Remove temporary backup ravel_revision_results/aggregate_results/significance_tests.csv.pre_e03_mechanism_patch.bak

ravel_revision_results/aggregate_results/significance_tests.csv.pre_e03_mechanism_patch.bak

@@ -1,136 +0,0 @@
-dataset,method_a,method_b,metric,mean_difference,ci_lower,ci_upper,raw_p_value,holm_adjusted_p_value,significant,bootstrap_samples,test_type
-mvsa_multiple,full_revised,frozen_concat,macro_f1,0.020066832775777033,0.0057848085397526365,0.0343659240457928,0.007,0.546,False,10000,paired_sample_bootstrap
-mvsa_multiple,full_revised,frozen_concat,weighted_f1,0.002572746830869055,-0.0067684588201203984,0.011856361007606932,0.5936,1.0,False,10000,paired_sample_bootstrap
-mvsa_multiple,full_revised,frozen_concat,accuracy,-0.019529411764705906,-0.028588235294117692,-0.01047058823529412,0.0,0.0,True,10000,paired_sample_bootstrap
-mvsa_multiple,full_revised,frozen_concat,nll,0.11876129575406347,0.10346443342387404,0.13407032974455424,0.0,0.0,True,10000,paired_sample_bootstrap
-mvsa_multiple,full_revised,frozen_concat,brier_score,0.05607443499341791,0.04738164475382037,0.06482397869799202,0.0,0.0,True,10000,paired_sample_bootstrap
-mvsa_multiple,full_revised,lora_concat,macro_f1,-0.004938576207554779,-0.01760881837740349,0.007762494153010783,0.4468,1.0,False,10000,paired_sample_bootstrap
-mvsa_multiple,full_revised,lora_concat,weighted_f1,-0.007594421606060497,-0.015767545942271803,0.0006139267735679038,0.072,1.0,False,10000,paired_sample_bootstrap
-mvsa_multiple,full_revised,lora_concat,accuracy,-0.011529411764705899,-0.019882352941176462,-0.0032941176470587807,0.0076,0.5852,False,10000,paired_sample_bootstrap
-mvsa_multiple,full_revised,lora_concat,nll,-0.020200105409502567,-0.03680463260254247,-0.0035998218970084623,0.019,1.0,False,10000,paired_sample_bootstrap
-mvsa_multiple,full_revised,lora_concat,brier_score,0.009269811121336458,0.0003203863466070212,0.018272893866471986,0.0426,1.0,False,10000,paired_sample_bootstrap
-mvsa_multiple,full_revised,frozen_token_coattn,macro_f1,0.015663515250249782,0.0005091741564305478,0.03053224897581969,0.0412,1.0,False,10000,paired_sample_bootstrap
-mvsa_multiple,full_revised,frozen_token_coattn,weighted_f1,-0.0030632419913666498,-0.012330853460841234,0.006147386043377006,0.505,1.0,False,10000,paired_sample_bootstrap
-mvsa_multiple,full_revised,frozen_token_coattn,accuracy,-0.01811764705882357,-0.027176470588235246,-0.009058823529411675,0.0,0.0,True,10000,paired_sample_bootstrap
-mvsa_multiple,full_revised,frozen_token_coattn,nll,0.105452149365447,0.08986588561134974,0.12132855679073183,0.0,0.0,True,10000,paired_sample_bootstrap
-mvsa_multiple,full_revised,frozen_token_coattn,brier_score,0.05219777337112208,0.04345680982690577,0.06102413605656277,0.0,0.0,True,10000,paired_sample_bootstrap
-mvsa_multiple,full_revised,token_coattn,macro_f1,-0.00039691996875323987,-0.008270374265418897,0.007608798536497209,0.9244,1.0,False,10000,paired_sample_bootstrap
-mvsa_multiple,full_revised,token_coattn,weighted_f1,-0.003143226493161566,-0.008782264127487071,0.002587181434662039,0.2846,1.0,False,10000,paired_sample_bootstrap
-mvsa_multiple,full_revised,token_coattn,accuracy,-0.0065882352941176725,-0.012352941176470567,-0.0008235294117646674,0.0248,1.0,False,10000,paired_sample_bootstrap
-mvsa_multiple,full_revised,token_coattn,nll,0.023933011885805988,0.015786287222579118,0.032032129016327134,0.0,0.0,True,10000,paired_sample_bootstrap
-mvsa_multiple,full_revised,token_coattn,brier_score,0.01069654520288188,0.005764678506901647,0.01555092970508178,0.0,0.0,True,10000,paired_sample_bootstrap
-mvsa_multiple,full_revised,token_aux,macro_f1,0.009693260177997765,0.0006082501803778596,0.018956002204523478,0.0352,1.0,False,10000,paired_sample_bootstrap
-mvsa_multiple,full_revised,token_aux,weighted_f1,-0.0004943054966149996,-0.006751835403173703,0.005855852371025213,0.8948,1.0,False,10000,paired_sample_bootstrap
-mvsa_multiple,full_revised,token_aux,accuracy,-0.010705882352941232,-0.016941176470588237,-0.0043529411764705594,0.001,0.082,False,10000,paired_sample_bootstrap
-mvsa_multiple,full_revised,token_aux,nll,0.04933955327011874,0.03990359492103896,0.059162960210279246,0.0,0.0,True,10000,paired_sample_bootstrap
-mvsa_multiple,full_revised,token_aux,brier_score,0.02414248609476527,0.018320015716583496,0.030124280145159613,0.0,0.0,True,10000,paired_sample_bootstrap
-mvsa_multiple,full_revised,param_mlp,macro_f1,-0.0011715312833310287,-0.009410865369571688,0.006762873409839581,0.7856,1.0,False,10000,paired_sample_bootstrap
-mvsa_multiple,full_revised,param_mlp,weighted_f1,0.0005436484986727219,-0.004960772394869003,0.006094014205118426,0.835,1.0,False,10000,paired_sample_bootstrap
-mvsa_multiple,full_revised,param_mlp,accuracy,-0.003176470588235336,-0.008823529411764675,0.0023529411764705577,0.2694,1.0,False,10000,paired_sample_bootstrap
-mvsa_multiple,full_revised,param_mlp,nll,-0.0013916211241469245,-0.009298858970633943,0.006354556278329275,0.7394,1.0,False,10000,paired_sample_bootstrap
-mvsa_multiple,full_revised,param_mlp,brier_score,0.0022488118661867507,-0.0024101127592518895,0.006879013358772168,0.3496,1.0,False,10000,paired_sample_bootstrap
-mvsa_multiple,full_revised,legacy_global,macro_f1,-0.008197320614301229,-0.020420638689687604,0.0038855025803866254,0.1838,1.0,False,10000,paired_sample_bootstrap
-mvsa_multiple,full_revised,legacy_global,weighted_f1,-0.01491151964671844,-0.022900915869610378,-0.007120494248624721,0.0002,0.017,True,10000,paired_sample_bootstrap
-mvsa_multiple,full_revised,legacy_global,accuracy,-0.02400000000000002,-0.03188235294117647,-0.016235294117647125,0.0,0.0,True,10000,paired_sample_bootstrap
-mvsa_multiple,full_revised,legacy_global,nll,0.035368468966724964,0.01955483413689201,0.051659936739351264,0.0,0.0,True,10000,paired_sample_bootstrap
-mvsa_multiple,full_revised,legacy_global,brier_score,0.029564178148612563,0.02118307951607031,0.03829596474528979,0.0,0.0,True,10000,paired_sample_bootstrap
-hfm_existing,full_revised,frozen_concat,macro_f1,0.016257605654958707,0.011073153389422833,0.021469306275427112,0.0,0.0,True,10000,paired_sample_bootstrap
-hfm_existing,full_revised,frozen_concat,weighted_f1,0.01588067533049764,0.010821253263161223,0.020961006143304425,0.0,0.0,True,10000,paired_sample_bootstrap
-hfm_existing,full_revised,frozen_concat,accuracy,0.015940224159402328,0.010875882108758783,0.021087588210875863,0.0,0.0,True,10000,paired_sample_bootstrap
-hfm_existing,full_revised,frozen_concat,nll,-0.008150792223092673,-0.019604351722340884,0.0035159442996647197,0.169,1.0,False,10000,paired_sample_bootstrap
-hfm_existing,full_revised,frozen_concat,brier_score,-0.018162162696121975,-0.024558441835329053,-0.011769192317486792,0.0,0.0,True,10000,paired_sample_bootstrap
-hfm_existing,full_revised,lora_concat,macro_f1,-0.0034664817716099083,-0.00792972114058831,0.0010038040648003748,0.1262,1.0,False,10000,paired_sample_bootstrap
-hfm_existing,full_revised,lora_concat,weighted_f1,-0.0032951485876200337,-0.007660128164745386,0.001080983690619076,0.1382,1.0,False,10000,paired_sample_bootstrap
-hfm_existing,full_revised,lora_concat,accuracy,-0.0032378580323785267,-0.0076380240763802565,0.0011623080116230922,0.1502,1.0,False,10000,paired_sample_bootstrap
-hfm_existing,full_revised,lora_concat,nll,-0.011972504644064963,-0.02353047819602693,-0.0003837276436477885,0.0446,1.0,False,10000,paired_sample_bootstrap
-hfm_existing,full_revised,lora_concat,brier_score,-0.0014114901812026515,-0.007184838979391291,0.004364964248460122,0.6112,1.0,False,10000,paired_sample_bootstrap
-hfm_existing,full_revised,frozen_token_coattn,macro_f1,0.028864845676740192,0.023188766355089107,0.03453472529788361,0.0,0.0,True,10000,paired_sample_bootstrap
-hfm_existing,full_revised,frozen_token_coattn,weighted_f1,0.02824809377355164,0.022682629048435682,0.033809031218973884,0.0,0.0,True,10000,paired_sample_bootstrap
-hfm_existing,full_revised,frozen_token_coattn,accuracy,0.028393524283935268,0.022828974678289694,0.03395599833955998,0.0,0.0,True,10000,paired_sample_bootstrap
-hfm_existing,full_revised,frozen_token_coattn,nll,-0.026881466146720157,-0.038470238584716786,-0.014829617414723148,0.0002,0.017,True,10000,paired_sample_bootstrap
-hfm_existing,full_revised,frozen_token_coattn,brier_score,-0.033658768694887264,-0.03999667336812558,-0.02718203261158909,0.0,0.0,True,10000,paired_sample_bootstrap
-hfm_existing,full_revised,token_coattn,macro_f1,0.005228584500790667,0.0015802626819165111,0.008929799797367383,0.0052,0.416,False,10000,paired_sample_bootstrap
-hfm_existing,full_revised,token_coattn,weighted_f1,0.004983325620118939,0.0014223670535055883,0.008606735761219448,0.006,0.47400000000000003,False,10000,paired_sample_bootstrap
-hfm_existing,full_revised,token_coattn,accuracy,0.0048982980489830075,0.001328352013283518,0.008551266085512602,0.009,0.6839999999999999,False,10000,paired_sample_bootstrap
-hfm_existing,full_revised,token_coattn,nll,-0.07311031031023468,-0.08426886957331263,-0.0620652749309621,0.0,0.0,True,10000,paired_sample_bootstrap
-hfm_existing,full_revised,token_coattn,brier_score,-0.022236200346752166,-0.027220928951680892,-0.017178733293990132,0.0,0.0,True,10000,paired_sample_bootstrap
-hfm_existing,full_revised,token_aux,macro_f1,0.0003733398243205288,-0.0034572546996622018,0.004169470645221255,0.8534,1.0,False,10000,paired_sample_bootstrap
-hfm_existing,full_revised,token_aux,weighted_f1,0.0003920768327438928,-0.0033391020635095774,0.00409208432861082,0.8442,1.0,False,10000,paired_sample_bootstrap
-hfm_existing,full_revised,token_aux,accuracy,0.0004151100041511757,-0.0033208800332088506,0.00415110004151098,0.8522,1.0,False,10000,paired_sample_bootstrap
-hfm_existing,full_revised,token_aux,nll,-0.05746015868173315,-0.06915448496440055,-0.04573397015881426,0.0,0.0,True,10000,paired_sample_bootstrap
-hfm_existing,full_revised,token_aux,brier_score,-0.010603811336075686,-0.015765423335840134,-0.005440497605446217,0.0,0.0,True,10000,paired_sample_bootstrap
-hfm_existing,full_revised,param_mlp,macro_f1,0.0008167545096154916,-0.0029111740621649753,0.004584577334963095,0.6774,1.0,False,10000,paired_sample_bootstrap
-hfm_existing,full_revised,param_mlp,weighted_f1,0.0009089338009082848,-0.002735851878575202,0.004599994455333264,0.6368,1.0,False,10000,paired_sample_bootstrap
-hfm_existing,full_revised,param_mlp,accuracy,0.0009962640099626663,-0.002656704026567036,0.004732254047322471,0.6232,1.0,False,10000,paired_sample_bootstrap
-hfm_existing,full_revised,param_mlp,nll,-0.005347099657774912,-0.013536138513443657,0.0027702099776657873,0.1968,1.0,False,10000,paired_sample_bootstrap
-hfm_existing,full_revised,param_mlp,brier_score,-0.0018800210718132315,-0.00628841621989572,0.0024881314468953803,0.3976,1.0,False,10000,paired_sample_bootstrap
-hfm_existing,full_revised,legacy_global,macro_f1,0.005339631274256518,0.000879076278162555,0.009772974462660176,0.0186,1.0,False,10000,paired_sample_bootstrap
-hfm_existing,full_revised,legacy_global,weighted_f1,0.005122297927253827,0.000757572436765866,0.009463764931742565,0.022,1.0,False,10000,paired_sample_bootstrap
-hfm_existing,full_revised,legacy_global,accuracy,0.005064342050643433,0.0006641760066418145,0.00938148609381495,0.0246,1.0,False,10000,paired_sample_bootstrap
-hfm_existing,full_revised,legacy_global,nll,-0.052398749131388256,-0.0650561661222991,-0.039758321985807664,0.0,0.0,True,10000,paired_sample_bootstrap
-hfm_existing,full_revised,legacy_global,brier_score,-0.015318166291229257,-0.02107656893395719,-0.009540781071810821,0.0,0.0,True,10000,paired_sample_bootstrap
-hfm_deleak,full_revised,frozen_concat,macro_f1,0.0057029378187638535,0.0005329930687821782,0.01089070723524561,0.0334,1.0,False,10000,paired_sample_bootstrap
-hfm_deleak,full_revised,frozen_concat,weighted_f1,0.005515978240973829,0.00041767008208605245,0.010619292430598379,0.0344,1.0,False,10000,paired_sample_bootstrap
-hfm_deleak,full_revised,frozen_concat,accuracy,0.005438311688311659,0.00032467532467528315,0.010551948051948035,0.0374,1.0,False,10000,paired_sample_bootstrap
-hfm_deleak,full_revised,frozen_concat,nll,0.0385204082710654,0.025613113891912287,0.05166971590024954,0.0,0.0,True,10000,paired_sample_bootstrap
-hfm_deleak,full_revised,frozen_concat,brier_score,-0.0004739194319577644,-0.007044644051144565,0.0062599965784705695,0.8868,1.0,False,10000,paired_sample_bootstrap
-hfm_deleak,full_revised,lora_concat,macro_f1,-0.003006440512365982,-0.007320538495257161,0.0012416929923921155,0.1728,1.0,False,10000,paired_sample_bootstrap
-hfm_deleak,full_revised,lora_concat,weighted_f1,-0.003019929625652451,-0.007255712717270851,0.0011725729580525743,0.1606,1.0,False,10000,paired_sample_bootstrap
-hfm_deleak,full_revised,lora_concat,accuracy,-0.003084415584415634,-0.00730519480519487,0.001136363636363602,0.1588,1.0,False,10000,paired_sample_bootstrap
-hfm_deleak,full_revised,lora_concat,nll,0.039436018275669726,0.028051974113459124,0.05096913611007752,0.0,0.0,True,10000,paired_sample_bootstrap
-hfm_deleak,full_revised,lora_concat,brier_score,0.009610444218235425,0.0040406185071012925,0.01518921129984066,0.0008,0.0664,False,10000,paired_sample_bootstrap
-hfm_deleak,full_revised,frozen_token_coattn,macro_f1,0.01629628806474992,0.011090918126557778,0.021484153499179974,0.0,0.0,True,10000,paired_sample_bootstrap
-hfm_deleak,full_revised,frozen_token_coattn,weighted_f1,0.01586978795559535,0.010735736770444957,0.02100318570211117,0.0,0.0,True,10000,paired_sample_bootstrap
-hfm_deleak,full_revised,frozen_token_coattn,accuracy,0.01574675324675323,0.010633116883116855,0.020860389610389607,0.0,0.0,True,10000,paired_sample_bootstrap
-hfm_deleak,full_revised,frozen_token_coattn,nll,0.0014172834873030227,-0.012119597582326449,0.01537457043764394,0.8526,1.0,False,10000,paired_sample_bootstrap
-hfm_deleak,full_revised,frozen_token_coattn,brier_score,-0.015505745831747492,-0.022353077955219968,-0.00850251768843144,0.0,0.0,True,10000,paired_sample_bootstrap
-hfm_deleak,full_revised,token_coattn,macro_f1,0.0038952748731079234,0.0005365485843692176,0.007187139437685987,0.022,1.0,False,10000,paired_sample_bootstrap
-hfm_deleak,full_revised,token_coattn,weighted_f1,0.0039060240305515137,0.0005917306564495184,0.007145096349333123,0.0188,1.0,False,10000,paired_sample_bootstrap
-hfm_deleak,full_revised,token_coattn,accuracy,0.003977272727272663,0.0006493506493506773,0.007224025974025938,0.0184,1.0,False,10000,paired_sample_bootstrap
-hfm_deleak,full_revised,token_coattn,nll,-0.03577200444611678,-0.04739955503673045,-0.024351364815132108,0.0,0.0,True,10000,paired_sample_bootstrap
-hfm_deleak,full_revised,token_coattn,brier_score,-0.01026585100725555,-0.014945950167591043,-0.005610785389524072,0.0,0.0,True,10000,paired_sample_bootstrap
-hfm_deleak,full_revised,token_aux,macro_f1,0.0007642318431851924,-0.0021538560751889362,0.0036749974366132973,0.6216,1.0,False,10000,paired_sample_bootstrap
-hfm_deleak,full_revised,token_aux,weighted_f1,0.0008719085287203221,-0.0020251293016792155,0.0037277652680195662,0.5654,1.0,False,10000,paired_sample_bootstrap
-hfm_deleak,full_revised,token_aux,accuracy,0.0009740259740259605,-0.001948051948051921,0.003814935064935132,0.5332,1.0,False,10000,paired_sample_bootstrap
-hfm_deleak,full_revised,token_aux,nll,0.009930314632173254,0.0033837789050907355,0.01670759262331475,0.0024,0.1944,False,10000,paired_sample_bootstrap
-hfm_deleak,full_revised,token_aux,brier_score,0.00012211040332860135,-0.0031691988513880645,0.003455493635834324,0.956,1.0,False,10000,paired_sample_bootstrap
-hfm_deleak,full_revised,param_mlp,macro_f1,-8.534466641851868e-05,-0.004444229612790914,0.004181832817593261,0.9586,1.0,False,10000,paired_sample_bootstrap
-hfm_deleak,full_revised,param_mlp,weighted_f1,-0.00012462133896096184,-0.004407465252190851,0.004077719994258887,0.946,1.0,False,10000,paired_sample_bootstrap
-hfm_deleak,full_revised,param_mlp,accuracy,-0.00016233766233764158,-0.004464285714285698,0.0040584415584414835,0.947,1.0,False,10000,paired_sample_bootstrap
-hfm_deleak,full_revised,param_mlp,nll,-0.011498872806270488,-0.024721942121056713,0.0016060700762643193,0.0894,1.0,False,10000,paired_sample_bootstrap
-hfm_deleak,full_revised,param_mlp,brier_score,-0.0014839572355782593,-0.007133447553027752,0.004273782545379146,0.6088,1.0,False,10000,paired_sample_bootstrap
-hfm_deleak,full_revised,legacy_global,macro_f1,0.009984144944578999,0.005908024546903154,0.014122534331497771,0.0,0.0,True,10000,paired_sample_bootstrap
-hfm_deleak,full_revised,legacy_global,weighted_f1,0.009943969633812721,0.00591523990073291,0.014006517603795607,0.0,0.0,True,10000,paired_sample_bootstrap
-hfm_deleak,full_revised,legacy_global,accuracy,0.010064935064934999,0.006006493506493515,0.014123376623376704,0.0,0.0,True,10000,paired_sample_bootstrap
-hfm_deleak,full_revised,legacy_global,nll,0.023336756650091606,0.01281363102102529,0.034140771607844324,0.0,0.0,True,10000,paired_sample_bootstrap
-hfm_deleak,full_revised,legacy_global,brier_score,-0.0050213577491669825,-0.01000406399540528,8.615775671809222e-05,0.0544,1.0,False,10000,paired_sample_bootstrap
-hfm_existing_vs_hfm_deleak,text_only_deleak,text_only_existing,macro_f1,-0.00851845821847419,-0.011514759156961452,-0.005544566120640337,0.0,0.0,True,10000,paired_seed_bootstrap
-hfm_existing_vs_hfm_deleak,text_only_deleak,text_only_existing,weighted_f1,-0.00970000483489688,-0.012625905514444447,-0.006636784068338919,0.0,0.0,True,10000,paired_seed_bootstrap
-hfm_existing_vs_hfm_deleak,text_only_deleak,text_only_existing,accuracy,-0.01000563363577065,-0.013057062800213525,-0.006806692166281247,0.0,0.0,True,10000,paired_seed_bootstrap
-hfm_existing_vs_hfm_deleak,text_only_deleak,text_only_existing,nll,0.02427535653114319,0.011180448532104491,0.03530116081237793,0.0,0.0,True,10000,paired_seed_bootstrap
-hfm_existing_vs_hfm_deleak,text_only_deleak,text_only_existing,brier_score,0.01342612588280131,0.008972246167319476,0.017691788208273412,0.0,0.0,True,10000,paired_seed_bootstrap
-hfm_existing_vs_hfm_deleak,vision_only_deleak,vision_only_existing,macro_f1,0.0021354254075617307,-0.003583074623501403,0.006891392517423545,0.4496,1.0,False,10000,paired_seed_bootstrap
-hfm_existing_vs_hfm_deleak,vision_only_deleak,vision_only_existing,weighted_f1,0.0014153190597669286,-0.004099420603854575,0.006374441767465133,0.596,1.0,False,10000,paired_seed_bootstrap
-hfm_existing_vs_hfm_deleak,vision_only_deleak,vision_only_existing,accuracy,0.0022823637549664877,-0.0033038308723239984,0.00809353317914958,0.457,1.0,False,10000,paired_seed_bootstrap
-hfm_existing_vs_hfm_deleak,vision_only_deleak,vision_only_existing,nll,-0.06535450220108033,-0.22075437307357787,0.07617897987365722,0.3652,1.0,False,10000,paired_seed_bootstrap
-hfm_existing_vs_hfm_deleak,vision_only_deleak,vision_only_existing,brier_score,-0.019149817236875095,-0.0487390985972258,0.008730519084631749,0.2008,1.0,False,10000,paired_seed_bootstrap
-hfm_existing_vs_hfm_deleak,lora_concat_deleak,lora_concat_existing,macro_f1,-0.007028347538132506,-0.01043265067232375,-0.0033841179173973003,0.0,0.0,True,10000,paired_seed_bootstrap
-hfm_existing_vs_hfm_deleak,lora_concat_deleak,lora_concat_existing,weighted_f1,-0.007417184946114453,-0.011092117042584837,-0.0035094733158390623,0.0,0.0,True,10000,paired_seed_bootstrap
-hfm_existing_vs_hfm_deleak,lora_concat_deleak,lora_concat_existing,accuracy,-0.0071391508035344,-0.011107528316432469,-0.0029750785743936524,0.0,0.0,True,10000,paired_seed_bootstrap
-hfm_existing_vs_hfm_deleak,lora_concat_deleak,lora_concat_existing,nll,-0.014224156737327576,-0.04818010032176971,0.012443551421165466,0.3496,1.0,False,10000,paired_seed_bootstrap
-hfm_existing_vs_hfm_deleak,lora_concat_deleak,lora_concat_existing,brier_score,0.004169815413930239,-0.0018635942349254976,0.010769539378622767,0.2204,1.0,False,10000,paired_seed_bootstrap
-hfm_existing_vs_hfm_deleak,legacy_global_deleak,legacy_global_existing,macro_f1,-0.01113696638539501,-0.013853385850134648,-0.008934354296305024,0.0,0.0,True,10000,paired_seed_bootstrap
-hfm_existing_vs_hfm_deleak,legacy_global_deleak,legacy_global_existing,weighted_f1,-0.011898438835648627,-0.014486713229387483,-0.009535045934179465,0.0,0.0,True,10000,paired_seed_bootstrap
-hfm_existing_vs_hfm_deleak,legacy_global_deleak,legacy_global_existing,accuracy,-0.011986301369863006,-0.014496975627112607,-0.009423645703611467,0.0,0.0,True,10000,paired_seed_bootstrap
-hfm_existing_vs_hfm_deleak,legacy_global_deleak,legacy_global_existing,nll,-0.03855114579200745,-0.10776569247245789,0.02648504972457886,0.3152,1.0,False,10000,paired_seed_bootstrap
-hfm_existing_vs_hfm_deleak,legacy_global_deleak,legacy_global_existing,brier_score,0.004894941271306091,-0.008270707133365297,0.018060589675977477,0.5216,1.0,False,10000,paired_seed_bootstrap
-hfm_existing_vs_hfm_deleak,token_aux_deleak,token_aux_existing,macro_f1,-0.006891462210487376,-0.012076957281214874,-0.00028521434826056513,0.0214,1.0,False,10000,paired_seed_bootstrap
-hfm_existing_vs_hfm_deleak,token_aux_deleak,token_aux_existing,weighted_f1,-0.007568003875900109,-0.012595453911355903,-0.001391749348904514,0.0116,0.8583999999999999,False,10000,paired_seed_bootstrap
-hfm_existing_vs_hfm_deleak,token_aux_deleak,token_aux_existing,accuracy,-0.007544624325446248,-0.012507412678645547,-0.001652286070094311,0.0116,0.8583999999999999,False,10000,paired_seed_bootstrap
-hfm_existing_vs_hfm_deleak,token_aux_deleak,token_aux_existing,nll,-0.03020610809326172,-0.12206547856330871,0.05743524432182312,0.5162,1.0,False,10000,paired_seed_bootstrap
-hfm_existing_vs_hfm_deleak,token_aux_deleak,token_aux_existing,brier_score,0.004465828073964051,-0.011142684833194805,0.020074340981122908,0.5488,1.0,False,10000,paired_seed_bootstrap
-hfm_existing_vs_hfm_deleak,full_revised_deleak,full_revised_existing,macro_f1,-0.006529838599939342,-0.015785606318038693,0.0012785437437494052,0.1246,1.0,False,10000,paired_seed_bootstrap
-hfm_existing_vs_hfm_deleak,full_revised_deleak,full_revised_existing,weighted_f1,-0.00710518168763592,-0.01657510245959872,0.0008264405011171982,0.0924,1.0,False,10000,paired_seed_bootstrap
-hfm_existing_vs_hfm_deleak,full_revised_deleak,full_revised_existing,accuracy,-0.006985708355571374,-0.016790829033979725,0.001214567396074262,0.1394,1.0,False,10000,paired_seed_bootstrap
-hfm_existing_vs_hfm_deleak,full_revised_deleak,full_revised_existing,nll,0.03718435764312744,-0.016977697610855103,0.09439651370048523,0.2224,1.0,False,10000,paired_seed_bootstrap
-hfm_existing_vs_hfm_deleak,full_revised_deleak,full_revised_existing,brier_score,0.015191749813368394,0.0038520340065806733,0.02374341286765353,0.0104,0.7799999999999999,False,10000,paired_seed_bootstrap