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

Reports/report-Model-1_Queries-1_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
+1,1,30,30,1,0,0.03333333333333333,1.0,0.06451612903225806,0.5166666666666667
+2,2,288,288,76,50,0.2638888888888889,0.6031746031746031,0.3671497584541063,0.5451388888888888
+3,3,87,87,48,13,0.5517241379310345,0.7868852459016393,0.6486486486486487,0.7011494252873564
+4,4,94,94,3,0,0.031914893617021274,1.0,0.06185567010309278,0.5159574468085106
+5,5,62,62,11,12,0.1774193548387097,0.4782608695652174,0.25882352941176473,0.49193548387096775
+6,6,63,63,4,0,0.06349206349206349,1.0,0.11940298507462686,0.5317460317460317
+7,7,17,17,3,1,0.17647058823529413,0.75,0.2857142857142857,0.5588235294117647
+8,8,65,65,17,11,0.26153846153846155,0.6071428571428571,0.3655913978494623,0.5461538461538461
+9,9,31,31,21,15,0.6774193548387096,0.5833333333333334,0.626865671641791,0.5967741935483871
+10,10,57,57,7,6,0.12280701754385964,0.5384615384615384,0.19999999999999998,0.5087719298245614
+11,11,48,48,22,13,0.4583333333333333,0.6285714285714286,0.5301204819277109,0.59375
+12,12,36,36,9,9,0.25,0.5,0.3333333333333333,0.5
+13,13,17,17,3,1,0.17647058823529413,0.75,0.2857142857142857,0.5588235294117647
+14,14,77,77,16,14,0.2077922077922078,0.5333333333333333,0.2990654205607477,0.512987012987013
+15,15,40,40,2,1,0.05,0.6666666666666666,0.09302325581395349,0.5125
+16,16,29,29,0,1,0.0,0.0,0.0,0.4827586206896552
+17,total,1043,1043,243,147,,,,
+18,,,,,Micro avg.,0.23298178331735378,0.6230769230769231,0.33914863921842286,0.5460210930009588
+19,,,,,Macro avg.,0.20603554256577714,0.6132841103618009,0.26704852078118047,0.5396433297232596
+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
+1,1,30,30,10,5,0.3333333333333333,0.6666666666666666,0.4444444444444444,0.5833333333333334
+2,2,288,288,202,205,0.7013888888888888,0.4963144963144963,0.581294964028777,0.4947916666666667
+3,3,87,87,75,59,0.8620689655172413,0.5597014925373134,0.6787330316742081,0.5919540229885057
+4,4,94,94,39,41,0.4148936170212766,0.4875,0.4482758620689655,0.48936170212765956
+5,5,62,62,44,48,0.7096774193548387,0.4782608695652174,0.5714285714285714,0.46774193548387094
+6,6,63,63,50,23,0.7936507936507936,0.684931506849315,0.7352941176470589,0.7142857142857143
+7,7,17,17,7,7,0.4117647058823529,0.5,0.45161290322580644,0.5
+8,8,65,65,57,44,0.8769230769230769,0.5643564356435643,0.6867469879518071,0.6
+9,9,31,31,30,29,0.967741935483871,0.5084745762711864,0.6666666666666666,0.5161290322580645
+10,10,57,57,48,41,0.8421052631578947,0.5393258426966292,0.6575342465753424,0.5614035087719298
+11,11,48,48,46,45,0.9583333333333334,0.5054945054945055,0.6618705035971223,0.5104166666666666
+12,12,36,36,33,33,0.9166666666666666,0.5,0.6470588235294118,0.5
+13,13,17,17,12,9,0.7058823529411765,0.5714285714285714,0.6315789473684211,0.5882352941176471
+14,14,77,77,55,46,0.7142857142857143,0.5445544554455446,0.6179775280898876,0.5584415584415584
+15,15,40,40,11,19,0.275,0.36666666666666664,0.3142857142857143,0.4
+16,16,29,29,19,20,0.6551724137931034,0.48717948717948717,0.5588235294117647,0.4827586206896552
+17,total,1043,1043,738,674,,,,
+18,,,,,Micro avg.,0.7075743048897412,0.5226628895184136,0.6012219959266802,0.5306807286673059
+19,,,,,Macro avg.,0.6552287341313859,0.49769738663289187,0.5502133436467043,0.5328737091665454
+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
+1,1,30,30,7,2,0.23333333333333334,0.7777777777777778,0.35897435897435903,0.5833333333333334
+2,2,288,288,132,126,0.4583333333333333,0.5116279069767442,0.4835164835164835,0.5104166666666666
+3,3,87,87,64,28,0.735632183908046,0.6956521739130435,0.7150837988826816,0.7068965517241379
+4,4,94,94,14,9,0.14893617021276595,0.6086956521739131,0.2393162393162393,0.526595744680851
+5,5,62,62,27,33,0.43548387096774194,0.45,0.4426229508196722,0.45161290322580644
+6,6,63,63,39,3,0.6190476190476191,0.9285714285714286,0.742857142857143,0.7857142857142857
+7,7,17,17,4,3,0.23529411764705882,0.5714285714285714,0.3333333333333333,0.5294117647058824
+8,8,65,65,44,34,0.676923076923077,0.5641025641025641,0.6153846153846154,0.5769230769230769
+9,9,31,31,26,15,0.8387096774193549,0.6341463414634146,0.7222222222222222,0.6774193548387096
+10,10,57,57,36,21,0.631578947368421,0.631578947368421,0.631578947368421,0.631578947368421
+11,11,48,48,38,29,0.7916666666666666,0.5671641791044776,0.6608695652173913,0.59375
+12,12,36,36,23,21,0.6388888888888888,0.5227272727272727,0.575,0.5277777777777778
+13,13,17,17,5,3,0.29411764705882354,0.625,0.4,0.5588235294117647
+14,14,77,77,30,28,0.38961038961038963,0.5172413793103449,0.4444444444444445,0.512987012987013
+15,15,40,40,5,9,0.125,0.35714285714285715,0.18518518518518517,0.45
+16,16,29,29,9,9,0.3103448275862069,0.5,0.3829787234042554,0.5
+17,total,1043,1043,503,373,,,,
+18,,,,,Micro avg.,0.4822627037392138,0.5742009132420092,0.5242313705054716,0.5623202301054651
+19,,,,,Macro avg.,0.4448765147042193,0.5566386501212253,0.4666687065250852,0.5660729970210427
+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
+1,1,30,30,5,0,0.16666666666666666,1.0,0.2857142857142857,0.5833333333333334
+2,2,288,288,49,34,0.1701388888888889,0.5903614457831325,0.2641509433962264,0.5260416666666666
+3,3,87,87,42,14,0.4827586206896552,0.75,0.5874125874125874,0.6609195402298851
+4,4,94,94,7,1,0.07446808510638298,0.875,0.1372549019607843,0.5319148936170213
+5,5,62,62,14,9,0.22580645161290322,0.6086956521739131,0.3294117647058823,0.5403225806451613
+6,6,63,63,12,2,0.19047619047619047,0.8571428571428571,0.31168831168831174,0.5793650793650794
+7,7,17,17,2,3,0.11764705882352941,0.4,0.1818181818181818,0.47058823529411764
+8,8,65,65,21,20,0.3230769230769231,0.5121951219512195,0.39622641509433965,0.5076923076923077
+9,9,31,31,16,11,0.5161290322580645,0.5925925925925926,0.5517241379310345,0.5806451612903226
+10,10,57,57,17,12,0.2982456140350877,0.5862068965517241,0.3953488372093023,0.543859649122807
+11,11,48,48,29,19,0.6041666666666666,0.6041666666666666,0.6041666666666666,0.6041666666666666
+12,12,36,36,10,4,0.2777777777777778,0.7142857142857143,0.4,0.5833333333333334
+13,13,17,17,1,1,0.058823529411764705,0.5,0.10526315789473684,0.5
+14,14,77,77,14,16,0.18181818181818182,0.4666666666666667,0.26168224299065423,0.487012987012987
+15,15,40,40,2,5,0.05,0.2857142857142857,0.0851063829787234,0.4625
+16,16,29,29,1,3,0.034482758620689655,0.25,0.0606060606060606,0.46551724137931033
+17,total,1043,1043,242,154,,,,
+18,,,,,Micro avg.,0.23202301054650049,0.6111111111111112,0.33634468380820015,0.5421860019175455
+19,,,,,Macro avg.,0.22191073211349246,0.5642957587958102,0.2916220516510458,0.5368948632734706
+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
+1,1,30,30,3,0,0.1,1.0,0.18181818181818182,0.55
+2,2,288,288,9,7,0.03125,0.5625,0.05921052631578947,0.5034722222222222
+3,3,87,87,16,1,0.1839080459770115,0.9411764705882353,0.3076923076923077,0.5862068965517241
+4,4,94,94,2,0,0.02127659574468085,1.0,0.04166666666666667,0.5106382978723404
+5,5,62,62,3,1,0.04838709677419355,0.75,0.0909090909090909,0.5161290322580645
+6,6,63,63,4,0,0.06349206349206349,1.0,0.11940298507462686,0.5317460317460317
+7,7,17,17,2,1,0.11764705882352941,0.6666666666666666,0.2,0.5294117647058824
+8,8,65,65,10,10,0.15384615384615385,0.5,0.23529411764705882,0.5
+9,9,31,31,8,2,0.25806451612903225,0.8,0.3902439024390244,0.5967741935483871
+10,10,57,57,7,6,0.12280701754385964,0.5384615384615384,0.19999999999999998,0.5087719298245614
+11,11,48,48,25,8,0.5208333333333334,0.7575757575757576,0.617283950617284,0.6770833333333334
+12,12,36,36,2,2,0.05555555555555555,0.5,0.09999999999999999,0.5
+13,13,17,17,1,1,0.058823529411764705,0.5,0.10526315789473684,0.5
+14,14,77,77,9,9,0.11688311688311688,0.5,0.1894736842105263,0.5
+15,15,40,40,2,3,0.05,0.4,0.0888888888888889,0.4875
+16,16,29,29,0,0,0.0,0.0,0.0,0.5
+17,total,1043,1043,103,51,,,,
+18,,,,,Micro avg.,0.0987535953978907,0.6688311688311688,0.1720969089390142,0.524928092042186
+19,,,,,Macro avg.,0.11192788726554677,0.612728260781894,0.17218514471612842,0.5292784530625028
+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
+1,1,30,30,15,5,0.5,0.75,0.6,0.6666666666666666
+2,2,288,288,249,256,0.8645833333333334,0.49306930693069306,0.6279949558638083,0.4878472222222222
+3,3,87,87,82,69,0.9425287356321839,0.543046357615894,0.6890756302521007,0.5747126436781609
+4,4,94,94,63,53,0.6702127659574468,0.5431034482758621,0.6000000000000001,0.5531914893617021
+5,5,62,62,40,49,0.6451612903225806,0.449438202247191,0.5298013245033112,0.4274193548387097
+6,6,63,63,49,19,0.7777777777777778,0.7205882352941176,0.7480916030534351,0.7380952380952381
+7,7,17,17,11,9,0.6470588235294118,0.55,0.5945945945945946,0.5588235294117647
+8,8,65,65,62,54,0.9538461538461539,0.5344827586206896,0.6850828729281768,0.5615384615384615
+9,9,31,31,30,29,0.967741935483871,0.5084745762711864,0.6666666666666666,0.5161290322580645
+10,10,57,57,55,45,0.9649122807017544,0.55,0.7006369426751593,0.5877192982456141
+11,11,48,48,47,47,0.9791666666666666,0.5,0.6619718309859155,0.5
+12,12,36,36,33,34,0.9166666666666666,0.4925373134328358,0.6407766990291262,0.4861111111111111
+13,13,17,17,14,5,0.8235294117647058,0.7368421052631579,0.7777777777777778,0.7647058823529411
+14,14,77,77,57,47,0.7402597402597403,0.5480769230769231,0.6298342541436464,0.564935064935065
+15,15,40,40,25,29,0.625,0.46296296296296297,0.5319148936170213,0.45
+16,16,29,29,22,26,0.7586206896551724,0.4583333333333333,0.5714285714285715,0.43103448275862066
+17,total,1043,1043,854,776,,,,
+18,,,,,Micro avg.,0.8187919463087249,0.5239263803680981,0.6389824167601945,0.537392138063279
+19,,,,,Macro avg.,0.7515921336233804,0.5200562072544028,0.6032734480893712,0.5511134986749613
+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
+1,1,30,30,10,5,0.3333333333333333,0.6666666666666666,0.4444444444444444,0.5833333333333334
+2,2,288,288,233,233,0.8090277777777778,0.5,0.6180371352785147,0.5
+3,3,87,87,79,63,0.9080459770114943,0.5563380281690141,0.6899563318777292,0.5919540229885057
+4,4,94,94,51,49,0.5425531914893617,0.51,0.5257731958762887,0.5106382978723404
+5,5,62,62,34,40,0.5483870967741935,0.4594594594594595,0.5,0.45161290322580644
+6,6,63,63,46,12,0.7301587301587301,0.7931034482758621,0.7603305785123967,0.7698412698412699
+7,7,17,17,8,6,0.47058823529411764,0.5714285714285714,0.5161290322580646,0.5588235294117647
+8,8,65,65,59,47,0.9076923076923077,0.5566037735849056,0.6900584795321637,0.5923076923076923
+9,9,31,31,29,28,0.9354838709677419,0.5087719298245614,0.6590909090909092,0.5161290322580645
+10,10,57,57,51,36,0.8947368421052632,0.5862068965517241,0.7083333333333333,0.631578947368421
+11,11,48,48,39,40,0.8125,0.4936708860759494,0.6141732283464567,0.4895833333333333
+12,12,36,36,30,32,0.8333333333333334,0.4838709677419355,0.6122448979591837,0.4722222222222222
+13,13,17,17,14,4,0.8235294117647058,0.7777777777777778,0.7999999999999999,0.7941176470588235
+14,14,77,77,52,40,0.6753246753246753,0.5652173913043478,0.6153846153846153,0.577922077922078
+15,15,40,40,15,20,0.375,0.42857142857142855,0.39999999999999997,0.4375
+16,16,29,29,18,24,0.6206896551724138,0.42857142857142855,0.5070422535211268,0.39655172413793105
+17,total,1043,1043,768,679,,,,
+18,,,,,Micro avg.,0.7363374880153404,0.5307532826537664,0.616867469879518,0.5426653883029722
+19,,,,,Macro avg.,0.6600226140117325,0.5227210972943314,0.5682940256126604,0.5514185901930344
+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
+1,1,30,30,7,3,0.23333333333333334,0.7,0.35,0.5666666666666667
+2,2,288,288,217,203,0.7534722222222222,0.5166666666666667,0.612994350282486,0.5243055555555556
+3,3,87,87,75,54,0.8620689655172413,0.5813953488372093,0.6944444444444445,0.6206896551724138
+4,4,94,94,36,39,0.3829787234042553,0.48,0.4260355029585799,0.48404255319148937
+5,5,62,62,29,37,0.46774193548387094,0.4393939393939394,0.453125,0.43548387096774194
+6,6,63,63,41,5,0.6507936507936508,0.8913043478260869,0.7522935779816514,0.7857142857142857
+7,7,17,17,7,6,0.4117647058823529,0.5384615384615384,0.4666666666666667,0.5294117647058824
+8,8,65,65,53,39,0.8153846153846154,0.5760869565217391,0.6751592356687899,0.6076923076923076
+9,9,31,31,29,26,0.9354838709677419,0.5272727272727272,0.6744186046511628,0.5483870967741935
+10,10,57,57,45,28,0.7894736842105263,0.6164383561643836,0.6923076923076923,0.6491228070175439
+11,11,48,48,35,35,0.7291666666666666,0.5,0.5932203389830509,0.5
+12,12,36,36,29,26,0.8055555555555556,0.5272727272727272,0.6373626373626373,0.5416666666666666
+13,13,17,17,11,2,0.6470588235294118,0.8461538461538461,0.7333333333333334,0.7647058823529411
+14,14,77,77,43,32,0.5584415584415584,0.5733333333333334,0.5657894736842105,0.5714285714285714
+15,15,40,40,12,12,0.3,0.5,0.37499999999999994,0.5
+16,16,29,29,10,17,0.3448275862068966,0.37037037037037035,0.35714285714285715,0.3793103448275862
+17,total,1043,1043,679,564,,,,
+18,,,,,Micro avg.,0.6510067114093959,0.5462590506838294,0.5940507436570429,0.5551294343240653
+19,,,,,Macro avg.,0.5698556410352883,0.5402441269573276,0.5328996303216214,0.5593310605137556
+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
+1,1,30,30,6,1,0.2,0.8571428571428571,0.32432432432432434,0.5833333333333334
+2,2,288,288,181,163,0.6284722222222222,0.5261627906976745,0.5727848101265823,0.53125
+3,3,87,87,68,42,0.7816091954022989,0.6181818181818182,0.6903553299492386,0.6494252873563219
+4,4,94,94,20,20,0.2127659574468085,0.5,0.2985074626865672,0.5
+5,5,62,62,20,29,0.3225806451612903,0.40816326530612246,0.3603603603603604,0.4274193548387097
+6,6,63,63,29,0,0.4603174603174603,1.0,0.6304347826086957,0.7301587301587301
+7,7,17,17,5,4,0.29411764705882354,0.5555555555555556,0.3846153846153846,0.5294117647058824
+8,8,65,65,41,34,0.6307692307692307,0.5466666666666666,0.5857142857142857,0.5538461538461539
+9,9,31,31,27,23,0.8709677419354839,0.54,0.6666666666666666,0.5645161290322581
+10,10,57,57,30,16,0.5263157894736842,0.6521739130434783,0.5825242718446602,0.6228070175438597
+11,11,48,48,33,27,0.6875,0.55,0.6111111111111112,0.5625
+12,12,36,36,19,23,0.5277777777777778,0.4523809523809524,0.4871794871794871,0.4444444444444444
+13,13,17,17,6,1,0.35294117647058826,0.8571428571428571,0.5,0.6470588235294118
+14,14,77,77,31,25,0.4025974025974026,0.5535714285714286,0.46616541353383456,0.538961038961039
+15,15,40,40,8,4,0.2,0.6666666666666666,0.30769230769230765,0.55
+16,16,29,29,7,9,0.2413793103448276,0.4375,0.3111111111111111,0.46551724137931033
+17,total,1043,1043,531,421,,,,
+18,,,,,Micro avg.,0.5091083413231065,0.5577731092436975,0.5323308270676692,0.552732502396932
+19,,,,,Macro avg.,0.43177126805752347,0.5718416924327104,0.45762041820733046,0.5529793717134973