guanning's picture
Upload eval
5208c5c verified
Raw History Blame Contribute Delete
1.81 kB
label,questions_with_both,idk_attempts_probed,forced_acc_idk,forced_acc_submitted,within_q_acc_idk,within_q_acc_submitted,within_q_gap,gap_lo,gap_hi,submitted_probed,forced_matches_original
base,1388,9533,0.08318472673869716,0.3169148847657875,0.09658895979140937,0.26655345135172226,0.16996449156031287,0.1516845709825717,0.18702288750514617,12019.0,0.9856893252350445
l01_s200,1259,4199,0.06858775899023577,0.2969260954872466,0.0718162562880593,0.23768864177918983,0.16587238549113054,0.1474698835054276,0.18480275350807518,6116.0,0.9861020274689339
l01_s440,1346,8480,0.08797169811320754,0.30517466536075744,0.10007694756951814,0.2503360928323781,0.15025914526286,0.13330098439821697,0.16701094070614875,12252.0,0.9870225269343781
l01_s720,1449,5466,0.10501280643980973,0.30805999670347783,0.11082355647573038,0.279043018173453,0.16821946169772256,0.15044714745801702,0.18645186335403727,6067.0,0.9765946925993078
l02_s200,1389,5005,0.07872127872127872,0.28978388998035365,0.09113270938324934,0.244120470362371,0.15298776097912167,0.1359476241900648,0.1699079073674106,6108.0,0.9873935821872953
l02_s300,1224,5766,0.07891085674644467,0.2659990229604299,0.09363328664799253,0.20710784313725492,0.11347455648926237,0.09773332944288826,0.13052854127762215,12282.0,0.9891711447646963
l02_s620,1306,4312,0.08116883116883117,0.2864829610304908,0.08722562531904032,0.22894333843797857,0.14171771311893824,0.12365843542623788,0.15958397141398675,6133.0,0.9820642426218816
l02_s80,625,1298,0.06086286594761171,0.2828776041666667,0.06586666666666666,0.1668,0.10093333333333335,0.07506666666666667,0.12453666666666666,6144.0,0.9866536458333334
l05_s120,258,395,0.06329113924050633,0.2740885416666667,0.06492248062015504,0.14922480620155038,0.08430232558139535,0.04941860465116279,0.12015503875968993,6144.0,0.98828125