fact-11","hard-opus-a-long_policy-11","hard-opus-a-long_policy-13","hard-opus-a-long_policy-19","hard-opus-a-probability-03","hard-opus-a-probability-08","hard-opus-a-temporal_numeric-03","hard-opus-a-temporal_numeric-06","hard-opus-a-temporal_numeric-09","hard-opus-b-multi_hop-08","hard-opus-b-probability-03","hard-opus-b-tradeoff-06","hard-opus-b-tradeoff-08","hard-opus-c-long_policy-04","hard-opus-c-long_policy-11","hard-opus-c-temporal_numeric-02","hard-sol-a-adversarial-06","hard-sol-a-adversarial-08","hard-sol-a-trap-02","hard-sol-a-trap-04","hard-sol-a-trap-13","hard-sol-a-trap-15","hard-sol-b-judge_hard-01","hard-sol-b-judge_hard-02","hard-sol-b-judge_hard-05","hard-sol-b-judge_hard-08","hard-sol-b-judge_hard-10","hard-sol-b-judge_hard-14","hard-sol-b-judge_hard-15","hard-sol-b-judge_hard-18","hard-sol-c-judge_hard-03","hard-sol-c-judge_hard-05","hard-sol-c-judge_hard-07","hard-sol-c-judge_hard-08","hard-sol-c-judge_hard-09","hard-sol-c-judge_hard-10","hard-sol-c-judge_hard-11","hard-sol-c-judge_hard-13","hard-sol-c-judge_hard-15"],"latency_ms":[20.64466942101717,20.33213246613741,20.394393242895603,20.4674256965518,20.46294417232275,20.50259616225958,20.3660661354661,20.610510371625423,20.496550016105175,20.606206730008125,20.48912364989519,20.744425244629383,20.336872898042202,20.078576169908047,20.08567936718464,20.02174314111471,20.095140673220158,20.122983492910862,20.16355376690626,20.02216223627329,19.750175066292286,19.820749759674072,20.275967195630074,20.298251882195473,19.984272308647633,19.81259323656559,20.038767717778683,20.20475920289755,19.85337771475315,19.985031336545944,20.16496565192938,19.799972884356976,19.781146198511124,19.79983691126108,19.972892478108406,20.00555954873562,225.14593042433262,232.26636368781328,235.577124170959,48.54398127645254,43.71199477463961,52.52361390739679,60.745853930711746,55.8225279673934,225.0804826617241,116.95853341370821,79.17588762938976,61.101872473955154,322.86204118281603,337.1662814170122,94.08622421324253,28.68891879916191,27.834362350404263,33.56296569108963,26.30278654396534,26.309428736567497,33.37578661739826,32.87734556943178,27.05839928239584,29.14347406476736,27.184310369193554,28.435043059289455,28.331561014056206,27.205551974475384,24.775302037596703,42.86395478993654,39.60416745394468,36.951606161892414,33.963847905397415,38.86855952441692,40.80739617347717,39.503876119852066,38.00254128873348,33.258140087127686],"mean_ms":49.490136660736155,"response_timing_field_excluded":true}
{"experiment":"silu","model":"jev","arm":"candidate","run":1,"concurrency":1,"request_count":74,"source_file":"analysis/optimized-measured-1.jsonl","source_sha256":"2c7c03b30e7e83c8a1a957ec1e61e698642add3104c6a422b023e1be3f793a2f","response_semantics_sha256":"487c9568dd218821352340c14bf4816157b94c55b95a78c3077de168c1799638","request_ids":["original-policy-01-0","original-policy-01-1","original-policy-02-0","original-policy-02-1","original-policy-03-0","original-policy-03-1","original-policy-04-0","original-policy-04-1","original-policy-05-0","original-policy-05-1","original-policy-06-0","original-policy-06-1","original-adequacy-01-0","original-adequacy-01-1","original-adequacy-02-0","original-adequacy-02-1","original-adequacy-03-0","original-adequacy-03-1","original-adequacy-04-0","original-adequacy-04-1","original-adequacy-05-0","original-adequacy-05-1","original-adequacy-06-0","original-adequacy-06-1","easy-fact-00","easy-fact-01","easy-fact-02","easy-fact-03","easy-fact-04","easy-fact-05","easy-fact-06","easy-fact-07","easy-fact-08","easy-fact-09","easy-fact-10","easy-fact-11","hard-opus-a-long_policy-11","hard-opus-a-long_policy-13","hard-opus-a-long_policy-19","hard-opus-a-probability-03","hard-opus-a-probability-08","hard-opus-a-temporal_numeric-03","hard-opus-a-temporal_numeric-06","hard-opus-a-temporal_numeric-09","hard-opus-b-multi_hop-08","hard-opus-b-probability-03","hard-opus-b-tradeoff-06","hard-opus-b-tradeoff-08","hard-opus-c-long_policy-04","hard-opus-c-long_policy-11","hard-opus-c-temporal_numeric-02","hard-sol-a-adversarial-06","hard-sol-a-adversarial-08","hard-sol-a-trap-02","hard-sol-a-trap-04","hard-sol-a-trap-13","hard-sol-a-trap-15","hard-sol-b-judge_hard-01","hard-sol-b-judge_hard-02","hard-sol-b-judge_hard-05","hard-sol-b-judge_hard-08","hard-sol-b-judge_hard-10","hard-sol-b-judge_hard-14","hard-sol-b-judge_hard-15","hard-sol-b-judge_hard-18","hard-sol-c-judge_hard-03","hard-sol-c-judge_hard-05","hard-sol-c-judge_hard-07","hard-sol-c-judge_hard-08","hard-sol-c-judge_hard-09","hard-sol-c-judge_hard-10","hard-sol-c-judge_hard-11","hard-sol-c-judge_hard-13","hard-sol-c-judge_hard-15"],"latency_ms":[20.804237574338913,20.678143948316574,20.300893113017082,20.149577409029007,20.180808380246162,20.25045547634363,19.98122502118349,20.16453444957733,19.96292918920517,20.121836103498936,19.915946759283543,20.123847760260105,19.84484400600195,19.630227237939835,19.742918200790882,19.78874485939741,19.84736416488886,19.945216365158558,20.008760504424572,19.926625303924084,19.730275496840477,19.877552054822445,20.22190112620592,20.272620022296906,19.973340444266796,20.01484762877226,20.107027143239975,20.240264013409615,19.7865953668952,19.882114604115486,19.87996231764555,19.633597694337368,19.81520466506481,19.614877179265022,19.816984422504902,19.78244073688984,217.4271261319518,226.25485621392727,226.31463315337896,48.18118084222078,43.15142333507538,49.37656968832016,56.22041970491409,55.31067028641701,219.35197338461876,115.57156033813953,76.67484134435654,58.488997630774975,312.86004558205605,328.7007762119174,90.75631015002728,28.194915503263474,27.660873718559742,33.04055519402027,25.440840981900692,25.671797804534435,32.72390924394131,31.886544078588486,26.596848852932453,28.235836885869503,26.14841889590025,27.804243378341198,27.251015417277813,26.62404626607895,24.409407749772072,42.17935353517532,38.833665661513805,36.662060767412186,33.3439065143466,38.222248665988445,40.38384836167097,37.70720958709717,36.8186179548502,32.698689959943295],"mean_ms":48.286472698925316,"response_timing_field_excluded":true}
{"experiment":"silu","model":"jev","arm":"candidate","run":2,"concurrency":1,"request_count":74,"source_file":"analysis/optimized-measured-2.jsonl","source_sha256":"ee101f5ef7387c79a6e5108dd4d483c2c6abc992bc00706513f244480cf38236","response_semantics_sha256":"487c9568dd218821352340c14bf4816157b94c55b95a78c3077de168c1799638","request_ids":["original-policy-01-0","original-policy-01-1","original-policy-02-0","original-policy-02-1","original-policy-03-0","original-policy-03-1","original-policy-04-0","original-policy-04-1","original-policy-05-0","original-policy-05-1","original-policy-06-0","original-policy-06-1","original-adequacy-01-0","original-adequacy-01-1","original-adequacy-02-0","original-adequacy-02-1","original-adequacy-03-0","original-adequacy-03-1","original-adequacy-04-0","original-adequacy-04-1","original-adequacy-05-0","original-adequacy-05-1","original-adequacy-06-0","original-adequacy-06-1","easy-fact-00","easy-fact-01","easy-fact-02","easy-fact-03","easy-fact-04","easy-fact-05","easy-fact-06","easy-fact-07","easy-fact-08","easy-fact-09","easy-fact-10","easy-fact-11","hard-opus-a-long_policy-11","hard-opus-a-long_policy-13","hard-opus-a-long_policy-19","hard-opus-a-probability-03","hard-opus-a-probability-08","hard-opus-a-temporal_numeric-03","hard-opus-a-temporal_numeric-06","hard-opus-a-temporal_numeric-09","hard-opus-b-multi_hop-08","hard-opus-b-probability-03","hard-opus-b-tradeoff-06","hard-opus-b-tradeoff-08","hard-opus-c-long_policy-04","hard-opus-c-long_policy-11","hard-opus-c-temporal_numeric-02","hard-sol-a-adversarial-06","hard-sol-a-adversarial-08","hard-sol-a-trap-02","hard-sol-a-trap-04","hard-sol-a-trap-13","hard-sol-a-trap-15","hard-sol-b-judge_hard-01","hard-sol-b-judge_hard-02","hard-sol-b-judge_hard-05","hard-sol-b-judge_hard-08","hard-sol-b-judge_hard-10","hard-sol-b-judge_hard-14","hard-sol-b-judge_hard-15","hard-sol-b-judge_hard-18","hard-sol-c-judge_hard-03","hard-sol-c-judge_hard-05","hard-sol-c-judge_hard-07","hard-sol-c-judge_hard-08","hard-sol-c-judge_hard-09","hard-sol-c-judge_hard-10","hard-sol-c-judge_hard-11","hard-sol-c-judge_hard-13","hard-sol-c-judge_hard-15"],"latency_ms":[20.50857339054346,20.14897670596838,20.214615389704704,20.262977108359337,20.3558886423707,20.244945771992207,20.07880061864853,20.37597354501486,20.041292533278465,20.23693174123764,20.07812913507223,20.241975784301758,19.980091601610184,19.78092920035124,19.937544129788876,19.880314357578754,19.896130077540874,19.90854274481535,20.079114474356174,19.867555238306522,19.84377298504114,19.873499870300293,20.36114688962698,21.067763678729534,20.22556308656931,20.060072652995586,20.108962431550026,20.067594945430756,19.604917615652084,19.677450880408287,19.77779809385538,19.549839198589325,19.630511291325092,19.664928317070007,20.149054937064648,19.943677820265293,216.0580139607191,221.91317845135927,225.69846268743277,48.90700243413448,43.39179303497076,49.988992512226105,59.6945583820343,56.17630202323198,217.58305188268423,115.67451898008585,76.8368961289525,58.07914771139622,312.8143548965454,327.9300155118108,91.5616499260068,28.594164177775383,27.941719628870487,31.968362629413605,25.45694075524807,25.712142698466778,32.408395782113075,31.97986725717783,26.48178953677416,28.060805052518845,27.112964540719986,29.043841175734997,27.740870602428913,26.059585623443127,23.857061751186848,41.17548745125532,38.28923124819994,36.48080583661795,32.98577945679426,37.96276729553938,41.09353758394718,38.89476042240858,38.03775552660227,33.36153086274862],"mean_ms":48.30721570682284,"response_timing_field_excluded":true}
{"experiment":"pr78","model":"cua","arm":"baseline","run":1,"concurrency":1,"request_count":64,"source_file":"analysis/cua-baseline-measured-c1-r1/responses.jsonl","source_sha256":"9ded2076957d933dd3f48096b091b4d3df71b7512350aeeb0aeee42c4746c5a8","response_semantics_sha256":"5e797f138aa3aa07239cbfe9bd172148f9b3d4a761bb7dc95abaaf592342a189","request_ids":["cua-010","cua-050","cua-017","cua-032","cua-038","cua-049","cua-029","cua-028","cua-018","cua-007","cua-001","cua-048","cua-039","cua-013","cua-043","cua-053","cua-057","cua-037","cua-005","cua-008","cua-056","cua-020","cua-061","cua-036","cua-051","cua-014","cua-004","cua-045","cua-031","cua-058","cua-062","cua-003","cua-033","cua-023","cua-035","cua-040","cua-026","cua-021","cua-054","cua-022","cua-011","cua-015","cua-000","cua-034","cua-063","cua-030","cua-044","cua-012","cua-060","cua-025","cua-052","cua-009","cua-041","cua-002","cua-027","cua-047","cua-016","cua-055","cua-046","cua-042","cua-059","cua-019","cua-006","cua-024"],"latency_ms":[38.683146238327026,38.69577590376139,24.910287000238895,6.6663529723882675,38.467902690172195,24.756922386586666,24.43796396255493,6.77963811904192,38.1657462567091,25.267655961215496,23.697711527347565,6.543812341988087,24.67958629131317,24.226916953921318,24.815844371914864,24.512654170393944,24.271604605019093,24.344397708773613,23.480313830077648,6.614154204726219,6.482528522610664,6.489410065114498,24.229420349001884,6.5497225150465965,24.822302162647247,38.175132125616074,6.680283695459366,24.95727315545082,24.920737370848656,38.293239660561085,39.13312125951052,25.651611387729645,24.945068173110485,24.86060280352831,24.747449904680252,6.5270354971289635,38.211023434996605,25.142009370028973,38.725268095731735,39.1646483913064,25.26132855564356,24.960764683783054,6.541615352034569,38.28408941626549,25.44139325618744,38.46076875925064,6.554233841598034,6.523586809635162,6.611381657421589,24.497315287590027,6.539745256304741,23.4826086089015,24.275521747767925,38.17050252109766,25.614023208618164,25.053879246115685,6.549627520143986,24.776794016361237,38.16777840256691,38.99501822888851,25.6872633472085,24.94050655514002,38.19588292390108,6.876235827803612],"mean_ms":23.643564694793895,"response_timing_field_excluded":true,"wall_seconds":1.5133566949516535}
{"experiment":"pr78","model":"cua","arm":"baseline","run":2,"concurrency":1,"request_count":64,"source_file":"analysis/cua-baseline-measured-c1-r2/responses.jsonl","source_sha256":"81a1210d4b3725fc2c8d07ed9404861064aaa980715df0f57893a643eac7ea50","response_semantics_sha256":"5e797f138aa3aa07239cbfe9bd172148f9b3d4a761bb7dc95abaaf592342a189","request_ids":["cua-010","cua-050","cua-017","cua-032","cua-038","cua-049","cua-029","cua-028","cua-018","cua-007","cua-001","cua-048","cua-039","cua-013","cua-043","cua-053","cua-057","cua-037","cua-005","cua-008","cua-056","cua-020","cua-061","cua-036","cua-051","cua-014","cua-004","cua-045","cua-031","cua-058","cua-062","cua-003","cua-033","cua-023","cua-035","cua-040","cua-026","cua-021","cua-054","cua-022","cua-011","cua-015","cua-000","cua-034","cua-063","cua-030","cua-044","cua-012","cua-060","cua-025","cua-052","cua-009","cua-041","cua-002","cua-027","cua-047","cua-016","cua-055","cua-046","cua-042","cua-059","cua-019","cua-006","cua-024"],"latency_ms":[38.21853920817375,38.2873322814703,24.42276943475008,6.492936983704567,38.35045639425516,25.147524662315845,24.624017998576164,6.69360626488924,38.274092599749565,25.38539096713066,23.84182531386614,6.483877077698708,24.738158099353313,24.406208656728268,24.64840281754732,24.316119961440563,24.235788732767105,24.44692701101303,23.600070737302303,6.481824442744255,6.455158814787865,6.4254142343997955,24.24481976777315,6.474549882113934,24.70269612967968,38.337006233632565,6.547358818352222,24.764442816376686,24.807189591228962,38.27598039060831,38.770548067986965,25.349427945911884,24.524729698896408,24.77291226387024,24.602793157100677,6.43002986907959,38.13015669584274,24.507957510650158,38.49614039063454,39.03811611235142,25.14506597071886,24.96282197535038,6.430808454751968,38.47685270011425,25.044377893209457,38.32923248410225,6.540066562592983,6.459509022533894,6.480805575847626,24.392745457589626,6.431722082197666,23.30178488045931,24.09866824746132,38.24815712869167,25.05464944988489,24.73085280507803,6.566716358065605,24.70516972243786,38.35595212876797,38.95614109933376,25.493914261460304,24.87246971577406,38.37601561099291,6.774669513106346],"mean_ms":23.546601049019955,"response_timing_field_excluded":true,"wall_seconds":1.5071411235257983}
{"experiment":"pr78","model":"cua","arm":"candidate","run":1,"concurrency":1,"request_count":64,"source_file":"analysis/cua-candidate-measured-c1-r1/responses.jsonl","source_sha256":"5843e0f87eab4f0f6867e629fef3de67fdf10085274be872b8b02e62732784b6","response_semantics_sha256":"5e797f138aa3aa07239cbfe9bd172148f9b3d4a761bb7dc95abaaf592342a189","request_ids":["cua-010","cua-050","cua-017","cua-032","cua-038","cua-049","cua-029","cua-028","cua-018","cua-007","cua-001","cua-048","cua-039","cua-013","cua-043","cua-053","cua-057","cua-037","cua-005","cua-008","cua-056","cua-020","cua-061","cua-036","cua-051","cua-014","cua-004","cua-045","cua-031","cua-058","cua-062","cua-003","cua-033","cua-023","cua-035","cua-040","cua-026","cua-021","cua-054","cua-022","cua-011","cua-015","cua-000","cua-034","cua-063","cua-030","cua-044","cua-012","cua-060","cua-025","cua-052","cua-009","cua-041","cua-002","cua-027","cua-047","cua-016","cua-055","cua-046","cua-042","cua-059","cua-019","cua-006","cua-024"],"latency_ms":[38.093650713562965,38.68339490145445,25.035806000232697,6.4717847853899,38.27877156436443,24.98256228864193,24.837137199938297,6.586629897356033,37.962145172059536,25.425363332033157,23.957534693181515,6.46606832742691,24.67915415763855,24.27516784518957,24.714493192732334,24.392812512815,24.436457082629204,24.348323233425617,23.576805368065834,6.43899105489254,6.39432854950428,6.424613296985626,24.211425334215164,6.454060785472393,24.84056167304516,38.31595368683338,6.498013623058796,24.233941920101643,24.87505879253149,38.531629368662834,38.58705144375563,25.465277023613453,24.66027718037367,24.777387268841267,24.633709341287613,6.382700987160206,38.201628252863884,24.873003363609314,38.44188526272774,38.81786484271288,25.58869868516922,25.17293393611908,6.445940583944321,38.57463225722313,24.97562114149332,38.24920207262039,6.4613064751029015,6.5337782725691795,6.622909568250179,24.923689663410187,6.453174166381359,23.55680987238884,24.232960306107998,38.331564515829086,25.136475451290607,24.798895232379436,6.382409483194351,24.6327742934227,38.18082623183727,38.66343665868044,25.413003750145435,24.96717870235443,38.24594058096409,6.869658827781677],"mean_ms":23.573081969516352,"response_timing_field_excluded":true,"wall_seconds":1.5088259782642126}
{"experiment":"pr78","model":"cua","arm":"candidate","run":2,"concurrency":1,"request_count":64,"source_file":"analysis/cua-candidate-measured-c1-r2/responses.jsonl","source_sha256":"a67eb220641fc40e2cd1b24cb7b8bfc9c23a79d62e326d6e351b6de3c61ee98d","response_semantics_sha256":"5e797f138aa3aa07239cbfe9bd172148f9b3d4a761bb7dc95abaaf592342a189","request_ids":["cua-010","cua-050","cua-017","cua-032","cua-038","cua-049","cua-029","cua-028","cua-018","cua-007","cua-001","cua-048","cua-039","cua-013","cua-043","cua-053","cua-057","cua-037","cua-005","cua-008","cua-056","cua-020","cua-061","cua-036","cua-051","cua-014","cua-004","cua-045","cua-031","cua-058","cua-062","cua-003","cua-033","cua-023","cua-035","cua-040","cua-026","cua-021","cua-054","cua-022","cua-011","cua-015","cua-000","cua-034","cua-063","cua-030","cua-044","cua-012","cua-060","cua-025","cua-052","cua-009","cua-041","cua-002","cua-027","cua-047","cua-016","cua-055","cua-046","cua-042","cua-059","cua-019","cua-006","cua-024"],"latency_ms":[38.49807195365429,38.948383182287216,25.265008211135864,6.491854786872864,38.18418085575104,24.698288179934025,24.382502771914005,6.565592251718044,38.121375255286694,25.04517510533333,23.65727536380291,6.430191919207573,24.721630848944187,24.410509504377842,24.67649057507515,24.42752104252577,24.277922697365284,24.23257566988468,23.427129723131657,6.406385451555252,6.363673135638237,6.390317343175411,24.161510169506073,6.421823985874653,24.713588878512383,38.153573870658875,6.591557525098324,24.685527198016644,24.76125117391348,38.41192089021206,38.220690563321114,25.51536913961172,24.814480915665627,24.747607298195362,24.596955627202988,6.453623063862324,37.97782678157091,25.016059167683125,38.44507969915867,38.9155363664031,25.440890341997147,24.86901730298996,6.399299018085003,38.2587444037199,25.359539315104485,38.320123217999935,6.622003391385078,6.55911210924387,6.530876271426678,24.73639789968729,6.435171701014042,23.44696596264839,24.17127788066864,38.07235416024923,25.561117567121983,25.115475989878178,6.546441465616226,25.043265894055367,38.3991077542305,38.9747591689229,25.64043365418911,25.135070085525513,38.446483202278614,6.881079636514187],"mean_ms":23.58111008652486,"response_timing_field_excluded":true,"wall_seconds":1.5093425484374166}
{"experiment":"pr78","model":"cua","arm":"baseline","run":1,"concurrency":8,"request_count":64,"source_file":"analysis/cua-baseline-measured-c8-r1/responses.jsonl","source_sha256":"cc66bd95546610bd579667a897287d586341f14be122a8a9bda1c1ff002c79b8","response_semantics_sha256":"5e797f138aa3aa07239cbfe9bd172148f9b3d4a761bb7dc95abaaf592342a189","request_ids":["cua-010","cua-050","cua-017","cua-032","cua-038","cua-049","cua-029","cua-028","cua-018","cua-007","cua-001","cua-048","cua-039","cua-013","cua-043","cua-053","cua-057","cua-037","cua-005","cua-008","cua-056","cua-020","cua-061","cua-036","cua-051","cua-014","cua-004","cua-045","cua-031","cua-058","cua-062","cua-003","cua-033","cua-023","cua-035","cua-040","cua-026","cua-021","cua-054","cua-022","cua-011","cua-015","cua-000","cua-034","cua-063","cua-030","cua-044","cua-012","cua-060","cua-025","cua-052","cua-009","cua-041","cua-002","cua-027","cua-047","cua-016","cua-055","cua-046","cua-042","cua-059","cua-019","cua-006","cua-024"],"latency_ms":[39.93741702288389,92.90571603924036,237.93209809809923,57.010116055607796,141.2065690383315,265.1971923187375,273.2422761619091,50.43970700353384,138.44923861324787,302.1968621760607,250.91254245489836,109.89557486027479,243.60275361686945,163.31064514815807,214.61003553122282,162.1029730886221,161.04739531874657,162.36313711851835,160.3288296610117,49.28199853748083,51.83676537126303,56.5743837505579,248.2270821928978,53.232056088745594,295.0752340257168,86.06202155351639,81.85228705406189,241.47512298077345,320.99784072488546,109.45433937013149,135.6570990756154,320.19163481891155,213.05118408054113,321.04151882231236,291.1399295553565,50.45864824205637,79.08712793141603,268.3004178106785,110.4869544506073,137.50385586172342,342.53752417862415,342.5929360091686,78.30814179033041,106.9974834099412,283.2865696400404,108.94626937806606,108.99715777486563,108.80979057401419,79.29462753236294,205.71685303002596,47.16337937861681,179.92052994668484,183.72253887355328,77.2995138540864,313.7373961508274,277.8589455410838,48.47507458180189,265.4475709423423,85.66100709140301,116.53268989175558,225.67322850227356,216.33408032357693,135.85723098367453,107.26451966911554],"mean_ms":168.6580256355228,"response_timing_field_excluded":true,"wall_seconds":1.3952045626938343}
{"experiment":"pr78","model":"cua","arm":"baseline","run":2,"concurrency":8,"request_count":64,"source_file":"analysis/cua-baseline-measured-c8-r2/responses.jsonl","source_sha256":"03a390cdc99c1bb8e69fd8865dd594831c32b49d829032b67ee3829363f30564","response_semantics_sha256":"5e797f138aa3aa07239cbfe9bd172148f9b3d4a761bb7dc95abaaf592342a189","request_ids":["cua-010","cua-050","cua-017","cua-032","cua-038","cua-049","cua-029","cua-028","cua-018","cua-007","cua-001","cua-048","cua-039","cua-013","cua-043","cua-053","cua-057","cua-037","cua-005","cua-008","cua-056","cua-020","cua-061","cua-036","cua-051","cua-014","cua-004","cua-045","cua-031","cua-058","cua-062","cua-003","cua-033","cua-023","cua-035","cua-040","cua-026","cua-021","cua-054","cua-022","cua-011","cua-015","cua-000","cua-034","cua-063","cua-030","cua-044","cua-012","cua-060","cua-025","cua-052","cua-009","cua-041","cua-002","cua-027","cua-047","cua-016","cua-055","cua-046","cua-042","cua-059","cua-019","cua-006","cua-024"],"latency_ms":[40.445621125400066,105.0660265609622,243.0816451087594,45.33709865063429,140.71890339255333,258.22399370372295,267.5743168219924,56.34773708879948,137.51115277409554,301.4896307140589,250.87378546595573,111.17994040250778,244.1972065716982,163.8552388176322,220.45745979994535,162.8254922106862,162.47145272791386,162.631306797266,161.09538823366165,49.52507186681032,49.1505628451705,56.82940222322941,249.61739033460617,57.60451778769493,296.76357097923756,83.19869823753834,79.25537321716547,243.313018232584,322.7483993396163,110.58767698705196,136.82319689542055,321.02906331419945,213.56739848852158,321.7828180640936,291.79363138973713,50.772945396602154,78.95723450928926,268.91757920384407,110.41822843253613,137.8947924822569,343.1320618838072,343.0094476789236,78.73257622122765,107.33596980571747,283.1376101821661,109.46788266301155,109.49874110519886,109.11948047578335,80.01854363828897,205.24419844150543,47.188788652420044,179.16499357670546,183.0980498343706,77.02027261257172,311.7342349141836,276.13137662410736,48.35150204598904,263.9602841809392,85.99590323865414,115.79721700400114,224.36435613781214,215.09223524481058,134.93085745722055,105.99119029939175],"mean_ms":168.8039334549103,"response_timing_field_excluded":true,"wall_seconds":1.3961598612368107}
{"experiment":"pr78","model":"cua","arm":"candidate","run":1,"concurrency":8,"request_count":64,"source_file":"analysis/cua-candidate-measured-c8-r1/responses.jsonl","source_sha256":"83f9299321e88086e8999d5e8f749930e2f78348acb4276c6b9059ca1e0e7691","response_semantics_sha256":"5e797f138aa3aa07239cbfe9bd172148f9b3d4a761bb7dc95abaaf592342a189","request_ids":["cua-010","cua-050","cua-017","cua-032","cua-038","cua-049","cua-029","cua-028","cua-018","cua-007","cua-001","cua-048","cua-039","cua-013","cua-043","cua-053","cua-057","cua-037","cua-005","cua-008","cua-056","cua-020","cua-061","cua-036","cua-051","cua-014","cua-004","cua-045","cua-031","cua-058","cua-062","cua-003","cua-033","cua-023","cua-035","cua-040","cua-026","cua-021","cua-054","cua-022","cua-011","cua-015","cua-000","cua-034","cua-063","cua-030","cua-044","cua-012","cua-060","cua-025","cua-052","cua-009","cua-041","cua-002","cua-027","cua-047","cua-016","cua-055","cua-046","cua-042","cua-059","cua-019","cua-006","cua-024"],"latency_ms":[40.27820285409689,104.97225727885962,243.30370407551527,45.203651301562786,140.6765729188919,258.3624003455043,267.74683594703674,56.33196700364351,137.96610105782747,301.4503363519907,250.74454676359892,111.6089103743434,244.19661797583103,163.48342318087816,220.26749793440104,162.4797387048602,162.34745737165213,162.5592913478613,160.84699798375368,49.392206594347954,49.28012751042843,56.86521157622337,249.09135792404413,57.45041277259588,296.01963981986046,82.39472564309835,78.29067576676607,242.47382674366236,321.96362502872944,109.97779481112957,136.23877335339785,320.28242759406567,213.69934920221567,320.61025127768517,290.4998008161783,50.77628046274185,78.62232998013496,266.9834280386567,109.94529351592064,136.6357784718275,341.24394319951534,340.8053498715162,77.88357324898243,106.69165477156639,282.160684466362,108.64336043596268,108.8161813095212,108.60877204686403,79.31628078222275,204.90757562220097,46.99831362813711,179.00423146784306,182.68414679914713,76.86707656830549,311.98535300791264,276.3541294261813,48.24991896748543,264.1581427305937,85.50710789859295,115.81629514694214,224.8617224395275,215.38268122822046,134.78550035506487,106.28701839596033],"mean_ms":168.44279439828824,"response_timing_field_excluded":true,"wall_seconds":1.393466611392796}
{"experiment":"pr78","model":"cua","arm":"candidate","run":2,"concurrency":8,"request_count":64,"source_file":"analysis/cua-candidate-measured-c8-r2/responses.jsonl","source_sha256":"eca2895282d9abed7b7e4ec2cd3ccb15a1b94535dd3d18629bf043c51ab79d8c","response_semantics_sha256":"5e797f138aa3aa07239cbfe9bd172148f9b3d4a761bb7dc95abaaf592342a189","request_ids":["cua-010","cua-050","cua-017","cua-032","cua-038","cua-049","cua-029","cua-028","cua-018","cua-007","cua-001","cua-048","cua-039","cua-013","cua-043","cua-053","cua-057","cua-037","cua-005","cua-008","cua-056","cua-020","cua-061","cua-036","cua-051","cua-014","cua-004","cua-045","cua-031","cua-058","cua-062","cua-003","cua-033","cua-023","cua-035","cua-040","cua-026","cua-021","cua-054","cua-022","cua-011","cua-015","cua-000","cua-034","cua-063","cua-030","cua-044","cua-012","cua-060","cua-025","cua-052","cua-009","cua-041","cua-002","cua-027","cua-047","cua-016","cua-055","cua-046","cua-042","cua-059","cua-019","cua-006","cua-024"],"latency_ms":[40.2960404753685,105.03456741571426,244.0613955259323,45.23349925875664,140.86131658405066,259.0006208047271,268.4217421337962,56.335135363042355,137.77280878275633,302.29341331869364,251.7403019592166,111.96340620517731,244.92594227194786,164.5345250144601,220.78786697238684,162.51426562666893,162.52185218036175,162.48728893697262,160.86809244006872,49.325620755553246,49.25244953483343,56.86443950980902,249.20585844665766,57.52875003963709,296.65982257574797,82.52934645861387,78.58465891331434,242.8684625774622,322.1398005262017,110.17290502786636,136.11802272498608,320.8675663918257,214.19502142816782,321.1456844583154,291.33451730012894,51.183381117880344,78.7698132917285,267.754171974957,109.92935486137867,136.81077398359776,342.1355877071619,342.1652363613248,78.21800280362368,107.02342633157969,283.3682941272855,109.19697489589453,109.32441800832748,109.0422822162509,79.61851079016924,205.64470253884792,47.12904244661331,179.77622151374817,183.46684891730547,76.91505458205938,312.47857585549355,277.206065133214,48.88493288308382,264.6233094856143,85.39576642215252,115.7218860462308,224.64243043214083,215.16809333115816,134.97895374894142,106.708699837327],"mean_ms":168.80824718100484,"response_timing_field_excluded":true,"wall_seconds":1.3962427414953709}
{"experiment":"pr78","model":"cua","arm":"baseline","run":1,"concurrency":16,"request_count":64,"source_file":"analysis/cua-baseline-measured-c16-r1/responses.jsonl","source_sha256":"10a1479d2f5a2c81b6039675fc16a785ae1c48268e1eab00c9d50e7ff143939f","response_semantics_sha256":"5e797f138aa3aa07239cbfe9bd172148f9b3d4a761bb7dc95abaaf592342a189","request_ids":["cua-010","cua-050","cua-017","cua-032","cua-038","cua-049","cua-029","cua-028","cua-018","cua-007","cua-001","cua-048","cua-039","cua-013","cua-043","cua-053","cua-057","cua-037","cua-005","cua-008","cua-056","cua-020","cua-061","cua-036","cua-051","cua-014","cua-004","cua-045","cua-031","cua-058","cua-062","cua-003","cua-033","cua-023","cua-035","cua-040","cua-026","cua-021","cua-054","cua-022","cua-011","cua-015","cua-000","cua-034","cua-063","cua-030","cua-044","cua-012","cua-060","cua-025","cua-052","cua-009","cua-041","cua-002","cua-027","cua-047","cua-016","cua-055","cua-046","cua-042","cua-059","cua-019","cua-006","cua-024"],"latency_ms":[41.38574190437794,76.91898662596941,368.22775565087795,88.01471162587404,164.25389517098665,378.56077309697866,351.7426159232855,81.48735016584396,217.91034657508135,513.6675518006086,439.33077808469534,116.5463449433446,571.9981351867318,458.8234042748809,565.6851064413786,450.10082609951496,436.77704967558384,410.66984087228775,414.7660881280899,155.30484728515148,157.33069274574518,127.63272505253553,417.8342344239354,99.44238234311342,663.7594206258655,138.98503873497248,159.82894599437714,563.1239367648959,660.2268787100911,176.96526646614075,178.02290618419647,652.3619722574949,519.7403281927109,644.0558442845941,640.1369040831923,160.45934986323118,186.02033611387014,507.93884973973036,217.92323887348175,218.25385093688965,662.8697393462062,662.7627294510603,188.6613955721259,214.62791133672,657.1085462346673,215.26187472045422,188.32627777010202,158.89683924615383,158.1436414271593,447.4045094102621,102.60787513107061,405.14300391077995,409.2744207009673,130.2149072289467,433.15436970442533,422.12877701967955,126.75994634628296,388.95792234689,153.6319823935628,184.61926002055407,332.4372274801135,308.54901671409607,184.27689839154482,183.97861532866955],"mean_ms":323.62520217429847,"response_timing_field_excluded":true,"wall_seconds":1.4023225475102663}
{"experiment":"pr78","model":"cua","arm":"baseline","run":2,"concurrency":16,"request_count":64,"source_file":"analysis/cua-baseline-measured-c16-r2/responses.jsonl","source_sha256":"54ffef0c3f00fa05af9e548c0acf28ceecebfe903722ea834dd696b3db2c0978","response_semantics_sha256":"5e797f138aa3aa07239cbfe9bd172148f9b3d4a761bb7dc95abaaf592342a189","request_ids":["cua-010","cua-050","cua-017","cua-032","cua-038","cua-049","cua-029","cua-028","cua-018","cua-007","cua-001","cua-048","cua-039","cua-013","cua-043","cua-053","cua-057","cua-037","cua-005","cua-008","cua-056","cua-020","cua-061","cua-036","cua-051","cua-014","cua-004","cua-045","cua-031","cua-058","cua-062","cua-003","cua-033","cua-023","cua-035","cua-040","cua-026","cua-021","cua-054","cua-022","cua-011","cua-015","cua-000","cua-034","cua-063","cua-030","cua-044","cua-012","cua-060","cua-025","cua-052","cua-009","cua-041","cua-002","cua-027","cua-047","cua-016","cua-055","cua-046","cua-042","cua-059","cua-019","cua-006","cua-024"],"latency_ms":[41.46511014550924,76.62822213023901,382.7351024374366,81.95467665791512,181.9149125367403,357.2158645838499,372.52841517329216,87.009665556252,217.3405596986413,520.0585005804896,391.1883346736431,92.07097440958023,602.6797937229276,413.2712446153164,608.4416350349784,422.79031965881586,436.9052769616246,411.43280267715454,415.7252302393317,155.01215402036905,155.0533939152956,129.4751800596714,419.86048221588135,99.62751436978579,663.9697579666972,148.95083662122488,160.87828297168016,564.9664187803864,691.807808354497,179.64246962219477,205.7733591645956,679.7876842319965,548.3486391603947,645.6429045647383,641.0568850114942,161.45060304552317,186.63836549967527,508.61906446516514,217.5679737702012,218.70699618011713,634.2733502388,634.3658361583948,188.08540981262922,214.15944676846266,657.7011849731207,214.94103223085403,189.4610896706581,159.36387330293655,158.92245154827833,448.6783444881439,102.94919461011887,410.12763045728207,409.9667379632592,130.80751989036798,433.7282497435808,422.6091206073761,127.22088675945997,389.5822400227189,153.59273552894592,155.86847346276045,332.6032189652324,308.61291848123074,185.12850161641836,184.72293764352798],"mean_ms":324.1197781317169,"response_timing_field_excluded":true,"wall_seconds":1.4040509779006243}
{"experiment":"pr78","model":"cua","arm":"candidate","run":1,"concurrency":16,"request_count":64,"source_file":"analysis/cua-candidate-measured-c16-r1/responses.jsonl","source_sha256":"ffb0475ae76a5d559b8f04851dd877e27efa3f20c4abe26e963dc63f2229564f","response_semantics_sha256":"5e797f138aa3aa07239cbfe9bd172148f9b3d4a761bb7dc95abaaf592342a189","request_ids":["cua-010","cua-050","cua-017","cua-032","cua-038","cua-049","cua-029","cua-028","cua-018","cua-007","cua-001","cua-048","cua-039","cua-013","cua-043","cua-053","cua-057","cua-037","cua-005","cua-008","cua-056","cua-020","cua-061","cua-036","cua-051","cua-014","cua-004","cua-045","cua-031","cua-058","cua-062","cua-003","cua-033","cua-023","cua-035","cua-040","cua-026","cua-021","cua-054","cua-022","cua-011","cua-015","cua-000","cua-034","cua-063","cua-030","cua-044","cua-012","cua-060","cua-025","cua-052","cua-009","cua-041","cua-002","cua-027","cua-047","cua-016","cua-055","cua-046","cua-042","cua-059","cua-019","cua-006","cua-024"],"latency_ms":[41.353859938681126,76.7895495519042,352.39650402218103,82.10904616862535,182.0009332150221,361.37685365974903,376.77195481956005,87.02782168984413,217.4713546410203,517.2530170530081,403.48709654062986,116.00958835333586,563.8499902561307,412.642371840775,569.4633899256587,421.9288509339094,434.85230300575495,408.96822698414326,413.12136221677065,155.20396642386913,157.6200257986784,129.39682509750128,416.33457504212856,99.58462789654732,660.5040859431028,147.32641819864511,158.17759279161692,559.7808752208948,657.1865612640977,176.11601669341326,202.1237062290311,674.9512879177928,544.4083651527762,641.902613453567,637.9242958500981,160.59920843690634,186.23161781579256,506.2886755913496,217.1175852417946,217.2167943790555,660.9814958646894,661.064132116735,187.50108778476715,213.15047424286604,654.1613023728132,213.44736497849226,188.31174075603485,158.8320853188634,158.0983493477106,446.3854357600212,102.66675613820553,403.6210421472788,401.2992065399885,130.18452748656273,430.80948293209076,419.6034697815776,126.4840392395854,386.46275363862514,153.02032232284546,183.066145516932,330.0616815686226,306.2914712354541,183.8693581521511,183.58850106596947],"mean_ms":322.30987533694133,"response_timing_field_excluded":true,"wall_seconds":1.3964113788679242}
{"experiment":"pr78","model":"cua","arm":"candidate","run":2,"concurrency":16,"request_count":64,"source_file":"analysis/cua-candidate-measured-c16-r2/responses.jsonl","source_sha256":"f0cad8a9b0de68ae556c69fdad8cbda57a1eb47a37a1442c5b6ab469a9c6b29f","response_semantics_sha256":"5e797f138aa3aa07239cbfe9bd172148f9b3d4a761bb7dc95abaaf592342a189","request_ids":["cua-010","cua-050","cua-017","cua-032","cua-038","cua-049","cua-029","cua-028","cua-018","cua-007","cua-001","cua-048","cua-039","cua-013","cua-043","cua-053","cua-057","cua-037","cua-005","cua-008","cua-056","cua-020","cua-061","cua-036","cua-051","cua-014","cua-004","cua-045","cua-031","cua-058","cua-062","cua-003","cua-033","cua-023","cua-035","cua-040","cua-026","cua-021","cua-054","cua-022","cua-011","cua-015","cua-000","cua-034","cua-063","cua-030","cua-044","cua-012","cua-060","cua-025","cua-052","cua-009","cua-041","cua-002","cua-027","cua-047","cua-016","cua-055","cua-046","cua-042","cua-059","cua-019","cua-006","cua-024"],"latency_ms":[41.51402320712805,77.0080043002963,377.98966094851494,88.22811767458916,182.49158840626478,358.41334890574217,367.6592577248812,81.60845655947924,218.1624947115779,508.5037862882018,391.86660945415497,116.70103389769793,609.1389395296574,423.27433731406927,602.9020836576819,413.464205339551,437.1696598827839,411.3074727356434,415.7452713698149,155.47153912484646,157.70885720849037,129.44206036627293,419.27902959287167,99.34905543923378,664.4086763262749,148.50349351763725,160.50871927291155,563.5661277920008,660.8361601829529,179.23211585730314,205.65333776175976,678.443044424057,547.7629667147994,644.7549965232611,640.0256883352995,161.82660311460495,186.76567170768976,507.8239915892482,217.1435384079814,218.19290332496166,631.2332702800632,631.3123321160674,188.01869824528694,213.70752528309822,654.3723726645112,214.50859680771828,185.39273273199797,158.99105463176966,158.21983199566603,446.2265111505985,102.33865305781364,407.57369343191385,407.2344144806266,129.73797600716352,430.6313991546631,419.75326370447874,126.69076304882765,386.7630008608103,153.2474420964718,183.51211305707693,330.3067088127136,306.2591627240181,183.2360988482833,182.91606102138758],"mean_ms":323.469228198519,"response_timing_field_excluded":true,"wall_seconds":1.400895081460476}
{"experiment":"pr78","model":"jev","arm":"baseline","run":1,"concurrency":1,"request_count":64,"source_file":"analysis/jev-baseline-measured-c1-r1/responses.jsonl","source_sha256":"4214ea1f137c99cc5dc6f81cdfc6efc0f9a53cbb308a6908e15b368a6728531c","response_semantics_sha256":"d841d043178d0bad3fa2138c9a37785b89d5c8fddd81329b78a6272bed0bdb06","request_ids":["jev-010","jev-050","jev-017","jev-032","jev-038","jev-049","jev-029","jev-028","jev-018","jev-007","jev-001","jev-048","jev-039","jev-013","jev-043","jev-053","jev-057","jev-037","jev-005","jev-008","jev-056","jev-020","jev-061","jev-036","jev-051","jev-014","jev-004","jev-045","jev-031","jev-058","jev-062","jev-003","jev-033","jev-023","jev-035","jev-040","jev-026","jev-021","jev-054","jev-022","jev-011","jev-015","jev-000","jev-034","jev-063","jev-030","jev-044","jev-012","jev-060","jev-025","jev-052","jev-009","jev-041","jev-002","jev-027","jev-047","jev-016","jev-055","jev-046","jev-042","jev-059","jev-019","jev-006","jev-024"],"latency_ms":[180.01308292150497,185.85451506078243,143.61135568469763,19.3186579272151,180.9604074805975,140.97857475280762,138.32887914031744,19.427225925028324,179.19067200273275,95.4484986141324,138.05411383509636,19.062350504100323,93.75849552452564,138.1016382947564,94.16018519550562,141.78231451660395,138.20845913141966,138.23998346924782,138.25651910156012,19.115498289465904,19.05488595366478,18.996628001332283,138.02683353424072,19.235814921557903,94.01761554181576,181.41441326588392,20.08325234055519,139.6124316379428,93.93785893917084,179.5989042147994,185.1208871230483,96.69779427349567,137.99035176634789,93.92309840768576,93.8533153384924,19.115518778562546,180.48580922186375,140.4048204421997,181.58279452472925,187.53416556864977,95.98915837705135,93.79640966653824,18.986131064593792,179.62971609085798,95.8131579682231,179.7938048839569,20.046080462634563,19.61433421820402,19.229319877922535,138.09567410498857,19.092976115643978,138.20757158100605,138.32846004515886,181.98411911725998,96.974341198802,94.11933645606041,19.167869351804256,93.89147721230984,179.44485787302256,185.1260606199503,96.10043000429869,94.03929766267538,181.28822185099125,20.313081331551075],"mean_ms":108.77547669224441,"response_timing_field_excluded":true,"wall_seconds":6.961810017935932}
{"experiment":"pr78","model":"jev","arm":"baseline","run":2,"concurrency":1,"request_count":64,"source_file":"analysis/jev-baseline-measured-c1-r2/responses.jsonl","source_sha256":"f368ecfb46a093c9121e1ba5ffd6a936b70f920d971bfd14a824ff8c928bb8c2","response_semantics_sha256":"d841d043178d0bad3fa2138c9a37785b89d5c8fddd81329b78a6272bed0bdb06","request_ids":["jev-010","jev-050","jev-017","jev-032","jev-038","jev-049","jev-029","jev-028","jev-018","jev-007","jev-001","jev-048","jev-039","jev-013","jev-043","jev-053","jev-057","jev-037","jev-005","jev-008","jev-056","jev-020","jev-061","jev-036","jev-051","jev-014","jev-004","jev-045","jev-031","jev-058","jev-062","jev-003","jev-033","jev-023","jev-035","jev-040","jev-026","jev-021","jev-054","jev-022","jev-011","jev-015","jev-000","jev-034","jev-063","jev-030","jev-044","jev-012","jev-060","jev-025","jev-052","jev-009","jev-041","jev-002","jev-027","jev-047","jev-016","jev-055","jev-046","jev-042","jev-059","jev-019","jev-006","jev-024"],"latency_ms":[181.52727466076612,185.46465318650007,144.60098091512918,19.484286196529865,183.9484293013811,141.30143821239471,138.60629312694073,19.32941284030676,181.39511719346046,95.78953124582767,138.2369427010417,19.164813682436943,93.82039494812489,138.27121630311012,93.98441854864359,138.22988979518414,138.33982218056917,138.45577742904425,138.22672981768847,19.21881828457117,19.082291051745415,19.103766418993473,138.25482223182917,19.239062443375587,93.9141558483243,182.98291973769665,20.11572476476431,139.2727540805936,94.00135837495327,182.9374972730875,190.61492756009102,96.37882933020592,138.25048878788948,94.09218840301037,93.90666149556637,19.270429387688637,181.08223658055067,140.709244646132,181.7092103883624,188.4499853476882,96.36118728667498,94.11729499697685,19.11821123212576,180.01688830554485,96.21288254857063,181.66219629347324,20.008698105812073,19.513671286404133,19.178660586476326,138.0637688562274,19.080610014498234,138.11183348298073,138.80183547735214,182.5877958908677,96.43097314983606,94.02354806661606,19.105627201497555,93.87032315135002,181.96570873260498,183.8182294741273,96.76241129636765,94.05799210071564,178.70815098285675,20.279414020478725],"mean_ms":109.10347980097868,"response_timing_field_excluded":true,"wall_seconds":6.982815099880099}
{"experiment":"pr78","model":"jev","arm":"candidate","run":1,"concurrency":1,"request_count":64,"source_file":"analysis/jev-candidate-measured-c1-r1/responses.jsonl","source_sha256":"7dbd203ef7298ec0afb40b5b1a93864a6ac48d1e247a6d23e2802519ed170af6","response_semantics_sha256":"d841d043178d0bad3fa2138c9a37785b89d5c8fddd81329b78a6272bed0bdb06","request_ids":["jev-010","jev-050","jev-017","jev-032","jev-038","jev-049","jev-029","jev-028","jev-018","jev-007","jev-001","jev-048","jev-039","jev-013","jev-043","jev-053","jev-057","jev-037","jev-005","jev-008","jev-056","jev-020","jev-061","jev-036","jev-051","jev-014","jev-004","jev-045","jev-031","jev-058","jev-062","jev-003","jev-033","jev-023","jev-035","jev-040","jev-026","jev-021","jev-054","jev-022","jev-011","jev-015","jev-000","jev-034","jev-063","jev-030","jev-044","jev-012","jev-060","jev-025","jev-052","jev-009","jev-041","jev-002","jev-027","jev-047","jev-016","jev-055","jev-046","jev-042","jev-059","jev-019","jev-006","jev-024"],"latency_ms":[181.02325405925512,188.1588390097022,145.48107516020536,19.247056916356087,181.8947046995163,140.4499765485525,137.11466640233994,19.21713538467884,179.43114507943392,94.9677973985672,137.49161828309298,19.115745089948177,93.29366590827703,137.60385010391474,93.27313769608736,137.31377199292183,137.43587769567966,137.28761114180088,137.45442032814026,19.029761664569378,19.00374237447977,18.98447796702385,137.14346662163734,19.089503213763237,93.3754937723279,182.16091953217983,20.127003081142902,138.89522664248943,93.28270424157381,180.97893241792917,189.59846999496222,95.63033003360033,137.21970934420824,93.06260105222464,93.05089060217142,18.969777040183544,180.3738484159112,139.50173370540142,180.20433373749256,187.87392508238554,95.65714746713638,93.22146698832512,18.92193593084812,180.6570878252387,95.26869468390942,180.16133829951286,19.982632249593735,19.614731892943382,19.252624362707138,137.39071134477854,18.99796538054943,137.14666478335857,137.8872711211443,181.7261492833495,95.81875521689653,93.20003632456064,19.05527524650097,93.1981848552823,179.7225158661604,182.76447616517544,95.87547834962606,93.51894445717335,181.01787474006414,20.263229496777058],"mean_ms":108.51770924637094,"response_timing_field_excluded":true,"wall_seconds":6.945331913419068}
{"experiment":"pr78","model":"jev","arm":"candidate","run":2,"concurrency":1,"request_count":64,"source_file":"analysis/jev-candidate-measured-c1-r2/responses.jsonl","source_sha256":"192d6f9ac412200e0851e89aaa3ede8dee14bab9dbfce61483c6a9ca5abcb58a","response_semantics_sha256":"d841d043178d0bad3fa2138c9a37785b89d5c8fddd81329b78a6272bed0bdb06","request_ids":["jev-010","jev-050","jev-017","jev-032","jev-038","jev-049","jev-029","jev-028","jev-018","jev-007","jev-001","jev-048","jev-039","jev-013","jev-043","jev-053","jev-057","jev-037","jev-005","jev-008","jev-056","jev-020","jev-061","jev-036","jev-051","jev-014","jev-004","jev-045","jev-031","jev-058","jev-062","jev-003","jev-033","jev-023","jev-035","jev-040","jev-026","jev-021","jev-054","jev-022","jev-011","jev-015","jev-000","jev-034","jev-063","jev-030","jev-044","jev-012","jev-060","jev-025","jev-052","jev-009","jev-041","jev-002","jev-027","jev-047","jev-016","jev-055","jev-046","jev-042","jev-059","jev-019","jev-006","jev-024"],"latency_ms":[181.95439036935568,187.00420390814543,143.95285490900278,19.137419760227203,181.0819422826171,139.76532872766256,137.71705608814955,19.219993613660336,181.3012771308422,94.81299389153719,137.48068641871214,19.08197719603777,92.97254122793674,137.11347617208958,93.04292500019073,137.11436185985804,137.12827768176794,137.3382778838277,137.3615264892578,19.01890803128481,18.892192281782627,18.851665779948235,137.42835819721222,18.99154856801033,93.16955879330635,182.4688445776701,19.980893470346928,138.05691339075565,92.92932879179716,181.52698408812284,186.75451260060072,95.5015616491437,137.27364223450422,93.00337638705969,92.95337181538343,18.918205983936787,181.3412569463253,139.7185642272234,182.96305742114782,190.4420694336295,95.7591375336051,93.18993799388409,18.951717764139175,181.60487059503794,95.49371618777514,181.3309295102954,20.196154713630676,19.502080976963043,19.13308911025524,137.6632135361433,19.168549217283726,137.70592864602804,137.9916062578559,183.75169578939676,95.66003922373056,93.22348888963461,18.997344188392162,93.10570824891329,181.80581647902727,185.0515278056264,95.5575117841363,93.2102371007204,181.3437370583415,20.15507034957409],"mean_ms":108.6612411600072,"response_timing_field_excluded":true,"wall_seconds":6.954503798857331}
{"experiment":"pr78","model":"jev","arm":"baseline","run":1,"concurrency":8,"request_count":64,"source_file":"analysis/jev-baseline-measured-c8-r1/responses.jsonl","source_sha256":"4968eebd2650ce889be2525e6d7811ad65151d686a667e92451b45c07c8850be","response_semantics_sha256":"d841d043178d0bad3fa2138c9a37785b89d5c8fddd81329b78a6272bed0bdb06","request_ids":["jev-010","jev-050","jev-017","jev-032","jev-038","jev-049","jev-029","jev-028","jev-018","jev-007","jev-001","jev-048","jev-039","jev-013","jev-043","jev-053","jev-057","jev-037","jev-005","jev-008","jev-056","jev-020","jev-061","jev-036","jev-051","jev-014","jev-004","jev-045","jev-031","jev-058","jev-062","jev-003","jev-033","jev-023","jev-035","jev-040","jev-026","jev-021","jev-054","jev-022","jev-011","jev-015","jev-000","jev-034","jev-063","jev-030","jev-044","jev-012","jev-060","jev-025","jev-052","jev-009","jev-041","jev-002","jev-027","jev-047","jev-016","jev-055","jev-046","jev-042","jev-059","jev-019","jev-006","jev-024"],"latency_ms":[182.1258570998907,819.8222704231739,339.8585980758071,201.7576526850462,1005.2214646711946,497.35989794135094,634.568396024406,357.1999818086624,1007.2882855311036,1082.1866700425744,1087.3562386259437,1087.1761441230774,1040.0901501998305,1039.1767816618085,947.3800109699368,897.9819426313043,851.1391784995794,892.2559209167957,886.023691855371,886.1645739525557,811.9021290913224,693.7446855008602,738.7058390304446,620.3570468351245,576.5183949843049,623.299521394074,505.73110673576593,626.2845443561673,700.5054773762822,862.0721027255058,910.7589460909367,987.8467312082648,1031.6025279462337,941.1497572436929,1014.4311627373099,893.8433667644858,980.7844143360853,940.1754029095173,930.9452809393406,1025.0964323058724,983.6218692362309,983.678256161511,909.1772809624672,1070.5230729654431,985.7544908300042,1025.3269420936704,867.2992922365665,696.7413360252976,620.4888261854649,664.8271335288882,664.7769659757614,621.9101687893271,664.2953008413315,665.7571215182543,742.1474363654852,815.9501207992435,815.5978675931692,770.9500584751368,930.7902827858925,979.1445033624768,936.9424385949969,849.3163380771875,931.5887773409486,858.1490935757756],"mean_ms":815.8225555089302,"response_timing_field_excluded":true,"wall_seconds":6.908270952291787}
{"experiment":"pr78","model":"jev","arm":"baseline","run":2,"concurrency":8,"request_count":64,"source_file":"analysis/jev-baseline-measured-c8-r2/responses.jsonl","source_sha256":"ac82b07d989b691e1c1f3a74a5f71837fe477b297f3c0feae9a21645f1a5b0f7","response_semantics_sha256":"d841d043178d0bad3fa2138c9a37785b89d5c8fddd81329b78a6272bed0bdb06","request_ids":["jev-010","jev-050","jev-017","jev-032","jev-038","jev-049","jev-029","jev-028","jev-018","jev-007","jev-001","jev-048","jev-039","jev-013","jev-043","jev-053","jev-057","jev-037","jev-005","jev-008","jev-056","jev-020","jev-061","jev-036","jev-051","jev-014","jev-004","jev-045","jev-031","jev-058","jev-062","jev-003","jev-033","jev-023","jev-035","jev-040","jev-026","jev-021","jev-054","jev-022","jev-011","jev-015","jev-000","jev-034","jev-063","jev-030","jev-044","jev-012","jev-060","jev-025","jev-052","jev-009","jev-041","jev-002","jev-027","jev-047","jev-016","jev-055","jev-046","jev-042","jev-059","jev-019","jev-006","jev-024"],"latency_ms":[180.60108087956905,812.3443089425564,319.21258848160505,355.4730359464884,1000.6498629227281,493.98760963231325,630.5834539234638,336.4924807101488,1007.4264304712415,963.4090252220631,1081.7432533949614,1081.5962506458163,1035.457143560052,1035.1504841819406,946.5978378430009,894.3399526178837,844.2118046805263,885.9447604045272,886.2313386052847,886.2575460225344,811.8128199130297,693.7144491821527,738.2617173716426,619.9464267119765,576.227443292737,622.4195342510939,504.83435671776533,624.9012611806393,699.1735808551311,859.1332649812102,910.8793223276734,987.8884553909302,1031.541483476758,941.0237921401858,1014.4292339682579,894.4047307595611,982.3228986933827,943.3545051142573,934.2937059700489,1028.9672957733274,987.5319544225931,987.6637225970626,913.1904374808073,1074.8043190687895,989.1981538385153,1026.9651906564832,868.343660607934,695.8179324865341,619.5116937160492,663.8510683551431,663.8669958338141,620.8710167557001,663.8630116358399,668.124046176672,742.5417704507709,817.8213434293866,817.2933831810951,772.8662779554725,932.9537535086274,981.4996663480997,938.9349687844515,850.2404578030109,933.4802571684122,860.163246281445],"mean_ms":815.4474821203621,"response_timing_field_excluded":true,"wall_seconds":6.906525990925729}
{"experiment":"pr78","model":"jev","arm":"candidate","run":1,"concurrency":8,"request_count":64,"source_file":"analysis/jev-candidate-measured-c8-r1/responses.jsonl","source_sha256":"2cbfa57b076082b4a6dc4abc90b90cc2ffde94e266481e0b3c94dfc4813c43c5","response_semantics_sha256":"d841d043178d0bad3fa2138c9a37785b89d5c8fddd81329b78a6272bed0bdb06","request_ids":["jev-010","jev-050","jev-017","jev-032","jev-038","jev-049","jev-029","jev-028","jev-018","jev-007","jev-001","jev-048","jev-039","jev-013","jev-043","jev-053","jev-057","jev-037","jev-005","jev-008","jev-056","jev-020","jev-061","jev-036","jev-051","jev-014","jev-004","jev-045","jev-031","jev-058","jev-062","jev-003","jev-033","jev-023","jev-035","jev-040","jev-026","jev-021","jev-054","jev-022","jev-011","jev-015","jev-000","jev-034","jev-063","jev-030","jev-044","jev-012","jev-060","jev-025","jev-052","jev-009","jev-041","jev-002","jev-027","jev-047","jev-016","jev-055","jev-046","jev-042","jev-059","jev-019","jev-006","jev-024"],"latency_ms":[182.90194030851126,809.2060228809714,320.54364681243896,356.5508034080267,997.281831689179,628.6730766296387,493.1404683738947,337.57699839770794,1002.8888173401356,958.7220819666982,1076.4245530590415,1076.308318413794,1031.0268625617027,1031.0553880408406,943.1778127327561,890.3675163164735,838.4924419224262,879.8996480181813,879.6786777675152,879.9460306763649,806.0041703283787,688.7863148003817,733.8621634989977,615.9164914861321,572.3668215796351,617.9851060733199,501.4166571199894,620.9387630224228,694.7485934942961,854.6919915825129,902.9184076935053,979.3073311448097,1023.0794129893184,933.6108397692442,1006.3304351642728,886.5248961374164,974.1972126066685,934.2620484530926,927.6925846934319,1023.2574725523591,982.2133034467697,982.3966966941953,908.6077092215419,1066.702020354569,981.1755483970046,1021.3692141696811,861.844040453434,690.6580235809088,614.3866488710046,658.3300353959203,658.2457758486271,618.0127104744315,661.0488118603826,664.7728895768523,740.7571449875832,813.9992840588093,813.5612867772579,769.5291480049491,929.8440497368574,976.5077969059348,933.9079074561596,843.6474436894059,930.376916192472,857.6974896714091],"mean_ms":810.8023835520726,"response_timing_field_excluded":true,"wall_seconds":6.869770880788565}
{"experiment":"pr78","model":"jev","arm":"candidate","run":2,"concurrency":8,"request_count":64,"source_file":"analysis/jev-candidate-measured-c8-r2/responses.jsonl","source_sha256":"11cd742cc078df4280e59442514237437d2f5f22dd992a13bfb8f1369b14519f","response_semantics_sha256":"d841d043178d0bad3fa2138c9a37785b89d5c8fddd81329b78a6272bed0bdb06","request_ids":["jev-010","jev-050","jev-017","jev-032","jev-038","jev-049","jev-029","jev-028","jev-018","jev-007","jev-001","jev-048","jev-039","jev-013","jev-043","jev-053","jev-057","jev-037","jev-005","jev-008","jev-056","jev-020","jev-061","jev-036","jev-051","jev-014","jev-004","jev-045","jev-031","jev-058","jev-062","jev-003","jev-033","jev-023","jev-035","jev-040","jev-026","jev-021","jev-054","jev-022","jev-011","jev-015","jev-000","jev-034","jev-063","jev-030","jev-044","jev-012","jev-060","jev-025","jev-052","jev-009","jev-041","jev-002","jev-027","jev-047","jev-016","jev-055","jev-046","jev-042","jev-059","jev-019","jev-006","jev-024"],"latency_ms":[183.0367734655738,810.2913545444608,337.92104199528694,201.14318653941154,997.9184856638312,493.0907739326358,629.142296500504,354.98775262385607,1002.6339711621404,1078.092255629599,1077.2512964904308,1077.3517126217484,1031.4224185422063,1030.742739327252,942.705468274653,890.3993926942348,838.5639414191246,879.8160292208195,879.9128858372569,879.8437435179949,806.2960980460048,688.9379946514964,733.3592539653182,615.5280293896794,572.4676856771111,619.9451303109527,503.1874477863312,622.491417452693,696.0567031055689,855.1724404096603,904.3754553422332,981.0328986495733,1024.9005807563663,933.5992066189647,1006.2939012423158,886.9983814656734,975.9710943326354,936.0855584964156,930.0455898046494,1025.865763425827,984.4533475115895,984.4833696261048,910.7272941619158,1070.720685645938,984.3016974627972,1025.807099416852,864.9736512452364,693.2664811611176,617.2607326880097,661.4305544644594,661.3945076242089,619.3369533866644,662.5093007460237,665.3615739196539,741.1595480516553,814.328495413065,813.9248751103878,769.9495470151305,930.508247576654,978.7646317854524,935.8718292787671,846.00914362818,931.932738982141,859.3004373833537],"mean_ms":811.9164827221539,"response_timing_field_excluded":true,"wall_seconds":6.878648453392088}
{"experiment":"pr78","model":"jev","arm":"baseline","run":1,"concurrency":16,"request_count":64,"source_file":"analysis/jev-baseline-measured-c16-r1/responses.jsonl","source_sha256":"f6550bda3a2be9ecb40b4673b11d9b5a4061f2c0c56bbf26c9e1ee0c5bb83bbb","response_semantics_sha256":"d841d043178d0bad3fa2138c9a37785b89d5c8fddd81329b78a6272bed0bdb06","request_ids":["jev-010","jev-050","jev-017","jev-032","jev-038","jev-049","jev-029","jev-028","jev-018","jev-007","jev-001","jev-048","jev-039","jev-013","jev-043","jev-053","jev-057","jev-037","jev-005","jev-008","jev-056","jev-020","jev-061","jev-036","jev-051","jev-014","jev-004","jev-045","jev-031","jev-058","jev-062","jev-003","jev-033","jev-023","jev-035","jev-040","jev-026","jev-021","jev-054","jev-022","jev-011","jev-015","jev-000","jev-034","jev-063","jev-030","jev-044","jev-012","jev-060","jev-025","jev-052","jev-009","jev-041","jev-002","jev-027","jev-047","jev-016","jev-055","jev-046","jev-042","jev-059","jev-019","jev-006","jev-024"],"latency_ms":[185.2359278127551,366.8180210515857,819.0627796575427,385.90490352362394,1708.073620684445,681.9301666691899,545.0252247974277,405.00654466450214,1896.8596141785383,928.4578375518322,1157.2936484590173,835.7176827266812,1020.7513757050037,1385.975589044392,1249.1911463439465,1522.3966958001256,1854.0805829688907,1808.6174074560404,1925.7146026939154,1923.7685455009341,1802.2076236084104,1683.8069390505552,1683.5392219945788,1683.7661154568195,1683.7823782116175,1767.8793026134372,1650.797389447689,1697.2338240593672,1653.3148037269711,1697.5209591910243,1702.5884557515383,1608.2497108727694,1603.9126953110099,1559.800224378705,1515.835553407669,1515.9308640286326,1676.344039849937,1797.2683105617762,1840.8945696428418,2013.2317710667849,2016.1367850378156,1931.882530450821,1930.8377876877785,1970.4050812870264,1972.2711713984609,1968.9545733854175,1799.209302291274,1722.69640956074,1604.9127513542771,1649.4496436789632,1574.9724199995399,1693.7699764966965,1653.0091539025307,1694.9379062280059,1611.169465817511,1513.2521241903305,1435.8897572383285,1435.9114076942205,1594.3746389821172,1598.635945469141,1598.963231779635,1513.89445271343,1675.752703100443,1676.696010865271],"mean_ms":1520.0276859395672,"response_timing_field_excluded":true,"wall_seconds":6.906252690590918}
{"experiment":"pr78","model":"jev","arm":"baseline","run":2,"concurrency":16,"request_count":64,"source_file":"analysis/jev-baseline-measured-c16-r2/responses.jsonl","source_sha256":"19d7bf74413e3be96395675f04e33d1c1577c759e4cae17fe06419b73f060fd1","response_semantics_sha256":"d841d043178d0bad3fa2138c9a37785b89d5c8fddd81329b78a6272bed0bdb06","request_ids":["jev-010","jev-050","jev-017","jev-032","jev-038","jev-049","jev-029","jev-028","jev-018","jev-007","jev-001","jev-048","jev-039","jev-013","jev-043","jev-053","jev-057","jev-037","jev-005","jev-008","jev-056","jev-020","jev-061","jev-036","jev-051","jev-014","jev-004","jev-045","jev-031","jev-058","jev-062","jev-003","jev-033","jev-023","jev-035","jev-040","jev-026","jev-021","jev-054","jev-022","jev-011","jev-015","jev-000","jev-034","jev-063","jev-030","jev-044","jev-012","jev-060","jev-025","jev-052","jev-009","jev-041","jev-002","jev-027","jev-047","jev-016","jev-055","jev-046","jev-042","jev-059","jev-019","jev-006","jev-024"],"latency_ms":[185.1588385179639,366.65000580251217,681.0965100303292,385.3325853124261,1428.2952658832073,543.818193487823,817.2220457345247,403.72411347925663,1890.51016792655,927.523773163557,1156.2189664691687,834.5335274934769,1019.5601116865873,1566.9813510030508,1247.9774989187717,1703.0585194006562,1847.5164510309696,1802.3237874731421,1919.5388471707702,1918.4965202584863,1797.1031684428453,1678.6635490134358,1678.1965978443623,1678.24421916157,1678.1131494790316,1765.1128685101867,1647.961238399148,1695.1067075133324,1609.162900596857,1650.9364992380142,1704.1252423077822,1612.4591873958707,1608.1955200061202,1564.0218714252114,1520.2178349718451,1520.9723496809602,1679.5079736039042,1800.6029892712831,1843.9095867797732,2016.8062271550298,2019.6609105914831,1932.8930350020528,1931.778741069138,1969.7257680818439,1971.5763246640563,1968.1838536635041,1797.651318833232,1721.7399254441261,1604.063586331904,1648.748860694468,1574.3303280323744,1692.2881454229355,1653.589827939868,1693.3282688260078,1608.899561688304,1510.3339850902557,1433.428750373423,1433.1085672602057,1593.94933283329,1598.7681970000267,1599.42970238626,1513.5426679626107,1676.120687276125,1676.5372343361378],"mean_ms":1519.0411615913035,"response_timing_field_excluded":true,"wall_seconds":6.903079108335078}
{"experiment":"pr78","model":"jev","arm":"candidate","run":1,"concurrency":16,"request_count":64,"source_file":"analysis/jev-candidate-measured-c16-r1/responses.jsonl","source_sha256":"d8368dbb7bca28bf3f0d8319afe1b5e968dc181f4eac8b15689445d602991759","response_semantics_sha256":"d841d043178d0bad3fa2138c9a37785b89d5c8fddd81329b78a6272bed0bdb06","request_ids":["jev-010","jev-050","jev-017","jev-032","jev-038","jev-049","jev-029","jev-028","jev-018","jev-007","jev-001","jev-048","jev-039","jev-013","jev-043","jev-053","jev-057","jev-037","jev-005","jev-008","jev-056","jev-020","jev-061","jev-036","jev-051","jev-014","jev-004","jev-045","jev-031","jev-058","jev-062","jev-003","jev-033","jev-023","jev-035","jev-040","jev-026","jev-021","jev-054","jev-022","jev-011","jev-015","jev-000","jev-034","jev-063","jev-030","jev-044","jev-012","jev-060","jev-025","jev-052","jev-009","jev-041","jev-002","jev-027","jev-047","jev-016","jev-055","jev-046","jev-042","jev-059","jev-019","jev-006","jev-024"],"latency_ms":[186.05762347579002,527.582474052906,340.6611904501915,203.3030679449439,1107.9631987959146,684.0702230110765,819.5456247776747,545.6979991868138,1613.0187045782804,910.6596978381276,1336.8929764255881,928.4312846139073,1200.9165603667498,1751.5524383634329,1428.1028704717755,1887.1722873300314,1839.0462342649698,1958.1252224743366,1956.9560317322612,1788.1442271173,1787.0050529018044,1667.24406555295,1667.3444984480739,1593.7745766714215,1667.608086951077,1673.3784219250083,1598.1440134346485,1599.697575904429,1599.8215191066265,1594.769968651235,1642.767148092389,1601.4204733073711,1601.9532466307282,1556.7014049738646,1512.3590603470802,1512.4963652342558,1674.3135154247284,1794.8460821062326,1837.4997144564986,2010.2122677490115,2013.1019791588187,1920.8351373672485,1919.835327193141,1960.944321937859,1962.9408018663526,1961.962572298944,1793.5319133102894,1717.8162811324,1600.7057670503855,1645.734048448503,1571.9537325203419,1689.9053705856204,1647.3081558942795,1692.3147914931178,1608.6914483457804,1509.7085544839501,1433.1641914322972,1433.0869540572166,1592.8413067013025,1598.8015998154879,1599.1288824006915,1513.0926053971052,1674.2063369601965,1674.9520860612392],"mean_ms":1514.74720564147,"response_timing_field_excluded":true,"wall_seconds":6.8841054029762745}
{"experiment":"pr78","model":"jev","arm":"candidate","run":2,"concurrency":16,"request_count":64,"source_file":"analysis/jev-candidate-measured-c16-r2/responses.jsonl","source_sha256":"2cbf72c308667e01318f7aaf3d308e31494d1fac3e5f13f6e2e85a83bd237846","response_semantics_sha256":"d841d043178d0bad3fa2138c9a37785b89d5c8fddd81329b78a6272bed0bdb06","request_ids":["jev-010","jev-050","jev-017","jev-032","jev-038","jev-049","jev-029","jev-028","jev-018","jev-007","jev-001","jev-048","jev-039","jev-013","jev-043","jev-053","jev-057","jev-037","jev-005","jev-008","jev-056","jev-020","jev-061","jev-036","jev-051","jev-014","jev-004","jev-045","jev-031","jev-058","jev-062","jev-003","jev-033","jev-023","jev-035","jev-040","jev-026","jev-021","jev-054","jev-022","jev-011","jev-015","jev-000","jev-034","jev-063","jev-030","jev-044","jev-012","jev-060","jev-025","jev-052","jev-009","jev-041","jev-002","jev-027","jev-047","jev-016","jev-055","jev-046","jev-042","jev-059","jev-019","jev-006","jev-024"],"latency_ms":[183.59237350523472,529.0288468822837,339.29182682186365,201.71538926661015,1108.75494312495,685.279605910182,820.6117376685143,546.9991136342287,1750.6208634003997,911.9662223383784,1337.4667866155505,929.7984763979912,1201.470747590065,1565.369107760489,1428.6654768511653,1889.446772634983,1843.8504924997687,1960.7923459261656,1959.25163757056,1787.7901969477534,1786.9090912863612,1667.1702908352017,1667.8374074399471,1594.0033607184887,1667.8466899320483,1672.2655203193426,1597.5483562797308,1599.5919005945325,1599.6245360001922,1641.320209018886,1645.3823577612638,1600.168103352189,1600.8974928408861,1556.8382805213332,1512.9334377124906,1512.9341334104538,1673.811400309205,1793.8878685235977,1838.5780025273561,2010.749228298664,2013.328262604773,1922.7670319378376,1921.5773306787014,1963.7580402195454,1966.2025962024927,1966.663571074605,1797.081702388823,1721.2250269949436,1603.4514103084803,1648.0251755565405,1574.1485236212611,1691.6700135916471,1649.6308976784348,1693.5976864770055,1607.5532520189881,1509.0497601777315,1432.5856333598495,1432.926693931222,1593.206307850778,1597.6789761334658,1597.6655930280685,1510.7433088123798,1673.4818033874035,1674.0120630711317],"mean_ms":1515.376426439616,"response_timing_field_excluded":true,"wall_seconds":6.887452506460249}
{"experiment":"pr80","model":"cua","arm":"baseline","run":1,"concurrency":1,"request_count":64,"source_file":"analysis/cua-baseline-measured-c1-r1/responses.jsonl","source_sha256":"a44f4d9ebf33bfec05f794b4bca5f7be4068d1b7130c9f587405d0152a61b4a0","response_semantics_sha256":"5e797f138aa3aa07239cbfe9bd172148f9b3d4a761bb7dc95abaaf592342a189","request_ids":["cua-010","cua-050","cua-017","cua-032","cua-038","cua-049","cua-029","cua-028","cua-018","cua-007","cua-001","cua-048","cua-039","cua-013","cua-043","cua-053","cua-057","cua-037","cua-005","cua-008","cua-056","cua-020","cua-061","cua-036","cua-051","cua-014","cua-004","cua-045","cua-031","cua-058","cua-062","cua-003","cua-033","cua-023","cua-035","cua-040","cua-026","cua-021","cua-054","cua-022","cua-011","cua-015","cua-000","cua-034","cua-063","cua-030","cua-044","cua-012","cua-060","cua-025","cua-052","cua-009","cua-041","cua-002","cua-027","cua-047","cua-016","cua-055","cua-046","cua-042","cua-059","cua-019","cua-006","cua-024"],"latency_ms":[38.78873214125633,38.73073868453503,25.228281505405903,6.6158343106508255,38.35773188620806,24.798518978059292,24.90469627082348,6.779259070754051,38.144705817103386,25.096286088228226,23.733007721602917,6.469220854341984,24.578945711255074,24.26318172365427,24.768272414803505,24.42397829145193,24.19848833233118,24.190369062125683,23.4707398340106,6.418694742023945,6.378467194736004,6.367136724293232,24.24607239663601,6.4307162538170815,24.875719100236893,38.12674153596163,6.456500850617886,24.74795002490282,24.90790281444788,38.050102069973946,38.00383675843477,24.96069949120283,24.600486271083355,24.870061315596104,24.852859787642956,6.4860982820391655,38.17251604050398,25.5832402035594,38.32515887916088,38.74084819108248,25.67012794315815,24.929838255047798,6.4633190631866455,38.15303556621075,25.0793294981122,38.28551061451435,6.567506119608879,6.489005871117115,6.482443772256374,24.555551819503307,6.400739774107933,23.42168800532818,24.240117520093918,38.0488820374012,25.497835129499435,25.16769152134657,6.651937961578369,24.715542793273926,38.19978050887585,38.74545078724623,25.351849384605885,24.9323807656765,38.29433675855398,7.121437229216099],"mean_ms":23.572002130094916,"response_timing_field_excluded":true,"wall_seconds":1.5087885754182935}
{"experiment":"pr80","model":"cua","arm":"baseline","run":2,"concurrency":1,"request_count":64,"source_file":"analysis/cua-baseline-measured-c1-r2/responses.jsonl","source_sha256":"01f904c6603bd80b6327d70d676ab9f42710963f33bd43a2a4d73c0b86b0b0cc","response_semantics_sha256":"5e797f138aa3aa07239cbfe9bd172148f9b3d4a761bb7dc95abaaf592342a189","request_ids":["cua-010","cua-050","cua-017","cua-032","cua-038","cua-049","cua-029","cua-028","cua-018","cua-007","cua-001","cua-048","cua-039","cua-013","cua-043","cua-053","cua-057","cua-037","cua-005","cua-008","cua-056","cua-020","cua-061","cua-036","cua-051","cua-014","cua-004","cua-045","cua-031","cua-058","cua-062","cua-003","cua-033","cua-023","cua-035","cua-040","cua-026","cua-021","cua-054","cua-022","cua-011","cua-015","cua-000","cua-034","cua-063","cua-030","cua-044","cua-012","cua-060","cua-025","cua-052","cua-009","cua-041","cua-002","cua-027","cua-047","cua-016","cua-055","cua-046","cua-042","cua-059","cua-019","cua-006","cua-024"],"latency_ms":[38.10160607099533,38.56433741748333,24.80046357959509,6.545709446072578,38.16027380526066,24.48573149740696,24.323216639459133,6.646621040999889,37.92406804859638,25.018525309860706,23.656344041228294,6.487722508609295,24.63826071470976,24.41028133034706,24.631104432046413,24.213245138525963,24.222977459430695,24.186978116631508,23.39474856853485,6.446043029427528,6.392348557710648,6.423499435186386,24.15648102760315,6.431771442294121,24.74122028797865,38.121518678963184,6.830703467130661,25.063286535441875,24.833669885993004,38.090428337454796,39.13216106593609,25.397522374987602,24.817440658807755,24.772384203970432,24.702339433133602,6.587355397641659,38.17776311188936,25.264272466301918,38.56153227388859,39.05713278800249,25.336220860481262,24.82561394572258,6.391303613781929,38.13526500016451,26.09159518033266,38.88298198580742,6.62931427359581,6.537273526191711,6.460727192461491,24.368682876229286,6.407258100807667,23.41470494866371,24.22808576375246,38.1480073556304,25.306995026767254,25.003328919410706,6.5364232286810875,24.731244891881943,38.17030414938927,38.926729932427406,25.409678928554058,24.852494709193707,38.109542801976204,6.704823113977909],"mean_ms":23.562838905490935,"response_timing_field_excluded":true,"wall_seconds":1.5081975357607007}
{"experiment":"pr80","model":"cua","arm":"candidate","run":1,"concurrency":1,"request_count":64,"source_file":"analysis/cua-candidate-measured-c1-r1/responses.jsonl","source_sha256":"0ad8859d705e6f1367c39628ede6a8bca72ee0e3e9496fbff598de756b918eab","response_semantics_sha256":"5e797f138aa3aa07239cbfe9bd172148f9b3d4a761bb7dc95abaaf592342a189","request_ids":["cua-010","cua-050","cua-017","cua-032","cua-038","cua-049","cua-029","cua-028","cua-018","cua-007","cua-001","cua-048","cua-039","cua-013","cua-043","cua-053","cua-057","cua-037","cua-005","cua-008","cua-056","cua-020","cua-061","cua-036","cua-051","cua-014","cua-004","cua-045","cua-031","cua-058","cua-062","cua-003","cua-033","cua-023","cua-035","cua-040","cua-026","cua-021","cua-054","cua-022","cua-011","cua-015","cua-000","cua-034","cua-063","cua-030","cua-044","cua-012","cua-060","cua-025","cua-052","cua-009","cua-041","cua-002","cua-027","cua-047","cua-016","cua-055","cua-046","cua-042","cua-059","cua-019","cua-006","cua-024"],"latency_ms":[38.28347101807594,38.914550095796585,25.047479197382927,6.506049074232578,38.574693724513054,24.773080833256245,24.408345110714436,6.626815535128117,37.930697202682495,25.13846941292286,23.54871667921543,6.424150429666042,24.586772546172142,24.267171509563923,24.463688023388386,24.12522677332163,24.177015759050846,24.24374595284462,23.341226391494274,6.355263292789459,6.364695727825165,6.320315413177013,23.984474129974842,6.459953263401985,24.589864537119865,38.193763233721256,6.618817336857319,24.821805767714977,24.704658426344395,38.287133909761906,38.46710827201605,25.113104842603207,24.456246756017208,24.54628236591816,24.889887310564518,6.541011855006218,38.317871280014515,24.647222831845284,38.262393325567245,38.97881414741278,25.231425650417805,24.58519209176302,6.417340599000454,38.36572915315628,24.693254381418228,38.02440036088228,6.650631316006184,6.440892815589905,6.4795492216944695,24.24850035458803,6.488814018666744,23.327880539000034,24.088838137686253,38.1475780159235,25.093412026762962,24.6767345815897,6.489249877631664,24.525519460439682,38.133006542921066,38.43423258513212,25.095200166106224,24.747539311647415,38.21872267872095,6.83626439422369],"mean_ms":23.464718149625696,"response_timing_field_excluded":true,"wall_seconds":1.5019049495458603}
{"experiment":"pr80","model":"cua","arm":"candidate","run":2,"concurrency":1,"request_count":64,"source_file":"analysis/cua-candidate-measured-c1-r2/responses.jsonl","source_sha256":"766347e78f10059b1933dd1fa10d957baed64941897ebb4449464c95294f4310","response_semantics_sha256":"5e797f138aa3aa07239cbfe9bd172148f9b3d4a761bb7dc95abaaf592342a189","request_ids":["cua-010","cua-050","cua-017","cua-032","cua-038","cua-049","cua-029","cua-028","cua-018","cua-007","cua-001","cua-048","cua-039","cua-013","cua-043","cua-053","cua-057","cua-037","cua-005","cua-008","cua-056","cua-020","cua-061","cua-036","cua-051","cua-014","cua-004","cua-045","cua-031","cua-058","cua-062","cua-003","cua-033","cua-023","cua-035","cua-040","cua-026","cua-021","cua-054","cua-022","cua-011","cua-015","cua-000","cua-034","cua-063","cua-030","cua-044","cua-012","cua-060","cua-025","cua-052","cua-009","cua-041","cua-002","cua-027","cua-047","cua-016","cua-055","cua-046","cua-042","cua-059","cua-019","cua-006","cua-024"],"latency_ms":[38.436622358858585,38.44343684613705,24.681744165718555,6.475570611655712,37.793577648699284,24.721628986299038,24.387103505432606,6.593473255634308,38.21777831763029,24.77876842021942,23.454031907022,6.3902027904987335,24.329902604222298,24.06197413802147,24.5208777487278,24.080228060483932,24.067026562988758,24.12778977304697,23.445780389010906,6.365719251334667,6.3631245866417885,6.361188367009163,24.08137172460556,6.402628496289253,24.632866494357586,38.338376209139824,6.6405730322003365,24.621987715363503,24.560480378568172,38.236322812736034,38.16284239292145,25.74917860329151,24.731445126235485,24.698998779058456,24.493285454809666,6.5672388300299644,38.24483696371317,25.025831535458565,38.56380004435778,38.648287765681744,25.130228139460087,24.62598867714405,6.372724659740925,38.244932889938354,25.140244513750076,38.3704649284482,6.678602658212185,6.549883633852005,6.680757738649845,24.751759134232998,6.750224158167839,23.618750274181366,24.307582527399063,38.045709021389484,25.203845463693142,24.71343893557787,6.5258946269750595,24.428395554423332,38.060068152844906,39.091519080102444,25.594611652195454,25.316976010799408,39.54095579683781,6.893236190080643],"mean_ms":23.51772964175325,"response_timing_field_excluded":true,"wall_seconds":1.505307937040925}
{"experiment":"pr80","model":"cua","arm":"baseline","run":1,"concurrency":8,"request_count":64,"source_file":"analysis/cua-baseline-measured-c8-r1/responses.jsonl","source_sha256":"1fa1a2083557898e338ef3582286afa0af9dec50ac453b03d4f53441f77413ed","response_semantics_sha256":"5e797f138aa3aa07239cbfe9bd172148f9b3d4a761bb7dc95abaaf592342a189","request_ids":["cua-010","cua-050","cua-017","cua-032","cua-038","cua-049","cua-029","cua-028","cua-018","cua-007","cua-001","cua-048","cua-039","cua-013","cua-043","cua-053","cua-057","cua-037","cua-005","cua-008","cua-056","cua-020","cua-061","cua-036","cua-051","cua-014","cua-004","cua-045","cua-031","cua-058","cua-062","cua-003","cua-033","cua-023","cua-035","cua-040","cua-026","cua-021","cua-054","cua-022","cua-011","cua-015","cua-000","cua-034","cua-063","cua-030","cua-044","cua-012","cua-060","cua-025","cua-052","cua-009","cua-041","cua-002","cua-027","cua-047","cua-016","cua-055","cua-046","cua-042","cua-059","cua-019","cua-006","cua-024"],"latency_ms":[39.969777688384056,104.48353737592697,234.7877062857151,57.0821026340127,139.2022930085659,255.25616947561502,264.5366555079818,50.089744850993156,135.85188798606396,299.3476763367653,247.56416399031878,109.36068557202816,242.34312120825052,162.5753166154027,219.533015973866,161.99166048318148,162.10914589464664,162.13727090507746,160.99489945918322,49.30748511105776,51.76971759647131,56.85929395258427,249.3509380146861,53.597149439156055,296.4711394160986,83.01267866045237,79.15530540049076,242.6412245258689,321.76296692341566,110.7213543727994,136.38497050851583,319.9984021484852,213.1351474672556,319.7191068902612,289.92353193461895,50.54047144949436,78.7688484415412,267.25548319518566,110.05722265690565,136.95967197418213,340.79721570014954,340.77202808111906,77.52034813165665,106.14876449108124,281.6469222307205,108.49027149379253,108.738680370152,108.54803398251534,79.38141655176878,204.60994727909565,46.843026764690876,179.06477861106396,182.76676163077354,76.75916142761707,313.68046533316374,278.11411768198013,48.32433070987463,265.879662707448,85.57034470140934,116.29780195653439,226.19432117789984,216.75484534353018,136.4096077159047,107.90852271020412],"mean_ms":168.18484872055706,"response_timing_field_excluded":true,"wall_seconds":1.3914518635720015}
{"experiment":"pr80","model":"cua","arm":"baseline","run":2,"concurrency":8,"request_count":64,"source_file":"analysis/cua-baseline-measured-c8-r2/responses.jsonl","source_sha256":"a3ded9a53bb872fcc0ecbce4b7a00c8a32b52e45dbc2f9adb540f1a781d84055","response_semantics_sha256":"5e797f138aa3aa07239cbfe9bd172148f9b3d4a761bb7dc95abaaf592342a189","request_ids":["cua-010","cua-050","cua-017","cua-032","cua-038","cua-049","cua-029","cua-028","cua-018","cua-007","cua-001","cua-048","cua-039","cua-013","cua-043","cua-053","cua-057","cua-037","cua-005","cua-008","cua-056","cua-020","cua-061","cua-036","cua-051","cua-014","cua-004","cua-045","cua-031","cua-058","cua-062","cua-003","cua-033","cua-023","cua-035","cua-040","cua-026","cua-021","cua-054","cua-022","cua-011","cua-015","cua-000","cua-034","cua-063","cua-030","cua-044","cua-012","cua-060","cua-025","cua-052","cua-009","cua-041","cua-002","cua-027","cua-047","cua-016","cua-055","cua-046","cua-042","cua-059","cua-019","cua-006","cua-024"],"latency_ms":[40.1366138830781,75.43927058577538,252.57618725299835,86.31111774593592,140.17570205032825,261.39223482459784,270.72278410196304,79.81541566550732,136.2331137061119,268.8614297658205,218.53969991207123,106.80729802697897,241.8181048706174,162.57865726947784,211.6897339001298,161.96499299257994,162.18010615557432,162.1628226712346,160.95034312456846,49.281143583357334,49.14168454706669,56.61016423255205,249.72999561578035,57.24875442683697,299.62392058223486,86.1759465187788,82.26197771728039,242.80386697500944,322.37453293055296,110.39723828434944,136.66106294840574,321.2602911517024,213.94580882042646,320.99809497594833,291.0251980647445,50.3049660474062,78.98048218339682,267.0468632131815,111.3289687782526,137.28122878819704,340.2780955657363,340.4526002705097,77.38588936626911,106.33577778935432,280.98608925938606,108.09844080358744,107.90661163628101,107.99781698733568,78.61713599413633,204.35091760009527,46.69097438454628,178.44145372509956,182.43626412004232,76.47393736988306,312.1522543951869,276.95040311664343,48.36431983858347,264.38343059271574,85.75001265853643,116.01020209491253,224.95801467448473,215.61058517545462,135.33621653914452,106.48409090936184],"mean_ms":168.08264615247026,"response_timing_field_excluded":true,"wall_seconds":1.390524529851973}
{"experiment":"pr80","model":"cua","arm":"candidate","run":1,"concurrency":8,"request_count":64,"source_file":"analysis/cua-candidate-measured-c8-r1/responses.jsonl","source_sha256":"7f317a778182d5e3a882ce10c3d7382b620ba2bacaba3350eabb49c976077f40","response_semantics_sha256":"5e797f138aa3aa07239cbfe9bd172148f9b3d4a761bb7dc95abaaf592342a189","request_ids":["cua-010","cua-050","cua-017","cua-032","cua-038","cua-049","cua-029","cua-028","cua-018","cua-007","cua-001","cua-048","cua-039","cua-013","cua-043","cua-053","cua-057","cua-037","cua-005","cua-008","cua-056","cua-020","cua-061","cua-036","cua-051","cua-014","cua-004","cua-045","cua-031","cua-058","cua-062","cua-003","cua-033","cua-023","cua-035","cua-040","cua-026","cua-021","cua-054","cua-022","cua-011","cua-015","cua-000","cua-034","cua-063","cua-030","cua-044","cua-012","cua-060","cua-025","cua-052","cua-009","cua-041","cua-002","cua-027","cua-047","cua-016","cua-055","cua-046","cua-042","cua-059","cua-019","cua-006","cua-024"],"latency_ms":[39.94288761168718,103.48529927432537,239.93146233260632,44.625469483435154,138.91550432890654,254.76296339184046,264.07493371516466,55.365609005093575,135.82607172429562,297.6609179750085,247.65624571591616,109.97714474797249,241.2913767620921,161.6082340478897,218.18603668361902,161.02967504411936,161.13445162773132,161.06178238987923,159.50557310134172,48.9896135404706,48.83106425404549,56.33251368999481,248.27444460242987,57.17536248266697,294.9407445266843,82.08533748984337,78.3533276990056,241.84716120362282,320.88715583086014,109.97902601957321,136.24879345297813,319.03494335711,212.8250701352954,318.5285497456789,288.60469441860914,50.4729263484478,78.47788743674755,265.3889348730445,109.64652802795172,136.02304831147194,338.94769102334976,338.83823547512293,76.89958531409502,105.64044490456581,280.34471813589334,108.4635853767395,108.64890459924936,108.4169577807188,79.23818193376064,203.97669728845358,46.4171227067709,177.87579633295536,181.73249997198582,76.19260437786579,311.4807177335024,276.0926354676485,48.08128625154495,263.9373429119587,85.7330821454525,116.23718217015266,224.5435919612646,215.2816578745842,135.08237805217505,106.33866861462593],"mean_ms":167.39734898146708,"response_timing_field_excluded":true,"wall_seconds":1.3848771387711167}
{"experiment":"pr80","model":"cua","arm":"candidate","run":2,"concurrency":8,"request_count":64,"source_file":"analysis/cua-candidate-measured-c8-r2/responses.jsonl","source_sha256":"2f4588eda61145d6f06e832274af3b20689cd916456b802a641f6424afc9018c","response_semantics_sha256":"5e797f138aa3aa07239cbfe9bd172148f9b3d4a761bb7dc95abaaf592342a189","request_ids":["cua-010","cua-050","cua-017","cua-032","cua-038","cua-049","cua-029","cua-028","cua-018","cua-007","cua-001","cua-048","cua-039","cua-013","cua-043","cua-053","cua-057","cua-037","cua-005","cua-008","cua-056","cua-020","cua-061","cua-036","cua-051","cua-014","cua-004","cua-045","cua-031","cua-058","cua-062","cua-003","cua-033","cua-023","cua-035","cua-040","cua-026","cua-021","cua-054","cua-022","cua-011","cua-015","cua-000","cua-034","cua-063","cua-030","cua-044","cua-012","cua-060","cua-025","cua-052","cua-009","cua-041","cua-002","cua-027","cua-047","cua-016","cua-055","cua-046","cua-042","cua-059","cua-019","cua-006","cua-024"],"latency_ms":[39.862711913883686,102.8415709733963,239.5786363631487,44.51538622379303,138.17378599196672,254.51545976102352,263.9678008854389,55.18055893480778,135.09082328528166,297.8951819241047,247.7589650079608,110.1349014788866,242.05608572810888,162.7555787563324,218.68270263075829,161.35286446660757,161.25398594886065,161.16330306977034,159.76336225867271,48.75486996024847,48.73380530625582,56.34822230786085,247.81503900885582,57.0888202637434,294.17627211660147,82.37101696431637,78.41884531080723,241.21639132499695,320.02966199070215,109.80141628533602,135.89463848620653,318.4217046946287,211.99923194944859,319.03609447181225,289.0905709937215,50.226252526044846,78.34606803953648,266.5950646623969,109.84624177217484,136.81199122220278,340.0691784918308,339.9565853178501,77.74162385612726,106.60835448652506,280.4603558033705,108.51930268108845,108.63103158771992,108.32345113158226,78.85482255369425,203.60254310071468,46.3386494666338,177.71939001977444,181.6568188369274,76.53116900473833,310.73242612183094,274.97559133917093,47.85710293799639,262.96520978212357,85.56533604860306,116.16489011794329,223.47288578748703,214.26023449748755,134.88265220075846,106.12615942955017],"mean_ms":167.33721327909734,"response_timing_field_excluded":true,"wall_seconds":1.384014980867505}
{"experiment":"pr80","model":"cua","arm":"baseline","run":1,"concurrency":16,"request_count":64,"source_file":"analysis/cua-baseline-measured-c16-r1/responses.jsonl","source_sha256":"6de6e81c9818ef9758c584b397f0770733918fd96b9ceb116ac25d0125618fec","response_semantics_sha256":"5e797f138aa3aa07239cbfe9bd172148f9b3d4a761bb7dc95abaaf592342a189","request_ids":["cua-010","cua-050","cua-017","cua-032","cua-038","cua-049","cua-029","cua-028","cua-018","cua-007","cua-001","cua-048","cua-039","cua-013","cua-043","cua-053","cua-057","cua-037","cua-005","cua-008","cua-056","cua-020","cua-061","cua-036","cua-051","cua-014","cua-004","cua-045","cua-031","cua-058","cua-062","cua-003","cua-033","cua-023","cua-035","cua-040","cua-026","cua-021","cua-054","cua-022","cua-011","cua-015","cua-000","cua-034","cua-063","cua-030","cua-044","cua-012","cua-060","cua-025","cua-052","cua-009","cua-041","cua-002","cua-027","cua-047","cua-016","cua-055","cua-046","cua-042","cua-059","cua-019","cua-006","cua-024"],"latency_ms":[41.14310070872307,76.12711656838655,376.1335453018546,81.3755989074707,217.5900638103485,360.00914219766855,350.1598061993718,86.30609046667814,180.92111125588417,516.0985207185149,389.78509698063135,115.82567356526852,609.9926987662911,420.7791304215789,603.7880098447204,398.5631950199604,434.14104729890823,408.4664238616824,412.67478186637163,155.02010844647884,156.81848861277103,128.38705629110336,415.25378450751305,99.0399494767189,659.3158785253763,147.31341414153576,158.43944996595383,559.3019686639309,655.9007661417127,176.21445935219526,202.86162197589874,674.3192598223686,543.4058448299766,640.4335126280785,636.0500007867813,159.8134422674775,185.06157118827105,504.8824604600668,216.11323114484549,217.39582810550928,629.6829646453261,629.4200280681252,187.10063304752111,213.04331440478563,652.9601057991385,213.97873666137457,188.47181275486946,157.8623168170452,157.50753041356802,445.1409298926592,101.80207993835211,402.4145556613803,400.26917587965727,129.60910517722368,430.1336035132408,419.1757468506694,126.23875681310892,386.2231746315956,152.85310614854097,182.95095581561327,329.8749504610896,317.8863227367401,183.42801742255688,183.19497723132372],"mean_ms":321.756955498131,"response_timing_field_excluded":true,"wall_seconds":1.3935265466570854}
{"experiment":"pr80","model":"cua","arm":"baseline","run":2,"concurrency":16,"request_count":64,"source_file":"analysis/cua-baseline-measured-c16-r2/responses.jsonl","source_sha256":"75d1388114d317a7898dd4788ba14b31eaba8f9ca12e1cc91382590d526a4c47","response_semantics_sha256":"5e797f138aa3aa07239cbfe9bd172148f9b3d4a761bb7dc95abaaf592342a189","request_ids":["cua-010","cua-050","cua-017","cua-032","cua-038","cua-049","cua-029","cua-028","cua-018","cua-007","cua-001","cua-048","cua-039","cua-013","cua-043","cua-053","cua-057","cua-037","cua-005","cua-008","cua-056","cua-020","cua-061","cua-036","cua-051","cua-014","cua-004","cua-045","cua-031","cua-058","cua-062","cua-003","cua-033","cua-023","cua-035","cua-040","cua-026","cua-021","cua-054","cua-022","cua-011","cua-015","cua-000","cua-034","cua-063","cua-030","cua-044","cua-012","cua-060","cua-025","cua-052","cua-009","cua-041","cua-002","cua-027","cua-047","cua-016","cua-055","cua-046","cua-042","cua-059","cua-019","cua-006","cua-024"],"latency_ms":[41.2236787378788,76.06667466461658,365.3861153870821,86.91698219627142,180.47225754708052,374.38266444951296,355.08113633841276,80.45802172273397,215.46108461916447,503.6602606996894,388.7036209926009,115.18583726137877,603.328475728631,410.1579859852791,597.0571348443627,419.6880115196109,433.03940165787935,407.9152224585414,412.09752205759287,154.1037494316697,156.2088755890727,128.39010171592236,416.0096002742648,99.0186333656311,659.7927734255791,147.50328660011292,158.81154779344797,559.1437006369233,656.527447514236,176.97983514517546,202.93606352061033,674.6536400169134,543.6089839786291,641.2831796333194,636.9706876575947,159.95778050273657,185.14825217425823,505.20306546241045,215.53311124444008,217.11459383368492,629.8923538997769,629.8423362895846,187.16588988900185,212.72525563836098,652.8892070055008,213.37902266532183,184.30391512811184,157.80928079038858,157.39483386278152,445.7008372992277,102.60510351508856,407.2184469550848,406.72957990318537,129.87779080867767,430.41133508086205,419.42099016159773,126.60388927906752,386.10438350588083,152.86677330732346,183.83142445236444,329.7542929649353,305.54363690316677,183.0862509086728,182.7478874474764],"mean_ms":321.5482143132249,"response_timing_field_excluded":true,"wall_seconds":1.39288841933012}
{"experiment":"pr80","model":"cua","arm":"candidate","run":1,"concurrency":16,"request_count":64,"source_file":"analysis/cua-candidate-measured-c16-r1/responses.jsonl","source_sha256":"872a5f7c06448aebb35861bffadc0ef0ad79b2e3c8e7debb3756d03a28bd7c26","response_semantics_sha256":"5e797f138aa3aa07239cbfe9bd172148f9b3d4a761bb7dc95abaaf592342a189","request_ids":["cua-010","cua-050","cua-017","cua-032","cua-038","cua-049","cua-029","cua-028","cua-018","cua-007","cua-001","cua-048","cua-039","cua-013","cua-043","cua-053","cua-057","cua-037","cua-005","cua-008","cua-056","cua-020","cua-061","cua-036","cua-051","cua-014","cua-004","cua-045","cua-031","cua-058","cua-062","cua-003","cua-033","cua-023","cua-035","cua-040","cua-026","cua-021","cua-054","cua-022","cua-011","cua-015","cua-000","cua-034","cua-063","cua-030","cua-044","cua-012","cua-060","cua-025","cua-052","cua-009","cua-041","cua-002","cua-027","cua-047","cua-016","cua-055","cua-046","cua-042","cua-059","cua-019","cua-006","cua-024"],"latency_ms":[41.28977004438639,76.34640205651522,347.375750541687,81.56056795269251,174.08865969628096,356.28989432007074,365.5082443729043,86.43157966434956,214.32885061949492,553.4574054181576,392.2684686258435,109.5679048448801,558.8584486395121,401.4825550839305,605.7437770068645,452.5631945580244,430.94113282859325,405.2653228864074,409.4314109534025,152.1500749513507,154.44706939160824,125.85785519331694,413.7996369972825,98.2815120369196,656.8376896902919,144.45506408810616,158.8140530511737,557.4677130207419,653.8181733340025,177.0314620807767,202.42114085704088,671.8620052561164,515.826040878892,637.3000582680106,632.9712895676494,158.8243767619133,184.23887435346842,502.44947616010904,185.86292304098606,216.59239474684,656.4017487689853,626.7273863777518,185.9366213902831,211.7472141981125,650.1642102375627,212.35752291977406,187.38235346972942,156.77524264901876,157.20397513359785,443.5554537922144,101.6342593356967,401.14721562713385,399.0628579631448,128.94159462302923,428.58181428164244,417.5546560436487,125.7023187354207,384.7463736310601,151.81496366858482,182.11614526808262,328.51011864840984,310.4034084826708,182.73407220840454,182.55355395376682],"mean_ms":319.966614144505,"response_timing_field_excluded":true,"wall_seconds":1.3864850895479321}
{"experiment":"pr80","model":"cua","arm":"candidate","run":2,"concurrency":16,"request_count":64,"source_file":"analysis/cua-candidate-measured-c16-r2/responses.jsonl","source_sha256":"bfbd66b269badf7416c6406d6a2b5c1e2064184251ff45994f5168993244878b","response_semantics_sha256":"5e797f138aa3aa07239cbfe9bd172148f9b3d4a761bb7dc95abaaf592342a189","request_ids":["cua-010","cua-050","cua-017","cua-032","cua-038","cua-049","cua-029","cua-028","cua-018","cua-007","cua-001","cua-048","cua-039","cua-013","cua-043","cua-053","cua-057","cua-037","cua-005","cua-008","cua-056","cua-020","cua-061","cua-036","cua-051","cua-014","cua-004","cua-045","cua-031","cua-058","cua-062","cua-003","cua-033","cua-023","cua-035","cua-040","cua-026","cua-021","cua-054","cua-022","cua-011","cua-015","cua-000","cua-034","cua-063","cua-030","cua-044","cua-012","cua-060","cua-025","cua-052","cua-009","cua-041","cua-002","cua-027","cua-047","cua-016","cua-055","cua-046","cua-042","cua-059","cua-019","cua-006","cua-024"],"latency_ms":[41.388181038200855,87.75837626308203,336.80829126387835,46.12204525619745,140.8114042133093,357.1042465046048,366.3864927366376,92.32077840715647,215.90615902096033,553.2832704484463,421.53310775756836,150.68296529352665,599.8224541544914,437.38165125250816,611.6484934464097,453.285857103765,431.2414461746812,435.4335553944111,409.44915637373924,154.31877318769693,125.59083290398121,125.32891239970922,411.9496000930667,100.46770330518484,655.5306557565928,135.55545173585415,150.35149548202753,556.447708979249,652.6663210242987,176.1261560022831,177.03879345208406,645.5988604575396,515.48080611974,635.7354130595922,631.538899615407,158.1094805151224,187.7114875242114,501.58438086509705,185.34956499934196,216.1337062716484,625.9582340717316,625.9669763967395,186.45877856761217,211.7555309087038,649.3500722572207,212.58346177637577,187.6675607636571,157.0621971040964,159.92018952965736,442.68786162137985,101.55101213604212,400.14452766627073,398.1052050366998,128.65013536065817,427.67487186938524,412.3891117051244,125.36361161619425,383.8504021987319,151.24940034002066,181.55650049448013,327.68190931528807,315.738208591938,182.49068316072226,182.31539893895388],"mean_ms":319.7680433950154,"response_timing_field_excluded":true,"wall_seconds":1.3849683590233326}
{"experiment":"pr80","model":"jev","arm":"baseline","run":1,"concurrency":1,"request_count":64,"source_file":"analysis/jev-baseline-measured-c1-r1/responses.jsonl","source_sha256":"3bf265b18006d3f5ed21c868882359fc486c88dea6cd735035e18d5c5011b1e2","response_semantics_sha256":"d841d043178d0bad3fa2138c9a37785b89d5c8fddd81329b78a6272bed0bdb06","request_ids":["jev-010","jev-050","jev-017","jev-032","jev-038","jev-049","jev-029","jev-028","jev-018","jev-007","jev-001","jev-048","jev-039","jev-013","jev-043","jev-053","jev-057","jev-037","jev-005","jev-008","jev-056","jev-020","jev-061","jev-036","jev-051","jev-014","jev-004","jev-045","jev-031","jev-058","jev-062","jev-003","jev-033","jev-023","jev-035","jev-040","jev-026","jev-021","jev-054","jev-022","jev-011","jev-015","jev-000","jev-034","jev-063","jev-030","jev-044","jev-012","jev-060","jev-025","jev-052","jev-009","jev-041","jev-002","jev-027","jev-047","jev-016","jev-055","jev-046","jev-042","jev-059","jev-019","jev-006","jev-024"],"latency_ms":[181.47689662873745,184.42910071462393,142.2190684825182,19.228669814765453,183.41377563774586,140.10443165898323,137.71607540547848,19.28673405200243,180.46917486935854,94.98047363013029,137.70848233252764,19.20986734330654,93.24916359037161,137.56557367742062,93.246771954,137.49046064913273,137.56957463920116,137.33322452753782,137.31542509049177,18.959580920636654,18.85796058923006,18.97837221622467,137.28714734315872,19.08297650516033,93.38021837174892,180.88585697114468,20.059567876160145,138.50357104092836,93.38257741183043,182.00600892305374,185.24310644716024,96.47310338914394,137.40101177245378,93.26185192912817,93.13019458204508,18.966371193528175,180.05885370075703,140.91086760163307,181.38086050748825,189.54598251730204,95.74111830443144,93.33605132997036,18.940411508083344,179.5993149280548,95.90779058635235,181.24384805560112,20.10488696396351,19.394771195948124,19.238024950027466,137.52804696559906,19.371663220226765,137.3236794024706,137.38346938043833,181.93488847464323,95.83255369216204,93.30528415739536,18.986945040524006,93.25492568314075,181.64807930588722,183.09194687753916,95.00191826373339,93.25138386338949,180.3473262116313,20.04721388220787],"mean_ms":108.49350826174486,"response_timing_field_excluded":true,"wall_seconds":6.943773970939219}
{"experiment":"pr80","model":"jev","arm":"baseline","run":2,"concurrency":1,"request_count":64,"source_file":"analysis/jev-baseline-measured-c1-r2/responses.jsonl","source_sha256":"b3b825e0fb1e4477d0d375db916c52e98354fef818b6cbc8b54a857973fa4f3d","response_semantics_sha256":"d841d043178d0bad3fa2138c9a37785b89d5c8fddd81329b78a6272bed0bdb06","request_ids":["jev-010","jev-050","jev-017","jev-032","jev-038","jev-049","jev-029","jev-028","jev-018","jev-007","jev-001","jev-048","jev-039","jev-013","jev-043","jev-053","jev-057","jev-037","jev-005","jev-008","jev-056","jev-020","jev-061","jev-036","jev-051","jev-014","jev-004","jev-045","jev-031","jev-058","jev-062","jev-003","jev-033","jev-023","jev-035","jev-040","jev-026","jev-021","jev-054","jev-022","jev-011","jev-015","jev-000","jev-034","jev-063","jev-030","jev-044","jev-012","jev-060","jev-025","jev-052","jev-009","jev-041","jev-002","jev-027","jev-047","jev-016","jev-055","jev-046","jev-042","jev-059","jev-019","jev-006","jev-024"],"latency_ms":[181.22427444905043,182.73677304387093,142.09115970879793,19.350431859493256,183.29492397606373,140.0184202939272,137.86735944449902,19.299019128084183,183.05567279458046,95.21531220525503,137.6217734068632,19.116436131298542,93.13399810343981,137.2322291135788,93.2271471247077,137.45275977998972,137.4598192051053,137.23772205412388,137.58951425552368,19.032043404877186,18.94799154251814,18.90293601900339,137.26062513887882,19.04645748436451,93.41270662844181,181.57823756337166,19.96749173849821,138.37097771465778,93.20547990500927,181.03400990366936,186.7149956524372,95.69535497575998,137.46084738522768,93.23448967188597,93.29896420240402,19.132603891193867,182.03171156346798,139.72030021250248,180.41154835373163,187.4699853360653,95.91213334351778,93.13429426401854,18.874778412282467,180.41282147169113,95.20991891622543,179.893902502954,19.929299131035805,19.47433315217495,19.189990125596523,137.7669693902135,19.212511368095875,137.48414907604456,138.12614791095257,185.15109363943338,95.89909855276346,93.2523813098669,18.95131077617407,93.19638554006815,181.32839258760214,184.84843336045742,95.66745441406965,93.31838972866535,182.88719188421965,20.24500723928213],"mean_ms":108.58626394474413,"response_timing_field_excluded":true,"wall_seconds":6.949708368629217}
{"experiment":"pr80","model":"jev","arm":"candidate","run":1,"concurrency":1,"request_count":64,"source_file":"analysis/jev-candidate-measured-c1-r1/responses.jsonl","source_sha256":"592b8172875101363326aaf7637d0351145a54c40d2055c9cd202c4879ace92f","response_semantics_sha256":"d841d043178d0bad3fa2138c9a37785b89d5c8fddd81329b78a6272bed0bdb06","request_ids":["jev-010","jev-050","jev-017","jev-032","jev-038","jev-049","jev-029","jev-028","jev-018","jev-007","jev-001","jev-048","jev-039","jev-013","jev-043","jev-053","jev-057","jev-037","jev-005","jev-008","jev-056","jev-020","jev-061","jev-036","jev-051","jev-014","jev-004","jev-045","jev-031","jev-058","jev-062","jev-003","jev-033","jev-023","jev-035","jev-040","jev-026","jev-021","jev-054","jev-022","jev-011","jev-015","jev-000","jev-034","jev-063","jev-030","jev-044","jev-012","jev-060","jev-025","jev-052","jev-009","jev-041","jev-002","jev-027","jev-047","jev-016","jev-055","jev-046","jev-042","jev-059","jev-019","jev-006","jev-024"],"latency_ms":[178.78962866961956,182.9304015263915,142.39423535764217,19.576512277126312,183.6915072053671,140.36308322101831,138.0367949604988,19.37386952340603,182.39409662783146,95.5860847607255,137.54868786782026,19.496040418744087,94.15523335337639,137.76782620698214,93.67163479328156,137.72718608379364,137.61054631322622,137.60187942534685,137.6251569017768,19.3290114402771,19.310995005071163,19.078842364251614,137.46496848762035,19.472641870379448,93.72652694582939,181.8346558138728,20.277620293200016,138.6975860223174,93.46036054193974,181.24010786414146,185.75445655733347,96.15298733115196,137.82769534736872,93.76735612750053,93.75416580587626,19.1821102052927,179.17750403285027,140.13694506138563,181.53628334403038,189.09703195095062,96.00402414798737,93.54982618242502,19.12623830139637,180.2554177120328,95.60452308505774,181.49019498378038,20.480530336499214,19.502820447087288,19.167262129485607,137.6181710511446,19.297322258353233,137.32906058430672,137.33937684446573,180.7940797880292,95.61064373701811,93.34552194923162,19.055450335144997,93.26826222240925,180.10448198765516,186.70623376965523,95.67080065608025,93.79980340600014,181.0705829411745,20.189090631902218],"mean_ms":108.64062464679591,"response_timing_field_excluded":true,"wall_seconds":6.953225891105831}
{"experiment":"pr80","model":"jev","arm":"candidate","run":2,"concurrency":1,"request_count":64,"source_file":"analysis/jev-candidate-measured-c1-r2/responses.jsonl","source_sha256":"5bad060227a50d3739b7a7d9714c197b9936b915bb69576795dbbe7f8fcc1c6f","response_semantics_sha256":"d841d043178d0bad3fa2138c9a37785b89d5c8fddd81329b78a6272bed0bdb06","request_ids":["jev-010","jev-050","jev-017","jev-032","jev-038","jev-049","jev-029","jev-028","jev-018","jev-007","jev-001","jev-048","jev-039","jev-013","jev-043","jev-053","jev-057","jev-037","jev-005","jev-008","jev-056","jev-020","jev-061","jev-036","jev-051","jev-014","jev-004","jev-045","jev-031","jev-058","jev-062","jev-003","jev-033","jev-023","jev-035","jev-040","jev-026","jev-021","jev-054","jev-022","jev-011","jev-015","jev-000","jev-034","jev-063","jev-030","jev-044","jev-012","jev-060","jev-025","jev-052","jev-009","jev-041","jev-002","jev-027","jev-047","jev-016","jev-055","jev-046","jev-042","jev-059","jev-019","jev-006","jev-024"],"latency_ms":[177.93848924338818,184.3387857079506,144.05298233032227,19.18836310505867,183.29474609345198,140.06024692207575,138.17414082586765,19.419429823756218,181.8826012313366,95.3961219638586,137.6761393621564,19.203880801796913,93.73003523796797,137.67098542302847,93.79908908158541,137.72109895944595,137.5477183610201,137.53543328493834,137.70086970180273,19.27581150084734,19.085673615336418,19.096254371106625,137.21022941172123,19.265596754848957,93.48233882337809,182.8092997893691,20.27891017496586,138.58552277088165,93.63813884556293,181.10669404268265,186.6066660732031,96.20498958975077,137.8043917939067,93.63070409744978,93.5937324538827,19.234096631407738,181.2638146802783,140.24738036096096,182.42456484586,188.91042284667492,96.23327571898699,93.8132256269455,19.205150194466114,181.13447166979313,95.69758456200361,180.31364679336548,20.27089800685644,19.62501462548971,19.2372789606452,137.53354735672474,19.173718988895416,137.48287223279476,137.85483967512846,183.46698116511106,96.29823639988899,93.86995062232018,19.24185547977686,93.63439865410328,181.3335819169879,185.45156624168158,96.07090428471565,93.71563792228699,181.42366595566273,20.262121222913265],"mean_ms":108.7879814876942,"response_timing_field_excluded":true,"wall_seconds":6.96267659869045}
{"experiment":"pr80","model":"jev","arm":"baseline","run":1,"concurrency":8,"request_count":64,"source_file":"analysis/jev-baseline-measured-c8-r1/responses.jsonl","source_sha256":"243445ed5005759d9531bd5589afaebc5d70be168e687db9b34c22a732264acb","response_semantics_sha256":"d841d043178d0bad3fa2138c9a37785b89d5c8fddd81329b78a6272bed0bdb06","request_ids":["jev-010","jev-050","jev-017","jev-032","jev-038","jev-049","jev-029","jev-028","jev-018","jev-007","jev-001","jev-048","jev-039","jev-013","jev-043","jev-053","jev-057","jev-037","jev-005","jev-008","jev-056","jev-020","jev-061","jev-036","jev-051","jev-014","jev-004","jev-045","jev-031","jev-058","jev-062","jev-003","jev-033","jev-023","jev-035","jev-040","jev-026","jev-021","jev-054","jev-022","jev-011","jev-015","jev-000","jev-034","jev-063","jev-030","jev-044","jev-012","jev-060","jev-025","jev-052","jev-009","jev-041","jev-002","jev-027","jev-047","jev-016","jev-055","jev-046","jev-042","jev-059","jev-019","jev-006","jev-024"],"latency_ms":[181.23221583664417,809.9292255938053,337.2755916789174,199.67944640666246,994.6976769715548,493.90323739498854,629.8953024670482,354.3155863881111,999.9727141112089,1075.0152273103595,1073.503402993083,1073.6332321539521,1026.7354305833578,1026.29198692739,939.0345430001616,889.2367267981172,839.1765225678682,880.6905373930931,880.4679093882442,880.2876630797982,806.7863434553146,689.1247956082225,733.3343205973506,615.8529063686728,572.4423686042428,618.2389948517084,501.43210776150227,621.3069930672646,694.4903125986457,855.7217912748456,903.5776564851403,980.3679157048464,1024.0642121061683,934.276775456965,1007.4606202542782,887.6740895211697,977.0158799365163,935.9966050833464,930.1687609404325,1022.0825476571918,980.4516946896911,980.7924218475819,906.8207144737244,1066.2311390042305,979.1502021253109,1020.2005039900541,861.1280620098114,693.1993393227458,617.4117438495159,661.6175649687648,661.5065019577742,620.0969181954861,661.8760377168655,664.680065587163,740.4290791600943,813.5564457625151,813.071746379137,768.9620889723301,926.5372343361378,974.9638512730598,933.1764858216047,842.9674105718732,927.3721324279904,854.5856522396207],"mean_ms":810.4246127040824,"response_timing_field_excluded":true,"wall_seconds":6.864528428763151}
{"experiment":"pr80","model":"jev","arm":"baseline","run":2,"concurrency":8,"request_count":64,"source_file":"analysis/jev-baseline-measured-c8-r2/responses.jsonl","source_sha256":"7f922bd2b69fd4b78f75ea50a47e42835501dcd531698e550ba07951a5672dc7","response_semantics_sha256":"d841d043178d0bad3fa2138c9a37785b89d5c8fddd81329b78a6272bed0bdb06","request_ids":["jev-010","jev-050","jev-017","jev-032","jev-038","jev-049","jev-029","jev-028","jev-018","jev-007","jev-001","jev-048","jev-039","jev-013","jev-043","jev-053","jev-057","jev-037","jev-005","jev-008","jev-056","jev-020","jev-061","jev-036","jev-051","jev-014","jev-004","jev-045","jev-031","jev-058","jev-062","jev-003","jev-033","jev-023","jev-035","jev-040","jev-026","jev-021","jev-054","jev-022","jev-011","jev-015","jev-000","jev-034","jev-063","jev-030","jev-044","jev-012","jev-060","jev-025","jev-052","jev-009","jev-041","jev-002","jev-027","jev-047","jev-016","jev-055","jev-046","jev-042","jev-059","jev-019","jev-006","jev-024"],"latency_ms":[182.9185551032424,812.9109693691134,320.8358408883214,356.64159525185823,1000.4021739587188,493.31937078386545,629.1520418599248,337.75684982538223,1004.4260006397963,960.1577380672097,1078.0084626749158,1078.1013770028949,1033.0130765214562,1032.8499330207705,941.8727718293667,889.3710058182478,838.9492779970169,880.442432127893,880.5020041763783,880.3396970033646,806.4367705956101,688.8508554548025,733.1301383674145,615.6668746843934,572.114652954042,620.023712515831,503.28863598406315,622.5807070732117,696.2794288992882,856.2658717855811,907.4752265587449,983.9744810014963,1027.8783654794097,936.075690202415,1008.8693872094154,889.5501224324107,979.0430730208755,939.3803160637617,930.7033261284232,1026.2050637975335,984.7689084708691,984.7848182544112,911.0227590426803,1071.1410958319902,983.9488063007593,1023.4373835846782,863.7038329616189,692.4706129357219,616.741606965661,660.7882222160697,660.6327472254634,618.4400543570518,661.6572216153145,664.9134354665875,740.2506619691849,813.5872315615416,812.8339648246765,768.937885761261,925.9284073486924,974.9489314854145,931.3733903691173,842.1527659520507,927.3941181600094,854.285647161305],"mean_ms":811.967318499228,"response_timing_field_excluded":true,"wall_seconds":6.877018581144512}
{"experiment":"pr80","model":"jev","arm":"candidate","run":1,"concurrency":8,"request_count":64,"source_file":"analysis/jev-candidate-measured-c8-r1/responses.jsonl","source_sha256":"2cf90aa84befc957bb48a43ed1260f02931e1bbf00dbf9c2b8cb73a1406aa744","response_semantics_sha256":"d841d043178d0bad3fa2138c9a37785b89d5c8fddd81329b78a6272bed0bdb06","request_ids":["jev-010","jev-050","jev-017","jev-032","jev-038","jev-049","jev-029","jev-028","jev-018","jev-007","jev-001","jev-048","jev-039","jev-013","jev-043","jev-053","jev-057","jev-037","jev-005","jev-008","jev-056","jev-020","jev-061","jev-036","jev-051","jev-014","jev-004","jev-045","jev-031","jev-058","jev-062","jev-003","jev-033","jev-023","jev-035","jev-040","jev-026","jev-021","jev-054","jev-022","jev-011","jev-015","jev-000","jev-034","jev-063","jev-030","jev-044","jev-012","jev-060","jev-025","jev-052","jev-009","jev-041","jev-002","jev-027","jev-047","jev-016","jev-055","jev-046","jev-042","jev-059","jev-019","jev-006","jev-024"],"latency_ms":[182.08952620625496,809.0131711214781,338.1355497986078,200.22326800972223,997.0198590308428,492.2788552939892,627.6661697775126,355.0615943968296,1002.0149871706963,1078.0998673290014,1075.9348087012768,1076.0848307982087,1031.3562732189894,1031.774622388184,943.2041347026825,890.2503633871675,839.5663974806666,880.1886206492782,880.1608234643936,880.0727762281895,806.1981908977032,688.5652849450707,732.4732132256031,614.7702410817146,571.4176455512643,618.5738062486053,502.03267205506563,621.4184127748013,694.9710128828883,855.7875044643879,905.7226553559303,982.8312834724784,1026.521435007453,935.8119564130902,1008.6258472874761,889.4567918032408,976.1567655950785,935.7256172224879,928.2715003937483,1022.6725656539202,981.1669569462538,981.4431183040142,907.5603587552905,1067.5159487873316,982.9696733504534,1020.4441696405411,861.0636815428734,690.5192341655493,614.6831158548594,658.3147896453738,658.3347041159868,616.2068946287036,659.0171344578266,666.9742157682776,743.1681854650378,816.3653863593936,815.9092022106051,772.0944741740823,932.6623706147075,977.7697930112481,935.9564287588,844.0965889021754,927.0048271864653,854.0338566526771],"mean_ms":811.1480626685079,"response_timing_field_excluded":true,"wall_seconds":6.8694704826921225}
{"experiment":"pr80","model":"jev","arm":"candidate","run":2,"concurrency":8,"request_count":64,"source_file":"analysis/jev-candidate-measured-c8-r2/responses.jsonl","source_sha256":"537b1a16e8d160518775553562d023c2ad1452453623b78ed815bf0e8160d6b0","response_semantics_sha256":"d841d043178d0bad3fa2138c9a37785b89d5c8fddd81329b78a6272bed0bdb06","request_ids":["jev-010","jev-050","jev-017","jev-032","jev-038","jev-049","jev-029","jev-028","jev-018","jev-007","jev-001","jev-048","jev-039","jev-013","jev-043","jev-053","jev-057","jev-037","jev-005","jev-008","jev-056","jev-020","jev-061","jev-036","jev-051","jev-014","jev-004","jev-045","jev-031","jev-058","jev-062","jev-003","jev-033","jev-023","jev-035","jev-040","jev-026","jev-021","jev-054","jev-022","jev-011","jev-015","jev-000","jev-034","jev-063","jev-030","jev-044","jev-012","jev-060","jev-025","jev-052","jev-009","jev-041","jev-002","jev-027","jev-047","jev-016","jev-055","jev-046","jev-042","jev-059","jev-019","jev-006","jev-024"],"latency_ms":[181.35412503033876,807.9947531223297,336.7795404046774,199.64492041617632,996.3604658842087,491.856275126338,627.2814003750682,353.8870709016919,1000.2219937741756,1075.3894308581948,1073.9612830802798,1073.8727431744337,1028.4592621028423,1028.4225223585963,940.4690358787775,886.9720976799726,837.8628110513091,879.4025676324964,879.6529769897461,879.7586429864168,805.6700900197029,688.2744524627924,732.7033011242747,615.29650259763,572.0504755154252,620.2371269464493,503.43846157193184,622.5969102233648,696.2803713977337,856.0466421768069,905.8110443875194,982.8308550640941,1026.6600465402007,934.7948431968689,1007.7583761885762,888.5859968140721,975.0676853582263,935.5611503124237,927.567271515727,1021.8112543225288,980.661847628653,980.7603694498539,906.892716884613,1066.9734328985214,983.2713045179844,1023.1830151751637,863.7279104441404,693.1955758482218,616.9236693531275,660.9490597620606,660.711606964469,618.5706853866577,660.4943992570043,664.6242290735245,740.9716723486781,814.3204841762781,813.8188039883971,769.9405467137694,931.1484815552831,978.9642198011279,936.7057960480452,846.4767476543784,930.8814210817218,858.0966042354703],"mean_ms":810.9517402626807,"response_timing_field_excluded":true,"wall_seconds":6.869797022081912}
{"experiment":"pr80","model":"jev","arm":"baseline","run":1,"concurrency":16,"request_count":64,"source_file":"analysis/jev-baseline-measured-c16-r1/responses.jsonl","source_sha256":"390df47653ae1ff0e51e87022bb61c46aa50c3946608fa8cc1da6496f67112bd","response_semantics_sha256":"d841d043178d0bad3fa2138c9a37785b89d5c8fddd81329b78a6272bed0bdb06","request_ids":["jev-010","jev-050","jev-017","jev-032","jev-038","jev-049","jev-029","jev-028","jev-018","jev-007","jev-001","jev-048","jev-039","jev-013","jev-043","jev-053","jev-057","jev-037","jev-005","jev-008","jev-056","jev-020","jev-061","jev-036","jev-051","jev-014","jev-004","jev-045","jev-031","jev-058","jev-062","jev-003","jev-033","jev-023","jev-035","jev-040","jev-026","jev-021","jev-054","jev-022","jev-011","jev-015","jev-000","jev-034","jev-063","jev-030","jev-044","jev-012","jev-060","jev-025","jev-052","jev-009","jev-041","jev-002","jev-027","jev-047","jev-016","jev-055","jev-046","jev-042","jev-059","jev-019","jev-006","jev-024"],"latency_ms":[182.7861424535513,363.91269229352474,677.2253233939409,383.0136675387621,1419.1536232829094,812.2540907934308,540.6857086345553,401.71373449265957,1733.6959661915898,921.6135004535317,1057.2653710842133,829.1833130642772,1148.9263596013188,1872.2412129864097,1240.5436718836427,1555.3530286997557,1827.6348384097219,1783.167121000588,1899.4544688612223,1897.8004651144147,1777.1610487252474,1659.6653396263719,1660.0643917918205,1660.0546669214964,1660.0490007549524,1701.4384549111128,1628.5128463059664,1674.2117730900645,1589.0943808481097,1629.2939856648445,1636.3572534173727,1591.287212446332,1591.195734217763,1546.0696807131171,1502.314304932952,1502.5966074317694,1661.2430652603507,1782.4015393853188,1824.9147720634937,1995.1478661969304,1997.442995198071,1912.225903943181,1911.3193424418569,1951.8340341746807,1954.2494285851717,1953.7110393866897,1788.2544547319412,1712.6630702987313,1595.4695390537381,1639.6774034947157,1565.6511830165982,1683.2990609109402,1643.044133670628,1682.7780893072486,1599.1550711914897,1502.9714927077293,1426.5801291912794,1426.772910170257,1585.710677318275,1589.0157790854573,1588.75931520015,1503.1359447166324,1661.3014237955213,1662.0571091771126],"mean_ms":1505.5902774329297,"response_timing_field_excluded":true,"wall_seconds":6.840801717713475}
{"experiment":"pr80","model":"jev","arm":"baseline","run":2,"concurrency":16,"request_count":64,"source_file":"analysis/jev-baseline-measured-c16-r2/responses.jsonl","source_sha256":"3db950154a45c7fede863b67babcdf45319dfbf85b455c579de41373573c6afb","response_semantics_sha256":"d841d043178d0bad3fa2138c9a37785b89d5c8fddd81329b78a6272bed0bdb06","request_ids":["jev-010","jev-050","jev-017","jev-032","jev-038","jev-049","jev-029","jev-028","jev-018","jev-007","jev-001","jev-048","jev-039","jev-013","jev-043","jev-053","jev-057","jev-037","jev-005","jev-008","jev-056","jev-020","jev-061","jev-036","jev-051","jev-014","jev-004","jev-045","jev-031","jev-058","jev-062","jev-003","jev-033","jev-023","jev-035","jev-040","jev-026","jev-021","jev-054","jev-022","jev-011","jev-015","jev-000","jev-034","jev-063","jev-030","jev-044","jev-012","jev-060","jev-025","jev-052","jev-009","jev-041","jev-002","jev-027","jev-047","jev-016","jev-055","jev-046","jev-042","jev-059","jev-019","jev-006","jev-024"],"latency_ms":[183.16974490880966,364.6768033504486,815.2300911024213,402.5231571868062,1697.921609506011,679.0958419442177,542.5567273050547,382.5662601739168,1887.303370051086,923.9489557221532,1151.3849161565304,831.7679837346077,1015.4212079942226,1513.842842541635,1242.6437437534332,1377.8967736288905,1845.7440929487348,1800.359208136797,1917.0879432931542,1915.8055037260056,1793.3417977765203,1675.2252466976643,1675.4682371392846,1675.4889013245702,1675.5657522007823,1762.0363114401698,1645.454566925764,1691.8612867593765,1648.34058098495,1694.615992717445,1699.4507517665625,1604.1847439482808,1599.759672768414,1555.1725775003433,1511.555576696992,1511.752177029848,1672.2580306231976,1792.944055981934,1836.2181140109897,2006.1054285615683,2008.9918617159128,1922.6880548521876,1921.5433727949858,1963.3938949555159,1965.6126499176025,1962.2965538874269,1793.7701297923923,1717.6915761083364,1600.6314158439636,1644.9392111971974,1571.0689034312963,1688.8292226940393,1647.0373719930649,1688.7595681473613,1603.9529535919428,1509.6482643857598,1431.7760095000267,1431.6228218376637,1591.981852427125,1594.7405882179737,1595.1541950926185,1508.4249870851636,1670.4763639718294,1670.648797415197],"mean_ms":1514.4285500136903,"response_timing_field_excluded":true,"wall_seconds":6.881528333760798}
{"experiment":"pr80","model":"jev","arm":"candidate","run":1,"concurrency":16,"request_count":64,"source_file":"analysis/jev-candidate-measured-c16-r1/responses.jsonl","source_sha256":"ceb41bc735143ad788934d29d9f6114bf82809b71ef621fb2d447df27026ffd1","response_semantics_sha256":"d841d043178d0bad3fa2138c9a37785b89d5c8fddd81329b78a6272bed0bdb06","request_ids":["jev-010","jev-050","jev-017","jev-032","jev-038","jev-049","jev-029","jev-028","jev-018","jev-007","jev-001","jev-048","jev-039","jev-013","jev-043","jev-053","jev-057","jev-037","jev-005","jev-008","jev-056","jev-020","jev-061","jev-036","jev-051","jev-014","jev-004","jev-045","jev-031","jev-058","jev-062","jev-003","jev-033","jev-023","jev-035","jev-040","jev-026","jev-021","jev-054","jev-022","jev-011","jev-015","jev-000","jev-034","jev-063","jev-030","jev-044","jev-012","jev-060","jev-025","jev-052","jev-009","jev-041","jev-002","jev-027","jev-047","jev-016","jev-055","jev-046","jev-042","jev-059","jev-019","jev-006","jev-024"],"latency_ms":[184.13343653082848,544.6283901110291,339.5547913387418,202.1383810788393,1106.0880366712809,682.8181892633438,818.0622849613428,356.55807983130217,1881.0856668278575,909.4376312568784,1334.6223095431924,927.1080922335386,1198.8430013880134,1561.897792853415,1426.0326037183404,1697.4061615765095,1837.3629488050938,1954.9407921731472,1953.2797820866108,1953.2990995794535,1784.4959469512105,1663.888880982995,1664.1902783885598,1590.3202844783664,1664.9578884243965,1666.0764729604125,1591.0537941381335,1592.875087633729,1592.8996866568923,1638.813349418342,1691.9777551665902,1604.000954888761,1601.0125167667866,1556.521262973547,1513.0584063008428,1512.9978703334928,1674.997073598206,1795.0884737074375,1837.7557415515184,2008.9652193710208,2011.3255204632878,1924.5467130094767,1923.3385790139437,1963.9331828802824,1966.3473758846521,1961.6628792136908,1791.5308605879545,1715.467233210802,1598.1301562860608,1642.3771008849144,1568.1627476587892,1686.1018482595682,1642.5942033529282,1685.6677420437336,1601.8890971317887,1505.1220832392573,1427.9919350519776,1427.977230399847,1589.4764494150877,1594.7512546554208,1594.8496898636222,1509.894186630845,1671.6019893065095,1671.9764713197947],"mean_ms":1512.3743897856912,"response_timing_field_excluded":true,"wall_seconds":6.874285157769918}
{"experiment":"pr80","model":"jev","arm":"candidate","run":2,"concurrency":16,"request_count":64,"source_file":"analysis/jev-candidate-measured-c16-r2/responses.jsonl","source_sha256":"cb51c098380f45a6200bddd4c141873c9c7e287ef6da5459be938a73ccdc57f4","response_semantics_sha256":"d841d043178d0bad3fa2138c9a37785b89d5c8fddd81329b78a6272bed0bdb06","request_ids":["jev-010","jev-050","jev-017","jev-032","jev-038","jev-049","jev-029","jev-028","jev-018","jev-007","jev-001","jev-048","jev-039","jev-013","jev-043","jev-053","jev-057","jev-037","jev-005","jev-008","jev-056","jev-020","jev-061","jev-036","jev-051","jev-014","jev-004","jev-045","jev-031","jev-058","jev-062","jev-003","jev-033","jev-023","jev-035","jev-040","jev-026","jev-021","jev-054","jev-022","jev-011","jev-015","jev-000","jev-034","jev-063","jev-030","jev-044","jev-012","jev-060","jev-025","jev-052","jev-009","jev-041","jev-002","jev-027","jev-047","jev-016","jev-055","jev-046","jev-042","jev-059","jev-019","jev-006","jev-024"],"latency_ms":[179.70070149749517,521.6450057923794,317.38883070647717,335.23441199213266,1100.179422646761,676.9225485622883,812.4407576397061,539.5569009706378,1874.257936142385,903.6482274532318,1237.5423135235906,921.6883350163698,1329.1058670729399,1556.4976781606674,1420.8426950499415,1692.1322792768478,1834.2786012217402,1831.4779736101627,1949.3348291143775,1781.4279226586223,1780.50774987787,1661.7564400658011,1661.762099713087,1588.136705569923,1661.9427679106593,1663.744137622416,1544.1468860954046,1589.5446464419365,1589.4609494134784,1635.111639276147,1687.64254078269,1601.3755276799202,1599.1686107590795,1555.7312732562423,1511.7225078865886,1511.5802641957998,1669.988309033215,1790.1216046884656,1834.193174727261,2006.0575203970075,2008.5753807798028,1921.5758694335818,1920.6896871328354,1961.634430103004,1963.9252787455916,1960.9845653176308,1791.413877159357,1715.257678180933,1597.8265954181552,1642.0237943530083,1568.130686879158,1685.954830609262,1646.7902343720198,1689.805037342012,1605.0620060414076,1507.3049934580922,1430.450134910643,1430.993378162384,1590.8035449683666,1592.7552301436663,1592.946581542492,1506.735379807651,1668.4087263420224,1668.749524280429],"mean_ms":1509.8093131091446,"response_timing_field_excluded":true,"wall_seconds":6.86137109529227}
{"experiment":"backend","model":"jev","arm":"hf","run":1,"concurrency":1,"request_count":74,"source_file":"analysis/hf-measured-1.jsonl","source_sha256":"56d1c3b1ef514684784439d1a18ae69e1740d45c4ce7a96b598c63420328dfd2","response_semantics_sha256":"2cdb21484fd34893ee136cc88fd7d63dc59974dfd3f7dfc384873572aa3b1de6","request_ids":["original-policy-01-0","original-policy-01-1","original-policy-02-0","original-policy-02-1","original-policy-03-0","original-policy-03-1","original-policy-04-0","original-policy-04-1","original-policy-05-0","original-policy-05-1","original-policy-06-0","original-policy-06-1","original-adequacy-01-0","original-adequacy-01-1","original-adequacy-02-0","original-adequacy-02-1","original-adequacy-03-0","original-adequacy-03-1","original-adequacy-04-0","original-adequacy-04-1","original-adequacy-05-0","original-adequacy-05-1","original-adequacy-06-0","original-adequacy-06-1","easy-fact-00","easy-fact-01","easy-fact-02","easy-fact-03","easy-fact-04","easy-fact-05","easy-fact-06","easy-fact-07","easy-fact-08","easy-fact-09","easy-fact-10","easy-fact-11","hard-opus-a-long_policy-11","hard-opus-a-long_policy-13","hard-opus-a-long_policy-19","hard-opus-a-probability-03","hard-opus-a-probability-08","hard-opus-a-temporal_numeric-03","hard-opus-a-temporal_numeric-06","hard-opus-a-temporal_numeric-09","hard-opus-b-multi_hop-08","hard-opus-b-probability-03","hard-opus-b-tradeoff-06","hard-opus-b-tradeoff-08","hard-opus-c-long_policy-04","hard-opus-c-long_policy-11","hard-opus-c-temporal_numeric-02","hard-sol-a-adversarial-06","hard-sol-a-adversarial-08","hard-sol-a-trap-02","hard-sol-a-trap-04","hard-sol-a-trap-13","hard-sol-a-trap-15","hard-sol-b-judge_hard-01","hard-sol-b-judge_hard-02","hard-sol-b-judge_hard-05","hard-sol-b-judge_hard-08","hard-sol-b-judge_hard-10","hard-sol-b-judge_hard-14","hard-sol-b-judge_hard-15","hard-sol-b-judge_hard-18","hard-sol-c-judge_hard-03","hard-sol-c-judge_hard-05","hard-sol-c-judge_hard-07","hard-sol-c-judge_hard-08","hard-sol-c-judge_hard-09","hard-sol-c-judge_hard-10","hard-sol-c-judge_hard-11","hard-sol-c-judge_hard-13","hard-sol-c-judge_hard-15"],"latency_ms":[319.46511566638947,309.86113380640745,302.67443880438805,355.0368659198284,306.38429895043373,305.0078535452485,306.0595793649554,305.678634904325,305.3719801828265,306.07456993311644,330.98806627094746,304.6403154730797,305.1690040156245,305.94636127352715,303.68512589484453,303.55440359562635,302.50303354114294,301.7036207020283,303.3129731193185,304.4798541814089,306.6370552405715,304.1085395962,304.9195371568203,305.0833251327276,302.7393026277423,310.5862904340029,312.00557481497526,313.5389294475317,310.2828999981284,303.49383410066366,404.24083918333054,307.5817693024874,306.8865882232785,304.9638895317912,303.7972981110215,303.6201046779752,650.7587786763906,675.2952029928565,654.969141818583,356.6955020651221,357.4281819164753,367.3968221992254,381.1527891084552,378.3010486513376,651.9985096529126,480.568733997643,416.99801571667194,387.85687927156687,833.3251401782036,861.4875124767423,436.5319823846221,327.6576893404126,324.76646080613136,334.78808403015137,323.4748560935259,324.877948500216,335.98996698856354,337.7632489427924,326.0222626850009,330.01039922237396,325.7828988134861,324.7408466413617,326.1443842202425,329.8382982611656,318.4001259505749,354.1428353637457,355.5286033079028,345.1794469729066,338.4289303794503,355.35275656729937,346.3976038619876,347.94320072978735,348.07354863733053,341.4268661290407],"mean_ms":362.2375474361753,"response_timing_field_excluded":true}
{"experiment":"backend","model":"jev","arm":"hf","run":2,"concurrency":1,"request_count":74,"source_file":"analysis/hf-measured-2.jsonl","source_sha256":"7aeecee33dfee875398576579dd8c837cc6d96c605528ca9feb15af10ed66e82","response_semantics_sha256":"2cdb21484fd34893ee136cc88fd7d63dc59974dfd3f7dfc384873572aa3b1de6","request_ids":["original-policy-01-0","original-policy-01-1","original-policy-02-0","original-policy-02-1","original-policy-03-0","original-policy-03-1","original-policy-04-0","original-policy-04-1","original-policy-05-0","original-policy-05-1","original-policy-06-0","original-policy-06-1","original-adequacy-01-0","original-adequacy-01-1","original-adequacy-02-0","original-adequacy-02-1","original-adequacy-03-0","original-adequacy-03-1","original-adequacy-04-0","original-adequacy-04-1","original-adequacy-05-0","original-adequacy-05-1","original-adequacy-06-0","original-adequacy-06-1","easy-fact-00","easy-fact-01","easy-fact-02","easy-fact-03","easy-fact-04","easy-fact-05","easy-fact-06","easy-fact-07","easy-fact-08","easy-fact-09","easy-fact-10","easy-fact-11","hard-opus-a-long_policy-11","hard-opus-a-long_policy-13","hard-opus-a-long_policy-19","hard-opus-a-probability-03","hard-opus-a-probability-08","hard-opus-a-temporal_numeric-03","hard-opus-a-temporal_numeric-06","hard-opus-a-temporal_numeric-09","hard-opus-b-multi_hop-08","hard-opus-b-probability-03","hard-opus-b-tradeoff-06","hard-opus-b-tradeoff-08","hard-opus-c-long_policy-04","hard-opus-c-long_policy-11","hard-opus-c-temporal_numeric-02","hard-sol-a-adversarial-06","hard-sol-a-adversarial-08","hard-sol-a-trap-02","hard-sol-a-trap-04","hard-sol-a-trap-13","hard-sol-a-trap-15","hard-sol-b-judge_hard-01","hard-sol-b-judge_hard-02","hard-sol-b-judge_hard-05","hard-sol-b-judge_hard-08","hard-sol-b-judge_hard-10","hard-sol-b-judge_hard-14","hard-sol-b-judge_hard-15","hard-sol-b-judge_hard-18","hard-sol-c-judge_hard-03","hard-sol-c-judge_hard-05","hard-sol-c-judge_hard-07","hard-sol-c-judge_hard-08","hard-sol-c-judge_hard-09","hard-sol-c-judge_hard-10","hard-sol-c-judge_hard-11","hard-sol-c-judge_hard-13","hard-sol-c-judge_hard-15"],"latency_ms":[304.00814209133387,308.1020303070545,304.90358639508486,307.6217770576477,306.7588619887829,305.8530827984214,304.30146399885416,304.3947424739599,305.5712217465043,306.2849994748831,304.92278933525085,305.0675531849265,305.39584904909134,305.193442851305,306.14787619560957,309.4085147604346,304.79960329830647,314.0740506350994,304.71651908010244,301.8686957657337,307.13981483131647,315.0827260687947,305.64125161617994,309.12878178060055,300.92205200344324,309.45197492837906,305.55765703320503,304.2767131701112,305.0080854445696,302.07014363259077,305.14634773135185,306.3476923853159,307.77230486273766,305.607033893466,300.95147900283337,302.1221999078989,652.9114712029696,670.7902131602168,653.9937192574143,357.96280950307846,356.1327466741204,364.3085593357682,375.9153727442026,374.6268954128027,650.8902870118618,475.3386462107301,421.0551204159856,391.0042541101575,997.7227067574859,860.8060535043478,446.83931674808264,329.05041240155697,329.1343851014972,338.9847697690129,326.28586888313293,326.88560895621777,338.62400613725185,336.45702339708805,329.0795562788844,328.29470466822386,330.7183254510164,325.12077037245035,326.4735210686922,328.73573433607817,317.52065010368824,357.90980514138937,352.3121736943722,354.0948135778308,338.8595497235656,350.250537507236,346.0641847923398,347.23562374711037,346.02654725313187,335.2531772106886],"mean_ms":362.1796078703089,"response_timing_field_excluded":true}
{"experiment":"backend","model":"jev","arm":"native","run":1,"concurrency":1,"request_count":74,"source_file":"analysis/native-measured-1.jsonl","source_sha256":"f964c0e61ef3877aac130b795c46070de6e73d261272c33f1a2f45f4e6e66b83","response_semantics_sha256":"487c9568dd218821352340c14bf4816157b94c55b95a78c3077de168c1799638","request_ids":["original-policy-01-0","original-policy-01-1","original-policy-02-0","original-policy-02-1","original-policy-03-0","original-policy-03-1","original-policy-04-0","original-policy-04-1","original-policy-05-0","original-policy-05-1","original-policy-06-0","original-policy-06-1","original-adequacy-01-0","original-adequacy-01-1","original-adequacy-02-0","original-adequacy-02-1","original-adequacy-03-0","original-adequacy-03-1","original-adequacy-04-0","original-adequacy-04-1","original-adequacy-05-0","original-adequacy-05-1","original-adequacy-06-0","original-adequacy-06-1","easy-fact-00","easy-fact-01","easy-fact-02","easy-fact-03","easy-fact-04","easy-fact-05","easy-fact-06","easy-fact-07","easy-fact-08","easy-fact-09","easy-fact-10","easy-fact-11","hard-opus-a-long_policy-11","hard-opus-a-long_policy-13","hard-opus-a-long_policy-19","hard-opus-a-probability-03","hard-opus-a-probability-08","hard-opus-a-temporal_numeric-03","hard-opus-a-temporal_numeric-06","hard-opus-a-temporal_numeric-09","hard-opus-b-multi_hop-08","hard-opus-b-probability-03","hard-opus-b-tradeoff-06","hard-opus-b-tradeoff-08","hard-opus-c-long_policy-04","hard-opus-c-long_policy-11","hard-opus-c-temporal_numeric-02","hard-sol-a-adversarial-06","hard-sol-a-adversarial-08","hard-sol-a-trap-02","hard-sol-a-trap-04","hard-sol-a-trap-13","hard-sol-a-trap-15","hard-sol-b-judge_hard-01","hard-sol-b-judge_hard-02","hard-sol-b-judge_hard-05","hard-sol-b-judge_hard-08","hard-sol-b-judge_hard-10","hard-sol-b-judge_hard-14","hard-sol-b-judge_hard-15","hard-sol-b-judge_hard-18","hard-sol-c-judge_hard-03","hard-sol-c-judge_hard-05","hard-sol-c-judge_hard-07","hard-sol-c-judge_hard-08","hard-sol-c-judge_hard-09","hard-sol-c-judge_hard-10","hard-sol-c-judge_hard-11","hard-sol-c-judge_hard-13","hard-sol-c-judge_hard-15"],"latency_ms":[21.045741625130177,20.759988576173782,20.402141846716404,20.241839811205864,20.254753530025482,20.17874363809824,19.923408515751362,20.196781493723392,20.125385373830795,20.18928900361061,20.067067816853523,20.25449089705944,20.046405494213104,19.789631478488445,19.89191770553589,20.013660192489624,19.972295500338078,19.995872862637043,19.95538640767336,19.91462241858244,19.84203327447176,19.849393516778946,20.17627377063036,20.14128677546978,19.916227087378502,19.73196491599083,19.968997687101364,20.121715031564236,19.839315675199032,19.909813068807125,19.94175836443901,19.733057357370853,19.699313677847385,19.743304699659348,20.12371737509966,20.049634389579296,215.6955124810338,228.8771914318204,227.30786819010973,47.245968133211136,42.37977322191,49.024966545403004,55.91208394616842,55.33540714532137,214.7803008556366,115.97900278866291,78.94490379840136,60.56626699864864,319.63619124144316,326.1075122281909,89.60009925067425,27.93713565915823,27.70219836384058,32.90186170488596,26.010028086602688,26.366698555648327,33.12067687511444,32.39226806908846,26.687067933380604,28.892092406749725,26.936803944408894,29.357299208641052,28.987213037908077,27.37837191671133,25.583967566490173,42.1702666208148,39.07614480704069,37.20251936465502,33.41357223689556,38.33167627453804,40.31439684331417,37.46974375098944,36.79170645773411,32.419309951364994],"mean_ms":48.47085538848832,"response_timing_field_excluded":true}
{"experiment":"backend","model":"jev","arm":"native","run":2,"concurrency":1,"request_count":74,"source_file":"analysis/native-measured-2.jsonl","source_sha256":"3d573f7cb246a1ff03c688034a1d5f9e6100103f92802b3dcaab1298fbe24017","response_semantics_sha256":"487c9568dd218821352340c14bf4816157b94c55b95a78c3077de168c1799638","request_ids":["original-policy-01-0","original-policy-01-1","original-policy-02-0","original-policy-02-1","original-policy-03-0","original-policy-03-1","original-policy-04-0","original-policy-04-1","original-policy-05-0","original-policy-05-1","original-policy-06-0","original-policy-06-1","original-adequacy-01-0","original-adequacy-01-1","original-adequacy-02-0","original-adequacy-02-1","original-adequacy-03-0","original-adequacy-03-1","original-adequacy-04-0","original-adequacy-04-1","original-adequacy-05-0","original-adequacy-05-1","original-adequacy-06-0","original-adequacy-06-1","easy-fact-00","easy-fact-01","easy-fact-02","easy-fact-03","easy-fact-04","easy-fact-05","easy-fact-06","easy-fact-07","easy-fact-08","easy-fact-09","easy-fact-10","easy-fact-11","hard-opus-a-long_policy-11","hard-opus-a-long_policy-13","hard-opus-a-long_policy-19","hard-opus-a-probability-03","hard-opus-a-probability-08","hard-opus-a-temporal_numeric-03","hard-opus-a-temporal_numeric-06","hard-opus-a-temporal_numeric-09","hard-opus-b-multi_hop-08","hard-opus-b-probability-03","hard-opus-b-tradeoff-06","hard-opus-b-tradeoff-08","hard-opus-c-long_policy-04","hard-opus-c-long_policy-11","hard-opus-c-temporal_numeric-02","hard-sol-a-adversarial-06","hard-sol-a-adversarial-08","hard-sol-a-trap-02","hard-sol-a-trap-04","hard-sol-a-trap-13","hard-sol-a-trap-15","hard-sol-b-judge_hard-01","hard-sol-b-judge_hard-02","hard-sol-b-judge_hard-05","hard-sol-b-judge_hard-08","hard-sol-b-judge_hard-10","hard-sol-b-judge_hard-14","hard-sol-b-judge_hard-15","hard-sol-b-judge_hard-18","hard-sol-c-judge_hard-03","hard-sol-c-judge_hard-05","hard-sol-c-judge_hard-07","hard-sol-c-judge_hard-08","hard-sol-c-judge_hard-09","hard-sol-c-judge_hard-10","hard-sol-c-judge_hard-11","hard-sol-c-judge_hard-13","hard-sol-c-judge_hard-15"],"latency_ms":[20.369287580251694,20.17165720462799,20.225882530212402,20.202496089041233,20.24026680737734,20.153379067778587,19.930330105125904,20.20168397575617,19.985731691122055,20.18297277390957,20.0651241466403,20.172233693301678,19.952683709561825,19.81156785041094,19.90545727312565,19.9061231687665,20.037655718624592,20.26927098631859,20.462244749069214,20.265206694602966,20.03072015941143,19.84651107341051,20.22244967520237,20.178980194032192,19.868834875524044,19.76804994046688,19.98614612966776,20.1684832572937,19.80614010244608,19.845636561512947,20.044872537255287,19.904781132936478,19.813431426882744,19.819965586066246,19.949762150645256,19.949013367295265,218.03975943475962,223.0551978573203,229.30395510047674,48.39277919381857,43.328301049768925,50.00771675258875,57.020245119929314,56.43933266401291,218.8819870352745,116.27547536045313,76.1554166674614,59.63974632322788,318.07217188179493,329.9342980608344,92.12307073175907,28.471095487475395,28.201857581734657,33.30056741833687,25.728208012878895,25.74372384697199,32.32843428850174,31.92242607474327,26.521635241806507,28.148137032985687,26.35602094233036,28.302812948822975,27.67907176166773,26.131981052458286,24.062776006758213,42.127300053834915,39.59500975906849,37.630025297403336,33.98508299142122,39.30070623755455,40.48516880720854,38.02660945802927,36.99445445090532,32.16303698718548],"mean_ms":48.53500849944917,"response_timing_field_excluded":true}
{"experiment":"backend","model":"jev","arm":"fast","run":1,"concurrency":1,"request_count":74,"source_file":"analysis/fast-measured-1.jsonl","source_sha256":"d3b3d649934925809fd0859561ff44ce5389b0017ce2ec11f35ba7fc9ce5f071","response_semantics_sha256":"b7869a5b59e704a086d932dea5d6ec4adaddfd65840ec131a2de0543008d0354","request_ids":["original-policy-01-0","original-policy-01-1","original-policy-02-0","original-policy-02-1","original-policy-03-0","original-policy-03-1","original-policy-04-0","original-policy-04-1","original-policy-05-0","original-policy-05-1","original-policy-06-0","original-policy-06-1","original-adequacy-01-0","original-adequacy-01-1","original-adequacy-02-0","original-adequacy-02-1","original-adequacy-03-0","original-adequacy-03-1","original-adequacy-04-0","original-adequacy-04-1","original-adequacy-05-0","original-adequacy-05-1","original-adequacy-06-0","original-adequacy-06-1","easy-fact-00","easy-fact-01","easy-fact-02","easy-fact-03","easy-fact-04","easy-fact-05","easy-fact-06","easy-fact-07","easy-fact-08","easy-fact-09","easy-fact-10","easy-fact-11","hard-opus-a-long_policy-11","hard-opus-a-long_policy-13","hard-opus-a-long_policy-19","hard-opus-a-probability-03","hard-opus-a-probability-08","hard-opus-a-temporal_numeric-03","hard-opus-a-temporal_numeric-06","hard-opus-a-temporal_numeric-09","hard-opus-b-multi_hop-08","hard-opus-b-probability-03","hard-opus-b-tradeoff-06","hard-opus-b-tradeoff-08","hard-opus-c-long_policy-04","hard-opus-c-long_policy-11","hard-opus-c-temporal_numeric-02","hard-sol-a-adversarial-06","hard-sol-a-adversarial-08","hard-sol-a-trap-02","hard-sol-a-trap-04","hard-sol-a-trap-13","hard-sol-a-trap-15","hard-sol-b-judge_hard-01","hard-sol-b-judge_hard-02","hard-sol-b-judge_hard-05","hard-sol-b-judge_hard-08","hard-sol-b-judge_hard-10","hard-sol-b-judge_hard-14","hard-sol-b-judge_hard-15","hard-sol-b-judge_hard-18","hard-sol-c-judge_hard-03","hard-sol-c-judge_hard-05","hard-sol-c-judge_hard-07","hard-sol-c-judge_hard-08","hard-sol-c-judge_hard-09","hard-sol-c-judge_hard-10","hard-sol-c-judge_hard-11","hard-sol-c-judge_hard-13","hard-sol-c-judge_hard-15"],"latency_ms":[18.869378603994846,18.759068101644516,18.306742422282696,18.447875045239925,18.44335626810789,18.536319956183434,18.625707365572453,18.671960569918156,18.67694314569235,18.734749406576157,18.758141435682774,18.686281517148018,17.6482992246747,17.64773577451706,17.71582569926977,17.596696503460407,17.510886304080486,17.528677359223366,17.48996414244175,17.60043203830719,17.52458233386278,17.52660423517227,18.55401787906885,18.57442781329155,17.50495284795761,17.601080238819122,17.542703077197075,18.599593080580235,17.555068247020245,17.49084424227476,18.60078703612089,17.57887378334999,17.470459453761578,17.392870970070362,17.630206421017647,17.569907940924168,258.67681950330734,257.89404567331076,246.28956522792578,46.57927993685007,43.93818601965904,49.36196841299534,56.93440791219473,56.74957204610109,248.1209049001336,124.62593615055084,80.1516892388463,60.870327055454254,361.06925550848246,374.23371989279985,93.15857663750648,27.597645297646523,26.71817969530821,43.906666338443756,25.30872728675604,25.111056864261627,44.13482453674078,30.601085163652897,25.112533941864967,27.257323265075684,26.544385589659214,26.92826557904482,27.579261921346188,26.77135169506073,24.191834963858128,44.23130303621292,38.925071246922016,41.75200033932924,44.566113501787186,37.084054201841354,38.64914923906326,38.02158124744892,39.10689987242222,43.44772547483444],"mean_ms":51.09693668782711,"response_timing_field_excluded":true}
{"experiment":"backend","model":"jev","arm":"fast","run":2,"concurrency":1,"request_count":74,"source_file":"analysis/fast-measured-2.jsonl","source_sha256":"b43ef2dbfbca14f670485e37be0bb9304c8641f42ade1607f57560444c54c28b","response_semantics_sha256":"b7869a5b59e704a086d932dea5d6ec4adaddfd65840ec131a2de0543008d0354","request_ids":["original-policy-01-0","original-policy-01-1","original-policy-02-0","original-policy-02-1","original-policy-03-0","original-policy-03-1","original-policy-04-0","original-policy-04-1","original-policy-05-0","original-policy-05-1","original-policy-06-0","original-policy-06-1","original-adequacy-01-0","original-adequacy-01-1","original-adequacy-02-0","original-adequacy-02-1","original-adequacy-03-0","original-adequacy-03-1","original-adequacy-04-0","original-adequacy-04-1","original-adequacy-05-0","original-adequacy-05-1","original-adequacy-06-0","original-adequacy-06-1","easy-fact-00","easy-fact-01","easy-fact-02","easy-fact-03","easy-fact-04","easy-fact-05","easy-fact-06","easy-fact-07","easy-fact-08","easy-fact-09","easy-fact-10","easy-fact-11","hard-opus-a-long_policy-11","hard-opus-a-long_policy-13","hard-opus-a-long_policy-19","hard-opus-a-probability-03","hard-opus-a-probability-08","hard-opus-a-temporal_numeric-03","hard-opus-a-temporal_numeric-06","hard-opus-a-temporal_numeric-09","hard-opus-b-multi_hop-08","hard-opus-b-probability-03","hard-opus-b-tradeoff-06","hard-opus-b-tradeoff-08","hard-opus-c-long_policy-04","hard-opus-c-long_policy-11","hard-opus-c-temporal_numeric-02","hard-sol-a-adversarial-06","hard-sol-a-adversarial-08","hard-sol-a-trap-02","hard-sol-a-trap-04","hard-sol-a-trap-13","hard-sol-a-trap-15","hard-sol-b-judge_hard-01","hard-sol-b-judge_hard-02","hard-sol-b-judge_hard-05","hard-sol-b-judge_hard-08","hard-sol-b-judge_hard-10","hard-sol-b-judge_hard-14","hard-sol-b-judge_hard-15","hard-sol-b-judge_hard-18","hard-sol-c-judge_hard-03","hard-sol-c-judge_hard-05","hard-sol-c-judge_hard-07","hard-sol-c-judge_hard-08","hard-sol-c-judge_hard-09","hard-sol-c-judge_hard-10","hard-sol-c-judge_hard-11","hard-sol-c-judge_hard-13","hard-sol-c-judge_hard-15"],"latency_ms":[18.71473155915737,18.671276047825813,18.558613024652004,18.64189002662897,18.63680500537157,18.487256951630116,18.626212142407894,18.479363061487675,18.551096320152283,18.512005917727947,18.660593777894974,18.572106026113033,17.514606937766075,17.559622414410114,17.58450921624899,17.599227838218212,17.62930676341057,17.619268968701363,17.561454325914383,17.594304867088795,17.640882171690464,17.477134242653847,18.597626127302647,18.633943051099777,17.751690931618214,17.847846262156963,17.67015364021063,18.514947965741158,17.475226894021034,17.52996537834406,18.5193857178092,17.456469126045704,17.48155802488327,17.499038949608803,17.649770714342594,17.658192664384842,253.51559277623892,257.4510918930173,251.1934107169509,47.97167517244816,43.763832189142704,48.760670237243176,58.345433324575424,59.23718027770519,249.2766436189413,122.56274092942476,79.24567349255085,60.63017062842846,349.54113978892565,365.2699114754796,93.45499519258738,27.60845422744751,26.9484743475914,42.855304665863514,24.887753650546074,26.097112335264683,43.137744069099426,30.635331757366657,26.38261951506138,27.31632348150015,26.274854317307472,27.566727250814438,27.51922607421875,26.116170920431614,24.35585204511881,43.98633353412151,39.74214103072882,39.497761987149715,42.97842178493738,36.615053191781044,38.29669486731291,38.54024317115545,38.11485134065151,42.45523642748594],"mean_ms":50.774688253531586,"response_timing_field_excluded":true}
{"experiment":"graph-mixed","model":"jev","arm":"eager","run":1,"concurrency":1,"request_count":74,"source_file":"analysis/eager-mixed-measured-1.jsonl","source_sha256":"2a9c9dd813488aa65180d0a120c02c91a8b73551ca03c6c26587687e6b261c79","response_semantics_sha256":"487c9568dd218821352340c14bf4816157b94c55b95a78c3077de168c1799638","request_ids":["original-policy-01-0","original-policy-01-1","original-policy-02-0","original-policy-02-1","original-policy-03-0","original-policy-03-1","original-policy-04-0","original-policy-04-1","original-policy-05-0","original-policy-05-1","original-policy-06-0","original-policy-06-1","original-adequacy-01-0","original-adequacy-01-1","original-adequacy-02-0","original-adequacy-02-1","original-adequacy-03-0","original-adequacy-03-1","original-adequacy-04-0","original-adequacy-04-1","original-adequacy-05-0","original-adequacy-05-1","original-adequacy-06-0","original-adequacy-06-1","easy-fact-00","easy-fact-01","easy-fact-02","easy-fact-03","easy-fact-04","easy-fact-05","easy-fact-06","easy-fact-07","easy-fact-08","easy-fact-09","easy-fact-10","easy-fact-11","hard-opus-a-long_policy-11","hard-opus-a-long_policy-13","hard-opus-a-long_policy-19","hard-opus-a-probability-03","hard-opus-a-probability-08","hard-opus-a-temporal_numeric-03","hard-opus-a-temporal_numeric-06","hard-opus-a-temporal_numeric-09","hard-opus-b-multi_hop-08","hard-opus-b-probability-03","hard-opus-b-tradeoff-06","hard-opus-b-tradeoff-08","hard-opus-c-long_policy-04","hard-opus-c-long_policy-11","hard-opus-c-temporal_numeric-02","hard-sol-a-adversarial-06","hard-sol-a-adversarial-08","hard-sol-a-trap-02","hard-sol-a-trap-04","hard-sol-a-trap-13","hard-sol-a-trap-15","hard-sol-b-judge_hard-01","hard-sol-b-judge_hard-02","hard-sol-b-judge_hard-05","hard-sol-b-judge_hard-08","hard-sol-b-judge_hard-10","hard-sol-b-judge_hard-14","hard-sol-b-judge_hard-15","hard-sol-b-judge_hard-18","hard-sol-c-judge_hard-03","hard-sol-c-judge_hard-05","hard-sol-c-judge_hard-07","hard-sol-c-judge_hard-08","hard-sol-c-judge_hard-09","hard-sol-c-judge_hard-10","hard-sol-c-judge_hard-11","hard-sol-c-judge_hard-13","hard-sol-c-judge_hard-15"],"latency_ms":[20.713738,20.324688000000002,20.357788000000003,20.172499,20.623625,20.339703,20.044358000000003,20.222437,19.99797,20.11427,19.907897000000002,20.089104,19.859453,19.686948,19.843345,19.972054999999997,19.890727000000002,20.015192000000003,19.934367,20.011422,19.806055,19.639764,19.983901,19.992508,19.763629,19.642377999999997,19.87058,20.011246,19.714186,19.871983,19.885726,19.640826999999998,19.540167,19.559058,19.698313,19.738449000000003,215.692838,221.89486,221.871292,47.127125,43.442498,50.350299,60.337613,55.987856,219.58562,113.122002,76.028601,58.27145,310.934072,334.205669,89.500999,28.100974,27.328947,32.919665,25.639577,25.508064,31.984535,31.238063,26.256659000000003,27.445552000000003,26.611098,27.708719,27.181811,25.351844,23.665968,40.930071,38.312129,36.441855000000004,33.810706,37.505454,39.527243,36.995374999999996,36.423112,32.872577],"mean_ms":48.06206956756757,"response_timing_field_excluded":true}
{"experiment":"graph-mixed","model":"jev","arm":"eager","run":2,"concurrency":1,"request_count":74,"source_file":"analysis/eager-mixed-measured-2.jsonl","source_sha256":"7637d60382dc4613d091cfdca89ac366c92bf4859a14bc3b46afc67fa29d8842","response_semantics_sha256":"487c9568dd218821352340c14bf4816157b94c55b95a78c3077de168c1799638","request_ids":["original-policy-01-0","original-policy-01-1","original-policy-02-0","original-policy-02-1","original-policy-03-0","original-policy-03-1","original-policy-04-0","original-policy-04-1","original-policy-05-0","original-policy-05-1","original-policy-06-0","original-policy-06-1","original-adequacy-01-0","original-adequacy-01-1","original-adequacy-02-0","original-adequacy-02-1","original-adequacy-03-0","original-adequacy-03-1","original-adequacy-04-0","original-adequacy-04-1","original-adequacy-05-0","original-adequacy-05-1","original-adequacy-06-0","original-adequacy-06-1","easy-fact-00","easy-fact-01","easy-fact-02","easy-fact-03","easy-fact-04","easy-fact-05","easy-fact-06","easy-fact-07","easy-fact-08","easy-fact-09","easy-fact-10","easy-fact-11","hard-opus-a-long_policy-11","hard-opus-a-long_policy-13","hard-opus-a-long_policy-19","hard-opus-a-probability-03","hard-opus-a-probability-08","hard-opus-a-temporal_numeric-03","hard-opus-a-temporal_numeric-06","hard-opus-a-temporal_numeric-09","hard-opus-b-multi_hop-08","hard-opus-b-probability-03","hard-opus-b-tradeoff-06","hard-opus-b-tradeoff-08","hard-opus-c-long_policy-04","hard-opus-c-long_policy-11","hard-opus-c-temporal_numeric-02","hard-sol-a-adversarial-06","hard-sol-a-adversarial-08","hard-sol-a-trap-02","hard-sol-a-trap-04","hard-sol-a-trap-13","hard-sol-a-trap-15","hard-sol-b-judge_hard-01","hard-sol-b-judge_hard-02","hard-sol-b-judge_hard-05","hard-sol-b-judge_hard-08","hard-sol-b-judge_hard-10","hard-sol-b-judge_hard-14","hard-sol-b-judge_hard-15","hard-sol-b-judge_hard-18","hard-sol-c-judge_hard-03","hard-sol-c-judge_hard-05","hard-sol-c-judge_hard-07","hard-sol-c-judge_hard-08","hard-sol-c-judge_hard-09","hard-sol-c-judge_hard-10","hard-sol-c-judge_hard-11","hard-sol-c-judge_hard-13","hard-sol-c-judge_hard-15"],"latency_ms":[20.628704000000003,19.989857,20.145469,20.057179,20.121482,20.041397,19.70064,20.015441,19.860574,20.058556000000003,19.84894,20.142758999999998,19.832397,19.860239,19.830603,20.099743,19.908981999999998,20.011344,19.939641,19.916988,19.768655,19.78386,20.161282,20.063253,19.770265,19.683576000000002,19.90822,20.099562000000002,19.721759,19.812117,19.829948,19.65299,19.575186000000002,19.564149999999998,19.875568,19.864475,216.85712700000002,222.25056600000002,219.972101,49.01035,42.747572999999996,50.016826,57.454757,56.345845999999995,221.07427900000002,116.970911,75.80183799999999,58.743553,308.752703,333.03093299999995,90.174356,28.038848,29.894863,32.974001,25.414016,25.423209,32.195311,31.751714,26.057818,27.224870000000003,27.958806,27.912032,27.143085,25.264229,23.218816,41.44142,38.315304000000005,36.489617,32.852619,37.937065,39.785842,37.756222,36.785242000000004,31.965335999999997],"mean_ms":48.1101325,"response_timing_field_excluded":true}
{"experiment":"graph-mixed","model":"jev","arm":"graph8","run":1,"concurrency":1,"request_count":74,"source_file":"analysis/graph8-mixed-measured-1.jsonl","source_sha256":"39c7bb8eb6277a4d53eb2307cca917955f2852dfd2ce563f391171730e9583be","response_semantics_sha256":"487c9568dd218821352340c14bf4816157b94c55b95a78c3077de168c1799638","request_ids":["original-policy-01-0","original-policy-01-1","original-policy-02-0","original-policy-02-1","original-policy-03-0","original-policy-03-1","original-policy-04-0","original-policy-04-1","original-policy-05-0","original-policy-05-1","original-policy-06-0","original-policy-06-1","original-adequacy-01-0","original-adequacy-01-1","original-adequacy-02-0","original-adequacy-02-1","original-adequacy-03-0","original-adequacy-03-1","original-adequacy-04-0","original-adequacy-04-1","original-adequacy-05-0","original-adequacy-05-1","original-adequacy-06-0","original-adequacy-06-1","easy-fact-00","easy-fact-01","easy-fact-02","easy-fact-03","easy-fact-04","easy-fact-05","easy-fact-06","easy-fact-07","easy-fact-08","easy-fact-09","easy-fact-10","easy-fact-11","hard-opus-a-long_policy-11","hard-opus-a-long_policy-13","hard-opus-a-long_policy-19","hard-opus-a-probability-03","hard-opus-a-probability-08","hard-opus-a-temporal_numeric-03","hard-opus-a-temporal_numeric-06","hard-opus-a-temporal_numeric-09","hard-opus-b-multi_hop-08","hard-opus-b-probability-03","hard-opus-b-tradeoff-06","hard-opus-b-tradeoff-08","hard-opus-c-long_policy-04","hard-opus-c-long_policy-11","hard-opus-c-temporal_numeric-02","hard-sol-a-adversarial-06","hard-sol-a-adversarial-08","hard-sol-a-trap-02","hard-sol-a-trap-04","hard-sol-a-trap-13","hard-sol-a-trap-15","hard-sol-b-judge_hard-01","hard-sol-b-judge_hard-02","hard-sol-b-judge_hard-05","hard-sol-b-judge_hard-08","hard-sol-b-judge_hard-10","hard-sol-b-judge_hard-14","hard-sol-b-judge_hard-15","hard-sol-b-judge_hard-18","hard-sol-c-judge_hard-03","hard-sol-c-judge_hard-05","hard-sol-c-judge_hard-07","hard-sol-c-judge_hard-08","hard-sol-c-judge_hard-09","hard-sol-c-judge_hard-10","hard-sol-c-judge_hard-11","hard-sol-c-judge_hard-13","hard-sol-c-judge_hard-15"],"latency_ms":[44.445822,43.787551,44.529858999999995,44.168416,46.269825,44.095381,43.066892,43.309004,43.648658,43.869352,43.533771,19.271779,43.516508,42.743776999999994,42.987881,42.954858,18.899396999999997,43.166911,19.098596,43.420605,42.794645,42.623047,43.535628,43.528102,18.926790999999998,43.119358000000005,19.012914,44.107602,18.997343,43.484522999999996,43.577067,42.992771999999995,42.67792,18.657544,18.883558,43.487512,433.90032699999995,464.41895999999997,444.45186800000005,93.9832,84.94217900000001,99.027943,108.30915200000001,114.91145399999999,443.534624,236.434348,159.051884,119.89162,619.689981,654.449152,179.825559,59.401789,57.766579,67.399365,53.411016,53.921954,67.74837000000001,66.06920199999999,55.312247,57.67257600000001,54.737153,57.754608,58.820757,24.927496,50.148396999999996,84.25473099999999,78.966322,74.753371,68.69837500000001,76.566228,81.963138,37.430910999999995,76.960452,68.741178],"mean_ms":95.42485993243243,"response_timing_field_excluded":true}
{"experiment":"graph-mixed","model":"jev","arm":"graph8","run":2,"concurrency":1,"request_count":74,"source_file":"analysis/graph8-mixed-measured-2.jsonl","source_sha256":"6932be1bbf8911e8805c98601ac8b94cc202899715f2eb4d55f859e9eaea09b4","response_semantics_sha256":"487c9568dd218821352340c14bf4816157b94c55b95a78c3077de168c1799638","request_ids":["original-policy-01-0","original-policy-01-1","original-policy-02-0","original-policy-02-1","original-policy-03-0","original-policy-03-1","original-policy-04-0","original-policy-04-1","original-policy-05-0","original-policy-05-1","original-policy-06-0","original-policy-06-1","original-adequacy-01-0","original-adequacy-01-1","original-adequacy-02-0","original-adequacy-02-1","original-adequacy-03-0","original-adequacy-03-1","original-adequacy-04-0","original-adequacy-04-1","original-adequacy-05-0","original-adequacy-05-1","original-adequacy-06-0","original-adequacy-06-1","easy-fact-00","easy-fact-01","easy-fact-02","easy-fact-03","easy-fact-04","easy-fact-05","easy-fact-06","easy-fact-07","easy-fact-08","easy-fact-09","easy-fact-10","easy-fact-11","hard-opus-a-long_policy-11","hard-opus-a-long_policy-13","hard-opus-a-long_policy-19","hard-opus-a-probability-03","hard-opus-a-probability-08","hard-opus-a-temporal_numeric-03","hard-opus-a-temporal_numeric-06","hard-opus-a-temporal_numeric-09","hard-opus-b-multi_hop-08","hard-opus-b-probability-03","hard-opus-b-tradeoff-06","hard-opus-b-tradeoff-08","hard-opus-c-long_policy-04","hard-opus-c-long_policy-11","hard-opus-c-temporal_numeric-02","hard-sol-a-adversarial-06","hard-sol-a-adversarial-08","hard-sol-a-trap-02","hard-sol-a-trap-04","hard-sol-a-trap-13","hard-sol-a-trap-15","hard-sol-b-judge_hard-01","hard-sol-b-judge_hard-02","hard-sol-b-judge_hard-05","hard-sol-b-judge_hard-08","hard-sol-b-judge_hard-10","hard-sol-b-judge_hard-14","hard-sol-b-judge_hard-15","hard-sol-b-judge_hard-18","hard-sol-c-judge_hard-03","hard-sol-c-judge_hard-05","hard-sol-c-judge_hard-07","hard-sol-c-judge_hard-08","hard-sol-c-judge_hard-09","hard-sol-c-judge_hard-10","hard-sol-c-judge_hard-11","hard-sol-c-judge_hard-13","hard-sol-c-judge_hard-15"],"latency_ms":[44.169335,42.83282,43.042701,43.389737999999994,43.687454,43.102289,42.848734,43.512276,42.755846,43.20119,42.830383,19.087578,42.903851,42.435007,42.906551,42.813656,18.908486,43.349709,18.997205,43.123915,42.447471,42.848371,44.000689,43.78848300000001,18.889576,42.416177,18.956659000000002,43.41176,18.746807,43.303658,43.240301,42.768744,42.825699,18.792845,18.830033,43.245694,436.777541,462.530948,444.0991,92.838252,85.10969300000001,100.760603,111.92729999999999,114.22594799999999,440.35112,232.234512,156.33367,122.591082,620.040458,653.556389,181.090788,59.745628,57.781093,65.659223,54.080197000000005,53.62028,66.963623,66.83349399999999,55.155961000000005,57.712044,55.325127,57.658010000000004,58.729151,25.283904999999997,50.452204,83.06203400000001,81.45798,75.157797,68.361315,77.043226,80.350369,35.748852,75.32257200000001,66.931633],"mean_ms":95.15290287837838,"response_timing_field_excluded":true}
{"experiment":"graph-mixed","model":"jev","arm":"graph64","run":1,"concurrency":1,"request_count":74,"source_file":"analysis/graph64-mixed-measured-1.jsonl","source_sha256":"7dffd2f5774731e6b2f6d5d305b93028356b4823d5977c4b2048e5aa742df040","response_semantics_sha256":"487c9568dd218821352340c14bf4816157b94c55b95a78c3077de168c1799638","request_ids":["original-policy-01-0","original-policy-01-1","original-policy-02-0","original-policy-02-1","original-policy-03-0","original-policy-03-1","original-policy-04-0","original-policy-04-1","original-policy-05-0","original-policy-05-1","original-policy-06-0","original-policy-06-1","original-adequacy-01-0","original-adequacy-01-1","original-adequacy-02-0","original-adequacy-02-1","original-adequacy-03-0","original-adequacy-03-1","original-adequacy-04-0","original-adequacy-04-1","original-adequacy-05-0","original-adequacy-05-1","original-adequacy-06-0","original-adequacy-06-1","easy-fact-00","easy-fact-01","easy-fact-02","easy-fact-03","easy-fact-04","easy-fact-05","easy-fact-06","easy-fact-07","easy-fact-08","easy-fact-09","easy-fact-10","easy-fact-11","hard-opus-a-long_policy-11","hard-opus-a-long_policy-13","hard-opus-a-long_policy-19","hard-opus-a-probability-03","hard-opus-a-probability-08","hard-opus-a-temporal_numeric-03","hard-opus-a-temporal_numeric-06","hard-opus-a-temporal_numeric-09","hard-opus-b-multi_hop-08","hard-opus-b-probability-03","hard-opus-b-tradeoff-06","hard-opus-b-tradeoff-08","hard-opus-c-long_policy-04","hard-opus-c-long_policy-11","hard-opus-c-temporal_numeric-02","hard-sol-a-adversarial-06","hard-sol-a-adversarial-08","hard-sol-a-trap-02","hard-sol-a-trap-04","hard-sol-a-trap-13","hard-sol-a-trap-15","hard-sol-b-judge_hard-01","hard-sol-b-judge_hard-02","hard-sol-b-judge_hard-05","hard-sol-b-judge_hard-08","hard-sol-b-judge_hard-10","hard-sol-b-judge_hard-14","hard-sol-b-judge_hard-15","hard-sol-b-judge_hard-18","hard-sol-c-judge_hard-03","hard-sol-c-judge_hard-05","hard-sol-c-judge_hard-07","hard-sol-c-judge_hard-08","hard-sol-c-judge_hard-09","hard-sol-c-judge_hard-10","hard-sol-c-judge_hard-11","hard-sol-c-judge_hard-13","hard-sol-c-judge_hard-15"],"latency_ms":[19.543752,19.103234999999998,19.169581,19.070849000000003,19.146909,19.257376,18.890618,19.265515,19.041063,19.053644000000002,18.810624,19.047751,18.825848999999998,18.827256000000002,18.943129,18.849228999999998,18.909536000000003,18.901108999999998,19.080772999999997,18.974618,18.672918,18.615062,19.012283,18.954183999999998,18.710275,18.565399,18.772852999999998,18.957435,18.566391000000003,18.691178999999998,18.906509,18.776997,18.704711999999997,18.768157000000002,19.048855,18.876572,213.877269,222.91640800000002,228.009936,49.615934,42.400511,47.348929999999996,54.947966,52.393596,216.35126,112.529269,73.886246,57.938066000000006,312.62507,331.682839,90.12738300000001,26.876435,26.402826,31.010337999999997,24.313457,24.13705,31.5098,30.255436,25.443517,26.466118,25.264733,26.526681,26.524305000000002,24.971288,22.712860000000003,39.837536,37.610242,36.144878999999996,31.830145999999996,36.338082,38.073528,35.770722,35.117331,30.562814],"mean_ms":47.04950005405406,"response_timing_field_excluded":true}
{"experiment":"graph-mixed","model":"jev","arm":"graph64","run":2,"concurrency":1,"request_count":74,"source_file":"analysis/graph64-mixed-measured-2.jsonl","source_sha256":"d5b155635176c933cb39d7511ad8ad1ccc87ab1294abb39caf0f270519b8296d","response_semantics_sha256":"487c9568dd218821352340c14bf4816157b94c55b95a78c3077de168c1799638","request_ids":["original-policy-01-0","original-policy-01-1","original-policy-02-0","original-policy-02-1","original-policy-03-0","original-policy-03-1","original-policy-04-0","original-policy-04-1","original-policy-05-0","original-policy-05-1","original-policy-06-0","original-policy-06-1","original-adequacy-01-0","original-adequacy-01-1","original-adequacy-02-0","original-adequacy-02-1","original-adequacy-03-0","original-adequacy-03-1","original-adequacy-04-0","original-adequacy-04-1","original-adequacy-05-0","original-adequacy-05-1","original-adequacy-06-0","original-adequacy-06-1","easy-fact-00","easy-fact-01","easy-fact-02","easy-fact-03","easy-fact-04","easy-fact-05","easy-fact-06","easy-fact-07","easy-fact-08","easy-fact-09","easy-fact-10","easy-fact-11","hard-opus-a-long_policy-11","hard-opus-a-long_policy-13","hard-opus-a-long_policy-19","hard-opus-a-probability-03","hard-opus-a-probability-08","hard-opus-a-temporal_numeric-03","hard-opus-a-temporal_numeric-06","hard-opus-a-temporal_numeric-09","hard-opus-b-multi_hop-08","hard-opus-b-probability-03","hard-opus-b-tradeoff-06","hard-opus-b-tradeoff-08","hard-opus-c-long_policy-04","hard-opus-c-long_policy-11","hard-opus-c-temporal_numeric-02","hard-sol-a-adversarial-06","hard-sol-a-adversarial-08","hard-sol-a-trap-02","hard-sol-a-trap-04","hard-sol-a-trap-13","hard-sol-a-trap-15","hard-sol-b-judge_hard-01","hard-sol-b-judge_hard-02","hard-sol-b-judge_hard-05","hard-sol-b-judge_hard-08","hard-sol-b-judge_hard-10","hard-sol-b-judge_hard-14","hard-sol-b-judge_hard-15","hard-sol-b-judge_hard-18","hard-sol-c-judge_hard-03","hard-sol-c-judge_hard-05","hard-sol-c-judge_hard-07","hard-sol-c-judge_hard-08","hard-sol-c-judge_hard-09","hard-sol-c-judge_hard-10","hard-sol-c-judge_hard-11","hard-sol-c-judge_hard-13","hard-sol-c-judge_hard-15"],"latency_ms":[19.545784,18.909516,18.994314000000003,19.000709,19.106653,19.262975,18.829967999999997,19.136833,18.892999,18.994238,18.906802,19.025076,18.755097,18.5835,18.894828999999998,18.822573,18.769139,18.802715000000003,18.755554,18.725112,18.540083,18.536052,18.969165999999998,18.989262,18.741436,18.603849,18.800894,19.014943,18.612229,18.787892,18.889717,18.962637,18.812632,18.727304,18.872094999999998,18.852935000000002,214.50272900000002,221.608483,225.215475,46.570913999999995,40.524836,47.233389,55.943778,52.832784000000004,217.443759,114.844977,77.6387,58.649168,317.70284999999996,328.893479,87.09565099999999,27.54357,27.820749,32.967645,24.262939,24.474155,30.8324,31.128459,25.064846,26.862761,26.120114,27.573034,26.757213,25.127774,22.830734,39.90797,37.656939,35.452637,31.586099,35.790213,39.361266,36.856922,36.302945,32.50089],"mean_ms":47.1744697027027,"response_timing_field_excluded":true}
{"experiment":"graph-short","model":"jev","arm":"eager","run":1,"concurrency":1,"request_count":32,"source_file":"analysis/eager-short-measured-1.jsonl","source_sha256":"9c56f1dfa64a8c65dd670a8b3ee6d315477667a184a0793d52157099dadbc6e2","response_semantics_sha256":"6a1617270a6c07352891dddda69e638efd74d76aa9614d221938586a125dbe6c","request_ids":["original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0"],"latency_ms":[20.535619,19.867863999999997,19.824907999999997,19.758318,19.743861000000003,19.812777999999998,19.812723000000002,20.003774,19.817067,19.886435000000002,19.925076,19.74674,19.709094999999998,19.68269,19.777212,19.757239,19.714087000000003,19.708128,19.85834,19.962853,19.813871,19.850613,19.739178,19.798578,19.822277,19.774752,19.743387000000002,19.743205,19.823099,19.764416999999998,19.894926,20.037494],"mean_ms":19.834706375,"response_timing_field_excluded":true}
{"experiment":"graph-short","model":"jev","arm":"eager","run":2,"concurrency":1,"request_count":32,"source_file":"analysis/eager-short-measured-2.jsonl","source_sha256":"bf523bc325a01ac01d12c5090471d9cd0b8a65bc4ac3752b7d535c985ff48a16","response_semantics_sha256":"6a1617270a6c07352891dddda69e638efd74d76aa9614d221938586a125dbe6c","request_ids":["original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0"],"latency_ms":[20.611165,19.899193999999998,19.817108,19.819304,19.809053,19.733233,19.761854,19.898856,19.753937999999998,19.871627,19.8549,19.81075,19.830533000000003,19.796933,19.900298,19.818488,19.907051,19.748167000000002,19.763882,19.840394,19.78454,19.736309000000002,19.794335,19.829434,19.764626,19.734385,19.713860999999998,19.768648,19.702737000000003,19.740212,19.76537,19.767457],"mean_ms":19.8233950625,"response_timing_field_excluded":true}
{"experiment":"graph-short","model":"jev","arm":"graph8","run":1,"concurrency":1,"request_count":32,"source_file":"analysis/graph8-short-measured-1.jsonl","source_sha256":"159fc856902c29c4bd2543ad866e74aa7b49303411f274f78a0aba365b6a5d5c","response_semantics_sha256":"6a1617270a6c07352891dddda69e638efd74d76aa9614d221938586a125dbe6c","request_ids":["original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0"],"latency_ms":[19.545202,19.107617,18.934169,19.323885,18.924030000000002,18.732297,18.810956,18.768074,18.809267000000002,18.799887000000002,18.875609,18.896706,18.974149,18.921501,18.895367,18.890919999999998,18.862142,18.872994000000002,18.835686,18.881498,18.835833,18.785628,18.765551,18.831820999999998,18.769301,18.812487,18.859807,18.843467999999998,18.974931,18.914996,18.903774000000002,18.890064000000002],"mean_ms":18.90155053125,"response_timing_field_excluded":true}
{"experiment":"graph-short","model":"jev","arm":"graph8","run":2,"concurrency":1,"request_count":32,"source_file":"analysis/graph8-short-measured-2.jsonl","source_sha256":"ec4bb0fafcc90f08aaf6c1c9ba7dded0d3926c245dc97e64b858440ff5fbffb6","response_semantics_sha256":"6a1617270a6c07352891dddda69e638efd74d76aa9614d221938586a125dbe6c","request_ids":["original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0"],"latency_ms":[19.531212,18.940319000000002,18.930653,19.006166,18.849073,18.872563,18.882816000000002,18.807591,18.820173,18.848957,18.842752,18.794573,18.839185,18.808003,18.922016,18.944893,18.927934,18.852001,18.824431999999998,18.890708999999998,18.817342,18.816686999999998,18.815871,18.792815,18.804318000000002,18.759103999999997,18.738657999999997,18.731603,18.779148999999997,18.733512,18.784228,18.92049],"mean_ms":18.863431187499998,"response_timing_field_excluded":true}
{"experiment":"graph-short","model":"jev","arm":"graph64","run":1,"concurrency":1,"request_count":32,"source_file":"analysis/graph64-short-measured-1.jsonl","source_sha256":"43dae285c2413b591931ea9fbd9787bc2c7ab9e0de8567bf9a25ce5a3e0d304f","response_semantics_sha256":"6a1617270a6c07352891dddda69e638efd74d76aa9614d221938586a125dbe6c","request_ids":["original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0"],"latency_ms":[19.588419,19.072845,19.170182,18.987365,18.99471,18.908338999999998,18.920040999999998,18.92363,18.740664,18.776329,18.787899,18.892111999999997,18.768377,18.930244,18.761826,18.771240000000002,18.752270000000003,19.010119999999997,18.887169,18.846073,18.84599,18.918878,18.945991,19.030307999999998,19.064153,19.038641,19.047938000000002,19.112956,19.0484,19.091758,19.166480999999997,19.168761],"mean_ms":18.96781590625,"response_timing_field_excluded":true}
{"experiment":"graph-short","model":"jev","arm":"graph64","run":2,"concurrency":1,"request_count":32,"source_file":"analysis/graph64-short-measured-2.jsonl","source_sha256":"caae8282c6862b5727ed0eb2ea81e2a767d2c0997ed98e7d108593264953f6a1","response_semantics_sha256":"6a1617270a6c07352891dddda69e638efd74d76aa9614d221938586a125dbe6c","request_ids":["original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0","original-policy-04-0"],"latency_ms":[19.642566,19.390359999999998,19.388343,19.26361,19.555262,19.312881,19.187656,19.331070999999998,19.357567999999997,19.146727,19.324694,19.278114,19.257737,19.324585,19.484079,19.193825,18.969006,19.05404,18.998463,18.91439,18.945047,18.957398,19.143193,18.994627,19.281866,19.07553,19.095392999999998,19.062829,19.201144,19.002485,19.033231,19.040569],"mean_ms":19.19400903125,"response_timing_field_excluded":true}
{"experiment":"gdn-http","model":"jev","arm":"baseline","run":1,"concurrency":1,"request_count":74,"source_file":"e2e/baseline-measured-1.jsonl","source_sha256":"ff0edc3cd0581b2a8374a6ed5cfb13e70c086bb027e3b04208115c62a12a1ff9","response_semantics_sha256":"487c9568dd218821352340c14bf4816157b94c55b95a78c3077de168c1799638","request_ids":["original-policy-01-0","original-policy-01-1","original-policy-02-0","original-policy-02-1","original-policy-03-0","original-policy-03-1","original-policy-04-0","original-policy-04-1","original-policy-05-0","original-policy-05-1","original-policy-06-0","original-policy-06-1","original-adequacy-01-0","original-adequacy-01-1","original-adequacy-02-0","original-adequacy-02-1","original-adequacy-03-0","original-adequacy-03-1","original-adequacy-04-0","original-adequacy-04-1","original-adequacy-05-0","original-adequacy-05-1","original-adequacy-06-0","original-adequacy-06-1","easy-fact-00","easy-fact-01","easy-fact-02","easy-fact-03","easy-fact-04","easy-fact-05","easy-fact-06","easy-fact-07","easy-fact-08","easy-fact-09","easy-fact-10","easy-fact-11","hard-opus-a-long_policy-11","hard-opus-a-long_policy-13","hard-opus-a-long_policy-19","hard-opus-a-probability-03","hard-opus-a-probability-08","hard-opus-a-temporal_numeric-03","hard-opus-a-temporal_numeric-06","hard-opus-a-temporal_numeric-09","hard-opus-b-multi_hop-08","hard-opus-b-probability-03","hard-opus-b-tradeoff-06","hard-opus-b-tradeoff-08","hard-opus-c-long_policy-04","hard-opus-c-long_policy-11","hard-opus-c-temporal_numeric-02","hard-sol-a-adversarial-06","hard-sol-a-adversarial-08","hard-sol-a-trap-02","hard-sol-a-trap-04","hard-sol-a-trap-13","hard-sol-a-trap-15","hard-sol-b-judge_hard-01","hard-sol-b-judge_hard-02","hard-sol-b-judge_hard-05","hard-sol-b-judge_hard-08","hard-sol-b-judge_hard-10","hard-sol-b-judge_hard-14","hard-sol-b-judge_hard-15","hard-sol-b-judge_hard-18","hard-sol-c-judge_hard-03","hard-sol-c-judge_hard-05","hard-sol-c-judge_hard-07","hard-sol-c-judge_hard-08","hard-sol-c-judge_hard-09","hard-sol-c-judge_hard-10","hard-sol-c-judge_hard-11","hard-sol-c-judge_hard-13","hard-sol-c-judge_hard-15"],"latency_ms":[20.543300000000002,20.331927999999998,20.411296,20.301888,20.268914,20.241111,19.921615,20.172696000000002,20.034196,20.38789,20.279466,20.274807999999997,19.996752,20.00046,19.990632,20.041710000000002,20.072605,19.942362000000003,19.870143,19.78651,19.565118,19.592553,20.131638,20.37535,19.906001,19.730625000000003,19.893454000000002,19.98413,19.67335,19.81784,19.877522000000003,19.593477,19.554232000000003,19.675617,19.859841,19.859485,216.586335,227.743904,228.85186,48.422412,43.474886,49.650673,56.578214,53.745447,219.390449,115.25784,77.427522,60.552277000000004,319.923132,320.943951,90.533984,28.020785999999998,27.956827,32.438416,25.488983,25.812971,32.604034,32.084179999999996,26.587847,27.725289,26.302157,27.933243,27.940070000000002,26.633115,25.148325999999997,43.644906999999996,38.794964,36.876342,33.052608,38.909074000000004,40.432023,37.100113,37.118205,32.116688999999994],"mean_ms":48.37519689189189,"response_timing_field_excluded":true}
{"experiment":"gdn-http","model":"jev","arm":"baseline","run":2,"concurrency":1,"request_count":74,"source_file":"e2e/baseline-measured-2.jsonl","source_sha256":"5a60b08924461e9bfe50310c21832df29be5fed83825dc58502cf6c10c39e5d0","response_semantics_sha256":"487c9568dd218821352340c14bf4816157b94c55b95a78c3077de168c1799638","request_ids":["original-policy-01-0","original-policy-01-1","original-policy-02-0","original-policy-02-1","original-policy-03-0","original-policy-03-1","original-policy-04-0","original-policy-04-1","original-policy-05-0","original-policy-05-1","original-policy-06-0","original-policy-06-1","original-adequacy-01-0","original-adequacy-01-1","original-adequacy-02-0","original-adequacy-02-1","original-adequacy-03-0","original-adequacy-03-1","original-adequacy-04-0","original-adequacy-04-1","original-adequacy-05-0","original-adequacy-05-1","original-adequacy-06-0","original-adequacy-06-1","easy-fact-00","easy-fact-01","easy-fact-02","easy-fact-03","easy-fact-04","easy-fact-05","easy-fact-06","easy-fact-07","easy-fact-08","easy-fact-09","easy-fact-10","easy-fact-11","hard-opus-a-long_policy-11","hard-opus-a-long_policy-13","hard-opus-a-long_policy-19","hard-opus-a-probability-03","hard-opus-a-probability-08","hard-opus-a-temporal_numeric-03","hard-opus-a-temporal_numeric-06","hard-opus-a-temporal_numeric-09","hard-opus-b-multi_hop-08","hard-opus-b-probability-03","hard-opus-b-tradeoff-06","hard-opus-b-tradeoff-08","hard-opus-c-long_policy-04","hard-opus-c-long_policy-11","hard-opus-c-temporal_numeric-02","hard-sol-a-adversarial-06","hard-sol-a-adversarial-08","hard-sol-a-trap-02","hard-sol-a-trap-04","hard-sol-a-trap-13","hard-sol-a-trap-15","hard-sol-b-judge_hard-01","hard-sol-b-judge_hard-02","hard-sol-b-judge_hard-05","hard-sol-b-judge_hard-08","hard-sol-b-judge_hard-10","hard-sol-b-judge_hard-14","hard-sol-b-judge_hard-15","hard-sol-b-judge_hard-18","hard-sol-c-judge_hard-03","hard-sol-c-judge_hard-05","hard-sol-c-judge_hard-07","hard-sol-c-judge_hard-08","hard-sol-c-judge_hard-09","hard-sol-c-judge_hard-10","hard-sol-c-judge_hard-11","hard-sol-c-judge_hard-13","hard-sol-c-judge_hard-15"],"latency_ms":[20.458415000000002,20.158814,20.345022,20.147824,20.121646,20.044933,19.855943,20.085289999999997,19.985014,20.108518999999998,19.941503,20.0763,19.909038,19.797371000000002,19.875639,19.863211,19.891498000000002,19.898643,19.88902,19.858019000000002,19.618408,19.714856,20.272581000000002,20.209215999999998,19.802176000000003,19.650348,19.853976999999997,19.965663000000003,19.690001,19.758079000000002,20.004665000000003,19.574034,19.640314999999998,19.54844,19.828233,19.740625,218.167674,227.70445899999999,228.29619300000002,48.737243,43.311509,49.260075,57.681389,54.410933,218.17646,114.518669,78.509552,60.1565,315.897746,323.81647200000003,92.227688,27.879022,27.569466000000002,32.937056,25.827249,26.113619,32.627528000000005,32.263071,26.752885,28.507126,26.753189,28.388299,28.105901999999997,27.283829,24.898069,42.847525,39.532976,37.695883,33.323485,38.428529000000005,40.57913,38.643777,37.169075,32.458974000000005],"mean_ms":48.44110141891892,"response_timing_field_excluded":true}
{"experiment":"gdn-http","model":"jev","arm":"candidate","run":1,"concurrency":1,"request_count":74,"source_file":"e2e/candidate-measured-1.jsonl","source_sha256":"aa11cb7a4ef76cd7551561cc50a09fa9885f11b89035f8457881376d7a024a2e","response_semantics_sha256":"487c9568dd218821352340c14bf4816157b94c55b95a78c3077de168c1799638","request_ids":["original-policy-01-0","original-policy-01-1","original-policy-02-0","original-policy-02-1","original-policy-03-0","original-policy-03-1","original-policy-04-0","original-policy-04-1","original-policy-05-0","original-policy-05-1","original-policy-06-0","original-policy-06-1","original-adequacy-01-0","original-adequacy-01-1","original-adequacy-02-0","original-adequacy-02-1","original-adequacy-03-0","original-adequacy-03-1","original-adequacy-04-0","original-adequacy-04-1","original-adequacy-05-0","original-adequacy-05-1","original-adequacy-06-0","original-adequacy-06-1","easy-fact-00","easy-fact-01","easy-fact-02","easy-fact-03","easy-fact-04","easy-fact-05","easy-fact-06","easy-fact-07","easy-fact-08","easy-fact-09","easy-fact-10","easy-fact-11","hard-opus-a-long_policy-11","hard-opus-a-long_policy-13","hard-opus-a-long_policy-19","hard-opus-a-probability-03","hard-opus-a-probability-08","hard-opus-a-temporal_numeric-03","hard-opus-a-temporal_numeric-06","hard-opus-a-temporal_numeric-09","hard-opus-b-multi_hop-08","hard-opus-b-probability-03","hard-opus-b-tradeoff-06","hard-opus-b-tradeoff-08","hard-opus-c-long_policy-04","hard-opus-c-long_policy-11","hard-opus-c-temporal_numeric-02","hard-sol-a-adversarial-06","hard-sol-a-adversarial-08","hard-sol-a-trap-02","hard-sol-a-trap-04","hard-sol-a-trap-13","hard-sol-a-trap-15","hard-sol-b-judge_hard-01","hard-sol-b-judge_hard-02","hard-sol-b-judge_hard-05","hard-sol-b-judge_hard-08","hard-sol-b-judge_hard-10","hard-sol-b-judge_hard-14","hard-sol-b-judge_hard-15","hard-sol-b-judge_hard-18","hard-sol-c-judge_hard-03","hard-sol-c-judge_hard-05","hard-sol-c-judge_hard-07","hard-sol-c-judge_hard-08","hard-sol-c-judge_hard-09","hard-sol-c-judge_hard-10","hard-sol-c-judge_hard-11","hard-sol-c-judge_hard-13","hard-sol-c-judge_hard-15"],"latency_ms":[20.488631,20.190618,20.316195,20.223447,20.192076999999998,20.085592,19.848269000000002,20.122536999999998,20.012507999999997,20.110243,19.978890999999997,20.089534999999998,19.847453,19.689221,19.867399000000002,19.805229,19.829340000000002,19.818913000000002,19.818895,19.716309000000003,19.587196000000002,19.573336,20.049217000000002,20.155039,19.894939,19.649805,19.879207,20.007443,19.744134,19.972084000000002,19.89398,19.627783,19.566298,19.526828,19.693121,19.675295,213.862995,225.918293,226.993519,46.686735,41.814568,50.126521,59.38195,55.016009,215.92103200000003,114.00741000000001,77.380201,59.989996,315.673906,324.642425,91.30927,28.250795,28.128444,33.12639,25.81685,25.861942999999997,32.516479000000004,31.719378,26.064619,27.82718,26.164987,27.395204999999997,27.228437,26.093138,23.887688,40.669623,38.380082,36.83791,33.916803,37.917548000000004,39.661431,37.347603,37.126906,32.526281999999995],"mean_ms":48.10456159459459,"response_timing_field_excluded":true}
{"experiment":"gdn-http","model":"jev","arm":"candidate","run":2,"concurrency":1,"request_count":74,"source_file":"e2e/candidate-measured-2.jsonl","source_sha256":"37d517470e0a2eb26f4faf956da2339c87eb9ca7e2123b4d4efa6f086b28f44e","response_semantics_sha256":"487c9568dd218821352340c14bf4816157b94c55b95a78c3077de168c1799638","request_ids":["original-policy-01-0","original-policy-01-1","original-policy-02-0","original-policy-02-1","original-policy-03-0","original-policy-03-1","original-policy-04-0","original-policy-04-1","original-policy-05-0","original-policy-05-1","original-policy-06-0","original-policy-06-1","original-adequacy-01-0","original-adequacy-01-1","original-adequacy-02-0","original-adequacy-02-1","original-adequacy-03-0","original-adequacy-03-1","original-adequacy-04-0","original-adequacy-04-1","original-adequacy-05-0","original-adequacy-05-1","original-adequacy-06-0","original-adequacy-06-1","easy-fact-00","easy-fact-01","easy-fact-02","easy-fact-03","easy-fact-04","easy-fact-05","easy-fact-06","easy-fact-07","easy-fact-08","easy-fact-09","easy-fact-10","easy-fact-11","hard-opus-a-long_policy-11","hard-opus-a-long_policy-13","hard-opus-a-long_policy-19","hard-opus-a-probability-03","hard-opus-a-probability-08","hard-opus-a-temporal_numeric-03","hard-opus-a-temporal_numeric-06","hard-opus-a-temporal_numeric-09","hard-opus-b-multi_hop-08","hard-opus-b-probability-03","hard-opus-b-tradeoff-06","hard-opus-b-tradeoff-08","hard-opus-c-long_policy-04","hard-opus-c-long_policy-11","hard-opus-c-temporal_numeric-02","hard-sol-a-adversarial-06","hard-sol-a-adversarial-08","hard-sol-a-trap-02","hard-sol-a-trap-04","hard-sol-a-trap-13","hard-sol-a-trap-15","hard-sol-b-judge_hard-01","hard-sol-b-judge_hard-02","hard-sol-b-judge_hard-05","hard-sol-b-judge_hard-08","hard-sol-b-judge_hard-10","hard-sol-b-judge_hard-14","hard-sol-b-judge_hard-15","hard-sol-b-judge_hard-18","hard-sol-c-judge_hard-03","hard-sol-c-judge_hard-05","hard-sol-c-judge_hard-07","hard-sol-c-judge_hard-08","hard-sol-c-judge_hard-09","hard-sol-c-judge_hard-10","hard-sol-c-judge_hard-11","hard-sol-c-judge_hard-13","hard-sol-c-judge_hard-15"],"latency_ms":[21.10884,20.608072,21.372746000000003,20.300463,20.239247,20.336491000000002,19.891498000000002,20.237059000000002,20.070688999999998,20.339783,20.122044,20.282716,20.012957,19.868988,19.941031000000002,19.863299,19.922858,19.963459999999998,20.04677,19.966763,19.731559,19.736072,20.199999,20.185964000000002,19.890338,19.721907,19.963567,20.110031,19.755336,19.838846,19.949204,19.670462,19.638355999999998,19.627577,19.867735,19.978326000000003,213.47955599999997,231.014741,225.79116499999998,46.791434,41.355917,49.830509,56.430421,52.705006,214.206521,114.468215,79.101175,60.853171999999994,316.45678,328.497239,90.80051999999999,28.252864,27.773342,33.041073999999995,25.938297,26.106558,32.898218,32.077019,26.32922,27.530546,26.039734,27.905648000000003,27.848753000000002,26.956241,23.819731,40.330737,39.127568000000004,37.233808,34.030411,38.080266,40.012958000000005,38.055377,37.478628,33.563383],"mean_ms":48.305051418918914,"response_timing_field_excluded":true}
