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

ravel_revision_results/aggregate_results/significance_tests.csv.pre_forced_rerun.bak

@@ -1,116 +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_f1,0.03999523420088935,0.01807806008213251,0.06238631838558387,0.0004,0.033600000000000005,True,10000,paired_sample_bootstrap
-mvsa_multiple,full_revised,frozen_concat,weighted_f1,0.02529468559833503,0.010158961501497064,0.04107928288278337,0.0018,0.1386,False,10000,paired_sample_bootstrap
-mvsa_multiple,full_revised,frozen_concat,accuracy,-0.0014705882352941124,-0.01588235294117646,0.013235294117647012,0.8808,1.0,False,10000,paired_sample_bootstrap
-mvsa_multiple,full_revised,frozen_concat,nll,0.06368609414550819,0.04311934796481261,0.08421108006125085,0.0,0.0,True,10000,paired_sample_bootstrap
-mvsa_multiple,full_revised,frozen_concat,brier_score,0.031341537546752396,0.0182035058677146,0.04446463744580618,0.0,0.0,True,10000,paired_sample_bootstrap
-mvsa_multiple,full_revised,lora_concat,macro_f1,0.007603055297160655,-0.022123199578244098,0.03712116129681369,0.612,1.0,False,10000,paired_sample_bootstrap
-mvsa_multiple,full_revised,lora_concat,weighted_f1,0.009818394809140485,-0.00841373850807476,0.02826435004375558,0.2948,1.0,False,10000,paired_sample_bootstrap
-mvsa_multiple,full_revised,lora_concat,accuracy,0.011176470588235343,-0.007647058823529343,0.030000000000000027,0.256,1.0,False,10000,paired_sample_bootstrap
-mvsa_multiple,full_revised,lora_concat,nll,-0.11045132945606684,-0.14923826645737553,-0.07174961882453337,0.0,0.0,True,10000,paired_sample_bootstrap
-mvsa_multiple,full_revised,lora_concat,brier_score,-0.031739896156548264,-0.05342483127620054,-0.010200320992291578,0.004,0.296,False,10000,paired_sample_bootstrap
-mvsa_multiple,full_revised,token_coattn,macro_f1,-0.00039691996875323987,-0.008510201335981741,0.007478668858989839,0.915,1.0,False,10000,paired_sample_bootstrap
-mvsa_multiple,full_revised,token_coattn,weighted_f1,-0.003143226493161566,-0.008901840887073848,0.0025099325893607935,0.2736,1.0,False,10000,paired_sample_bootstrap
-mvsa_multiple,full_revised,token_coattn,accuracy,-0.0065882352941176725,-0.012470588235294122,-0.0009411764705882231,0.0266,1.0,False,10000,paired_sample_bootstrap
-mvsa_multiple,full_revised,token_coattn,nll,0.023933011885805988,0.01578397023299669,0.03201458134346059,0.0,0.0,True,10000,paired_sample_bootstrap
-mvsa_multiple,full_revised,token_coattn,brier_score,0.01069654520288188,0.005685978384813306,0.015657356432218356,0.0,0.0,True,10000,paired_sample_bootstrap
-mvsa_multiple,full_revised,token_aux,macro_f1,0.009693260177997765,0.0006784611716418367,0.018809592496341385,0.0344,1.0,False,10000,paired_sample_bootstrap
-mvsa_multiple,full_revised,token_aux,weighted_f1,-0.0004943054966149996,-0.006758560899787542,0.00573782955508211,0.8984,1.0,False,10000,paired_sample_bootstrap
-mvsa_multiple,full_revised,token_aux,accuracy,-0.010705882352941232,-0.017058823529411793,-0.004470588235294115,0.0008,0.064,False,10000,paired_sample_bootstrap
-mvsa_multiple,full_revised,token_aux,nll,0.04933955327011874,0.03974235644495317,0.058973852607057196,0.0,0.0,True,10000,paired_sample_bootstrap
-mvsa_multiple,full_revised,token_aux,brier_score,0.02414248609476527,0.0182785733369839,0.02999257428520541,0.0,0.0,True,10000,paired_sample_bootstrap
-mvsa_multiple,full_revised,param_mlp,macro_f1,-0.0011715312833310287,-0.009448066173733578,0.007266314952773184,0.7962,1.0,False,10000,paired_sample_bootstrap
-mvsa_multiple,full_revised,param_mlp,weighted_f1,0.0005436484986727219,-0.004819409510548561,0.006216048783641917,0.833,1.0,False,10000,paired_sample_bootstrap
-mvsa_multiple,full_revised,param_mlp,accuracy,-0.003176470588235336,-0.008588235294117674,0.0024705882352941133,0.2832,1.0,False,10000,paired_sample_bootstrap
-mvsa_multiple,full_revised,param_mlp,nll,-0.0013916211241469245,-0.009430982504673422,0.0063846780632857885,0.7312,1.0,False,10000,paired_sample_bootstrap
-mvsa_multiple,full_revised,param_mlp,brier_score,0.0022488118661867507,-0.0024638465278841643,0.006912212685945383,0.3574,1.0,False,10000,paired_sample_bootstrap
-mvsa_multiple,full_revised,legacy_global,macro_f1,-0.008197320614301229,-0.020304861662293585,0.0037180138254440955,0.1834,1.0,False,10000,paired_sample_bootstrap
-mvsa_multiple,full_revised,legacy_global,weighted_f1,-0.01491151964671844,-0.022879717944426635,-0.00712474756807581,0.0002,0.017,True,10000,paired_sample_bootstrap
-mvsa_multiple,full_revised,legacy_global,accuracy,-0.02400000000000002,-0.03188235294117647,-0.01635294117647057,0.0,0.0,True,10000,paired_sample_bootstrap
-mvsa_multiple,full_revised,legacy_global,nll,0.035368468966724964,0.019066361789295022,0.051458192246184566,0.0,0.0,True,10000,paired_sample_bootstrap
-mvsa_multiple,full_revised,legacy_global,brier_score,0.029564178148612563,0.020918170337892047,0.03797502860273434,0.0,0.0,True,10000,paired_sample_bootstrap
-hfm_existing,full_revised,frozen_concat,macro_f1,-0.0013482943197913322,-0.01266148874810325,0.009934410004901325,0.8114,1.0,False,10000,paired_sample_bootstrap
-hfm_existing,full_revised,frozen_concat,weighted_f1,-0.0010714064060872719,-0.012035997233165209,0.009859111032810456,0.8498,1.0,False,10000,paired_sample_bootstrap
-hfm_existing,full_revised,frozen_concat,accuracy,-0.0008302200083022404,-0.01162308011623081,0.00996264009962644,0.9058,1.0,False,10000,paired_sample_bootstrap
-hfm_existing,full_revised,frozen_concat,nll,0.020770294111867815,-0.0035574404471490867,0.0454959548159137,0.0956,1.0,False,10000,paired_sample_bootstrap
-hfm_existing,full_revised,frozen_concat,brier_score,0.005778557120701855,-0.008035502661777525,0.019880427265541362,0.4056,1.0,False,10000,paired_sample_bootstrap
-hfm_existing,full_revised,lora_concat,macro_f1,0.0008211421235955196,-0.009212891077211658,0.010576370522827812,0.8652,1.0,False,10000,paired_sample_bootstrap
-hfm_existing,full_revised,lora_concat,weighted_f1,0.0012464339191313734,-0.008608962522889032,0.010760010290822552,0.7976,1.0,False,10000,paired_sample_bootstrap
-hfm_existing,full_revised,lora_concat,accuracy,0.0016604400166043698,-0.00830220008302196,0.011207970112079746,0.7744,1.0,False,10000,paired_sample_bootstrap
-hfm_existing,full_revised,lora_concat,nll,-0.004222223291019234,-0.025183786783051068,0.01597890722488305,0.6704,1.0,False,10000,paired_sample_bootstrap
-hfm_existing,full_revised,lora_concat,brier_score,-0.003438069595770893,-0.015226423758087098,0.008200942458823603,0.5598,1.0,False,10000,paired_sample_bootstrap
-hfm_existing,full_revised,token_coattn,macro_f1,0.005228584500790667,0.001525290996856693,0.00895615085231859,0.0068,0.49639999999999995,False,10000,paired_sample_bootstrap
-hfm_existing,full_revised,token_coattn,weighted_f1,0.004983325620118939,0.0013559889819211024,0.008622440488714711,0.0084,0.6048,False,10000,paired_sample_bootstrap
-hfm_existing,full_revised,token_coattn,accuracy,0.0048982980489830075,0.001245330012453305,0.00855126608551271,0.0112,0.784,False,10000,paired_sample_bootstrap
-hfm_existing,full_revised,token_coattn,nll,-0.07311031031023468,-0.08420724814448448,-0.06241486828121154,0.0,0.0,True,10000,paired_sample_bootstrap
-hfm_existing,full_revised,token_coattn,brier_score,-0.022236200346752166,-0.02709839427177021,-0.017307720113695628,0.0,0.0,True,10000,paired_sample_bootstrap
-hfm_existing,full_revised,token_aux,macro_f1,0.0003733398243205288,-0.0034843332139675638,0.0043028678146032045,0.8634,1.0,False,10000,paired_sample_bootstrap
-hfm_existing,full_revised,token_aux,weighted_f1,0.0003920768327438928,-0.0033959336614855784,0.004222477076485342,0.854,1.0,False,10000,paired_sample_bootstrap
-hfm_existing,full_revised,token_aux,accuracy,0.0004151100041511757,-0.0034039020340390636,0.004234122042341304,0.8622,1.0,False,10000,paired_sample_bootstrap
-hfm_existing,full_revised,token_aux,nll,-0.05746015868173315,-0.06962724052323566,-0.04555886683545573,0.0,0.0,True,10000,paired_sample_bootstrap
-hfm_existing,full_revised,token_aux,brier_score,-0.010603811336075686,-0.01602522450086917,-0.005296795501585304,0.0,0.0,True,10000,paired_sample_bootstrap
-hfm_existing,full_revised,param_mlp,macro_f1,0.0008167545096154916,-0.0029878183238360194,0.004543096849847224,0.6864,1.0,False,10000,paired_sample_bootstrap
-hfm_existing,full_revised,param_mlp,weighted_f1,0.0009089338009082848,-0.002812391764818281,0.004550263322136627,0.6398,1.0,False,10000,paired_sample_bootstrap
-hfm_existing,full_revised,param_mlp,accuracy,0.0009962640099626663,-0.002739726027397249,0.004649232046492258,0.6248,1.0,False,10000,paired_sample_bootstrap
-hfm_existing,full_revised,param_mlp,nll,-0.005347099657774912,-0.013521644721330762,0.002887389545044435,0.2088,1.0,False,10000,paired_sample_bootstrap
-hfm_existing,full_revised,param_mlp,brier_score,-0.0018800210718132315,-0.006209053798479901,0.00247692855045205,0.412,1.0,False,10000,paired_sample_bootstrap
-hfm_existing,full_revised,legacy_global,macro_f1,0.005339631274256518,0.0007817238504592399,0.009858866464108162,0.0222,1.0,False,10000,paired_sample_bootstrap
-hfm_existing,full_revised,legacy_global,weighted_f1,0.005122297927253827,0.0006517339233845482,0.009529116734298973,0.0254,1.0,False,10000,paired_sample_bootstrap
-hfm_existing,full_revised,legacy_global,accuracy,0.005064342050643433,0.0005811540058114906,0.009464508094645163,0.0282,1.0,False,10000,paired_sample_bootstrap
-hfm_existing,full_revised,legacy_global,nll,-0.052398749131388256,-0.06506084322728277,-0.039921398898073994,0.0,0.0,True,10000,paired_sample_bootstrap
-hfm_existing,full_revised,legacy_global,brier_score,-0.015318166291229257,-0.02113222513992914,-0.009549155470324033,0.0,0.0,True,10000,paired_sample_bootstrap
-hfm_deleak,full_revised,frozen_concat,macro_f1,-0.017176063679798736,-0.027472293104847355,-0.006999289230408686,0.0004,0.033600000000000005,True,10000,paired_sample_bootstrap
-hfm_deleak,full_revised,frozen_concat,weighted_f1,-0.01717460424160544,-0.027279957123462567,-0.007104096733017177,0.0004,0.033600000000000005,True,10000,paired_sample_bootstrap
-hfm_deleak,full_revised,frozen_concat,accuracy,-0.0174512987012988,-0.02759740259740262,-0.00730519480519487,0.0004,0.033600000000000005,True,10000,paired_sample_bootstrap
-hfm_deleak,full_revised,frozen_concat,nll,0.008455372866876754,-0.008523291885726878,0.02508795644847988,0.3168,1.0,False,10000,paired_sample_bootstrap
-hfm_deleak,full_revised,frozen_concat,brier_score,0.013225777168924452,0.0022496862087007766,0.0240425695310415,0.0188,1.0,False,10000,paired_sample_bootstrap
-hfm_deleak,full_revised,lora_concat,macro_f1,-0.01715847350653621,-0.027194363495448792,-0.006628296013829558,0.0018,0.1386,False,10000,paired_sample_bootstrap
-hfm_deleak,full_revised,lora_concat,weighted_f1,-0.017354435412999192,-0.027218323863762016,-0.006925912455059649,0.0012,0.0948,False,10000,paired_sample_bootstrap
-hfm_deleak,full_revised,lora_concat,accuracy,-0.017857142857142905,-0.02759740259740262,-0.00730519480519487,0.0012,0.0948,False,10000,paired_sample_bootstrap
-hfm_deleak,full_revised,lora_concat,nll,0.00019864578121892018,-0.018685353753642896,0.0181502392702822,0.9834,1.0,False,10000,paired_sample_bootstrap
-hfm_deleak,full_revised,lora_concat,brier_score,0.01128206490039585,-0.00012275084780543884,0.02234976653237523,0.053,1.0,False,10000,paired_sample_bootstrap
-hfm_deleak,full_revised,token_coattn,macro_f1,0.0038952748731079234,0.0005458303010823341,0.0072865720003905616,0.0214,1.0,False,10000,paired_sample_bootstrap
-hfm_deleak,full_revised,token_coattn,weighted_f1,0.0039060240305515137,0.0005989253246272946,0.007246278786962375,0.0194,1.0,False,10000,paired_sample_bootstrap
-hfm_deleak,full_revised,token_coattn,accuracy,0.003977272727272663,0.0006493506493506773,0.00730519480519487,0.0186,1.0,False,10000,paired_sample_bootstrap
-hfm_deleak,full_revised,token_coattn,nll,-0.03577200444611678,-0.04719104736588135,-0.02417965426528159,0.0,0.0,True,10000,paired_sample_bootstrap
-hfm_deleak,full_revised,token_coattn,brier_score,-0.01026585100725555,-0.014913880703189917,-0.005566929903467646,0.0,0.0,True,10000,paired_sample_bootstrap
-hfm_deleak,full_revised,token_aux,macro_f1,0.0007642318431851924,-0.002241538377770705,0.0037416374275880235,0.607,1.0,False,10000,paired_sample_bootstrap
-hfm_deleak,full_revised,token_aux,weighted_f1,0.0008719085287203221,-0.0020962148218508334,0.0038053481322703653,0.555,1.0,False,10000,paired_sample_bootstrap
-hfm_deleak,full_revised,token_aux,accuracy,0.0009740259740259605,-0.0020292207792207417,0.003896103896103953,0.528,1.0,False,10000,paired_sample_bootstrap
-hfm_deleak,full_revised,token_aux,nll,0.009930314632173254,0.0033525630511430106,0.016709084736168313,0.0032,0.24000000000000002,False,10000,paired_sample_bootstrap
-hfm_deleak,full_revised,token_aux,brier_score,0.00012211040332860135,-0.0032225292704715766,0.0035088068963582335,0.943,1.0,False,10000,paired_sample_bootstrap
-hfm_deleak,full_revised,param_mlp,macro_f1,-8.534466641851868e-05,-0.00439763737109235,0.004176279231341202,0.9658,1.0,False,10000,paired_sample_bootstrap
-hfm_deleak,full_revised,param_mlp,weighted_f1,-0.00012462133896096184,-0.004368865842557151,0.004076444549943008,0.949,1.0,False,10000,paired_sample_bootstrap
-hfm_deleak,full_revised,param_mlp,accuracy,-0.00016233766233764158,-0.0043851461038962045,0.0040584415584414835,0.9486,1.0,False,10000,paired_sample_bootstrap
-hfm_deleak,full_revised,param_mlp,nll,-0.011498872806270488,-0.024551665485704605,0.0015626717920414783,0.0884,1.0,False,10000,paired_sample_bootstrap
-hfm_deleak,full_revised,param_mlp,brier_score,-0.0014839572355782593,-0.007286333174624766,0.004316883111331564,0.6218,1.0,False,10000,paired_sample_bootstrap
-hfm_deleak,full_revised,legacy_global,macro_f1,0.009984144944578999,0.005934684957892753,0.014161060147400342,0.0,0.0,True,10000,paired_sample_bootstrap
-hfm_deleak,full_revised,legacy_global,weighted_f1,0.009943969633812721,0.005948802307684242,0.014059378823923661,0.0,0.0,True,10000,paired_sample_bootstrap
-hfm_deleak,full_revised,legacy_global,accuracy,0.010064935064934999,0.006087662337662336,0.014204545454545414,0.0,0.0,True,10000,paired_sample_bootstrap
-hfm_deleak,full_revised,legacy_global,nll,0.023336756650091606,0.012322325525977163,0.03406293691585405,0.0,0.0,True,10000,paired_sample_bootstrap
-hfm_deleak,full_revised,legacy_global,brier_score,-0.0050213577491669825,-0.01026151929851382,6.009164926531684e-05,0.0524,1.0,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,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,-0.001391749348904514,0.0116,0.8004,False,10000,paired_seed_bootstrap
-hfm_existing_vs_hfm_deleak,token_aux_deleak,token_aux_existing,accuracy,-0.007544624325446248,-0.012507412678645547,-0.001652286070094311,0.0116,0.8004,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,0.015191749813368394,0.0038520340065806733,0.02374341286765353,0.0104,0.7384,False,10000,paired_seed_bootstrap