Buckets:

Pranav2748's picture
download
raw
53.1 kB
{
"rl60": {
"offset": -0.6799984872833753,
"calib_n": 109,
"eval_noul_n": 1395,
"eval_yes_rate": 0.6229390681003584,
"eval_yes_rate_offset": 0.5232974910394266,
"eval_gold_yes": 0.5039426523297491,
"eval_ba": 0.7839944827699619,
"eval_ba_offset": 0.8356794579794276,
"s1mb": {
"calibrated": {
"noul": 50.70371577975563,
"choice": 57.19274044054583,
"score": 35.767117161735676,
"task_avg": 47.88785779401238,
"s1mb_yes_rate": 0.31633891721291574,
"adjusted": {
"aegis2-noul-test-v1": 0.5602707152002926,
"laya--ag-news-choice-test-v1": 0.8358208955223883,
"aqua-rat-choice-test-v1": 0.21126760563380287,
"arc-choice-test-v1": 0.9558823529411764,
"arct-choice-test-v1": 0.5319148936170213,
"argument-quality-choice-test-v1": 0.6938775510204082,
"argument-quality-noul-test-v1": 0.12934047939043625,
"babi-nli-noul-test-v1": 0.6400000000000001,
"banking77-choice-test-v1": 0.6736842105263157,
"bbq-choice-test-v1": 0.9166666666666666,
"boardgameqa-choice-test-v1": 0.23437500000000003,
"canttalk-noul-test-v1": 0.5800000000000001,
"civil-comments-noul-test-v1": 0.2915103139204662,
"cladder-noul-test-v1": 0.48,
"clinc-choice-test-v1": 0.786206896551724,
"contract-nli-choice-test-v1": 0.5466377440347072,
"corr2cause-choice-test-v1": 0.11666666666666659,
"creak-noul-test-v1": 0.6400000000000001,
"crows-pairs-choice-test-v1": 0.6041666666666667,
"dbpedia-choice-test-v1": 0.9662921348314606,
"defeasible-nli-choice-test-v1": 0.5652173913043479,
"laya--enron-spam-noul-test-v1": 0.8999999999999999,
"esci-choice-test-v1": 0.2602739726027397,
"ethics-choice-test-v1": 0.6666666666666665,
"ethics-noul-test-v1": 0.38928571428571423,
"ethos-noul-test-v1": 0.6400000000000001,
"few-nerd-choice-test-v1": 0.6487455197132617,
"fol-nli-choice-test-v1": 0.13114754098360648,
"followir-core17-noul-test-v1": 0.29428904428904423,
"followir-news21-noul-test-v1": 0.18000000000000016,
"followir-robust04-noul-test-v1": 0.7923815062518174,
"go-emotions-noul-test-v1": 0.5142817874272971,
"gretel-pii-choice-test-v1": 0.7175324675324675,
"gsm8k-choice-test-v1": 0.5857142857142857,
"hans-noul-test-v1": 0.7000000000000002,
"hatecheck-noul-test-v1": 0.6800000000000002,
"hh-rlhf-choice-test-v1": 0.05128205128205133,
"hwu64-choice-test-v1": 0.7765957446808511,
"impli-noul-test-v1": 0.74,
"lexcomp-noul-test-v1": 0.43999999999999995,
"logical-entailment-noul-test-v1": 0.06000000000000005,
"lonli-choice-test-v1": 0.7704918032786885,
"massive-choice-test-v1": 0.829981718464351,
"miqa-choice-test-v1": 0.9318181818181818,
"mtop-choice-test-v1": 0.8001313927632908,
"nlsat-noul-test-v1": 0.06000000000000005,
"open-jev--amount-extraction-control-v1-choice-test-v1": 0.7254901960784313,
"open-jev--amount-extraction-control-v1-noul-test-v1": 0.46875,
"open-jev--browser-control-v1-choice-test-v1": 1.0,
"open-jev--citation-control-v1-choice-test-v1": 0.9848484848484849,
"open-jev--context-retention-control-v1-noul-test-v1": 0.0,
"open-jev--customer-control-v1-choice-test-v1": 0.8260869565217391,
"open-jev--customer-control-v1-noul-test-v1": 0.47058823529411775,
"open-jev--customer-control-v1-score-test-v1": 0.5010736256437411,
"open-jev--drone-control-v1-choice-test-v1": 0.0,
"open-jev--drone-control-v1-noul-test-v1": 1.0,
"open-jev--drone-control-v1-score-test-v1": 0.0,
"open-jev--email-selection-control-v1-choice-test-v1": 0.11304347826086972,
"open-jev--email-selection-control-v1-noul-test-v1": 0.6153846153846154,
"open-jev--entity-alignment-control-v1-noul-test-v1": 0.8333333333333335,
"open-jev--entity-alignment-control-v1-score-test-v1": 0.10768792068745892,
"open-jev--ir-control-v1-choice-test-v1": 0.84,
"open-jev--ir-control-v1-noul-test-v1": 0.8571428571428572,
"open-jev--ir-control-v1-score-test-v1": 0.0,
"open-jev--mailroom-control-v1-choice-test-v1": 1.0,
"open-jev--mailroom-control-v1-noul-test-v1": 0.8111111111111111,
"open-jev--painting-geometry-v1-choice-test-v1": 0.8947368421052632,
"open-jev--painting-geometry-v1-noul-test-v1": 0.2666666666666666,
"open-jev--painting-geometry-v1-score-test-v1": 0.31163678271733497,
"open-jev--phone-extraction-control-v1-choice-test-v1": 0.45652173913043476,
"open-jev--phone-extraction-control-v1-noul-test-v1": 0.8999999999999999,
"open-jev--reasoning-control-v1-choice-test-v1": 0.55,
"open-jev--reasoning-control-v1-noul-test-v1": 0.40808823529411775,
"open-jev--reasoning-control-v1-score-test-v1": 0.5116676314844353,
"open-jev--silent-failure-control-v1-noul-test-v1": 0.6000000000000001,
"open-jev--snake-v1-choice-test-v1": 0.0,
"open-jev--snake-v1-noul-test-v1": 0.027738264580369876,
"open-jev--sponsor-segment-control-v1-choice-test-v1": 1.0,
"open-jev--tic-tac-toe-v1-choice-test-v1": 0.03787878787878775,
"open-jev--vizdoom-basic-v1-noul-test-v1": 0.7058823529411766,
"open-jev--vizdoom-basic-v1-score-test-v1": 0.5611449747196239,
"open-jev--workflow-controls-v1--agent-trace-observability-noul-test-v1": 0.3659673659673659,
"open-jev--workflow-controls-v1--customer-service-noul-test-v1": 0.5628485628485629,
"open-jev--workflow-controls-v1--invoice-processing-noul-test-v1": 0.6801176965111391,
"open-jev--workflow-controls-v1--security-incidents-noul-test-v1": 0.7840112201963534,
"openbookqa-choice-test-v1": 0.8611111111111112,
"patent-similarity-score-test-v1": 0.290246823046062,
"paws-noul-test-v1": 0.6400000000000001,
"plane-noul-test-v1": 0.06000000000000005,
"poem-sentiment-choice-test-v1": 0.0,
"qasper-noul-test-v1": 0.54,
"quartz-choice-test-v1": 0.6428571428571428,
"robust-lr-choice-test-v1": 0.65,
"ruletaker-noul-test-v1": 0.48,
"s1mb-generalization-contextual-choice-choice-test-v1": 0.9613733905579399,
"s1mb-generalization-contextual-noul-noul-test-v1": 0.8999999999999999,
"s1mb-generalization-contextual-score-score-test-v1": 0.7493735516889689,
"s1mb-generalization-diverse-choice-choice-test-v1": 0.9207048458149779,
"s1mb-generalization-diverse-noul-noul-test-v1": 0.8799999999999999,
"s1mb-generalization-diverse-score-score-test-v1": 0.7605669662438349,
"scicite-choice-test-v1": 0.5806451612903225,
"scitail-noul-test-v1": 0.6799999999999999,
"scone-choice-test-v1": 0.72,
"sdoh-nli-noul-test-v1": 0.8199999999999998,
"sgd-choice-test-v1": 0.22033898305084754,
"snli-choice-test-v1": 0.7096774193548386,
"spartqa-choice-test-v1": 0.0967741935483871,
"stepgame-choice-test-v1": 0.33333333333333337,
"synthetic-relevance--nanobeir--nanoarguana-noul-test-v1": 0.3056378575842238,
"synthetic-relevance--nanobeir--nanoarguana-score-test-v1": 0.24287287966932491,
"synthetic-relevance--nanobeir--nanodbpedia-noul-test-v1": 0.3978836709428111,
"synthetic-relevance--nanobeir--nanodbpedia-score-test-v1": 0.4117364590263355,
"synthetic-relevance--nanobeir--nanofiqa2018-noul-test-v1": 0.44083812096059116,
"synthetic-relevance--nanobeir--nanofiqa2018-score-test-v1": 0.347061893737288,
"synthetic-relevance--nanobeir--nanohotpotqa-noul-test-v1": 0.1557554160303185,
"synthetic-relevance--nanobeir--nanohotpotqa-score-test-v1": 0.3533716425449749,
"synthetic-relevance--nanobeir--nanomsmarco-noul-test-v1": 0.5616846942591427,
"synthetic-relevance--nanobeir--nanomsmarco-score-test-v1": 0.4421745077469317,
"synthetic-relevance--nanobeir--nanonfcorpus-noul-test-v1": 0.3462396114391635,
"synthetic-relevance--nanobeir--nanonfcorpus-score-test-v1": 0.30330704037715905,
"synthetic-relevance--nanobeir--nanonq-noul-test-v1": 0.5649185247217279,
"synthetic-relevance--nanobeir--nanonq-score-test-v1": 0.34563416909402134,
"synthetic-relevance--nanobeir--nanoscidocs-noul-test-v1": 0.16736832720824957,
"synthetic-relevance--nanobeir--nanoscidocs-score-test-v1": 0.2551052742071359,
"synthetic-relevance--nanobeir--nanotouche2020-noul-test-v1": 0.4545782796020945,
"synthetic-relevance--nanobeir--nanotouche2020-score-test-v1": 0.29566497078210885,
"synthetic-relevance--nanocoir-noul-test-v1": 0.512296962815457,
"synthetic-relevance--nanocoir-score-test-v1": 0.21403263359189162,
"temporal-nli-choice-test-v1": 0.22580645161290325,
"tracie-noul-test-v1": 0.18000000000000016,
"laya--typed-decisions-choice-test-v1": 0.30864086833403337,
"laya--typed-decisions-noul-test-v1": 0.35900076645519086,
"laya--typed-decisions-score-test-v1": 0.5067348569558621,
"ud-ewt-choice-test-v1": 0.21651090342679127,
"winobias-choice-test-v1": 0.5652173913043479,
"winowhy-noul-test-v1": 0.3999999999999999,
"wiqa-choice-test-v1": 0.3492063492063492
}
},
"calibrated+offset": {
"noul": 49.90956027800102,
"choice": 57.19274044054583,
"score": 35.767117161735676,
"task_avg": 47.62313929342751,
"s1mb_yes_rate": 0.250303471716436,
"adjusted": {
"aegis2-noul-test-v1": 0.48765319187854406,
"laya--ag-news-choice-test-v1": 0.8358208955223883,
"aqua-rat-choice-test-v1": 0.21126760563380287,
"arc-choice-test-v1": 0.9558823529411764,
"arct-choice-test-v1": 0.5319148936170213,
"argument-quality-choice-test-v1": 0.6938775510204082,
"argument-quality-noul-test-v1": 0.23907189521958694,
"babi-nli-noul-test-v1": 0.74,
"banking77-choice-test-v1": 0.6736842105263157,
"bbq-choice-test-v1": 0.9166666666666666,
"boardgameqa-choice-test-v1": 0.23437500000000003,
"canttalk-noul-test-v1": 0.6600000000000001,
"civil-comments-noul-test-v1": 0.29226134282086713,
"cladder-noul-test-v1": 0.26,
"clinc-choice-test-v1": 0.786206896551724,
"contract-nli-choice-test-v1": 0.5466377440347072,
"corr2cause-choice-test-v1": 0.11666666666666659,
"creak-noul-test-v1": 0.72,
"crows-pairs-choice-test-v1": 0.6041666666666667,
"dbpedia-choice-test-v1": 0.9662921348314606,
"defeasible-nli-choice-test-v1": 0.5652173913043479,
"laya--enron-spam-noul-test-v1": 0.8999999999999999,
"esci-choice-test-v1": 0.2602739726027397,
"ethics-choice-test-v1": 0.6666666666666665,
"ethics-noul-test-v1": 0.4571428571428571,
"ethos-noul-test-v1": 0.6600000000000001,
"few-nerd-choice-test-v1": 0.6487455197132617,
"fol-nli-choice-test-v1": 0.13114754098360648,
"followir-core17-noul-test-v1": 0.2255244755244754,
"followir-news21-noul-test-v1": 0.11999999999999988,
"followir-robust04-noul-test-v1": 0.7618493748182611,
"go-emotions-noul-test-v1": 0.4825661789641007,
"gretel-pii-choice-test-v1": 0.7175324675324675,
"gsm8k-choice-test-v1": 0.5857142857142857,
"hans-noul-test-v1": 0.6800000000000002,
"hatecheck-noul-test-v1": 0.7,
"hh-rlhf-choice-test-v1": 0.05128205128205133,
"hwu64-choice-test-v1": 0.7765957446808511,
"impli-noul-test-v1": 0.78,
"lexcomp-noul-test-v1": 0.41999999999999993,
"logical-entailment-noul-test-v1": 0.1200000000000001,
"lonli-choice-test-v1": 0.7704918032786885,
"massive-choice-test-v1": 0.829981718464351,
"miqa-choice-test-v1": 0.9318181818181818,
"mtop-choice-test-v1": 0.8001313927632908,
"nlsat-noul-test-v1": 0.10000000000000009,
"open-jev--amount-extraction-control-v1-choice-test-v1": 0.7254901960784313,
"open-jev--amount-extraction-control-v1-noul-test-v1": 0.53125,
"open-jev--browser-control-v1-choice-test-v1": 1.0,
"open-jev--citation-control-v1-choice-test-v1": 0.9848484848484849,
"open-jev--context-retention-control-v1-noul-test-v1": 0.0,
"open-jev--customer-control-v1-choice-test-v1": 0.8260869565217391,
"open-jev--customer-control-v1-noul-test-v1": 0.47058823529411775,
"open-jev--customer-control-v1-score-test-v1": 0.5010736256437411,
"open-jev--drone-control-v1-choice-test-v1": 0.0,
"open-jev--drone-control-v1-noul-test-v1": 1.0,
"open-jev--drone-control-v1-score-test-v1": 0.0,
"open-jev--email-selection-control-v1-choice-test-v1": 0.11304347826086972,
"open-jev--email-selection-control-v1-noul-test-v1": 0.5769230769230769,
"open-jev--entity-alignment-control-v1-noul-test-v1": 0.8888888888888888,
"open-jev--entity-alignment-control-v1-score-test-v1": 0.10768792068745892,
"open-jev--ir-control-v1-choice-test-v1": 0.84,
"open-jev--ir-control-v1-noul-test-v1": 0.9285714285714286,
"open-jev--ir-control-v1-score-test-v1": 0.0,
"open-jev--mailroom-control-v1-choice-test-v1": 1.0,
"open-jev--mailroom-control-v1-noul-test-v1": 0.7666666666666666,
"open-jev--painting-geometry-v1-choice-test-v1": 0.8947368421052632,
"open-jev--painting-geometry-v1-noul-test-v1": 0.2666666666666666,
"open-jev--painting-geometry-v1-score-test-v1": 0.31163678271733497,
"open-jev--phone-extraction-control-v1-choice-test-v1": 0.45652173913043476,
"open-jev--phone-extraction-control-v1-noul-test-v1": 0.8999999999999999,
"open-jev--reasoning-control-v1-choice-test-v1": 0.55,
"open-jev--reasoning-control-v1-noul-test-v1": 0.2904411764705883,
"open-jev--reasoning-control-v1-score-test-v1": 0.5116676314844353,
"open-jev--silent-failure-control-v1-noul-test-v1": 0.6200000000000001,
"open-jev--snake-v1-choice-test-v1": 0.0,
"open-jev--snake-v1-noul-test-v1": 0.0,
"open-jev--sponsor-segment-control-v1-choice-test-v1": 1.0,
"open-jev--tic-tac-toe-v1-choice-test-v1": 0.03787878787878775,
"open-jev--vizdoom-basic-v1-noul-test-v1": 0.8823529411764706,
"open-jev--vizdoom-basic-v1-score-test-v1": 0.5611449747196239,
"open-jev--workflow-controls-v1--agent-trace-observability-noul-test-v1": 0.39160839160839167,
"open-jev--workflow-controls-v1--customer-service-noul-test-v1": 0.49764049764049756,
"open-jev--workflow-controls-v1--invoice-processing-noul-test-v1": 0.6780159730979403,
"open-jev--workflow-controls-v1--security-incidents-noul-test-v1": 0.8129967274427301,
"openbookqa-choice-test-v1": 0.8611111111111112,
"patent-similarity-score-test-v1": 0.290246823046062,
"paws-noul-test-v1": 0.72,
"plane-noul-test-v1": 0.0,
"poem-sentiment-choice-test-v1": 0.0,
"qasper-noul-test-v1": 0.5800000000000001,
"quartz-choice-test-v1": 0.6428571428571428,
"robust-lr-choice-test-v1": 0.65,
"ruletaker-noul-test-v1": 0.43999999999999995,
"s1mb-generalization-contextual-choice-choice-test-v1": 0.9613733905579399,
"s1mb-generalization-contextual-noul-noul-test-v1": 0.8399999999999999,
"s1mb-generalization-contextual-score-score-test-v1": 0.7493735516889689,
"s1mb-generalization-diverse-choice-choice-test-v1": 0.9207048458149779,
"s1mb-generalization-diverse-noul-noul-test-v1": 0.8999999999999999,
"s1mb-generalization-diverse-score-score-test-v1": 0.7605669662438349,
"scicite-choice-test-v1": 0.5806451612903225,
"scitail-noul-test-v1": 0.74,
"scone-choice-test-v1": 0.72,
"sdoh-nli-noul-test-v1": 0.8400000000000001,
"sgd-choice-test-v1": 0.22033898305084754,
"snli-choice-test-v1": 0.7096774193548386,
"spartqa-choice-test-v1": 0.0967741935483871,
"stepgame-choice-test-v1": 0.33333333333333337,
"synthetic-relevance--nanobeir--nanoarguana-noul-test-v1": 0.17215757534715537,
"synthetic-relevance--nanobeir--nanoarguana-score-test-v1": 0.24287287966932491,
"synthetic-relevance--nanobeir--nanodbpedia-noul-test-v1": 0.35078239625018104,
"synthetic-relevance--nanobeir--nanodbpedia-score-test-v1": 0.4117364590263355,
"synthetic-relevance--nanobeir--nanofiqa2018-noul-test-v1": 0.39330915751342177,
"synthetic-relevance--nanobeir--nanofiqa2018-score-test-v1": 0.347061893737288,
"synthetic-relevance--nanobeir--nanohotpotqa-noul-test-v1": 0.07027546806946106,
"synthetic-relevance--nanobeir--nanohotpotqa-score-test-v1": 0.3533716425449749,
"synthetic-relevance--nanobeir--nanomsmarco-noul-test-v1": 0.4875803017121183,
"synthetic-relevance--nanobeir--nanomsmarco-score-test-v1": 0.4421745077469317,
"synthetic-relevance--nanobeir--nanonfcorpus-noul-test-v1": 0.3172800095590098,
"synthetic-relevance--nanobeir--nanonfcorpus-score-test-v1": 0.30330704037715905,
"synthetic-relevance--nanobeir--nanonq-noul-test-v1": 0.49951897434363657,
"synthetic-relevance--nanobeir--nanonq-score-test-v1": 0.34563416909402134,
"synthetic-relevance--nanobeir--nanoscidocs-noul-test-v1": 0.12427811512515974,
"synthetic-relevance--nanobeir--nanoscidocs-score-test-v1": 0.2551052742071359,
"synthetic-relevance--nanobeir--nanotouche2020-noul-test-v1": 0.41341034863975357,
"synthetic-relevance--nanobeir--nanotouche2020-score-test-v1": 0.29566497078210885,
"synthetic-relevance--nanocoir-noul-test-v1": 0.37291762617480906,
"synthetic-relevance--nanocoir-score-test-v1": 0.21403263359189162,
"temporal-nli-choice-test-v1": 0.22580645161290325,
"tracie-noul-test-v1": 0.21999999999999997,
"laya--typed-decisions-choice-test-v1": 0.30864086833403337,
"laya--typed-decisions-noul-test-v1": 0.4564506044697436,
"laya--typed-decisions-score-test-v1": 0.5067348569558621,
"ud-ewt-choice-test-v1": 0.21651090342679127,
"winobias-choice-test-v1": 0.5652173913043479,
"winowhy-noul-test-v1": 0.20000000000000018,
"wiqa-choice-test-v1": 0.3492063492063492
}
}
}
},
"v1_joint": {
"offset": -0.5033793788230835,
"calib_n": 109,
"eval_noul_n": 1395,
"eval_yes_rate": 0.5842293906810035,
"eval_yes_rate_offset": 0.5326164874551972,
"eval_gold_yes": 0.5039426523297491,
"eval_ba": 0.7857335202558811,
"eval_ba_offset": 0.7904418717470132,
"s1mb": {
"calibrated": {
"noul": 50.07962257490453,
"choice": 52.30924425272342,
"score": 27.975023045764445,
"task_avg": 43.45462995779747,
"s1mb_yes_rate": 0.28073156915108843,
"adjusted": {
"aegis2-noul-test-v1": 0.4433875983171758,
"laya--ag-news-choice-test-v1": 0.7910447761194032,
"aqua-rat-choice-test-v1": 0.028169014084507067,
"arc-choice-test-v1": 0.9705882352941176,
"arct-choice-test-v1": 0.48936170212765956,
"argument-quality-choice-test-v1": 0.6326530612244897,
"argument-quality-noul-test-v1": 0.11079818480422476,
"babi-nli-noul-test-v1": 0.41999999999999993,
"banking77-choice-test-v1": 0.6631578947368422,
"bbq-choice-test-v1": 0.95,
"boardgameqa-choice-test-v1": 0.375,
"canttalk-noul-test-v1": 0.72,
"civil-comments-noul-test-v1": 0.314524306059917,
"cladder-noul-test-v1": 0.26,
"clinc-choice-test-v1": 0.8275862068965518,
"contract-nli-choice-test-v1": 0.6106290672451193,
"corr2cause-choice-test-v1": 0.0,
"creak-noul-test-v1": 0.74,
"crows-pairs-choice-test-v1": 0.5416666666666667,
"dbpedia-choice-test-v1": 0.9775280898876404,
"defeasible-nli-choice-test-v1": 0.41304347826086946,
"laya--enron-spam-noul-test-v1": 0.8999999999999999,
"esci-choice-test-v1": 0.17808219178082194,
"ethics-choice-test-v1": 0.3333333333333334,
"ethics-noul-test-v1": 0.43452380952380953,
"ethos-noul-test-v1": 0.72,
"few-nerd-choice-test-v1": 0.6093189964157706,
"fol-nli-choice-test-v1": 0.11475409836065575,
"followir-core17-noul-test-v1": 0.35897435897435903,
"followir-news21-noul-test-v1": 0.2333333333333334,
"followir-robust04-noul-test-v1": 0.8200058156440826,
"go-emotions-noul-test-v1": 0.48444169078029087,
"gretel-pii-choice-test-v1": 0.7727272727272728,
"gsm8k-choice-test-v1": 0.24285714285714285,
"hans-noul-test-v1": 0.7000000000000002,
"hatecheck-noul-test-v1": 0.7799999999999998,
"hh-rlhf-choice-test-v1": 0.10256410256410266,
"hwu64-choice-test-v1": 0.797872340425532,
"impli-noul-test-v1": 0.54,
"lexcomp-noul-test-v1": 0.3999999999999999,
"logical-entailment-noul-test-v1": 0.20000000000000018,
"lonli-choice-test-v1": 0.6229508196721312,
"massive-choice-test-v1": 0.8244972577696527,
"miqa-choice-test-v1": 0.8181818181818182,
"mtop-choice-test-v1": 0.7772892662219527,
"nlsat-noul-test-v1": 0.0,
"open-jev--amount-extraction-control-v1-choice-test-v1": 0.7254901960784313,
"open-jev--amount-extraction-control-v1-noul-test-v1": 0.6875,
"open-jev--browser-control-v1-choice-test-v1": 0.6086956521739129,
"open-jev--citation-control-v1-choice-test-v1": 0.7121212121212123,
"open-jev--context-retention-control-v1-noul-test-v1": 0.06000000000000005,
"open-jev--customer-control-v1-choice-test-v1": 0.8260869565217391,
"open-jev--customer-control-v1-noul-test-v1": 1.0,
"open-jev--customer-control-v1-score-test-v1": 0.4550389617256263,
"open-jev--drone-control-v1-choice-test-v1": 0.0,
"open-jev--drone-control-v1-noul-test-v1": 0.9411764705882353,
"open-jev--drone-control-v1-score-test-v1": 0.0,
"open-jev--email-selection-control-v1-choice-test-v1": 0.37391304347826093,
"open-jev--email-selection-control-v1-noul-test-v1": 0.42307692307692313,
"open-jev--entity-alignment-control-v1-noul-test-v1": 0.7115384615384615,
"open-jev--entity-alignment-control-v1-score-test-v1": 0.10354883642807688,
"open-jev--ir-control-v1-choice-test-v1": 0.6799999999999998,
"open-jev--ir-control-v1-noul-test-v1": 0.7857142857142856,
"open-jev--ir-control-v1-score-test-v1": 0.0,
"open-jev--mailroom-control-v1-choice-test-v1": 1.0,
"open-jev--mailroom-control-v1-noul-test-v1": 0.7722222222222221,
"open-jev--painting-geometry-v1-choice-test-v1": 0.47368421052631576,
"open-jev--painting-geometry-v1-noul-test-v1": 0.06666666666666665,
"open-jev--painting-geometry-v1-score-test-v1": 0.0,
"open-jev--phone-extraction-control-v1-choice-test-v1": 0.6739130434782609,
"open-jev--phone-extraction-control-v1-noul-test-v1": 0.9090909090909092,
"open-jev--reasoning-control-v1-choice-test-v1": 0.55,
"open-jev--reasoning-control-v1-noul-test-v1": 0.4007352941176472,
"open-jev--reasoning-control-v1-score-test-v1": 0.46228880266144246,
"open-jev--silent-failure-control-v1-noul-test-v1": 0.72,
"open-jev--snake-v1-choice-test-v1": 0.18556701030927833,
"open-jev--snake-v1-noul-test-v1": 0.1813655761024182,
"open-jev--sponsor-segment-control-v1-choice-test-v1": 0.9487179487179487,
"open-jev--tic-tac-toe-v1-choice-test-v1": 0.0,
"open-jev--vizdoom-basic-v1-noul-test-v1": 0.8235294117647058,
"open-jev--vizdoom-basic-v1-score-test-v1": 0.4189118599502557,
"open-jev--workflow-controls-v1--agent-trace-observability-noul-test-v1": 0.3543123543123543,
"open-jev--workflow-controls-v1--customer-service-noul-test-v1": 0.5851565851565852,
"open-jev--workflow-controls-v1--invoice-processing-noul-test-v1": 0.7057587221521646,
"open-jev--workflow-controls-v1--security-incidents-noul-test-v1": 0.5409069658719026,
"openbookqa-choice-test-v1": 0.7638888888888888,
"patent-similarity-score-test-v1": 0.3266830724535009,
"paws-noul-test-v1": 0.6400000000000001,
"plane-noul-test-v1": 0.1200000000000001,
"poem-sentiment-choice-test-v1": 0.0,
"qasper-noul-test-v1": 0.6400000000000001,
"quartz-choice-test-v1": 0.7142857142857143,
"robust-lr-choice-test-v1": 0.3166666666666666,
"ruletaker-noul-test-v1": 0.3600000000000001,
"s1mb-generalization-contextual-choice-choice-test-v1": 0.9613733905579399,
"s1mb-generalization-contextual-noul-noul-test-v1": 0.8799999999999999,
"s1mb-generalization-contextual-score-score-test-v1": 0.6149834321085637,
"s1mb-generalization-diverse-choice-choice-test-v1": 0.881057268722467,
"s1mb-generalization-diverse-noul-noul-test-v1": 0.8799999999999999,
"s1mb-generalization-diverse-score-score-test-v1": 0.7096966733728995,
"scicite-choice-test-v1": 0.4999999999999999,
"scitail-noul-test-v1": 0.6799999999999999,
"scone-choice-test-v1": 0.54,
"sdoh-nli-noul-test-v1": 0.8399999999999999,
"sgd-choice-test-v1": 0.2542372881355933,
"snli-choice-test-v1": 0.6612903225806452,
"spartqa-choice-test-v1": 0.0967741935483871,
"stepgame-choice-test-v1": 0.27380952380952384,
"synthetic-relevance--nanobeir--nanoarguana-noul-test-v1": 0.19926157464108507,
"synthetic-relevance--nanobeir--nanoarguana-score-test-v1": 0.11167728663667009,
"synthetic-relevance--nanobeir--nanodbpedia-noul-test-v1": 0.41770258066944344,
"synthetic-relevance--nanobeir--nanodbpedia-score-test-v1": 0.3649886179620183,
"synthetic-relevance--nanobeir--nanofiqa2018-noul-test-v1": 0.39002621310810626,
"synthetic-relevance--nanobeir--nanofiqa2018-score-test-v1": 0.34097038999966456,
"synthetic-relevance--nanobeir--nanohotpotqa-noul-test-v1": 0.15598167317155953,
"synthetic-relevance--nanobeir--nanohotpotqa-score-test-v1": 0.15821570935090346,
"synthetic-relevance--nanobeir--nanomsmarco-noul-test-v1": 0.5384503681124295,
"synthetic-relevance--nanobeir--nanomsmarco-score-test-v1": 0.39363766129605826,
"synthetic-relevance--nanobeir--nanonfcorpus-noul-test-v1": 0.3663022294130087,
"synthetic-relevance--nanobeir--nanonfcorpus-score-test-v1": 0.21236216453239287,
"synthetic-relevance--nanobeir--nanonq-noul-test-v1": 0.5156445494559176,
"synthetic-relevance--nanobeir--nanonq-score-test-v1": 0.229478884673753,
"synthetic-relevance--nanobeir--nanoscidocs-noul-test-v1": 0.17144951511129158,
"synthetic-relevance--nanobeir--nanoscidocs-score-test-v1": 0.14839491556145668,
"synthetic-relevance--nanobeir--nanotouche2020-noul-test-v1": 0.32832924999283186,
"synthetic-relevance--nanobeir--nanotouche2020-score-test-v1": 0.4100041834166628,
"synthetic-relevance--nanocoir-noul-test-v1": 0.4870635794503144,
"synthetic-relevance--nanocoir-score-test-v1": 0.0,
"temporal-nli-choice-test-v1": 0.24193548387096778,
"tracie-noul-test-v1": 0.0,
"laya--typed-decisions-choice-test-v1": 0.3138313776226675,
"laya--typed-decisions-noul-test-v1": 0.3480258402550176,
"laya--typed-decisions-score-test-v1": 0.41387338748058744,
"ud-ewt-choice-test-v1": 0.29595015576323985,
"winobias-choice-test-v1": 0.41304347826086946,
"winowhy-noul-test-v1": 0.3400000000000001,
"wiqa-choice-test-v1": 0.36507936507936506
}
},
"calibrated+offset": {
"noul": 47.56067110056,
"choice": 52.30924425272342,
"score": 27.975023045764445,
"task_avg": 42.61497946634929,
"s1mb_yes_rate": 0.22901998867038925,
"adjusted": {
"aegis2-noul-test-v1": 0.450887141027986,
"laya--ag-news-choice-test-v1": 0.7910447761194032,
"aqua-rat-choice-test-v1": 0.028169014084507067,
"arc-choice-test-v1": 0.9705882352941176,
"arct-choice-test-v1": 0.48936170212765956,
"argument-quality-choice-test-v1": 0.6326530612244897,
"argument-quality-noul-test-v1": 0.13491482054584236,
"babi-nli-noul-test-v1": 0.41999999999999993,
"banking77-choice-test-v1": 0.6631578947368422,
"bbq-choice-test-v1": 0.95,
"boardgameqa-choice-test-v1": 0.375,
"canttalk-noul-test-v1": 0.7999999999999998,
"civil-comments-noul-test-v1": 0.3013950476751732,
"cladder-noul-test-v1": 0.17999999999999994,
"clinc-choice-test-v1": 0.8275862068965518,
"contract-nli-choice-test-v1": 0.6106290672451193,
"corr2cause-choice-test-v1": 0.0,
"creak-noul-test-v1": 0.7200000000000002,
"crows-pairs-choice-test-v1": 0.5416666666666667,
"dbpedia-choice-test-v1": 0.9775280898876404,
"defeasible-nli-choice-test-v1": 0.41304347826086946,
"laya--enron-spam-noul-test-v1": 0.8999999999999999,
"esci-choice-test-v1": 0.17808219178082194,
"ethics-choice-test-v1": 0.3333333333333334,
"ethics-noul-test-v1": 0.30714285714285716,
"ethos-noul-test-v1": 0.6200000000000001,
"few-nerd-choice-test-v1": 0.6093189964157706,
"fol-nli-choice-test-v1": 0.11475409836065575,
"followir-core17-noul-test-v1": 0.32284382284382285,
"followir-news21-noul-test-v1": 0.20666666666666655,
"followir-robust04-noul-test-v1": 0.7257923815062517,
"go-emotions-noul-test-v1": 0.42167715248092175,
"gretel-pii-choice-test-v1": 0.7727272727272728,
"gsm8k-choice-test-v1": 0.24285714285714285,
"hans-noul-test-v1": 0.72,
"hatecheck-noul-test-v1": 0.8,
"hh-rlhf-choice-test-v1": 0.10256410256410266,
"hwu64-choice-test-v1": 0.797872340425532,
"impli-noul-test-v1": 0.48,
"lexcomp-noul-test-v1": 0.3999999999999999,
"logical-entailment-noul-test-v1": 0.14000000000000012,
"lonli-choice-test-v1": 0.6229508196721312,
"massive-choice-test-v1": 0.8244972577696527,
"miqa-choice-test-v1": 0.8181818181818182,
"mtop-choice-test-v1": 0.7772892662219527,
"nlsat-noul-test-v1": 0.0,
"open-jev--amount-extraction-control-v1-choice-test-v1": 0.7254901960784313,
"open-jev--amount-extraction-control-v1-noul-test-v1": 0.65625,
"open-jev--browser-control-v1-choice-test-v1": 0.6086956521739129,
"open-jev--citation-control-v1-choice-test-v1": 0.7121212121212123,
"open-jev--context-retention-control-v1-noul-test-v1": 0.020000000000000018,
"open-jev--customer-control-v1-choice-test-v1": 0.8260869565217391,
"open-jev--customer-control-v1-noul-test-v1": 1.0,
"open-jev--customer-control-v1-score-test-v1": 0.4550389617256263,
"open-jev--drone-control-v1-choice-test-v1": 0.0,
"open-jev--drone-control-v1-noul-test-v1": 0.9411764705882353,
"open-jev--drone-control-v1-score-test-v1": 0.0,
"open-jev--email-selection-control-v1-choice-test-v1": 0.37391304347826093,
"open-jev--email-selection-control-v1-noul-test-v1": 0.3846153846153846,
"open-jev--entity-alignment-control-v1-noul-test-v1": 0.6367521367521367,
"open-jev--entity-alignment-control-v1-score-test-v1": 0.10354883642807688,
"open-jev--ir-control-v1-choice-test-v1": 0.6799999999999998,
"open-jev--ir-control-v1-noul-test-v1": 0.7857142857142856,
"open-jev--ir-control-v1-score-test-v1": 0.0,
"open-jev--mailroom-control-v1-choice-test-v1": 1.0,
"open-jev--mailroom-control-v1-noul-test-v1": 0.6833333333333331,
"open-jev--painting-geometry-v1-choice-test-v1": 0.47368421052631576,
"open-jev--painting-geometry-v1-noul-test-v1": 0.03809523809523818,
"open-jev--painting-geometry-v1-score-test-v1": 0.0,
"open-jev--phone-extraction-control-v1-choice-test-v1": 0.6739130434782609,
"open-jev--phone-extraction-control-v1-noul-test-v1": 0.9090909090909092,
"open-jev--reasoning-control-v1-choice-test-v1": 0.55,
"open-jev--reasoning-control-v1-noul-test-v1": 0.2279411764705883,
"open-jev--reasoning-control-v1-score-test-v1": 0.46228880266144246,
"open-jev--silent-failure-control-v1-noul-test-v1": 0.8199999999999998,
"open-jev--snake-v1-choice-test-v1": 0.18556701030927833,
"open-jev--snake-v1-noul-test-v1": 0.08179231863442382,
"open-jev--sponsor-segment-control-v1-choice-test-v1": 0.9487179487179487,
"open-jev--tic-tac-toe-v1-choice-test-v1": 0.0,
"open-jev--vizdoom-basic-v1-noul-test-v1": 0.8235294117647058,
"open-jev--vizdoom-basic-v1-score-test-v1": 0.4189118599502557,
"open-jev--workflow-controls-v1--agent-trace-observability-noul-test-v1": 0.3018648018648018,
"open-jev--workflow-controls-v1--customer-service-noul-test-v1": 0.601029601029601,
"open-jev--workflow-controls-v1--invoice-processing-noul-test-v1": 0.5683060109289617,
"open-jev--workflow-controls-v1--security-incidents-noul-test-v1": 0.5666199158485274,
"openbookqa-choice-test-v1": 0.7638888888888888,
"patent-similarity-score-test-v1": 0.3266830724535009,
"paws-noul-test-v1": 0.6600000000000001,
"plane-noul-test-v1": 0.08000000000000007,
"poem-sentiment-choice-test-v1": 0.0,
"qasper-noul-test-v1": 0.6400000000000001,
"quartz-choice-test-v1": 0.7142857142857143,
"robust-lr-choice-test-v1": 0.3166666666666666,
"ruletaker-noul-test-v1": 0.3999999999999999,
"s1mb-generalization-contextual-choice-choice-test-v1": 0.9613733905579399,
"s1mb-generalization-contextual-noul-noul-test-v1": 0.8999999999999999,
"s1mb-generalization-contextual-score-score-test-v1": 0.6149834321085637,
"s1mb-generalization-diverse-choice-choice-test-v1": 0.881057268722467,
"s1mb-generalization-diverse-noul-noul-test-v1": 0.8599999999999999,
"s1mb-generalization-diverse-score-score-test-v1": 0.7096966733728995,
"scicite-choice-test-v1": 0.4999999999999999,
"scitail-noul-test-v1": 0.7599999999999998,
"scone-choice-test-v1": 0.54,
"sdoh-nli-noul-test-v1": 0.8199999999999998,
"sgd-choice-test-v1": 0.2542372881355933,
"snli-choice-test-v1": 0.6612903225806452,
"spartqa-choice-test-v1": 0.0967741935483871,
"stepgame-choice-test-v1": 0.27380952380952384,
"synthetic-relevance--nanobeir--nanoarguana-noul-test-v1": 0.13860702159931293,
"synthetic-relevance--nanobeir--nanoarguana-score-test-v1": 0.11167728663667009,
"synthetic-relevance--nanobeir--nanodbpedia-noul-test-v1": 0.4068302282083289,
"synthetic-relevance--nanobeir--nanodbpedia-score-test-v1": 0.3649886179620183,
"synthetic-relevance--nanobeir--nanofiqa2018-noul-test-v1": 0.34133308497820103,
"synthetic-relevance--nanobeir--nanofiqa2018-score-test-v1": 0.34097038999966456,
"synthetic-relevance--nanobeir--nanohotpotqa-noul-test-v1": 0.11380734204423337,
"synthetic-relevance--nanobeir--nanohotpotqa-score-test-v1": 0.15821570935090346,
"synthetic-relevance--nanobeir--nanomsmarco-noul-test-v1": 0.4893858453092492,
"synthetic-relevance--nanobeir--nanomsmarco-score-test-v1": 0.39363766129605826,
"synthetic-relevance--nanobeir--nanonfcorpus-noul-test-v1": 0.3218657508101743,
"synthetic-relevance--nanobeir--nanonfcorpus-score-test-v1": 0.21236216453239287,
"synthetic-relevance--nanobeir--nanonq-noul-test-v1": 0.45018684398983755,
"synthetic-relevance--nanobeir--nanonq-score-test-v1": 0.229478884673753,
"synthetic-relevance--nanobeir--nanoscidocs-noul-test-v1": 0.13067725926439566,
"synthetic-relevance--nanobeir--nanoscidocs-score-test-v1": 0.14839491556145668,
"synthetic-relevance--nanobeir--nanotouche2020-noul-test-v1": 0.24093301940993883,
"synthetic-relevance--nanobeir--nanotouche2020-score-test-v1": 0.4100041834166628,
"synthetic-relevance--nanocoir-noul-test-v1": 0.4365161351123097,
"synthetic-relevance--nanocoir-score-test-v1": 0.0,
"temporal-nli-choice-test-v1": 0.24193548387096778,
"tracie-noul-test-v1": 0.0,
"laya--typed-decisions-choice-test-v1": 0.3138313776226675,
"laya--typed-decisions-noul-test-v1": 0.3932225339837623,
"laya--typed-decisions-score-test-v1": 0.41387338748058744,
"ud-ewt-choice-test-v1": 0.29595015576323985,
"winobias-choice-test-v1": 0.41304347826086946,
"winowhy-noul-test-v1": 0.3799999999999999,
"wiqa-choice-test-v1": 0.36507936507936506
}
}
}
},
"base": {
"offset": 0.12125704256523087,
"calib_n": 109,
"eval_noul_n": 1395,
"eval_yes_rate": 0.4157706093189964,
"eval_yes_rate_offset": 0.45017921146953405,
"eval_gold_yes": 0.5039426523297491,
"eval_ba": 0.6859803977996859,
"eval_ba_offset": 0.7043482103947574,
"s1mb": {
"calibrated": {
"noul": 33.76706817616705,
"choice": 45.70255576401406,
"score": 18.882231543636387,
"task_avg": 32.78395182793917,
"s1mb_yes_rate": 0.18386339726470827,
"adjusted": {
"aegis2-noul-test-v1": 0.42052313883299797,
"laya--ag-news-choice-test-v1": 0.7910447761194032,
"aqua-rat-choice-test-v1": 0.042253521126760604,
"arc-choice-test-v1": 0.8823529411764708,
"arct-choice-test-v1": 0.2765957446808511,
"argument-quality-choice-test-v1": 0.28571428571428575,
"argument-quality-noul-test-v1": 0.09289526462740527,
"babi-nli-noul-test-v1": 0.10000000000000009,
"banking77-choice-test-v1": 0.631578947368421,
"bbq-choice-test-v1": 0.8999999999999999,
"boardgameqa-choice-test-v1": 0.25000000000000006,
"canttalk-noul-test-v1": 0.7200000000000002,
"civil-comments-noul-test-v1": 0.3041383169192424,
"cladder-noul-test-v1": 0.040000000000000036,
"clinc-choice-test-v1": 0.7931034482758621,
"contract-nli-choice-test-v1": 0.5173535791757051,
"corr2cause-choice-test-v1": 0.0,
"creak-noul-test-v1": 0.72,
"crows-pairs-choice-test-v1": 0.43749999999999994,
"dbpedia-choice-test-v1": 0.9775280898876404,
"defeasible-nli-choice-test-v1": 0.41304347826086946,
"laya--enron-spam-noul-test-v1": 0.76,
"esci-choice-test-v1": 0.0821917808219178,
"ethics-choice-test-v1": 0.5000000000000001,
"ethics-noul-test-v1": 0.1595238095238094,
"ethos-noul-test-v1": 0.45999999999999996,
"few-nerd-choice-test-v1": 0.6451612903225806,
"fol-nli-choice-test-v1": 0.16393442622950816,
"followir-core17-noul-test-v1": 0.26398601398601396,
"followir-news21-noul-test-v1": 0.03333333333333344,
"followir-robust04-noul-test-v1": 0.4736842105263157,
"go-emotions-noul-test-v1": 0.3630486674285902,
"gretel-pii-choice-test-v1": 0.6688311688311688,
"gsm8k-choice-test-v1": 0.12857142857142861,
"hans-noul-test-v1": 0.5,
"hatecheck-noul-test-v1": 0.72,
"hh-rlhf-choice-test-v1": 0.07692307692307698,
"hwu64-choice-test-v1": 0.797872340425532,
"impli-noul-test-v1": 0.28,
"lexcomp-noul-test-v1": 0.3799999999999999,
"logical-entailment-noul-test-v1": 0.040000000000000036,
"lonli-choice-test-v1": 0.540983606557377,
"massive-choice-test-v1": 0.7806215722120659,
"miqa-choice-test-v1": 0.7272727272727273,
"mtop-choice-test-v1": 0.74873660804528,
"nlsat-noul-test-v1": 0.0,
"open-jev--amount-extraction-control-v1-choice-test-v1": 0.5294117647058824,
"open-jev--amount-extraction-control-v1-noul-test-v1": 0.0,
"open-jev--browser-control-v1-choice-test-v1": 1.0,
"open-jev--citation-control-v1-choice-test-v1": 0.6363636363636365,
"open-jev--context-retention-control-v1-noul-test-v1": 0.0,
"open-jev--customer-control-v1-choice-test-v1": 0.8260869565217391,
"open-jev--customer-control-v1-noul-test-v1": 0.75,
"open-jev--customer-control-v1-score-test-v1": 0.3893950629833327,
"open-jev--drone-control-v1-choice-test-v1": 0.0,
"open-jev--drone-control-v1-noul-test-v1": 0.0,
"open-jev--drone-control-v1-score-test-v1": 0.0,
"open-jev--email-selection-control-v1-choice-test-v1": 0.0,
"open-jev--email-selection-control-v1-noul-test-v1": 0.5,
"open-jev--entity-alignment-control-v1-noul-test-v1": 0.0,
"open-jev--entity-alignment-control-v1-score-test-v1": 0.0,
"open-jev--ir-control-v1-choice-test-v1": 0.6799999999999998,
"open-jev--ir-control-v1-noul-test-v1": 0.5714285714285714,
"open-jev--ir-control-v1-score-test-v1": 0.0,
"open-jev--mailroom-control-v1-choice-test-v1": 1.0,
"open-jev--mailroom-control-v1-noul-test-v1": 0.7305555555555556,
"open-jev--painting-geometry-v1-choice-test-v1": 0.5263157894736842,
"open-jev--painting-geometry-v1-noul-test-v1": 0.1333333333333333,
"open-jev--painting-geometry-v1-score-test-v1": 0.11001724500712606,
"open-jev--phone-extraction-control-v1-choice-test-v1": 0.391304347826087,
"open-jev--phone-extraction-control-v1-noul-test-v1": 0.6000000000000001,
"open-jev--reasoning-control-v1-choice-test-v1": 0.050000000000000044,
"open-jev--reasoning-control-v1-noul-test-v1": 0.05514705882352944,
"open-jev--reasoning-control-v1-score-test-v1": 0.12618636261103344,
"open-jev--silent-failure-control-v1-noul-test-v1": 0.06000000000000005,
"open-jev--snake-v1-choice-test-v1": 0.0,
"open-jev--snake-v1-noul-test-v1": 0.0,
"open-jev--sponsor-segment-control-v1-choice-test-v1": 0.923076923076923,
"open-jev--tic-tac-toe-v1-choice-test-v1": 0.030303030303030165,
"open-jev--vizdoom-basic-v1-noul-test-v1": 0.06617647058823528,
"open-jev--vizdoom-basic-v1-score-test-v1": 0.1553597082025594,
"open-jev--workflow-controls-v1--agent-trace-observability-noul-test-v1": 0.2027972027972027,
"open-jev--workflow-controls-v1--customer-service-noul-test-v1": 0.36250536250536247,
"open-jev--workflow-controls-v1--invoice-processing-noul-test-v1": 0.02564102564102555,
"open-jev--workflow-controls-v1--security-incidents-noul-test-v1": 0.35811126694717155,
"openbookqa-choice-test-v1": 0.7361111111111112,
"patent-similarity-score-test-v1": 0.2934810047042089,
"paws-noul-test-v1": 0.5800000000000001,
"plane-noul-test-v1": 0.0,
"poem-sentiment-choice-test-v1": 0.0,
"qasper-noul-test-v1": 0.6599999999999999,
"quartz-choice-test-v1": 0.47619047619047633,
"robust-lr-choice-test-v1": 0.18333333333333332,
"ruletaker-noul-test-v1": 0.26,
"s1mb-generalization-contextual-choice-choice-test-v1": 0.9484978540772532,
"s1mb-generalization-contextual-noul-noul-test-v1": 0.8199999999999998,
"s1mb-generalization-contextual-score-score-test-v1": 0.5348292656817324,
"s1mb-generalization-diverse-choice-choice-test-v1": 0.86784140969163,
"s1mb-generalization-diverse-noul-noul-test-v1": 0.8399999999999999,
"s1mb-generalization-diverse-score-score-test-v1": 0.5785965969396042,
"scicite-choice-test-v1": 0.532258064516129,
"scitail-noul-test-v1": 0.8599999999999999,
"scone-choice-test-v1": 0.56,
"sdoh-nli-noul-test-v1": 0.8999999999999999,
"sgd-choice-test-v1": 0.23728813559322043,
"snli-choice-test-v1": 0.5967741935483871,
"spartqa-choice-test-v1": 0.0,
"stepgame-choice-test-v1": 0.25,
"synthetic-relevance--nanobeir--nanoarguana-noul-test-v1": 0.1322072402534249,
"synthetic-relevance--nanobeir--nanoarguana-score-test-v1": 0.009914357195622725,
"synthetic-relevance--nanobeir--nanodbpedia-noul-test-v1": 0.3597289535156989,
"synthetic-relevance--nanobeir--nanodbpedia-score-test-v1": 0.2412115992486591,
"synthetic-relevance--nanobeir--nanofiqa2018-noul-test-v1": 0.29607812321130966,
"synthetic-relevance--nanobeir--nanofiqa2018-score-test-v1": 0.23325885856088935,
"synthetic-relevance--nanobeir--nanohotpotqa-noul-test-v1": 0.18512359296340297,
"synthetic-relevance--nanobeir--nanohotpotqa-score-test-v1": 0.10831095033900406,
"synthetic-relevance--nanobeir--nanomsmarco-noul-test-v1": 0.48737468820639496,
"synthetic-relevance--nanobeir--nanomsmarco-score-test-v1": 0.2474660472587129,
"synthetic-relevance--nanobeir--nanonfcorpus-noul-test-v1": 0.34625575841540024,
"synthetic-relevance--nanobeir--nanonfcorpus-score-test-v1": 0.13921800746762414,
"synthetic-relevance--nanobeir--nanonq-noul-test-v1": 0.4997183632167408,
"synthetic-relevance--nanobeir--nanonq-score-test-v1": 0.0,
"synthetic-relevance--nanobeir--nanoscidocs-noul-test-v1": 0.14743786589533547,
"synthetic-relevance--nanobeir--nanoscidocs-score-test-v1": 0.11267844076262346,
"synthetic-relevance--nanobeir--nanotouche2020-noul-test-v1": 0.2508413593010428,
"synthetic-relevance--nanobeir--nanotouche2020-score-test-v1": 0.40182339219261376,
"synthetic-relevance--nanocoir-noul-test-v1": 0.28739000806659165,
"synthetic-relevance--nanocoir-score-test-v1": 0.0,
"temporal-nli-choice-test-v1": 0.08064516129032256,
"tracie-noul-test-v1": 0.0,
"laya--typed-decisions-choice-test-v1": 0.22748534707752452,
"laya--typed-decisions-noul-test-v1": 0.3635856680955216,
"laya--typed-decisions-score-test-v1": 0.28352172500829476,
"ud-ewt-choice-test-v1": 0.18302180685358257,
"winobias-choice-test-v1": 0.21739130434782605,
"winowhy-noul-test-v1": 0.3999999999999999,
"wiqa-choice-test-v1": 0.3015873015873017
}
},
"calibrated+offset": {
"noul": 36.14875624152523,
"choice": 45.70255576401406,
"score": 18.882231543636387,
"task_avg": 33.577847849725224,
"s1mb_yes_rate": 0.20619891559439993,
"adjusted": {
"aegis2-noul-test-v1": 0.42052313883299797,
"laya--ag-news-choice-test-v1": 0.7910447761194032,
"aqua-rat-choice-test-v1": 0.042253521126760604,
"arc-choice-test-v1": 0.8823529411764708,
"arct-choice-test-v1": 0.2765957446808511,
"argument-quality-choice-test-v1": 0.28571428571428575,
"argument-quality-noul-test-v1": 0.15506912289885677,
"babi-nli-noul-test-v1": 0.1399999999999999,
"banking77-choice-test-v1": 0.631578947368421,
"bbq-choice-test-v1": 0.8999999999999999,
"boardgameqa-choice-test-v1": 0.25000000000000006,
"canttalk-noul-test-v1": 0.72,
"civil-comments-noul-test-v1": 0.3157009512655522,
"cladder-noul-test-v1": 0.06000000000000005,
"clinc-choice-test-v1": 0.7931034482758621,
"contract-nli-choice-test-v1": 0.5173535791757051,
"corr2cause-choice-test-v1": 0.0,
"creak-noul-test-v1": 0.72,
"crows-pairs-choice-test-v1": 0.43749999999999994,
"dbpedia-choice-test-v1": 0.9775280898876404,
"defeasible-nli-choice-test-v1": 0.41304347826086946,
"laya--enron-spam-noul-test-v1": 0.76,
"esci-choice-test-v1": 0.0821917808219178,
"ethics-choice-test-v1": 0.5000000000000001,
"ethics-noul-test-v1": 0.18571428571428572,
"ethos-noul-test-v1": 0.52,
"few-nerd-choice-test-v1": 0.6451612903225806,
"fol-nli-choice-test-v1": 0.16393442622950816,
"followir-core17-noul-test-v1": 0.303030303030303,
"followir-news21-noul-test-v1": 0.05333333333333323,
"followir-robust04-noul-test-v1": 0.5207909275952312,
"go-emotions-noul-test-v1": 0.3798264384161578,
"gretel-pii-choice-test-v1": 0.6688311688311688,
"gsm8k-choice-test-v1": 0.12857142857142861,
"hans-noul-test-v1": 0.56,
"hatecheck-noul-test-v1": 0.74,
"hh-rlhf-choice-test-v1": 0.07692307692307698,
"hwu64-choice-test-v1": 0.797872340425532,
"impli-noul-test-v1": 0.3999999999999999,
"lexcomp-noul-test-v1": 0.43999999999999995,
"logical-entailment-noul-test-v1": 0.08000000000000007,
"lonli-choice-test-v1": 0.540983606557377,
"massive-choice-test-v1": 0.7806215722120659,
"miqa-choice-test-v1": 0.7272727272727273,
"mtop-choice-test-v1": 0.74873660804528,
"nlsat-noul-test-v1": 0.0,
"open-jev--amount-extraction-control-v1-choice-test-v1": 0.5294117647058824,
"open-jev--amount-extraction-control-v1-noul-test-v1": 0.0,
"open-jev--browser-control-v1-choice-test-v1": 1.0,
"open-jev--citation-control-v1-choice-test-v1": 0.6363636363636365,
"open-jev--context-retention-control-v1-noul-test-v1": 0.0,
"open-jev--customer-control-v1-choice-test-v1": 0.8260869565217391,
"open-jev--customer-control-v1-noul-test-v1": 0.875,
"open-jev--customer-control-v1-score-test-v1": 0.3893950629833327,
"open-jev--drone-control-v1-choice-test-v1": 0.0,
"open-jev--drone-control-v1-noul-test-v1": 0.0,
"open-jev--drone-control-v1-score-test-v1": 0.0,
"open-jev--email-selection-control-v1-choice-test-v1": 0.0,
"open-jev--email-selection-control-v1-noul-test-v1": 0.4615384615384617,
"open-jev--entity-alignment-control-v1-noul-test-v1": 0.0,
"open-jev--entity-alignment-control-v1-score-test-v1": 0.0,
"open-jev--ir-control-v1-choice-test-v1": 0.6799999999999998,
"open-jev--ir-control-v1-noul-test-v1": 0.6428571428571428,
"open-jev--ir-control-v1-score-test-v1": 0.0,
"open-jev--mailroom-control-v1-choice-test-v1": 1.0,
"open-jev--mailroom-control-v1-noul-test-v1": 0.7055555555555555,
"open-jev--painting-geometry-v1-choice-test-v1": 0.5263157894736842,
"open-jev--painting-geometry-v1-noul-test-v1": 0.09523809523809534,
"open-jev--painting-geometry-v1-score-test-v1": 0.11001724500712606,
"open-jev--phone-extraction-control-v1-choice-test-v1": 0.391304347826087,
"open-jev--phone-extraction-control-v1-noul-test-v1": 0.6000000000000001,
"open-jev--reasoning-control-v1-choice-test-v1": 0.050000000000000044,
"open-jev--reasoning-control-v1-noul-test-v1": 0.11029411764705888,
"open-jev--reasoning-control-v1-score-test-v1": 0.12618636261103344,
"open-jev--silent-failure-control-v1-noul-test-v1": 0.1200000000000001,
"open-jev--snake-v1-choice-test-v1": 0.0,
"open-jev--snake-v1-noul-test-v1": 0.0,
"open-jev--sponsor-segment-control-v1-choice-test-v1": 0.923076923076923,
"open-jev--tic-tac-toe-v1-choice-test-v1": 0.030303030303030165,
"open-jev--vizdoom-basic-v1-noul-test-v1": 0.12867647058823528,
"open-jev--vizdoom-basic-v1-score-test-v1": 0.1553597082025594,
"open-jev--workflow-controls-v1--agent-trace-observability-noul-test-v1": 0.2027972027972027,
"open-jev--workflow-controls-v1--customer-service-noul-test-v1": 0.5358215358215359,
"open-jev--workflow-controls-v1--invoice-processing-noul-test-v1": 0.06977721731820097,
"open-jev--workflow-controls-v1--security-incidents-noul-test-v1": 0.5371669004207575,
"openbookqa-choice-test-v1": 0.7361111111111112,
"patent-similarity-score-test-v1": 0.2934810047042089,
"paws-noul-test-v1": 0.5800000000000001,
"plane-noul-test-v1": 0.0,
"poem-sentiment-choice-test-v1": 0.0,
"qasper-noul-test-v1": 0.6200000000000001,
"quartz-choice-test-v1": 0.47619047619047633,
"robust-lr-choice-test-v1": 0.18333333333333332,
"ruletaker-noul-test-v1": 0.24,
"s1mb-generalization-contextual-choice-choice-test-v1": 0.9484978540772532,
"s1mb-generalization-contextual-noul-noul-test-v1": 0.7999999999999998,
"s1mb-generalization-contextual-score-score-test-v1": 0.5348292656817324,
"s1mb-generalization-diverse-choice-choice-test-v1": 0.86784140969163,
"s1mb-generalization-diverse-noul-noul-test-v1": 0.8400000000000001,
"s1mb-generalization-diverse-score-score-test-v1": 0.5785965969396042,
"scicite-choice-test-v1": 0.532258064516129,
"scitail-noul-test-v1": 0.8799999999999999,
"scone-choice-test-v1": 0.56,
"sdoh-nli-noul-test-v1": 0.8999999999999999,
"sgd-choice-test-v1": 0.23728813559322043,
"snli-choice-test-v1": 0.5967741935483871,
"spartqa-choice-test-v1": 0.0,
"stepgame-choice-test-v1": 0.25,
"synthetic-relevance--nanobeir--nanoarguana-noul-test-v1": 0.16057004623725102,
"synthetic-relevance--nanobeir--nanoarguana-score-test-v1": 0.009914357195622725,
"synthetic-relevance--nanobeir--nanodbpedia-noul-test-v1": 0.39872910302452924,
"synthetic-relevance--nanobeir--nanodbpedia-score-test-v1": 0.2412115992486591,
"synthetic-relevance--nanobeir--nanofiqa2018-noul-test-v1": 0.3402387701764291,
"synthetic-relevance--nanobeir--nanofiqa2018-score-test-v1": 0.23325885856088935,
"synthetic-relevance--nanobeir--nanohotpotqa-noul-test-v1": 0.2128174670513039,
"synthetic-relevance--nanobeir--nanohotpotqa-score-test-v1": 0.10831095033900406,
"synthetic-relevance--nanobeir--nanomsmarco-noul-test-v1": 0.5008487982533132,
"synthetic-relevance--nanobeir--nanomsmarco-score-test-v1": 0.2474660472587129,
"synthetic-relevance--nanobeir--nanonfcorpus-noul-test-v1": 0.3443827091719669,
"synthetic-relevance--nanobeir--nanonfcorpus-score-test-v1": 0.13921800746762414,
"synthetic-relevance--nanobeir--nanonq-noul-test-v1": 0.5229222433242113,
"synthetic-relevance--nanobeir--nanonq-score-test-v1": 0.0,
"synthetic-relevance--nanobeir--nanoscidocs-noul-test-v1": 0.16578339986726243,
"synthetic-relevance--nanobeir--nanoscidocs-score-test-v1": 0.11267844076262346,
"synthetic-relevance--nanobeir--nanotouche2020-noul-test-v1": 0.30098839141871947,
"synthetic-relevance--nanobeir--nanotouche2020-score-test-v1": 0.40182339219261376,
"synthetic-relevance--nanocoir-noul-test-v1": 0.3698319999897106,
"synthetic-relevance--nanocoir-score-test-v1": 0.0,
"temporal-nli-choice-test-v1": 0.08064516129032256,
"tracie-noul-test-v1": 0.0,
"laya--typed-decisions-choice-test-v1": 0.22748534707752452,
"laya--typed-decisions-noul-test-v1": 0.35194205311622095,
"laya--typed-decisions-score-test-v1": 0.28352172500829476,
"ud-ewt-choice-test-v1": 0.18302180685358257,
"winobias-choice-test-v1": 0.21739130434782605,
"winowhy-noul-test-v1": 0.24,
"wiqa-choice-test-v1": 0.3015873015873017
}
}
}
}
}

Xet Storage Details

Size:
53.1 kB
·
Xet hash:
153ac778378f17fbf6034459e2235a69a66132ea7fb060ba541ec5e91a8244b6

Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.