Nabidnur's picture
download
raw
14.3 kB
benchmark,f,seed,target_method,selected_p,validation_accuracy,test_accuracy,self_accuracy,trust_only_accuracy,n_test_tasks,selected_using
math500,0.5,20260912,aip_gated,0.0,0.475,0.48,0.6100000000000001,0.0,80,validation only; p ascending tie break
math500,0.5,20260912,aip_naive,1.0,0.6849999999999999,0.6675,0.6100000000000001,0.0,80,validation only; p ascending tie break
math500,0.5,20260912,aip_randomized,0.0,0.475,0.48,0.6100000000000001,0.0,80,validation only; p ascending tie break
math500,0.5,20260912,aip_soft,0.0,0.475,0.48,0.6100000000000001,0.0,80,validation only; p ascending tie break
math500,0.5,20260912,aip_soft_randomized,0.0,0.475,0.48,0.6100000000000001,0.0,80,validation only; p ascending tie break
math500,0.5,20260912,aip_trust_only,0.0,0.0,0.0,0.6100000000000001,0.0,80,validation only; p ascending tie break
math500,0.5,20260912,confidence,1.0,0.41500000000000004,0.46749999999999997,0.6100000000000001,0.0,80,validation only; p ascending tie break
math500,0.5,20260912,majority,0.0,0.175,0.2,0.6100000000000001,0.0,80,validation only; p ascending tie break
math500,0.5,20260912,sac,0.5,0.11499999999999999,0.1025,0.6100000000000001,0.0,80,validation only; p ascending tie break
math500,0.5,20260912,self_only,0.0,0.615,0.6100000000000001,0.6100000000000001,0.0,80,validation only; p ascending tie break
math500,0.5,20260913,aip_gated,0.5,0.6,0.615,0.65,0.0,80,validation only; p ascending tie break
math500,0.5,20260913,aip_naive,1.0,0.7,0.6575,0.65,0.0,80,validation only; p ascending tie break
math500,0.5,20260913,aip_randomized,0.5,0.6,0.615,0.65,0.0,80,validation only; p ascending tie break
math500,0.5,20260913,aip_soft,0.5,0.6,0.615,0.65,0.0,80,validation only; p ascending tie break
math500,0.5,20260913,aip_soft_randomized,0.5,0.6,0.615,0.65,0.0,80,validation only; p ascending tie break
math500,0.5,20260913,aip_trust_only,0.0,0.0,0.0,0.65,0.0,80,validation only; p ascending tie break
math500,0.5,20260913,confidence,1.0,0.48,0.495,0.65,0.0,80,validation only; p ascending tie break
math500,0.5,20260913,majority,0.0,0.325,0.3625,0.65,0.0,80,validation only; p ascending tie break
math500,0.5,20260913,sac,0.75,0.16999999999999998,0.225,0.65,0.0,80,validation only; p ascending tie break
math500,0.5,20260913,self_only,0.0,0.655,0.65,0.65,0.0,80,validation only; p ascending tie break
math500,0.5,20260914,aip_gated,1.0,0.25,0.2625,0.49749999999999994,0.0,80,validation only; p ascending tie break
math500,0.5,20260914,aip_naive,0.25,0.41000000000000003,0.4125,0.49749999999999994,0.355,80,validation only; p ascending tie break
math500,0.5,20260914,aip_randomized,1.0,0.25,0.2625,0.49749999999999994,0.0,80,validation only; p ascending tie break
math500,0.5,20260914,aip_soft,1.0,0.25,0.2625,0.49749999999999994,0.0,80,validation only; p ascending tie break
math500,0.5,20260914,aip_soft_randomized,1.0,0.25,0.2625,0.49749999999999994,0.0,80,validation only; p ascending tie break
math500,0.5,20260914,aip_trust_only,1.0,0.0,0.0,0.49749999999999994,0.0,80,validation only; p ascending tie break
math500,0.5,20260914,confidence,1.0,0.315,0.3225,0.49749999999999994,0.0,80,validation only; p ascending tie break
math500,0.5,20260914,majority,0.0,0.175,0.1625,0.49749999999999994,0.35,80,validation only; p ascending tie break
math500,0.5,20260914,sac,0.75,0.16999999999999998,0.14750000000000002,0.49749999999999994,0.175,80,validation only; p ascending tie break
math500,0.5,20260914,self_only,0.0,0.51,0.49749999999999994,0.49749999999999994,0.35,80,validation only; p ascending tie break
math500,0.7,20260912,aip_gated,1.0,0.8,0.7791666666666667,0.6958333333333333,0.0,80,validation only; p ascending tie break
math500,0.7,20260912,aip_naive,1.0,0.775,0.7458333333333333,0.6958333333333333,0.0,80,validation only; p ascending tie break
math500,0.7,20260912,aip_randomized,1.0,0.8,0.7791666666666667,0.6958333333333333,0.0,80,validation only; p ascending tie break
math500,0.7,20260912,aip_soft,1.0,0.8,0.7791666666666667,0.6958333333333333,0.0,80,validation only; p ascending tie break
math500,0.7,20260912,aip_soft_randomized,1.0,0.8,0.7791666666666667,0.6958333333333333,0.0,80,validation only; p ascending tie break
math500,0.7,20260912,aip_trust_only,0.0,0.0,0.0,0.6958333333333333,0.0,80,validation only; p ascending tie break
math500,0.7,20260912,confidence,0.0,0.0,0.0,0.6958333333333333,0.0,80,validation only; p ascending tie break
math500,0.7,20260912,majority,0.0,0.0,0.0,0.6958333333333333,0.0,80,validation only; p ascending tie break
math500,0.7,20260912,sac,0.0,0.0,0.0,0.6958333333333333,0.0,80,validation only; p ascending tie break
math500,0.7,20260912,self_only,0.0,0.7083333333333333,0.6958333333333333,0.6958333333333333,0.0,80,validation only; p ascending tie break
math500,0.7,20260913,aip_gated,0.5,0.2333333333333333,0.2333333333333333,0.5791666666666667,0.0,80,validation only; p ascending tie break
math500,0.7,20260913,aip_naive,1.0,0.6666666666666667,0.6416666666666667,0.5791666666666667,0.0,80,validation only; p ascending tie break
math500,0.7,20260913,aip_randomized,0.5,0.2333333333333333,0.2333333333333333,0.5791666666666667,0.0,80,validation only; p ascending tie break
math500,0.7,20260913,aip_soft,0.5,0.2333333333333333,0.2333333333333333,0.5791666666666667,0.0,80,validation only; p ascending tie break
math500,0.7,20260913,aip_soft_randomized,0.5,0.2333333333333333,0.2333333333333333,0.5791666666666667,0.0,80,validation only; p ascending tie break
math500,0.7,20260913,aip_trust_only,0.0,0.0,0.0,0.5791666666666667,0.0,80,validation only; p ascending tie break
math500,0.7,20260913,confidence,0.0,0.0,0.0,0.5791666666666667,0.0,80,validation only; p ascending tie break
math500,0.7,20260913,majority,0.0,0.0,0.0,0.5791666666666667,0.0,80,validation only; p ascending tie break
math500,0.7,20260913,sac,0.0,0.0,0.0,0.5791666666666667,0.0,80,validation only; p ascending tie break
math500,0.7,20260913,self_only,0.0,0.6,0.5791666666666667,0.5791666666666667,0.0,80,validation only; p ascending tie break
math500,0.7,20260914,aip_gated,0.0,0.0,0.0,0.4583333333333333,0.0,80,validation only; p ascending tie break
math500,0.7,20260914,aip_naive,1.0,0.5666666666666667,0.5666666666666667,0.4583333333333333,0.0,80,validation only; p ascending tie break
math500,0.7,20260914,aip_randomized,0.0,0.0,0.0,0.4583333333333333,0.0,80,validation only; p ascending tie break
math500,0.7,20260914,aip_soft,0.0,0.0,0.0,0.4583333333333333,0.0,80,validation only; p ascending tie break
math500,0.7,20260914,aip_soft_randomized,0.0,0.0,0.0,0.4583333333333333,0.0,80,validation only; p ascending tie break
math500,0.7,20260914,aip_trust_only,0.0,0.0,0.0,0.4583333333333333,0.0,80,validation only; p ascending tie break
math500,0.7,20260914,confidence,0.0,0.0,0.0,0.4583333333333333,0.0,80,validation only; p ascending tie break
math500,0.7,20260914,majority,0.0,0.0,0.0,0.4583333333333333,0.0,80,validation only; p ascending tie break
math500,0.7,20260914,sac,0.0,0.0,0.0,0.4583333333333333,0.0,80,validation only; p ascending tie break
math500,0.7,20260914,self_only,0.0,0.475,0.4583333333333333,0.4583333333333333,0.0,80,validation only; p ascending tie break
mmlu,0.5,20260912,aip_gated,0.25,0.8,0.7875,0.8625,0.7875,80,validation only; p ascending tie break
mmlu,0.5,20260912,aip_naive,1.0,0.030000000000000006,0.0475,0.8625,0.0,80,validation only; p ascending tie break
mmlu,0.5,20260912,aip_randomized,0.25,0.8,0.7875,0.8625,0.7875,80,validation only; p ascending tie break
mmlu,0.5,20260912,aip_soft,0.0,0.905,0.8275,0.8625,0.775,80,validation only; p ascending tie break
mmlu,0.5,20260912,aip_soft_randomized,0.25,0.9349999999999999,0.875,0.8625,0.7875,80,validation only; p ascending tie break
mmlu,0.5,20260912,aip_trust_only,1.0,0.0,0.0,0.8625,0.0,80,validation only; p ascending tie break
mmlu,0.5,20260912,confidence,0.25,0.9400000000000001,0.9025000000000001,0.8625,0.7875,80,validation only; p ascending tie break
mmlu,0.5,20260912,dawid_skene_full,1.0,0.0,0.0,0.8625,0.0,80,validation only; p ascending tie break
mmlu,0.5,20260912,majority,1.0,0.275,0.2875,0.8625,0.0,80,validation only; p ascending tie break
mmlu,0.5,20260912,sac,1.0,0.6849999999999999,0.6675,0.8625,0.0,80,validation only; p ascending tie break
mmlu,0.5,20260912,self_only,0.0,0.89,0.8625,0.8625,0.775,80,validation only; p ascending tie break
mmlu,0.5,20260913,aip_gated,0.75,0.7,0.7275,0.82,0.7275,80,validation only; p ascending tie break
mmlu,0.5,20260913,aip_naive,1.0,0.06,0.05,0.82,0.0,80,validation only; p ascending tie break
mmlu,0.5,20260913,aip_randomized,0.0,0.725,0.7375,0.82,0.7375,80,validation only; p ascending tie break
mmlu,0.5,20260913,aip_soft,0.0,0.77,0.77,0.82,0.7375,80,validation only; p ascending tie break
mmlu,0.5,20260913,aip_soft_randomized,0.0,0.755,0.7675,0.82,0.7375,80,validation only; p ascending tie break
mmlu,0.5,20260913,aip_trust_only,1.0,0.0,0.0,0.82,0.0,80,validation only; p ascending tie break
mmlu,0.5,20260913,confidence,1.0,0.635,0.7125,0.82,0.0,80,validation only; p ascending tie break
mmlu,0.5,20260913,dawid_skene_full,1.0,0.0,0.0,0.82,0.0,80,validation only; p ascending tie break
mmlu,0.5,20260913,majority,1.0,0.3,0.2625,0.82,0.0,80,validation only; p ascending tie break
mmlu,0.5,20260913,sac,1.0,0.465,0.5875,0.82,0.0,80,validation only; p ascending tie break
mmlu,0.5,20260913,self_only,0.0,0.825,0.82,0.82,0.7375,80,validation only; p ascending tie break
mmlu,0.5,20260914,aip_gated,0.5,0.625,0.6125,0.8275,0.6125,80,validation only; p ascending tie break
mmlu,0.5,20260914,aip_naive,1.0,0.025,0.034999999999999996,0.8275,0.0,80,validation only; p ascending tie break
mmlu,0.5,20260914,aip_randomized,0.5,0.625,0.6125,0.8275,0.6125,80,validation only; p ascending tie break
mmlu,0.5,20260914,aip_soft,0.25,0.755,0.79,0.8275,0.7375,80,validation only; p ascending tie break
mmlu,0.5,20260914,aip_soft_randomized,0.5,0.725,0.76,0.8275,0.6125,80,validation only; p ascending tie break
mmlu,0.5,20260914,aip_trust_only,1.0,0.0,0.0,0.8275,0.0,80,validation only; p ascending tie break
mmlu,0.5,20260914,confidence,1.0,0.75,0.7875,0.8275,0.0,80,validation only; p ascending tie break
mmlu,0.5,20260914,dawid_skene_full,1.0,0.0,0.0,0.8275,0.0,80,validation only; p ascending tie break
mmlu,0.5,20260914,majority,1.0,0.2,0.3125,0.8275,0.0,80,validation only; p ascending tie break
mmlu,0.5,20260914,sac,1.0,0.33999999999999997,0.40249999999999997,0.8275,0.0,80,validation only; p ascending tie break
mmlu,0.5,20260914,self_only,0.0,0.8400000000000001,0.8275,0.8275,0.7375,80,validation only; p ascending tie break
mmlu,0.7,20260912,aip_gated,0.0,0.0,0.0,0.8958333333333334,0.0,80,validation only; p ascending tie break
mmlu,0.7,20260912,aip_naive,1.0,0.008333333333333333,0.0375,0.8958333333333334,0.0,80,validation only; p ascending tie break
mmlu,0.7,20260912,aip_randomized,0.0,0.0,0.0,0.8958333333333334,0.0,80,validation only; p ascending tie break
mmlu,0.7,20260912,aip_soft,0.25,0.3,0.25,0.8958333333333334,0.0,80,validation only; p ascending tie break
mmlu,0.7,20260912,aip_soft_randomized,0.25,0.36666666666666664,0.4083333333333333,0.8958333333333334,0.0,80,validation only; p ascending tie break
mmlu,0.7,20260912,aip_trust_only,0.0,0.0,0.0,0.8958333333333334,0.0,80,validation only; p ascending tie break
mmlu,0.7,20260912,confidence,1.0,0.0,0.0,0.8958333333333334,0.0,80,validation only; p ascending tie break
mmlu,0.7,20260912,dawid_skene_full,0.0,0.0,0.0375,0.8958333333333334,0.0,80,validation only; p ascending tie break
mmlu,0.7,20260912,majority,0.75,0.0,0.0,0.8958333333333334,0.0,80,validation only; p ascending tie break
mmlu,0.7,20260912,sac,0.0,0.0,0.0,0.8958333333333334,0.0,80,validation only; p ascending tie break
mmlu,0.7,20260912,self_only,0.0,0.9083333333333334,0.8958333333333334,0.8958333333333334,0.0,80,validation only; p ascending tie break
mmlu,0.7,20260913,aip_gated,0.0,0.0,0.0,0.8541666666666666,0.0,80,validation only; p ascending tie break
mmlu,0.7,20260913,aip_naive,1.0,0.05833333333333333,0.041666666666666664,0.8541666666666666,0.0,80,validation only; p ascending tie break
mmlu,0.7,20260913,aip_randomized,0.0,0.0,0.0,0.8541666666666666,0.0,80,validation only; p ascending tie break
mmlu,0.7,20260913,aip_soft,0.0,0.5,0.425,0.8541666666666666,0.0,80,validation only; p ascending tie break
mmlu,0.7,20260913,aip_soft_randomized,0.0,0.4333333333333333,0.4,0.8541666666666666,0.0,80,validation only; p ascending tie break
mmlu,0.7,20260913,aip_trust_only,0.0,0.0,0.0,0.8541666666666666,0.0,80,validation only; p ascending tie break
mmlu,0.7,20260913,confidence,1.0,0.0,0.0,0.8541666666666666,0.0,80,validation only; p ascending tie break
mmlu,0.7,20260913,dawid_skene_full,0.25,0.0,0.025,0.8541666666666666,0.0875,80,validation only; p ascending tie break
mmlu,0.7,20260913,majority,0.5,0.0,0.025,0.8541666666666666,0.575,80,validation only; p ascending tie break
mmlu,0.7,20260913,sac,0.0,0.0,0.0,0.8541666666666666,0.0,80,validation only; p ascending tie break
mmlu,0.7,20260913,self_only,0.0,0.8416666666666666,0.8541666666666666,0.8541666666666666,0.0,80,validation only; p ascending tie break
mmlu,0.7,20260914,aip_gated,0.0,0.0,0.0,0.8208333333333334,0.0,80,validation only; p ascending tie break
mmlu,0.7,20260914,aip_naive,1.0,0.6333333333333333,0.5833333333333333,0.8208333333333334,0.0,80,validation only; p ascending tie break
mmlu,0.7,20260914,aip_randomized,0.0,0.0,0.0,0.8208333333333334,0.0,80,validation only; p ascending tie break
mmlu,0.7,20260914,aip_soft,0.25,0.375,0.3125,0.8208333333333334,0.0,80,validation only; p ascending tie break
mmlu,0.7,20260914,aip_soft_randomized,0.0,0.33333333333333337,0.29166666666666663,0.8208333333333334,0.0,80,validation only; p ascending tie break
mmlu,0.7,20260914,aip_trust_only,0.0,0.0,0.0,0.8208333333333334,0.0,80,validation only; p ascending tie break
mmlu,0.7,20260914,confidence,1.0,0.0,0.0,0.8208333333333334,0.0,80,validation only; p ascending tie break
mmlu,0.7,20260914,dawid_skene_full,0.0,0.0,0.0625,0.8208333333333334,0.0,80,validation only; p ascending tie break
mmlu,0.7,20260914,majority,0.75,0.0,0.0,0.8208333333333334,0.0625,80,validation only; p ascending tie break
mmlu,0.7,20260914,sac,0.0,0.0,0.0,0.8208333333333334,0.0,80,validation only; p ascending tie break
mmlu,0.7,20260914,self_only,0.0,0.8416666666666666,0.8208333333333334,0.8208333333333334,0.0,80,validation only; p ascending tie break

Xet Storage Details

Size:
14.3 kB
·
Xet hash:
d64fbbb5506ca9c67b6e5d8b2fabfc13ea41eb60aa5690711fdeb20ddd48abcd

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