Buckets:
Nabidnur/Liars_Are_Information-bucket / releases /dgx-research-20260912-v2 /results /dgx /standard /paired_comparisons.csv
| study,benchmark,f,p_obs,composition,attack,coherence_p,baseline,delta,ci_low,ci_high,n_unique_test_tasks,n_swarm_seeds,ci_kind | |
| diversity,math500,0.0,1.0,hom_qwen38_27b,always_wrong,1.0,aip_naive,0.0,0.0,0.0,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| diversity,math500,0.0,1.0,hom_qwen38_27b,always_wrong,1.0,aip_trust_only,0.0,0.0,0.0,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| diversity,math500,0.0,1.0,hom_qwen38_27b,always_wrong,1.0,confidence,0.0,0.0,0.0,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| diversity,math500,0.0,1.0,hom_qwen38_27b,always_wrong,1.0,majority,0.0,0.0,0.0,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| diversity,math500,0.0,1.0,hom_qwen38_27b,always_wrong,1.0,sac,0.0,0.0,0.0,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| diversity,math500,0.0,1.0,hom_qwen38_27b,always_wrong,1.0,self_only,0.0,0.0,0.0,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| diversity,math500,0.5,1.0,hom_qwen38_27b,always_wrong,1.0,aip_naive,-0.0375,-0.0875,0.0,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| diversity,math500,0.5,1.0,hom_qwen38_27b,always_wrong,1.0,aip_trust_only,0.0,0.0,0.0,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| diversity,math500,0.5,1.0,hom_qwen38_27b,always_wrong,1.0,confidence,0.0375,-0.025,0.1,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| diversity,math500,0.5,1.0,hom_qwen38_27b,always_wrong,1.0,majority,0.0,0.0,0.0,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| diversity,math500,0.5,1.0,hom_qwen38_27b,always_wrong,1.0,sac,0.0375,-0.025,0.1,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| diversity,math500,0.5,1.0,hom_qwen38_27b,always_wrong,1.0,self_only,-0.0375,-0.0875,0.0,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| diversity,mmlu,0.0,1.0,hom_qwen38_27b,always_wrong,1.0,aip_naive,0.0,0.0,0.0,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| diversity,mmlu,0.0,1.0,hom_qwen38_27b,always_wrong,1.0,aip_trust_only,0.0,0.0,0.0,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| diversity,mmlu,0.0,1.0,hom_qwen38_27b,always_wrong,1.0,confidence,0.0,0.0,0.0,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| diversity,mmlu,0.0,1.0,hom_qwen38_27b,always_wrong,1.0,dawid_skene_full,0.0,0.0,0.0,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| diversity,mmlu,0.0,1.0,hom_qwen38_27b,always_wrong,1.0,majority,0.0,0.0,0.0,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| diversity,mmlu,0.0,1.0,hom_qwen38_27b,always_wrong,1.0,sac,0.0,0.0,0.0,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| diversity,mmlu,0.0,1.0,hom_qwen38_27b,always_wrong,1.0,self_only,0.0,0.0,0.0,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| diversity,mmlu,0.5,1.0,hom_qwen38_27b,always_wrong,1.0,aip_naive,-0.4708333333333334,-0.5666666666666667,-0.3791666666666667,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| diversity,mmlu,0.5,1.0,hom_qwen38_27b,always_wrong,1.0,aip_trust_only,0.0,0.0,0.0,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| diversity,mmlu,0.5,1.0,hom_qwen38_27b,always_wrong,1.0,confidence,-0.4541666666666667,-0.5459375000000001,-0.3583333333333334,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| diversity,mmlu,0.5,1.0,hom_qwen38_27b,always_wrong,1.0,dawid_skene_full,-0.008333333333333321,-0.10843749999999998,0.09177083333333327,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| diversity,mmlu,0.5,1.0,hom_qwen38_27b,always_wrong,1.0,majority,0.0,0.0,0.0,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| diversity,mmlu,0.5,1.0,hom_qwen38_27b,always_wrong,1.0,sac,-0.4541666666666667,-0.55,-0.3541666666666667,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| diversity,mmlu,0.5,1.0,hom_qwen38_27b,always_wrong,1.0,self_only,-0.4666666666666667,-0.5625,-0.3708333333333334,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,boolq,0.0,0.5,frozen_mix,always_wrong,1.0,aip_naive,0.0,0.0,0.0,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,boolq,0.0,0.5,frozen_mix,always_wrong,1.0,aip_trust_only,0.0,0.0,0.0,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,boolq,0.0,0.5,frozen_mix,always_wrong,1.0,confidence,0.0004166666666666659,-0.00625,0.006666666666666659,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,boolq,0.0,0.5,frozen_mix,always_wrong,1.0,dawid_skene_full,-0.003333333333333336,-0.010010416666666674,0.0037499999999999973,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,boolq,0.0,0.5,frozen_mix,always_wrong,1.0,majority,-0.004166666666666666,-0.00834375,3.252606517453555e-20,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,boolq,0.0,0.5,frozen_mix,always_wrong,1.0,sac,0.00916666666666667,-0.004583333333333331,0.027093749999999996,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,boolq,0.0,0.5,frozen_mix,always_wrong,1.0,self_only,0.02166666666666666,0.0029062499999999857,0.04001041666666666,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,boolq,0.0,1.0,frozen_mix,always_wrong,1.0,aip_naive,0.0,0.0,0.0,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,boolq,0.0,1.0,frozen_mix,always_wrong,1.0,aip_trust_only,0.0,0.0,0.0,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,boolq,0.0,1.0,frozen_mix,always_wrong,1.0,confidence,0.0,0.0,0.0,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,boolq,0.0,1.0,frozen_mix,always_wrong,1.0,dawid_skene_full,0.0,0.0,0.0,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,boolq,0.0,1.0,frozen_mix,always_wrong,1.0,majority,0.0,0.0,0.0,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,boolq,0.0,1.0,frozen_mix,always_wrong,1.0,sac,0.01125,0.0,0.029583333333333333,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,boolq,0.0,1.0,frozen_mix,always_wrong,1.0,self_only,0.03124999999999999,0.0037499999999999964,0.05584374999999999,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,boolq,0.3,0.5,frozen_mix,always_wrong,1.0,aip_naive,0.0,0.0,0.0,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,boolq,0.3,0.5,frozen_mix,always_wrong,1.0,aip_trust_only,0.0,0.0,0.0,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,boolq,0.3,0.5,frozen_mix,always_wrong,1.0,confidence,-0.07023809523809525,-0.08870535714285716,-0.05000000000000001,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,boolq,0.3,0.5,frozen_mix,always_wrong,1.0,dawid_skene_full,-0.1601190476190476,-0.1904761904761905,-0.13095238095238096,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,boolq,0.3,0.5,frozen_mix,always_wrong,1.0,majority,-0.05119047619047621,-0.06726190476190477,-0.03630952380952382,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,boolq,0.3,0.5,frozen_mix,always_wrong,1.0,sac,-0.1333333333333333,-0.1583482142857143,-0.11130952380952382,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,boolq,0.3,0.5,frozen_mix,always_wrong,1.0,self_only,-0.11190476190476191,-0.13154761904761905,-0.09404761904761903,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,boolq,0.3,1.0,frozen_mix,always_wrong,1.0,aip_naive,0.0,0.0,0.0,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,boolq,0.3,1.0,frozen_mix,always_wrong,1.0,aip_trust_only,0.0,0.0,0.0,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,boolq,0.3,1.0,frozen_mix,always_wrong,1.0,confidence,-0.020833333333333336,-0.03928571428571429,-0.004761904761904762,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,boolq,0.3,1.0,frozen_mix,always_wrong,1.0,dawid_skene_full,-0.07678571428571429,-0.1285714285714286,-0.029166666666666667,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,boolq,0.3,1.0,frozen_mix,always_wrong,1.0,majority,-0.01011904761904762,-0.026190476190476188,0.0,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,boolq,0.3,1.0,frozen_mix,always_wrong,1.0,sac,-0.048809523809523817,-0.08215773809523809,-0.016666666666666666,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,boolq,0.3,1.0,frozen_mix,always_wrong,1.0,self_only,-0.02202380952380952,-0.05239583333333333,0.004776785714285712,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,boolq,0.5,0.5,frozen_mix,always_wrong,1.0,aip_naive,0.0,0.0,0.0,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,boolq,0.5,0.5,frozen_mix,always_wrong,1.0,aip_trust_only,0.0,0.0,0.0,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,boolq,0.5,0.5,frozen_mix,always_wrong,1.0,confidence,-0.2341666666666667,-0.26749999999999996,-0.19833333333333336,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,boolq,0.5,0.5,frozen_mix,always_wrong,1.0,dawid_skene_full,-0.3866666666666668,-0.42002083333333357,-0.35500000000000015,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,boolq,0.5,0.5,frozen_mix,always_wrong,1.0,majority,-0.11750000000000001,-0.15166666666666667,-0.08583333333333334,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,boolq,0.5,0.5,frozen_mix,always_wrong,1.0,sac,-0.3516666666666667,-0.3866666666666666,-0.3141458333333334,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,boolq,0.5,0.5,frozen_mix,always_wrong,1.0,self_only,-0.495,-0.53,-0.45914583333333336,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,boolq,0.5,1.0,frozen_mix,always_wrong,1.0,aip_naive,0.0,0.0,0.0,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,boolq,0.5,1.0,frozen_mix,always_wrong,1.0,aip_trust_only,0.0,0.0,0.0,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,boolq,0.5,1.0,frozen_mix,always_wrong,1.0,confidence,-0.7783333333333333,-0.8433541666666667,-0.7033125,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,boolq,0.5,1.0,frozen_mix,always_wrong,1.0,dawid_skene_full,0.0,0.0,0.0,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,boolq,0.5,1.0,frozen_mix,always_wrong,1.0,majority,-0.3125,-0.4084375,-0.2208333333333333,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,boolq,0.5,1.0,frozen_mix,always_wrong,1.0,sac,-0.3,-0.3541666666666667,-0.2424791666666667,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,boolq,0.5,1.0,frozen_mix,always_wrong,1.0,self_only,-0.8933333333333333,-0.9416666666666668,-0.8391458333333333,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,boolq,0.7,0.5,frozen_mix,always_wrong,1.0,aip_naive,0.0,0.0,0.0,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,boolq,0.7,0.5,frozen_mix,always_wrong,1.0,aip_trust_only,0.0,0.0,0.0,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,boolq,0.7,0.5,frozen_mix,always_wrong,1.0,confidence,-0.18888888888888886,-0.22361111111111107,-0.15416666666666665,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,boolq,0.7,0.5,frozen_mix,always_wrong,1.0,dawid_skene_full,0.07222222222222223,0.05277777777777778,0.09305555555555556,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,boolq,0.7,0.5,frozen_mix,always_wrong,1.0,majority,-0.07222222222222223,-0.09583333333333333,-0.05138888888888889,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,boolq,0.7,0.5,frozen_mix,always_wrong,1.0,sac,0.06944444444444445,0.05138888888888889,0.09027777777777779,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,boolq,0.7,0.5,frozen_mix,always_wrong,1.0,self_only,-0.8305555555555557,-0.8847222222222222,-0.7819444444444444,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,boolq,0.7,1.0,frozen_mix,always_wrong,1.0,aip_naive,0.0,0.0,0.0,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,boolq,0.7,1.0,frozen_mix,always_wrong,1.0,aip_trust_only,0.0,0.0,0.0,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,boolq,0.7,1.0,frozen_mix,always_wrong,1.0,confidence,0.0,0.0,0.0,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,boolq,0.7,1.0,frozen_mix,always_wrong,1.0,dawid_skene_full,0.0,0.0,0.0,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,boolq,0.7,1.0,frozen_mix,always_wrong,1.0,majority,0.0,0.0,0.0,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,boolq,0.7,1.0,frozen_mix,always_wrong,1.0,sac,0.0,0.0,0.0,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,boolq,0.7,1.0,frozen_mix,always_wrong,1.0,self_only,-0.9041666666666668,-0.9541666666666666,-0.8485763888888889,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,math500,0.0,0.5,frozen_mix,always_wrong,1.0,aip_naive,0.21541666666666667,0.1620625,0.26917708333333334,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,math500,0.0,0.5,frozen_mix,always_wrong,1.0,aip_trust_only,-2.0816681711721684e-18,-0.004999999999999993,0.004999999999999999,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,math500,0.0,0.5,frozen_mix,always_wrong,1.0,confidence,-0.10458333333333333,-0.13291666666666666,-0.07666666666666666,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,math500,0.0,0.5,frozen_mix,always_wrong,1.0,majority,-0.08083333333333334,-0.10666666666666666,-0.05748958333333334,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,math500,0.0,0.5,frozen_mix,always_wrong,1.0,sac,-0.1025,-0.12876041666666668,-0.07583333333333334,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,math500,0.0,0.5,frozen_mix,always_wrong,1.0,self_only,0.0495833333333333,0.032916666666666636,0.06666666666666662,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,math500,0.0,1.0,frozen_mix,always_wrong,1.0,aip_naive,0.37416666666666665,0.27291666666666664,0.47209375,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,math500,0.0,1.0,frozen_mix,always_wrong,1.0,aip_trust_only,0.0,0.0,0.0,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,math500,0.0,1.0,frozen_mix,always_wrong,1.0,confidence,-0.11541666666666668,-0.17126041666666672,-0.06708333333333334,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,math500,0.0,1.0,frozen_mix,always_wrong,1.0,majority,-0.10750000000000001,-0.15589583333333334,-0.06166666666666668,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,math500,0.0,1.0,frozen_mix,always_wrong,1.0,sac,-0.10166666666666666,-0.15375,-0.05623958333333334,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,math500,0.0,1.0,frozen_mix,always_wrong,1.0,self_only,0.10291666666666663,0.06372916666666664,0.1408333333333333,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,math500,0.3,0.5,frozen_mix,always_wrong,1.0,aip_naive,-0.021428571428571443,-0.07561011904761904,0.02620535714285712,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,math500,0.3,0.5,frozen_mix,always_wrong,1.0,aip_trust_only,0.10654761904761904,0.0875,0.12680059523809523,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,math500,0.3,0.5,frozen_mix,always_wrong,1.0,confidence,-0.11190476190476192,-0.1440625,-0.07976190476190478,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,math500,0.3,0.5,frozen_mix,always_wrong,1.0,majority,-0.06666666666666668,-0.0892857142857143,-0.04404761904761907,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,math500,0.3,0.5,frozen_mix,always_wrong,1.0,sac,-0.1011904761904762,-0.12918154761904765,-0.07500000000000001,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,math500,0.3,0.5,frozen_mix,always_wrong,1.0,self_only,-0.13452380952380955,-0.15952380952380954,-0.10950892857142856,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,math500,0.3,1.0,frozen_mix,always_wrong,1.0,aip_naive,0.05119047619047623,-0.0083630952380952,0.11370535714285716,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,math500,0.3,1.0,frozen_mix,always_wrong,1.0,aip_trust_only,0.23511904761904762,0.18569940476190477,0.28035714285714286,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,math500,0.3,1.0,frozen_mix,always_wrong,1.0,confidence,-0.07142857142857144,-0.12142857142857141,-0.020238095238095232,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,math500,0.3,1.0,frozen_mix,always_wrong,1.0,majority,-0.016071428571428556,-0.06249999999999998,0.029166666666666674,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,math500,0.3,1.0,frozen_mix,always_wrong,1.0,sac,-0.04226190476190476,-0.08334821428571428,-0.003556547619047617,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,math500,0.3,1.0,frozen_mix,always_wrong,1.0,self_only,-0.07559523809523808,-0.10297619047619042,-0.05058035714285712,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,math500,0.5,0.5,frozen_mix,always_wrong,1.0,aip_naive,-0.19666666666666668,-0.23083333333333336,-0.16331250000000003,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,math500,0.5,0.5,frozen_mix,always_wrong,1.0,aip_trust_only,0.2991666666666667,0.26166666666666666,0.3358541666666666,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,math500,0.5,0.5,frozen_mix,always_wrong,1.0,confidence,0.02583333333333331,-0.013333333333333358,0.06416666666666665,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,math500,0.5,0.5,frozen_mix,always_wrong,1.0,majority,0.08666666666666666,0.04999999999999999,0.12333333333333332,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,math500,0.5,0.5,frozen_mix,always_wrong,1.0,sac,0.2108333333333333,0.175,0.25,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,math500,0.5,0.5,frozen_mix,always_wrong,1.0,self_only,-0.18083333333333335,-0.21583333333333338,-0.14750000000000002,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,math500,0.5,1.0,frozen_mix,always_wrong,1.0,aip_naive,-0.15250000000000002,-0.1958333333333334,-0.11000000000000003,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,math500,0.5,1.0,frozen_mix,always_wrong,1.0,aip_trust_only,0.4883333333333333,0.42833333333333334,0.5433541666666667,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,math500,0.5,1.0,frozen_mix,always_wrong,1.0,confidence,0.059999999999999984,-0.010000000000000023,0.13262499999999985,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,math500,0.5,1.0,frozen_mix,always_wrong,1.0,majority,0.24666666666666665,0.1782708333333333,0.31916666666666665,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,math500,0.5,1.0,frozen_mix,always_wrong,1.0,sac,0.33166666666666667,0.2783333333333333,0.3875208333333333,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,math500,0.5,1.0,frozen_mix,always_wrong,1.0,self_only,-0.09750000000000003,-0.13000000000000006,-0.06414583333333336,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,math500,0.7,0.5,frozen_mix,always_wrong,1.0,aip_naive,-0.32777777777777783,-0.3819791666666667,-0.27222222222222225,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,math500,0.7,0.5,frozen_mix,always_wrong,1.0,aip_trust_only,0.2847222222222222,0.25,0.32086805555555553,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,math500,0.7,0.5,frozen_mix,always_wrong,1.0,confidence,0.15138888888888888,0.1125,0.18611111111111112,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,math500,0.7,0.5,frozen_mix,always_wrong,1.0,majority,0.19027777777777777,0.15555555555555553,0.21947916666666667,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,math500,0.7,0.5,frozen_mix,always_wrong,1.0,sac,0.29444444444444445,0.25555555555555554,0.3319444444444445,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,math500,0.7,0.5,frozen_mix,always_wrong,1.0,self_only,-0.2763888888888889,-0.3305555555555556,-0.225,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,math500,0.7,1.0,frozen_mix,always_wrong,1.0,aip_naive,-0.24027777777777787,-0.28611111111111115,-0.1944444444444445,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,math500,0.7,1.0,frozen_mix,always_wrong,1.0,aip_trust_only,0.4111111111111111,0.36111111111111105,0.4583333333333332,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,math500,0.7,1.0,frozen_mix,always_wrong,1.0,confidence,0.4111111111111111,0.3638888888888888,0.4570138888888888,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,math500,0.7,1.0,frozen_mix,always_wrong,1.0,majority,0.4111111111111111,0.36249999999999993,0.4555902777777777,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,math500,0.7,1.0,frozen_mix,always_wrong,1.0,sac,0.4111111111111111,0.36249999999999993,0.4555902777777776,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,math500,0.7,1.0,frozen_mix,always_wrong,1.0,self_only,-0.16666666666666669,-0.21111111111111117,-0.12222222222222223,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,mmlu,0.0,0.5,frozen_mix,always_wrong,1.0,aip_naive,0.8324999999999999,0.7425,0.9058541666666667,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,mmlu,0.0,0.5,frozen_mix,always_wrong,1.0,aip_trust_only,0.0,0.0,0.0,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,mmlu,0.0,0.5,frozen_mix,always_wrong,1.0,confidence,-0.003749999999999999,-0.015010416666666668,0.008333333333333335,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,mmlu,0.0,0.5,frozen_mix,always_wrong,1.0,dawid_skene_full,6.938893903907229e-19,-0.006250000000000003,0.006250000000000004,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,mmlu,0.0,0.5,frozen_mix,always_wrong,1.0,majority,0.006666666666666664,-0.002916666666666669,0.01958333333333333,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,mmlu,0.0,0.5,frozen_mix,always_wrong,1.0,sac,-0.023750000000000004,-0.04250000000000001,-0.00583333333333334,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,mmlu,0.0,0.5,frozen_mix,always_wrong,1.0,self_only,0.059999999999999984,0.03541666666666665,0.08667708333333332,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,mmlu,0.0,1.0,frozen_mix,always_wrong,1.0,aip_naive,0.8637499999999999,0.78203125,0.9408749999999999,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,mmlu,0.0,1.0,frozen_mix,always_wrong,1.0,aip_trust_only,0.0,0.0,0.0,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,mmlu,0.0,1.0,frozen_mix,always_wrong,1.0,confidence,-0.0008333333333333337,-0.013333333333333336,0.01001041666666666,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,mmlu,0.0,1.0,frozen_mix,always_wrong,1.0,dawid_skene_full,0.0020833333333333333,-0.00625,0.0125,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,mmlu,0.0,1.0,frozen_mix,always_wrong,1.0,majority,0.006249999999999999,-0.008333333333333335,0.020885416666666618,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,mmlu,0.0,1.0,frozen_mix,always_wrong,1.0,sac,-0.020833333333333336,-0.05710416666666667,0.004999999999999999,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,mmlu,0.0,1.0,frozen_mix,always_wrong,1.0,self_only,0.07375,0.03998958333333333,0.11001041666666667,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,mmlu,0.3,0.5,frozen_mix,always_wrong,1.0,aip_naive,0.806547619047619,0.725,0.8815773809523809,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,mmlu,0.3,0.5,frozen_mix,always_wrong,1.0,aip_trust_only,0.21011904761904762,0.18214285714285713,0.24107142857142855,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,mmlu,0.3,0.5,frozen_mix,always_wrong,1.0,confidence,0.08988095238095238,0.06904761904761905,0.11251488095238094,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,mmlu,0.3,0.5,frozen_mix,always_wrong,1.0,dawid_skene_full,0.01488095238095238,0.0035714285714285735,0.02678571428571428,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,mmlu,0.3,0.5,frozen_mix,always_wrong,1.0,majority,0.11845238095238093,0.08869047619047618,0.1529910714285714,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,mmlu,0.3,0.5,frozen_mix,always_wrong,1.0,sac,0.01547619047619048,0.000595238095238098,0.03273809523809523,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,mmlu,0.3,0.5,frozen_mix,always_wrong,1.0,self_only,0.0654761904761905,0.043452380952380965,0.0875,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,mmlu,0.3,1.0,frozen_mix,always_wrong,1.0,aip_naive,0.8714285714285716,0.7833035714285715,0.9428571428571427,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,mmlu,0.3,1.0,frozen_mix,always_wrong,1.0,aip_trust_only,0.07380952380952381,0.04107142857142857,0.1125,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,mmlu,0.3,1.0,frozen_mix,always_wrong,1.0,confidence,0.041666666666666664,0.01785714285714286,0.06904761904761905,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,mmlu,0.3,1.0,frozen_mix,always_wrong,1.0,dawid_skene_full,0.015476190476190477,0.0,0.03511904761904762,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,mmlu,0.3,1.0,frozen_mix,always_wrong,1.0,majority,0.0613095238095238,0.02857142857142857,0.09523809523809523,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,mmlu,0.3,1.0,frozen_mix,always_wrong,1.0,sac,0.017857142857142856,-1.42247325030098e-18,0.03751488095238093,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,mmlu,0.3,1.0,frozen_mix,always_wrong,1.0,self_only,0.08511904761904762,0.05892857142857144,0.11430059523809523,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,mmlu,0.5,0.5,frozen_mix,always_wrong,1.0,aip_naive,0.6083333333333334,0.5416458333333333,0.6683541666666667,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,mmlu,0.5,0.5,frozen_mix,always_wrong,1.0,aip_trust_only,0.5425,0.5033333333333333,0.5791875000000001,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,mmlu,0.5,0.5,frozen_mix,always_wrong,1.0,confidence,0.23499999999999996,0.20833333333333331,0.26166666666666666,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,mmlu,0.5,0.5,frozen_mix,always_wrong,1.0,dawid_skene_full,0.43833333333333335,0.4049791666666667,0.4683333333333334,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,mmlu,0.5,0.5,frozen_mix,always_wrong,1.0,majority,0.39916666666666667,0.35914583333333333,0.44002083333333336,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,mmlu,0.5,0.5,frozen_mix,always_wrong,1.0,sac,0.18333333333333335,0.15750000000000003,0.21083333333333334,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,mmlu,0.5,0.5,frozen_mix,always_wrong,1.0,self_only,0.04916666666666666,0.03083333333333333,0.06918749999999997,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,mmlu,0.5,1.0,frozen_mix,always_wrong,1.0,aip_naive,0.8549999999999999,0.7708333333333334,0.9266874999999999,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,mmlu,0.5,1.0,frozen_mix,always_wrong,1.0,aip_trust_only,0.8991666666666667,0.8441249999999999,0.9491666666666667,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,mmlu,0.5,1.0,frozen_mix,always_wrong,1.0,confidence,0.10333333333333335,0.06247916666666667,0.14750000000000002,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,mmlu,0.5,1.0,frozen_mix,always_wrong,1.0,dawid_skene_full,0.8991666666666667,0.8433333333333334,0.95,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,mmlu,0.5,1.0,frozen_mix,always_wrong,1.0,majority,0.6116666666666667,0.5199999999999999,0.6958333333333334,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,mmlu,0.5,1.0,frozen_mix,always_wrong,1.0,sac,0.3466666666666667,0.2866666666666666,0.4067083333333332,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,mmlu,0.5,1.0,frozen_mix,always_wrong,1.0,self_only,0.0625,0.03666666666666665,0.08833333333333332,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,mmlu,0.7,0.5,frozen_mix,always_wrong,1.0,aip_naive,0.3833333333333334,0.3305555555555556,0.4333333333333334,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,mmlu,0.7,0.5,frozen_mix,always_wrong,1.0,aip_trust_only,0.8180555555555555,0.7652777777777778,0.8680555555555556,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,mmlu,0.7,0.5,frozen_mix,always_wrong,1.0,confidence,0.6027777777777777,0.5541666666666667,0.6513888888888889,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,mmlu,0.7,0.5,frozen_mix,always_wrong,1.0,dawid_skene_full,0.8819444444444443,0.8236111111111111,0.9278125,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,mmlu,0.7,0.5,frozen_mix,always_wrong,1.0,majority,0.7652777777777777,0.7138888888888889,0.8125347222222222,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,mmlu,0.7,0.5,frozen_mix,always_wrong,1.0,sac,0.8763888888888889,0.8194444444444444,0.9277777777777778,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,mmlu,0.7,0.5,frozen_mix,always_wrong,1.0,self_only,0.02638888888888889,0.012500000000000002,0.04166666666666667,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,mmlu,0.7,1.0,frozen_mix,always_wrong,1.0,aip_naive,0.6708333333333332,0.6027430555555556,0.725,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,mmlu,0.7,1.0,frozen_mix,always_wrong,1.0,aip_trust_only,0.8916666666666668,0.8375,0.9416666666666667,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,mmlu,0.7,1.0,frozen_mix,always_wrong,1.0,confidence,0.8916666666666668,0.8333333333333333,0.9416666666666667,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,mmlu,0.7,1.0,frozen_mix,always_wrong,1.0,dawid_skene_full,0.8916666666666668,0.8416666666666668,0.9416666666666667,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,mmlu,0.7,1.0,frozen_mix,always_wrong,1.0,majority,0.8916666666666668,0.8375,0.9416666666666667,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,mmlu,0.7,1.0,frozen_mix,always_wrong,1.0,sac,0.8916666666666668,0.8375,0.9458333333333332,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
| mechanism,mmlu,0.7,1.0,frozen_mix,always_wrong,1.0,self_only,0.03472222222222223,0.018055555555555564,0.054166666666666675,80,3,task-cluster percentile; seeds averaged; pointwise exploratory | |
Xet Storage Details
- Size:
- 33 kB
- Xet hash:
- 217e934dfee2447e8d1672324202f2d81ade2a68d36d2d8a05a03536ddf51418
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.