Upload report-Model-0_Queries-0_Prompt-1_Strategies-argmax-threshold0.05-threshold0.25-threshold0.5-threshold0.75-topk9-topk7-topk5-topk3.csv

Reports/report-Model-0_Queries-0_Prompt-1_Strategies-argmax-threshold0.05-threshold0.25-threshold0.5-threshold0.75-topk9-topk7-topk5-topk3.csv

@@ -0,0 +1,189 @@
+argmax_max,class,N# of True samples,N# of False samples,True Positives,False Positives,r,p,f1,acc
+0,0,2,2,0,0,0.0,0.0,0.0,0.5
+1,1,30,30,0,0,0.0,0.0,0.0,0.5
+2,2,288,288,19,10,0.06597222222222222,0.6551724137931034,0.11987381703470032,0.515625
+3,3,87,87,2,4,0.022988505747126436,0.3333333333333333,0.04301075268817204,0.4885057471264368
+4,4,94,94,14,3,0.14893617021276595,0.8235294117647058,0.25225225225225223,0.5585106382978723
+5,5,62,62,1,0,0.016129032258064516,1.0,0.031746031746031744,0.5080645161290323
+6,6,63,63,2,1,0.031746031746031744,0.6666666666666666,0.06060606060606061,0.5079365079365079
+7,7,17,17,1,1,0.058823529411764705,0.5,0.10526315789473684,0.5
+8,8,65,65,4,4,0.06153846153846154,0.5,0.10958904109589042,0.5
+9,9,31,31,9,4,0.2903225806451613,0.6923076923076923,0.4090909090909091,0.5806451612903226
+10,10,57,57,25,13,0.43859649122807015,0.6578947368421053,0.5263157894736842,0.6052631578947368
+11,11,48,48,26,15,0.5416666666666666,0.6341463414634146,0.5842696629213483,0.6145833333333334
+12,12,36,36,2,4,0.05555555555555555,0.3333333333333333,0.09523809523809525,0.4722222222222222
+13,13,17,17,6,4,0.35294117647058826,0.6,0.4444444444444445,0.5588235294117647
+14,14,77,77,1,2,0.012987012987012988,0.3333333333333333,0.025,0.4935064935064935
+15,15,40,40,0,0,0.0,0.0,0.0,0.5
+16,16,29,29,12,19,0.41379310344827586,0.3870967741935484,0.39999999999999997,0.3793103448275862
+17,total,1043,1043,124,84,,,,
+18,,,,,Micro avg.,0.11888782358581017,0.5961538461538461,0.19824140687450043,0.5191754554170661
+19,,,,,Macro avg.,0.14776450236104516,0.4774596492371316,0.18862941261684268,0.5166468618809593
+threshold-0.05,class,N# of True samples,N# of False samples,True Positives,False Positives,r,p,f1,acc
+0,0,2,2,0,0,0.0,0.0,0.0,0.5
+1,1,30,30,5,4,0.16666666666666666,0.5555555555555556,0.2564102564102564,0.5166666666666667
+2,2,288,288,102,95,0.3541666666666667,0.5177664974619289,0.42061855670103093,0.5121527777777778
+3,3,87,87,69,59,0.7931034482758621,0.5390625,0.641860465116279,0.5574712643678161
+4,4,94,94,68,54,0.723404255319149,0.5573770491803278,0.6296296296296297,0.574468085106383
+5,5,62,62,15,11,0.24193548387096775,0.5769230769230769,0.3409090909090909,0.532258064516129
+6,6,63,63,51,38,0.8095238095238095,0.5730337078651685,0.6710526315789473,0.6031746031746031
+7,7,17,17,13,10,0.7647058823529411,0.5652173913043478,0.65,0.5882352941176471
+8,8,65,65,44,36,0.676923076923077,0.55,0.6068965517241379,0.5615384615384615
+9,9,31,31,27,31,0.8709677419354839,0.46551724137931033,0.6067415730337079,0.43548387096774194
+10,10,57,57,46,24,0.8070175438596491,0.6571428571428571,0.7244094488188977,0.6929824561403509
+11,11,48,48,44,47,0.9166666666666666,0.4835164835164835,0.6330935251798562,0.46875
+12,12,36,36,31,30,0.8611111111111112,0.5081967213114754,0.6391752577319588,0.5138888888888888
+13,13,17,17,16,14,0.9411764705882353,0.5333333333333333,0.6808510638297872,0.5588235294117647
+14,14,77,77,56,55,0.7272727272727273,0.5045045045045045,0.5957446808510638,0.5064935064935064
+15,15,40,40,5,10,0.125,0.3333333333333333,0.18181818181818182,0.4375
+16,16,29,29,29,29,1.0,0.5,0.6666666666666666,0.5
+17,total,1043,1043,621,547,,,,
+18,,,,,Micro avg.,0.5953978906999041,0.5316780821917808,0.5617367706919945,0.5354745925215724
+19,,,,,Macro avg.,0.6340965618254714,0.49532236781245315,0.5262280929411466,0.5329345570098668
+threshold-0.25,class,N# of True samples,N# of False samples,True Positives,False Positives,r,p,f1,acc
+0,0,2,2,0,0,0.0,0.0,0.0,0.5
+1,1,30,30,1,0,0.03333333333333333,1.0,0.06451612903225806,0.5166666666666667
+2,2,288,288,63,47,0.21875,0.5727272727272728,0.31658291457286436,0.5277777777777778
+3,3,87,87,45,33,0.5172413793103449,0.5769230769230769,0.5454545454545454,0.5689655172413793
+4,4,94,94,38,22,0.40425531914893614,0.6333333333333333,0.49350649350649345,0.5851063829787234
+5,5,62,62,6,2,0.0967741935483871,0.75,0.1714285714285714,0.532258064516129
+6,6,63,63,43,14,0.6825396825396826,0.7543859649122807,0.7166666666666668,0.7301587301587301
+7,7,17,17,9,7,0.5294117647058824,0.5625,0.5454545454545455,0.5588235294117647
+8,8,65,65,35,20,0.5384615384615384,0.6363636363636364,0.5833333333333334,0.6153846153846154
+9,9,31,31,21,28,0.6774193548387096,0.42857142857142855,0.525,0.3870967741935484
+10,10,57,57,39,19,0.6842105263157895,0.6724137931034483,0.6782608695652174,0.6754385964912281
+11,11,48,48,42,40,0.875,0.5121951219512195,0.6461538461538462,0.5208333333333334
+12,12,36,36,21,19,0.5833333333333334,0.525,0.5526315789473685,0.5277777777777778
+13,13,17,17,14,11,0.8235294117647058,0.56,0.6666666666666666,0.5882352941176471
+14,14,77,77,36,39,0.4675324675324675,0.48,0.4736842105263158,0.4805194805194805
+15,15,40,40,1,4,0.025,0.2,0.04444444444444445,0.4625
+16,16,29,29,27,27,0.9310344827586207,0.5,0.6506024096385543,0.5
+17,total,1043,1043,441,332,,,,
+18,,,,,Micro avg.,0.4228187919463087,0.5705045278137129,0.48568281938325997,0.5522531160115053
+19,,,,,Macro avg.,0.4757545169171606,0.5508478604638646,0.4514345426700995,0.5457377965040471
+threshold-0.5,class,N# of True samples,N# of False samples,True Positives,False Positives,r,p,f1,acc
+0,0,2,2,0,0,0.0,0.0,0.0,0.5
+1,1,30,30,0,0,0.0,0.0,0.0,0.5
+2,2,288,288,37,21,0.1284722222222222,0.6379310344827587,0.2138728323699422,0.5277777777777778
+3,3,87,87,22,14,0.25287356321839083,0.6111111111111112,0.3577235772357724,0.5459770114942529
+4,4,94,94,20,11,0.2127659574468085,0.6451612903225806,0.32,0.5478723404255319
+5,5,62,62,1,0,0.016129032258064516,1.0,0.031746031746031744,0.5080645161290323
+6,6,63,63,12,1,0.19047619047619047,0.9230769230769231,0.31578947368421056,0.5873015873015873
+7,7,17,17,5,1,0.29411764705882354,0.8333333333333334,0.4347826086956522,0.6176470588235294
+8,8,65,65,19,12,0.2923076923076923,0.6129032258064516,0.39583333333333337,0.5538461538461539
+9,9,31,31,11,13,0.3548387096774194,0.4583333333333333,0.39999999999999997,0.46774193548387094
+10,10,57,57,36,16,0.631578947368421,0.6923076923076923,0.6605504587155963,0.6754385964912281
+11,11,48,48,37,26,0.7708333333333334,0.5873015873015873,0.6666666666666666,0.6145833333333334
+12,12,36,36,13,10,0.3611111111111111,0.5652173913043478,0.44067796610169496,0.5416666666666666
+13,13,17,17,11,8,0.6470588235294118,0.5789473684210527,0.6111111111111113,0.5882352941176471
+14,14,77,77,14,13,0.18181818181818182,0.5185185185185185,0.2692307692307693,0.5064935064935064
+15,15,40,40,1,1,0.025,0.5,0.047619047619047616,0.5
+16,16,29,29,23,24,0.7931034482758621,0.48936170212765956,0.6052631578947368,0.4827586206896552
+17,total,1043,1043,262,171,,,,
+18,,,,,Micro avg.,0.25119846596356665,0.605080831408776,0.35501355013550134,0.5436241610738255
+19,,,,,Macro avg.,0.3030873447118785,0.5678532065557265,0.33946276672968034,0.5450237881808101
+threshold-0.75,class,N# of True samples,N# of False samples,True Positives,False Positives,r,p,f1,acc
+0,0,2,2,0,0,0.0,0.0,0.0,0.5
+1,1,30,30,0,0,0.0,0.0,0.0,0.5
+2,2,288,288,15,9,0.052083333333333336,0.625,0.09615384615384616,0.5104166666666666
+3,3,87,87,6,1,0.06896551724137931,0.8571428571428571,0.1276595744680851,0.5287356321839081
+4,4,94,94,9,2,0.09574468085106383,0.8181818181818182,0.17142857142857143,0.5372340425531915
+5,5,62,62,1,0,0.016129032258064516,1.0,0.031746031746031744,0.5080645161290323
+6,6,63,63,5,0,0.07936507936507936,1.0,0.14705882352941177,0.5396825396825397
+7,7,17,17,1,0,0.058823529411764705,1.0,0.1111111111111111,0.5294117647058824
+8,8,65,65,3,5,0.046153846153846156,0.375,0.08219178082191782,0.4846153846153846
+9,9,31,31,6,1,0.1935483870967742,0.8571428571428571,0.3157894736842105,0.5806451612903226
+10,10,57,57,29,16,0.5087719298245614,0.6444444444444445,0.5686274509803921,0.6140350877192983
+11,11,48,48,29,17,0.6041666666666666,0.6304347826086957,0.6170212765957447,0.625
+12,12,36,36,9,5,0.25,0.6428571428571429,0.36,0.5555555555555556
+13,13,17,17,4,3,0.23529411764705882,0.5714285714285714,0.3333333333333333,0.5294117647058824
+14,14,77,77,2,5,0.025974025974025976,0.2857142857142857,0.04761904761904762,0.4805194805194805
+15,15,40,40,1,1,0.025,0.5,0.047619047619047616,0.5
+16,16,29,29,20,18,0.6896551724137931,0.5263157894736842,0.5970149253731344,0.5344827586206896
+17,total,1043,1043,140,83,,,,
+18,,,,,Micro avg.,0.1342281879194631,0.6278026905829597,0.2211690363349131,0.5273250239693192
+19,,,,,Macro avg.,0.17351031283749477,0.607862502882021,0.21496319379199325,0.5328123738204609
+topk-9,class,N# of True samples,N# of False samples,True Positives,False Positives,r,p,f1,acc
+0,0,2,2,0,0,0.0,0.0,0.0,0.5
+1,1,30,30,6,4,0.2,0.6,0.3,0.5333333333333333
+2,2,288,288,92,85,0.3194444444444444,0.519774011299435,0.3956989247311828,0.5121527777777778
+3,3,87,87,75,65,0.8620689655172413,0.5357142857142857,0.6607929515418501,0.5574712643678161
+4,4,94,94,81,68,0.8617021276595744,0.5436241610738255,0.6666666666666666,0.5691489361702128
+5,5,62,62,13,2,0.20967741935483872,0.8666666666666667,0.33766233766233766,0.5887096774193549
+6,6,63,63,51,38,0.8095238095238095,0.5730337078651685,0.6710526315789473,0.6031746031746031
+7,7,17,17,12,8,0.7058823529411765,0.6,0.6486486486486486,0.6176470588235294
+8,8,65,65,46,34,0.7076923076923077,0.575,0.6344827586206897,0.5923076923076923
+9,9,31,31,30,31,0.967741935483871,0.4918032786885246,0.6521739130434782,0.4838709677419355
+10,10,57,57,42,25,0.7368421052631579,0.6268656716417911,0.6774193548387096,0.6491228070175439
+11,11,48,48,45,47,0.9375,0.4891304347826087,0.6428571428571429,0.4791666666666667
+12,12,36,36,31,30,0.8611111111111112,0.5081967213114754,0.6391752577319588,0.5138888888888888
+13,13,17,17,17,14,1.0,0.5483870967741935,0.7083333333333333,0.5882352941176471
+14,14,77,77,56,55,0.7272727272727273,0.5045045045045045,0.5957446808510638,0.5064935064935064
+15,15,40,40,6,8,0.15,0.42857142857142855,0.2222222222222222,0.475
+16,16,29,29,28,29,0.9655172413793104,0.49122807017543857,0.6511627906976745,0.4827586206896552
+17,total,1043,1043,631,543,,,,
+18,,,,,Micro avg.,0.6049856184084372,0.5374787052810903,0.5692377086152458,0.5421860019175455
+19,,,,,Macro avg.,0.6483515616260922,0.5236764728864322,0.5355349185309357,0.5442636526464801
+topk-7,class,N# of True samples,N# of False samples,True Positives,False Positives,r,p,f1,acc
+0,0,2,2,0,0,0.0,0.0,0.0,0.5
+1,1,30,30,1,0,0.03333333333333333,1.0,0.06451612903225806,0.5166666666666667
+2,2,288,288,76,63,0.2638888888888889,0.5467625899280576,0.3559718969555035,0.5225694444444444
+3,3,87,87,63,48,0.7241379310344828,0.5675675675675675,0.6363636363636365,0.5862068965517241
+4,4,94,94,73,46,0.776595744680851,0.6134453781512605,0.6854460093896713,0.6436170212765957
+5,5,62,62,11,2,0.1774193548387097,0.8461538461538461,0.29333333333333333,0.5725806451612904
+6,6,63,63,48,27,0.7619047619047619,0.64,0.6956521739130435,0.6666666666666666
+7,7,17,17,11,8,0.6470588235294118,0.5789473684210527,0.6111111111111113,0.5882352941176471
+8,8,65,65,40,27,0.6153846153846154,0.5970149253731343,0.606060606060606,0.6
+9,9,31,31,30,31,0.967741935483871,0.4918032786885246,0.6521739130434782,0.4838709677419355
+10,10,57,57,40,20,0.7017543859649122,0.6666666666666666,0.6837606837606838,0.6754385964912281
+11,11,48,48,44,45,0.9166666666666666,0.4943820224719101,0.6423357664233577,0.4895833333333333
+12,12,36,36,26,26,0.7222222222222222,0.5,0.5909090909090908,0.5
+13,13,17,17,17,14,1.0,0.5483870967741935,0.7083333333333333,0.5882352941176471
+14,14,77,77,53,39,0.6883116883116883,0.5760869565217391,0.6272189349112427,0.5909090909090909
+15,15,40,40,4,8,0.1,0.3333333333333333,0.15384615384615383,0.45
+16,16,29,29,27,29,0.9310344827586207,0.48214285714285715,0.6352941176470589,0.46551724137931033
+17,total,1043,1043,564,433,,,,
+18,,,,,Micro avg.,0.5407478427612655,0.5656970912738215,0.5529411764705883,0.5627996164908916
+19,,,,,Macro avg.,0.5898502844119433,0.5578055227761262,0.5083721700019742,0.5552998328739751
+topk-5,class,N# of True samples,N# of False samples,True Positives,False Positives,r,p,f1,acc
+0,0,2,2,0,0,0.0,0.0,0.0,0.5
+1,1,30,30,0,0,0.0,0.0,0.0,0.5
+2,2,288,288,57,43,0.19791666666666666,0.57,0.29381443298969073,0.5243055555555556
+3,3,87,87,51,36,0.5862068965517241,0.5862068965517241,0.5862068965517241,0.5862068965517241
+4,4,94,94,49,28,0.5212765957446809,0.6363636363636364,0.5730994152046783,0.6117021276595744
+5,5,62,62,3,2,0.04838709677419355,0.6,0.08955223880597016,0.5080645161290323
+6,6,63,63,26,13,0.4126984126984127,0.6666666666666666,0.5098039215686274,0.6031746031746031
+7,7,17,17,9,6,0.5294117647058824,0.6,0.5625,0.5882352941176471
+8,8,65,65,27,18,0.4153846153846154,0.6,0.4909090909090909,0.5692307692307692
+9,9,31,31,27,28,0.8709677419354839,0.4909090909090909,0.627906976744186,0.4838709677419355
+10,10,57,57,36,19,0.631578947368421,0.6545454545454545,0.6428571428571428,0.6491228070175439
+11,11,48,48,43,38,0.8958333333333334,0.5308641975308642,0.6666666666666666,0.5520833333333334
+12,12,36,36,24,21,0.6666666666666666,0.5333333333333333,0.5925925925925926,0.5416666666666666
+13,13,17,17,17,12,1.0,0.5862068965517241,0.7391304347826086,0.6470588235294118
+14,14,77,77,38,25,0.4935064935064935,0.6031746031746031,0.5428571428571428,0.5844155844155844
+15,15,40,40,2,7,0.05,0.2222222222222222,0.0816326530612245,0.4375
+16,16,29,29,27,27,0.9310344827586207,0.5,0.6506024096385543,0.5
+17,total,1043,1043,436,323,,,,
+18,,,,,Micro avg.,0.41802492809204217,0.5744400527009222,0.4839067702552719,0.5541706615532119
+19,,,,,Macro avg.,0.48534527729971727,0.49297017634407764,0.45000776560175876,0.5521551732425518
+topk-3,class,N# of True samples,N# of False samples,True Positives,False Positives,r,p,f1,acc
+0,0,2,2,0,0,0.0,0.0,0.0,0.5
+1,1,30,30,0,0,0.0,0.0,0.0,0.5
+2,2,288,288,38,23,0.13194444444444445,0.6229508196721312,0.2177650429799427,0.5260416666666666
+3,3,87,87,33,23,0.3793103448275862,0.5892857142857143,0.4615384615384615,0.5574712643678161
+4,4,94,94,31,14,0.32978723404255317,0.6888888888888889,0.4460431654676259,0.5904255319148937
+5,5,62,62,1,0,0.016129032258064516,1.0,0.031746031746031744,0.5080645161290323
+6,6,63,63,8,2,0.12698412698412698,0.8,0.2191780821917808,0.5476190476190477
+7,7,17,17,4,1,0.23529411764705882,0.8,0.3636363636363636,0.5882352941176471
+8,8,65,65,17,13,0.26153846153846155,0.5666666666666667,0.3578947368421053,0.5307692307692308
+9,9,31,31,20,27,0.6451612903225806,0.425531914893617,0.5128205128205128,0.3870967741935484
+10,10,57,57,34,17,0.5964912280701754,0.6666666666666666,0.6296296296296297,0.6491228070175439
+11,11,48,48,38,27,0.7916666666666666,0.5846153846153846,0.672566371681416,0.6145833333333334
+12,12,36,36,13,12,0.3611111111111111,0.52,0.42622950819672134,0.5138888888888888
+13,13,17,17,12,7,0.7058823529411765,0.631578947368421,0.6666666666666667,0.6470588235294118
+14,14,77,77,15,14,0.19480519480519481,0.5172413793103449,0.2830188679245283,0.5064935064935064
+15,15,40,40,2,2,0.05,0.5,0.09090909090909091,0.5
+16,16,29,29,25,25,0.8620689655172413,0.5,0.6329113924050632,0.5
+17,total,1043,1043,291,207,,,,
+18,,,,,Micro avg.,0.27900287631831255,0.5843373493975904,0.3776768332251784,0.540268456375839
+19,,,,,Macro avg.,0.3345985041868495,0.5537309636686961,0.35367964262564355,0.5392276873553274