Complete standalone final deliverable and unaligned Q2 results

This commit is contained in:
2026-09-25 22:22:37 +08:00
parent c6b018e5d0
commit adc9c2064b
267 changed files with 15479 additions and 7976 deletions
@@ -0,0 +1,13 @@
model,n,accuracy,macro_f1,negative_support,neutral_support,positive_support,negative_recall,middle_recall,positive_recall,regression_mae,regression_rmse,pearson,brier,classification_nll,ece_15,interval_90_coverage,interval_90_mean_width,selection_nll,temperature,description,predictive_variance_mean_uncalibrated,within_trajectory_variance_mean,between_trajectory_variance_mean,predictive_mean_mean_calibrated,predictive_variance_mean_calibrated,validation_selection_loss,rho_imp,lambda_u,lambda_gap,lambda_span,lambda_group,group_temperature
C0,728,0.5906593406593407,0.5573246854806906,206,184,338,0.5970873786407767,0.34782608695652173,0.7189349112426036,0.7267872095108032,0.9493674330569902,0.5186371207237244,0.5240320990297133,0.8831461776473413,0.04826531354954992,0.9354395604395604,3.5201075077056885,0.9197877716698537,2.320690790447983,observed mean/std + masks + maximum gap; logistic/ridge,,,,,,,,,,,,
C1,728,0.5879120879120879,0.47389937106918234,206,184,338,0.6262135922330098,0.06521739130434782,0.849112426035503,0.7446202039718628,0.9822674244990333,0.5362412333488464,0.527031031283926,0.8880350589752197,0.060032890352246515,0.9148351648351648,2.7002923488616943,2.818410634994507,0.7559785314090598,"masked BiGRU; no posterior imputation, explicit reliability or source gate",0.767420768737793,0.767420768737793,0.0,0.2549660801887512,0.705826461315155,2.818410634994507,0.5,0.05,0.05,0.05,nan,nan
C2,728,0.5961538461538461,0.450273379924267,206,184,338,0.6699029126213593,0.005434782608695652,0.8727810650887574,0.698158860206604,0.9260472748411018,0.5808078050613403,0.5106602366936009,0.8622351288795471,0.06248928942195664,0.9065934065934066,2.5688624382019043,2.7997119426727295,0.8488490623779881,exact Gaussian posterior mean; no joint trajectory integral,0.6898056864738464,0.6898056864738464,0.0,0.21209104359149933,0.6582686305046082,2.7997119426727295,0.5,0.05,0.05,0.05,nan,nan
C3,728,0.5906593406593407,0.443346825657295,206,184,338,0.6699029126213593,0.0,0.863905325443787,0.7317898869514465,0.985695966827773,0.5456575155258179,0.5164441425522118,0.8702284693717957,0.06148201186250855,0.9065934065934066,2.4972548484802246,2.811898708343506,1.0120878694650972,joint trajectory integral plus final reliability/content fusion gate,0.633382260799408,0.6333822011947632,7.366534049424445e-08,0.23270586133003235,0.6362141370773315,2.811903953552246,0.5,0.0,0.0,0.0,nan,nan
C4,728,0.554945054945055,0.4536351679548698,206,184,338,0.46601941747572817,0.09782608695652174,0.8579881656804734,0.7454220056533813,1.0156130863371253,0.503315806388855,0.5250710164495501,0.8871082663536072,0.07315124743259872,0.8791208791208791,2.4709346294403076,2.848031759262085,1.1013056928889957,C3 plus bounded cross-time source attention and null source,0.6384363770484924,0.6384357810020447,5.842408654643805e-07,0.273845911026001,0.6572040319442749,2.8480465412139893,0.7,0.05,0.05,0.05,nan,nan
C5,728,0.5824175824175825,0.4401015447285379,206,184,338,0.6601941747572816,0.005434782608695652,0.849112426035503,0.7787972092628479,1.024799634376836,0.5123178958892822,0.5304346310715194,0.8944377899169922,0.030563883729033414,0.8997252747252747,2.767879009246826,2.851557731628418,1.209048884859704,C4 plus reliability-modulated BiGRU update,0.7191231846809387,0.7191231846809387,3.2177736031258064e-09,0.14806683361530304,0.7649285197257996,2.851555109024048,0.3,0.05,0.05,0.05,nan,nan
C6,728,0.6085164835164835,0.518781225964892,206,184,338,0.6796116504854369,0.125,0.8284023668639053,0.6846672296524048,0.9208069125796768,0.6101511716842651,0.4977339610947482,0.8427405953407288,0.039509518706536545,0.8873626373626373,2.391038656234741,2.7836689949035645,1.122980387832455,C5 plus optional rank-4 CP residual,0.5537752509117126,0.5537748336791992,4.292722337595478e-07,0.20950497686862946,0.5816965699195862,2.78372859954834,0.3,0.05,0.05,0.05,nan,nan
C6_no_distance,728,0.6071428571428571,0.4720788453840183,206,184,338,0.7038834951456311,0.02717391304347826,0.863905325443787,0.7117781043052673,0.9322639795095579,0.6074535250663757,0.5082462727230644,0.8651163578033447,0.05943080136081674,0.8983516483516484,2.3641908168792725,2.8279078006744385,1.3842246499425326,C6 with uncertainty retained but both distance/span reliability penalties fixed to zero,0.5044943690299988,0.5044927000999451,1.6798628621472744e-06,0.1626720279455185,0.5792984366416931,2.8279669284820557,0.5,0.0,0.0,0.0,nan,nan
C6_no_reconstruction,728,0.5837912087912088,0.48325805552048157,206,184,338,0.6359223300970874,0.09239130434782608,0.8195266272189349,0.709170937538147,0.9543444540035635,0.5635251402854919,0.5161844703592794,0.8740492463111877,0.06073655040709527,0.8928571428571429,2.3883748054504395,2.825748920440674,1.141447589690795,C6 trained without the auxiliary hidden-feature reconstruction loss,0.5810816287994385,0.5810815691947937,4.87382330049968e-08,0.20374375581741333,0.6135826706886292,2.8257386684417725,0.3,0.05,0.05,0.05,nan,nan
C6_pointmask,728,0.5810439560439561,0.5025832785659426,206,184,338,0.5436893203883495,0.15760869565217392,0.834319526627219,0.679211437702179,0.9175777170595291,0.5958787798881531,0.5092818643196679,0.8619159460067749,0.05020872241520621,0.8901098901098901,2.4665889739990234,2.818068265914917,1.1026513503354962,C6 trained with independent point masking instead of contiguous spans,0.6072730422019958,0.6072730422019958,3.120251079735681e-08,0.24521614611148834,0.633151650428772,2.8180501461029053,0.3,0.05,0.05,0.05,nan,nan
C7_distill,728,0.592032967032967,0.4870960207460408,206,184,338,0.6650485436893204,0.07608695652173914,0.8284023668639053,0.7024686336517334,0.9442218762916826,0.5752816796302795,0.5166531638152239,0.8771014213562012,0.03309895266052133,0.8818681318681318,2.485671043395996,2.828686475753784,1.2328404661886574,C6 plus entropy/retention-weighted teacher distillation only,0.5969328880310059,0.5969326496124268,2.2941341626392386e-07,0.1737147569656372,0.6470145583152771,2.828679084777832,0.5,0.05,0.05,0.05,nan,nan
C7_group,728,0.6002747252747253,0.4509009833805456,206,184,338,0.7038834951456311,0.0,0.863905325443787,0.7323286533355713,0.9355743977553851,0.6008110046386719,0.5087103578214832,0.8661918044090271,0.06044913705561188,0.9024725274725275,2.5981743335723877,2.8037712574005127,1.0417083718358262,C6 plus smooth worst-group risk only,0.6530460119247437,0.6530460119247437,5.441940942318979e-08,0.14995495975017548,0.6626315116882324,2.8037784099578857,0.5,0.0,0.0,0.0,0.1,0.1
1 model n accuracy macro_f1 negative_support neutral_support positive_support negative_recall middle_recall positive_recall regression_mae regression_rmse pearson brier classification_nll ece_15 interval_90_coverage interval_90_mean_width selection_nll temperature description predictive_variance_mean_uncalibrated within_trajectory_variance_mean between_trajectory_variance_mean predictive_mean_mean_calibrated predictive_variance_mean_calibrated validation_selection_loss rho_imp lambda_u lambda_gap lambda_span lambda_group group_temperature
2 C0 728 0.5906593406593407 0.5573246854806906 206 184 338 0.5970873786407767 0.34782608695652173 0.7189349112426036 0.7267872095108032 0.9493674330569902 0.5186371207237244 0.5240320990297133 0.8831461776473413 0.04826531354954992 0.9354395604395604 3.5201075077056885 0.9197877716698537 2.320690790447983 observed mean/std + masks + maximum gap; logistic/ridge
3 C1 728 0.5879120879120879 0.47389937106918234 206 184 338 0.6262135922330098 0.06521739130434782 0.849112426035503 0.7446202039718628 0.9822674244990333 0.5362412333488464 0.527031031283926 0.8880350589752197 0.060032890352246515 0.9148351648351648 2.7002923488616943 2.818410634994507 0.7559785314090598 masked BiGRU; no posterior imputation, explicit reliability or source gate 0.767420768737793 0.767420768737793 0.0 0.2549660801887512 0.705826461315155 2.818410634994507 0.5 0.05 0.05 0.05 nan nan
4 C2 728 0.5961538461538461 0.450273379924267 206 184 338 0.6699029126213593 0.005434782608695652 0.8727810650887574 0.698158860206604 0.9260472748411018 0.5808078050613403 0.5106602366936009 0.8622351288795471 0.06248928942195664 0.9065934065934066 2.5688624382019043 2.7997119426727295 0.8488490623779881 exact Gaussian posterior mean; no joint trajectory integral 0.6898056864738464 0.6898056864738464 0.0 0.21209104359149933 0.6582686305046082 2.7997119426727295 0.5 0.05 0.05 0.05 nan nan
5 C3 728 0.5906593406593407 0.443346825657295 206 184 338 0.6699029126213593 0.0 0.863905325443787 0.7317898869514465 0.985695966827773 0.5456575155258179 0.5164441425522118 0.8702284693717957 0.06148201186250855 0.9065934065934066 2.4972548484802246 2.811898708343506 1.0120878694650972 joint trajectory integral plus final reliability/content fusion gate 0.633382260799408 0.6333822011947632 7.366534049424445e-08 0.23270586133003235 0.6362141370773315 2.811903953552246 0.5 0.0 0.0 0.0 nan nan
6 C4 728 0.554945054945055 0.4536351679548698 206 184 338 0.46601941747572817 0.09782608695652174 0.8579881656804734 0.7454220056533813 1.0156130863371253 0.503315806388855 0.5250710164495501 0.8871082663536072 0.07315124743259872 0.8791208791208791 2.4709346294403076 2.848031759262085 1.1013056928889957 C3 plus bounded cross-time source attention and null source 0.6384363770484924 0.6384357810020447 5.842408654643805e-07 0.273845911026001 0.6572040319442749 2.8480465412139893 0.7 0.05 0.05 0.05 nan nan
7 C5 728 0.5824175824175825 0.4401015447285379 206 184 338 0.6601941747572816 0.005434782608695652 0.849112426035503 0.7787972092628479 1.024799634376836 0.5123178958892822 0.5304346310715194 0.8944377899169922 0.030563883729033414 0.8997252747252747 2.767879009246826 2.851557731628418 1.209048884859704 C4 plus reliability-modulated BiGRU update 0.7191231846809387 0.7191231846809387 3.2177736031258064e-09 0.14806683361530304 0.7649285197257996 2.851555109024048 0.3 0.05 0.05 0.05 nan nan
8 C6 728 0.6085164835164835 0.518781225964892 206 184 338 0.6796116504854369 0.125 0.8284023668639053 0.6846672296524048 0.9208069125796768 0.6101511716842651 0.4977339610947482 0.8427405953407288 0.039509518706536545 0.8873626373626373 2.391038656234741 2.7836689949035645 1.122980387832455 C5 plus optional rank-4 CP residual 0.5537752509117126 0.5537748336791992 4.292722337595478e-07 0.20950497686862946 0.5816965699195862 2.78372859954834 0.3 0.05 0.05 0.05 nan nan
9 C6_no_distance 728 0.6071428571428571 0.4720788453840183 206 184 338 0.7038834951456311 0.02717391304347826 0.863905325443787 0.7117781043052673 0.9322639795095579 0.6074535250663757 0.5082462727230644 0.8651163578033447 0.05943080136081674 0.8983516483516484 2.3641908168792725 2.8279078006744385 1.3842246499425326 C6 with uncertainty retained but both distance/span reliability penalties fixed to zero 0.5044943690299988 0.5044927000999451 1.6798628621472744e-06 0.1626720279455185 0.5792984366416931 2.8279669284820557 0.5 0.0 0.0 0.0 nan nan
10 C6_no_reconstruction 728 0.5837912087912088 0.48325805552048157 206 184 338 0.6359223300970874 0.09239130434782608 0.8195266272189349 0.709170937538147 0.9543444540035635 0.5635251402854919 0.5161844703592794 0.8740492463111877 0.06073655040709527 0.8928571428571429 2.3883748054504395 2.825748920440674 1.141447589690795 C6 trained without the auxiliary hidden-feature reconstruction loss 0.5810816287994385 0.5810815691947937 4.87382330049968e-08 0.20374375581741333 0.6135826706886292 2.8257386684417725 0.3 0.05 0.05 0.05 nan nan
11 C6_pointmask 728 0.5810439560439561 0.5025832785659426 206 184 338 0.5436893203883495 0.15760869565217392 0.834319526627219 0.679211437702179 0.9175777170595291 0.5958787798881531 0.5092818643196679 0.8619159460067749 0.05020872241520621 0.8901098901098901 2.4665889739990234 2.818068265914917 1.1026513503354962 C6 trained with independent point masking instead of contiguous spans 0.6072730422019958 0.6072730422019958 3.120251079735681e-08 0.24521614611148834 0.633151650428772 2.8180501461029053 0.3 0.05 0.05 0.05 nan nan
12 C7_distill 728 0.592032967032967 0.4870960207460408 206 184 338 0.6650485436893204 0.07608695652173914 0.8284023668639053 0.7024686336517334 0.9442218762916826 0.5752816796302795 0.5166531638152239 0.8771014213562012 0.03309895266052133 0.8818681318681318 2.485671043395996 2.828686475753784 1.2328404661886574 C6 plus entropy/retention-weighted teacher distillation only 0.5969328880310059 0.5969326496124268 2.2941341626392386e-07 0.1737147569656372 0.6470145583152771 2.828679084777832 0.5 0.05 0.05 0.05 nan nan
13 C7_group 728 0.6002747252747253 0.4509009833805456 206 184 338 0.7038834951456311 0.0 0.863905325443787 0.7323286533355713 0.9355743977553851 0.6008110046386719 0.5087103578214832 0.8661918044090271 0.06044913705561188 0.9024725274725275 2.5981743335723877 2.8037712574005127 1.0417083718358262 C6 plus smooth worst-group risk only 0.6530460119247437 0.6530460119247437 5.441940942318979e-08 0.14995495975017548 0.6626315116882324 2.8037784099578857 0.5 0.0 0.0 0.0 0.1 0.1
@@ -0,0 +1,8 @@
metric,estimate,ci_2_5,ci_97_5,replicates,unit
accuracy,0.6717585232291114,0.6337437582438289,0.7083999622974622,300,source video group
macro_f1,0.5478055347952107,0.5108259770753341,0.5872370160716736,300,source video group
mae,0.7108274400234222,0.6579044133424758,0.7620256423950195,300,source video group
rmse,0.9714674680679505,0.8731931045635853,1.057953415758872,300,source video group
pearson,0.6378498673439026,0.5640437543392182,0.7087083235383034,300,source video group
interval_90_coverage,0.8956505821036529,0.8708135115106022,0.9182254293066758,300,source video group
interval_90_mean_width,2.486721992492676,2.4194449901580812,2.5640856266021728,300,source video group
1 metric estimate ci_2_5 ci_97_5 replicates unit
2 accuracy 0.6717585232291114 0.6337437582438289 0.7083999622974622 300 source video group
3 macro_f1 0.5478055347952107 0.5108259770753341 0.5872370160716736 300 source video group
4 mae 0.7108274400234222 0.6579044133424758 0.7620256423950195 300 source video group
5 rmse 0.9714674680679505 0.8731931045635853 1.057953415758872 300 source video group
6 pearson 0.6378498673439026 0.5640437543392182 0.7087083235383034 300 source video group
7 interval_90_coverage 0.8956505821036529 0.8708135115106022 0.9182254293066758 300 source video group
8 interval_90_mean_width 2.486721992492676 2.4194449901580812 2.5640856266021728 300 source video group
@@ -0,0 +1,6 @@
model,candidate,lambda_group,group_temperature,selected_reliability,inner_selection_nll,selected,selection_split
C7_group,C7_group_lambda0.05_tau0.10,0.05,0.1,"(0.3, 0.05, 0.05, 0.05)",2.9074912071228027,False,reliability_validation
C7_group,C7_group_lambda0.10_tau0.05,0.1,0.05,"(0.5, 0.1, 0.0, 0.0)",2.937703788280487,False,reliability_validation
C7_group,C7_group_lambda0.10_tau0.10,0.1,0.1,"(0.5, 0.0, 0.0, 0.0)",2.887659251689911,True,reliability_validation
C7_group,C7_group_lambda0.10_tau0.20,0.1,0.2,"(0.3, 0.05, 0.05, 0.05)",2.903527617454529,False,reliability_validation
C7_group,C7_group_lambda0.20_tau0.10,0.2,0.1,"(0.3, 0.05, 0.05, 0.05)",2.934680759906769,False,reliability_validation
1 model candidate lambda_group group_temperature selected_reliability inner_selection_nll selected selection_split
2 C7_group C7_group_lambda0.05_tau0.10 0.05 0.1 (0.3, 0.05, 0.05, 0.05) 2.9074912071228027 False reliability_validation
3 C7_group C7_group_lambda0.10_tau0.05 0.1 0.05 (0.5, 0.1, 0.0, 0.0) 2.937703788280487 False reliability_validation
4 C7_group C7_group_lambda0.10_tau0.10 0.1 0.1 (0.5, 0.0, 0.0, 0.0) 2.887659251689911 True reliability_validation
5 C7_group C7_group_lambda0.10_tau0.20 0.1 0.2 (0.3, 0.05, 0.05, 0.05) 2.903527617454529 False reliability_validation
6 C7_group C7_group_lambda0.20_tau0.10 0.2 0.1 (0.3, 0.05, 0.05, 0.05) 2.934680759906769 False reliability_validation
@@ -0,0 +1,70 @@
model,rho_imp,lambda_u,lambda_gap,lambda_span,inner_selection_nll,scenario_selection_nll,selected,selection_split,note,group_lambda,group_temperature,risk_candidate_selected,candidate
teacher,0.5,0.0,0.0,0.0,2.8551357984542847,"{""0.0/natural"": 2.8325021266937256, ""0.3/single"": 2.82944655418396, ""0.3/sync"": 2.859112024307251, ""0.5/async"": 2.899482488632202}",False,reliability_validation,,,,,
teacher,0.5,0.05,0.05,0.05,2.854786992073059,"{""0.0/natural"": 2.832460403442383, ""0.3/single"": 2.829251289367676, ""0.3/sync"": 2.8586926460266113, ""0.5/async"": 2.8987436294555664}",False,reliability_validation,,,,,
teacher,0.5,0.1,0.0,0.0,2.8547691702842712,"{""0.0/natural"": 2.83245849609375, ""0.3/single"": 2.8292293548583984, ""0.3/sync"": 2.858625650405884, ""0.5/async"": 2.8987631797790527}",False,reliability_validation,,,,,
teacher,0.3,0.05,0.05,0.05,2.8533658385276794,"{""0.0/natural"": 2.8321738243103027, ""0.3/single"": 2.8287193775177, ""0.3/sync"": 2.8565878868103027, ""0.5/async"": 2.895982265472412}",True,reliability_validation,,,,,
teacher,0.7,0.05,0.05,0.05,2.8578426241874695,"{""0.0/natural"": 2.8327653408050537, ""0.3/single"": 2.8310093879699707, ""0.3/sync"": 2.862823486328125, ""0.5/async"": 2.9047722816467285}",False,reliability_validation,,,,,
C1,0.5,0.05,0.05,0.05,nan,,True,,not used by this ablation,,,,
C2,0.5,0.05,0.05,0.05,nan,,True,,not used by this ablation,,,,
C3,0.5,0.0,0.0,0.0,2.868969738483429,"{""0.0/natural"": 2.8552894592285156, ""0.3/single"": 2.855238199234009, ""0.3/sync"": 2.898164987564087, ""0.5/async"": 2.8671863079071045}",True,reliability_validation,,,,,
C3,0.5,0.05,0.05,0.05,2.8690268993377686,"{""0.0/natural"": 2.8552863597869873, ""0.3/single"": 2.8554182052612305, ""0.3/sync"": 2.8979132175445557, ""0.5/async"": 2.867489814758301}",False,reliability_validation,,,,,
C3,0.5,0.1,0.0,0.0,2.8690126538276672,"{""0.0/natural"": 2.85528302192688, ""0.3/single"": 2.855442762374878, ""0.3/sync"": 2.8978819847106934, ""0.5/async"": 2.8674428462982178}",False,reliability_validation,,,,,
C3,0.3,0.05,0.05,0.05,2.870371162891388,"{""0.0/natural"": 2.855177640914917, ""0.3/single"": 2.8578999042510986, ""0.3/sync"": 2.896186351776123, ""0.5/async"": 2.872220754623413}",False,reliability_validation,,,,,
C3,0.7,0.05,0.05,0.05,2.869048058986664,"{""0.0/natural"": 2.8553781509399414, ""0.3/single"": 2.8541696071624756, ""0.3/sync"": 2.900033950805664, ""0.5/async"": 2.866610527038574}",False,reliability_validation,,,,,
C4,0.5,0.0,0.0,0.0,2.856395184993744,"{""0.0/natural"": 2.844621181488037, ""0.3/single"": 2.8557333946228027, ""0.3/sync"": 2.865926742553711, ""0.5/async"": 2.859299421310425}",False,reliability_validation,,,,,
C4,0.5,0.05,0.05,0.05,2.8565751910209656,"{""0.0/natural"": 2.8446505069732666, ""0.3/single"": 2.8562142848968506, ""0.3/sync"": 2.865856409072876, ""0.5/async"": 2.859579563140869}",False,reliability_validation,,,,,
C4,0.5,0.1,0.0,0.0,2.8565635085105896,"{""0.0/natural"": 2.8446319103240967, ""0.3/single"": 2.8562064170837402, ""0.3/sync"": 2.8658132553100586, ""0.5/async"": 2.859602451324463}",False,reliability_validation,,,,,
C4,0.3,0.05,0.05,0.05,2.857943594455719,"{""0.0/natural"": 2.8447465896606445, ""0.3/single"": 2.859677314758301, ""0.3/sync"": 2.864553928375244, ""0.5/async"": 2.8627965450286865}",False,reliability_validation,,,,,
C4,0.7,0.05,0.05,0.05,2.8553494215011597,"{""0.0/natural"": 2.844590663909912, ""0.3/single"": 2.852660894393921, ""0.3/sync"": 2.8664493560791016, ""0.5/async"": 2.857696771621704}",True,reliability_validation,,,,,
C5,0.5,0.0,0.0,0.0,2.858191132545471,"{""0.0/natural"": 2.837888717651367, ""0.3/single"": 2.8408918380737305, ""0.3/sync"": 2.865405321121216, ""0.5/async"": 2.8885786533355713}",False,reliability_validation,,,,,
C5,0.5,0.05,0.05,0.05,2.858053147792816,"{""0.0/natural"": 2.83787202835083, ""0.3/single"": 2.8407843112945557, ""0.3/sync"": 2.8655388355255127, ""0.5/async"": 2.888017416000366}",False,reliability_validation,,,,,
C5,0.5,0.1,0.0,0.0,2.858084976673126,"{""0.0/natural"": 2.8378803730010986, ""0.3/single"": 2.8407742977142334, ""0.3/sync"": 2.8655664920806885, ""0.5/async"": 2.8881187438964844}",False,reliability_validation,,,,,
C5,0.3,0.05,0.05,0.05,2.857841432094574,"{""0.0/natural"": 2.8378095626831055, ""0.3/single"": 2.839801549911499, ""0.3/sync"": 2.8676390647888184, ""0.5/async"": 2.886115550994873}",True,reliability_validation,,,,,
C5,0.7,0.05,0.05,0.05,2.8592984676361084,"{""0.0/natural"": 2.8379809856414795, ""0.3/single"": 2.8421387672424316, ""0.3/sync"": 2.865103244781494, ""0.5/async"": 2.8919708728790283}",False,reliability_validation,,,,,
C6,0.5,0.0,0.0,0.0,2.8277538418769836,"{""0.0/natural"": 2.8142545223236084, ""0.3/single"": 2.816837787628174, ""0.3/sync"": 2.844792127609253, ""0.5/async"": 2.8351309299468994}",False,reliability_validation,,,,,
C6,0.5,0.05,0.05,0.05,2.827627658843994,"{""0.0/natural"": 2.8141915798187256, ""0.3/single"": 2.816967725753784, ""0.3/sync"": 2.8447818756103516, ""0.5/async"": 2.8345694541931152}",False,reliability_validation,,,,,
C6,0.5,0.1,0.0,0.0,2.8276638984680176,"{""0.0/natural"": 2.814206123352051, ""0.3/single"": 2.817033052444458, ""0.3/sync"": 2.8448281288146973, ""0.5/async"": 2.8345882892608643}",False,reliability_validation,,,,,
C6,0.3,0.05,0.05,0.05,2.827383041381836,"{""0.0/natural"": 2.8139631748199463, ""0.3/single"": 2.818815231323242, ""0.3/sync"": 2.8443305492401123, ""0.5/async"": 2.832423210144043}",True,reliability_validation,,,,,
C6,0.7,0.05,0.05,0.05,2.8284868597984314,"{""0.0/natural"": 2.8144543170928955, ""0.3/single"": 2.815439224243164, ""0.3/sync"": 2.8442962169647217, ""0.5/async"": 2.8397576808929443}",False,reliability_validation,,,,,
C6_no_distance,0.5,0.0,0.0,0.0,2.8592775464057922,"{""0.0/natural"": 2.846463441848755, ""0.3/single"": 2.839015483856201, ""0.3/sync"": 2.851423501968384, ""0.5/async"": 2.900207757949829}",True,reliability_validation,,,,,
C6_no_distance,0.5,0.1,0.0,0.0,2.859361946582794,"{""0.0/natural"": 2.8463997840881348, ""0.3/single"": 2.8394994735717773, ""0.3/sync"": 2.8509953022003174, ""0.5/async"": 2.9005532264709473}",False,reliability_validation,,,,,
C6_no_reconstruction,0.5,0.0,0.0,0.0,2.814443826675415,"{""0.0/natural"": 2.797691583633423, ""0.3/single"": 2.7918920516967773, ""0.3/sync"": 2.818723678588867, ""0.5/async"": 2.8494679927825928}",False,reliability_validation,,,,,
C6_no_reconstruction,0.5,0.05,0.05,0.05,2.8139390349388123,"{""0.0/natural"": 2.7977092266082764, ""0.3/single"": 2.7918813228607178, ""0.3/sync"": 2.8184382915496826, ""0.5/async"": 2.8477272987365723}",False,reliability_validation,,,,,
C6_no_reconstruction,0.5,0.1,0.0,0.0,2.813948094844818,"{""0.0/natural"": 2.7976696491241455, ""0.3/single"": 2.791857957839966, ""0.3/sync"": 2.8183655738830566, ""0.5/async"": 2.8478991985321045}",False,reliability_validation,,,,,
C6_no_reconstruction,0.3,0.05,0.05,0.05,2.811177134513855,"{""0.0/natural"": 2.79757022857666, ""0.3/single"": 2.7916157245635986, ""0.3/sync"": 2.816753625869751, ""0.5/async"": 2.83876895904541}",True,reliability_validation,,,,,
C6_no_reconstruction,0.7,0.05,0.05,0.05,2.8178954124450684,"{""0.0/natural"": 2.7978579998016357, ""0.3/single"": 2.792189121246338, ""0.3/sync"": 2.8217227458953857, ""0.5/async"": 2.859811782836914}",False,reliability_validation,,,,,
C6_pointmask,0.5,0.0,0.0,0.0,2.8172501921653748,"{""0.0/natural"": 2.7916030883789062, ""0.3/single"": 2.7908267974853516, ""0.3/sync"": 2.8246986865997314, ""0.5/async"": 2.8618721961975098}",False,reliability_validation,,,,,
C6_pointmask,0.5,0.05,0.05,0.05,2.8165746927261353,"{""0.0/natural"": 2.791574001312256, ""0.3/single"": 2.790780544281006, ""0.3/sync"": 2.823692560195923, ""0.5/async"": 2.8602516651153564}",False,reliability_validation,,,,,
C6_pointmask,0.5,0.1,0.0,0.0,2.8165820837020874,"{""0.0/natural"": 2.791569232940674, ""0.3/single"": 2.7907233238220215, ""0.3/sync"": 2.82354998588562, ""0.5/async"": 2.860485792160034}",False,reliability_validation,,,,,
C6_pointmask,0.3,0.05,0.05,0.05,2.8119084239006042,"{""0.0/natural"": 2.7913870811462402, ""0.3/single"": 2.790656089782715, ""0.3/sync"": 2.814664602279663, ""0.5/async"": 2.850925922393799}",True,reliability_validation,,,,,
C6_pointmask,0.7,0.05,0.05,0.05,2.821407377719879,"{""0.0/natural"": 2.791775703430176, ""0.3/single"": 2.791663885116577, ""0.3/sync"": 2.8317697048187256, ""0.5/async"": 2.870420217514038}",False,reliability_validation,,,,,
C7_distill,0.5,0.0,0.0,0.0,2.8871994614601135,"{""0.0/natural"": 2.871961832046509, ""0.3/single"": 2.8787894248962402, ""0.3/sync"": 2.902831792831421, ""0.5/async"": 2.895214796066284}",False,reliability_validation,,,,,
C7_distill,0.5,0.05,0.05,0.05,2.887099504470825,"{""0.0/natural"": 2.8719308376312256, ""0.3/single"": 2.8785901069641113, ""0.3/sync"": 2.902597427368164, ""0.5/async"": 2.8952796459198}",True,reliability_validation,,,,,
C7_distill,0.5,0.1,0.0,0.0,2.8871177434921265,"{""0.0/natural"": 2.871976137161255, ""0.3/single"": 2.878659248352051, ""0.3/sync"": 2.902616262435913, ""0.5/async"": 2.895219326019287}",False,reliability_validation,,,,,
C7_distill,0.3,0.05,0.05,0.05,2.8883190751075745,"{""0.0/natural"": 2.8715980052948, ""0.3/single"": 2.8790061473846436, ""0.3/sync"": 2.9035727977752686, ""0.5/async"": 2.899099349975586}",False,reliability_validation,,,,,
C7_distill,0.7,0.05,0.05,0.05,2.888582468032837,"{""0.0/natural"": 2.8725264072418213, ""0.3/single"": 2.87967848777771, ""0.3/sync"": 2.905454635620117, ""0.5/async"": 2.896670341491699}",False,reliability_validation,,,,,
C7_group,0.5,0.0,0.0,0.0,2.9084319472312927,"{""0.0/natural"": 2.888453960418701, ""0.3/single"": 2.8795268535614014, ""0.3/sync"": 2.932856798171997, ""0.5/async"": 2.9328901767730713}",False,reliability_validation,,0.05,0.1,False,C7_group_lambda0.05_tau0.10
C7_group,0.5,0.05,0.05,0.05,2.9081557989120483,"{""0.0/natural"": 2.8884048461914062, ""0.3/single"": 2.879855155944824, ""0.3/sync"": 2.932080030441284, ""0.5/async"": 2.9322831630706787}",False,reliability_validation,,0.05,0.1,False,C7_group_lambda0.05_tau0.10
C7_group,0.5,0.1,0.0,0.0,2.908179998397827,"{""0.0/natural"": 2.888439893722534, ""0.3/single"": 2.8799004554748535, ""0.3/sync"": 2.9319827556610107, ""0.5/async"": 2.93239688873291}",False,reliability_validation,,0.05,0.1,False,C7_group_lambda0.05_tau0.10
C7_group,0.3,0.05,0.05,0.05,2.9074912071228027,"{""0.0/natural"": 2.8882105350494385, ""0.3/single"": 2.8837697505950928, ""0.3/sync"": 2.92631459236145, ""0.5/async"": 2.9316699504852295}",False,reliability_validation,,0.05,0.1,False,C7_group_lambda0.05_tau0.10
C7_group,0.7,0.05,0.05,0.05,2.9103721976280212,"{""0.0/natural"": 2.888576030731201, ""0.3/single"": 2.8777272701263428, ""0.3/sync"": 2.9382715225219727, ""0.5/async"": 2.9369139671325684}",False,reliability_validation,,0.05,0.1,False,C7_group_lambda0.05_tau0.10
C7_group,0.5,0.0,0.0,0.0,2.937848687171936,"{""0.0/natural"": 2.90403151512146, ""0.3/single"": 2.9019672870635986, ""0.3/sync"": 2.9718685150146484, ""0.5/async"": 2.973527431488037}",False,reliability_validation,,0.1,0.05,False,C7_group_lambda0.10_tau0.05
C7_group,0.5,0.05,0.05,0.05,2.937710404396057,"{""0.0/natural"": 2.9039723873138428, ""0.3/single"": 2.9019112586975098, ""0.3/sync"": 2.9715962409973145, ""0.5/async"": 2.9733617305755615}",False,reliability_validation,,0.1,0.05,False,C7_group_lambda0.10_tau0.05
C7_group,0.5,0.1,0.0,0.0,2.937703788280487,"{""0.0/natural"": 2.9039785861968994, ""0.3/single"": 2.901944160461426, ""0.3/sync"": 2.971575975418091, ""0.5/async"": 2.9733164310455322}",False,reliability_validation,,0.1,0.05,False,C7_group_lambda0.10_tau0.05
C7_group,0.3,0.05,0.05,0.05,2.93798565864563,"{""0.0/natural"": 2.9036080837249756, ""0.3/single"": 2.9026758670806885, ""0.3/sync"": 2.970571994781494, ""0.5/async"": 2.9750866889953613}",False,reliability_validation,,0.1,0.05,False,C7_group_lambda0.10_tau0.05
C7_group,0.7,0.05,0.05,0.05,2.939401626586914,"{""0.0/natural"": 2.9043807983398438, ""0.3/single"": 2.90256404876709, ""0.3/sync"": 2.9743330478668213, ""0.5/async"": 2.9763286113739014}",False,reliability_validation,,0.1,0.05,False,C7_group_lambda0.10_tau0.05
C7_group,0.5,0.0,0.0,0.0,2.887659251689911,"{""0.0/natural"": 2.8679378032684326, ""0.3/single"": 2.866154193878174, ""0.3/sync"": 2.889091968536377, ""0.5/async"": 2.92745304107666}",True,reliability_validation,,0.1,0.1,True,C7_group_lambda0.10_tau0.10
C7_group,0.5,0.05,0.05,0.05,2.8877416253089905,"{""0.0/natural"": 2.8679301738739014, ""0.3/single"": 2.8663411140441895, ""0.3/sync"": 2.8891632556915283, ""0.5/async"": 2.9275319576263428}",False,reliability_validation,,0.1,0.1,True,C7_group_lambda0.10_tau0.10
C7_group,0.5,0.1,0.0,0.0,2.88775235414505,"{""0.0/natural"": 2.867924213409424, ""0.3/single"": 2.8663671016693115, ""0.3/sync"": 2.889188051223755, ""0.5/async"": 2.92753005027771}",False,reliability_validation,,0.1,0.1,True,C7_group_lambda0.10_tau0.10
C7_group,0.3,0.05,0.05,0.05,2.8894190192222595,"{""0.0/natural"": 2.867828130722046, ""0.3/single"": 2.868374824523926, ""0.3/sync"": 2.8905928134918213, ""0.5/async"": 2.930880308151245}",False,reliability_validation,,0.1,0.1,True,C7_group_lambda0.10_tau0.10
C7_group,0.7,0.05,0.05,0.05,2.887662351131439,"{""0.0/natural"": 2.8680334091186523, ""0.3/single"": 2.8651366233825684, ""0.3/sync"": 2.889106273651123, ""0.5/async"": 2.928373098373413}",False,reliability_validation,,0.1,0.1,True,C7_group_lambda0.10_tau0.10
C7_group,0.5,0.0,0.0,0.0,2.9051475524902344,"{""0.0/natural"": 2.882009983062744, ""0.3/single"": 2.8719751834869385, ""0.3/sync"": 2.9277143478393555, ""0.5/async"": 2.9388906955718994}",False,reliability_validation,,0.1,0.2,False,C7_group_lambda0.10_tau0.20
C7_group,0.5,0.05,0.05,0.05,2.9047818183898926,"{""0.0/natural"": 2.8819169998168945, ""0.3/single"": 2.8721556663513184, ""0.3/sync"": 2.9272356033325195, ""0.5/async"": 2.937819004058838}",False,reliability_validation,,0.1,0.2,False,C7_group_lambda0.10_tau0.20
C7_group,0.5,0.1,0.0,0.0,2.904840886592865,"{""0.0/natural"": 2.8819549083709717, ""0.3/single"": 2.8721954822540283, ""0.3/sync"": 2.9272100925445557, ""0.5/async"": 2.9380030632019043}",False,reliability_validation,,0.1,0.2,False,C7_group_lambda0.10_tau0.20
C7_group,0.3,0.05,0.05,0.05,2.903527617454529,"{""0.0/natural"": 2.8815088272094727, ""0.3/single"": 2.8748013973236084, ""0.3/sync"": 2.9242103099823, ""0.5/async"": 2.9335899353027344}",False,reliability_validation,,0.1,0.2,False,C7_group_lambda0.10_tau0.20
C7_group,0.7,0.05,0.05,0.05,2.907408356666565,"{""0.0/natural"": 2.8823306560516357, ""0.3/single"": 2.8710365295410156, ""0.3/sync"": 2.9312281608581543, ""0.5/async"": 2.945038080215454}",False,reliability_validation,,0.1,0.2,False,C7_group_lambda0.10_tau0.20
C7_group,0.5,0.0,0.0,0.0,2.9365825057029724,"{""0.0/natural"": 2.9062917232513428, ""0.3/single"": 2.898517370223999, ""0.3/sync"": 2.957914352416992, ""0.5/async"": 2.9836065769195557}",False,reliability_validation,,0.2,0.1,False,C7_group_lambda0.20_tau0.10
C7_group,0.5,0.05,0.05,0.05,2.9361995458602905,"{""0.0/natural"": 2.9062345027923584, ""0.3/single"": 2.8984618186950684, ""0.3/sync"": 2.957249641418457, ""0.5/async"": 2.9828522205352783}",False,reliability_validation,,0.2,0.1,False,C7_group_lambda0.20_tau0.10
C7_group,0.5,0.1,0.0,0.0,2.936208724975586,"{""0.0/natural"": 2.906248092651367, ""0.3/single"": 2.898481845855713, ""0.3/sync"": 2.9571707248687744, ""0.5/async"": 2.9829342365264893}",False,reliability_validation,,0.2,0.1,False,C7_group_lambda0.20_tau0.10
C7_group,0.3,0.05,0.05,0.05,2.934680759906769,"{""0.0/natural"": 2.9059057235717773, ""0.3/single"": 2.8992602825164795, ""0.3/sync"": 2.95295786857605, ""0.5/async"": 2.9805991649627686}",False,reliability_validation,,0.2,0.1,False,C7_group_lambda0.20_tau0.10
C7_group,0.7,0.05,0.05,0.05,2.93935626745224,"{""0.0/natural"": 2.9065608978271484, ""0.3/single"": 2.899205207824707, ""0.3/sync"": 2.9629967212677, ""0.5/async"": 2.9886622428894043}",False,reliability_validation,,0.2,0.1,False,C7_group_lambda0.20_tau0.10
1 model rho_imp lambda_u lambda_gap lambda_span inner_selection_nll scenario_selection_nll selected selection_split note group_lambda group_temperature risk_candidate_selected candidate
2 teacher 0.5 0.0 0.0 0.0 2.8551357984542847 {"0.0/natural": 2.8325021266937256, "0.3/single": 2.82944655418396, "0.3/sync": 2.859112024307251, "0.5/async": 2.899482488632202} False reliability_validation
3 teacher 0.5 0.05 0.05 0.05 2.854786992073059 {"0.0/natural": 2.832460403442383, "0.3/single": 2.829251289367676, "0.3/sync": 2.8586926460266113, "0.5/async": 2.8987436294555664} False reliability_validation
4 teacher 0.5 0.1 0.0 0.0 2.8547691702842712 {"0.0/natural": 2.83245849609375, "0.3/single": 2.8292293548583984, "0.3/sync": 2.858625650405884, "0.5/async": 2.8987631797790527} False reliability_validation
5 teacher 0.3 0.05 0.05 0.05 2.8533658385276794 {"0.0/natural": 2.8321738243103027, "0.3/single": 2.8287193775177, "0.3/sync": 2.8565878868103027, "0.5/async": 2.895982265472412} True reliability_validation
6 teacher 0.7 0.05 0.05 0.05 2.8578426241874695 {"0.0/natural": 2.8327653408050537, "0.3/single": 2.8310093879699707, "0.3/sync": 2.862823486328125, "0.5/async": 2.9047722816467285} False reliability_validation
7 C1 0.5 0.05 0.05 0.05 nan True not used by this ablation
8 C2 0.5 0.05 0.05 0.05 nan True not used by this ablation
9 C3 0.5 0.0 0.0 0.0 2.868969738483429 {"0.0/natural": 2.8552894592285156, "0.3/single": 2.855238199234009, "0.3/sync": 2.898164987564087, "0.5/async": 2.8671863079071045} True reliability_validation
10 C3 0.5 0.05 0.05 0.05 2.8690268993377686 {"0.0/natural": 2.8552863597869873, "0.3/single": 2.8554182052612305, "0.3/sync": 2.8979132175445557, "0.5/async": 2.867489814758301} False reliability_validation
11 C3 0.5 0.1 0.0 0.0 2.8690126538276672 {"0.0/natural": 2.85528302192688, "0.3/single": 2.855442762374878, "0.3/sync": 2.8978819847106934, "0.5/async": 2.8674428462982178} False reliability_validation
12 C3 0.3 0.05 0.05 0.05 2.870371162891388 {"0.0/natural": 2.855177640914917, "0.3/single": 2.8578999042510986, "0.3/sync": 2.896186351776123, "0.5/async": 2.872220754623413} False reliability_validation
13 C3 0.7 0.05 0.05 0.05 2.869048058986664 {"0.0/natural": 2.8553781509399414, "0.3/single": 2.8541696071624756, "0.3/sync": 2.900033950805664, "0.5/async": 2.866610527038574} False reliability_validation
14 C4 0.5 0.0 0.0 0.0 2.856395184993744 {"0.0/natural": 2.844621181488037, "0.3/single": 2.8557333946228027, "0.3/sync": 2.865926742553711, "0.5/async": 2.859299421310425} False reliability_validation
15 C4 0.5 0.05 0.05 0.05 2.8565751910209656 {"0.0/natural": 2.8446505069732666, "0.3/single": 2.8562142848968506, "0.3/sync": 2.865856409072876, "0.5/async": 2.859579563140869} False reliability_validation
16 C4 0.5 0.1 0.0 0.0 2.8565635085105896 {"0.0/natural": 2.8446319103240967, "0.3/single": 2.8562064170837402, "0.3/sync": 2.8658132553100586, "0.5/async": 2.859602451324463} False reliability_validation
17 C4 0.3 0.05 0.05 0.05 2.857943594455719 {"0.0/natural": 2.8447465896606445, "0.3/single": 2.859677314758301, "0.3/sync": 2.864553928375244, "0.5/async": 2.8627965450286865} False reliability_validation
18 C4 0.7 0.05 0.05 0.05 2.8553494215011597 {"0.0/natural": 2.844590663909912, "0.3/single": 2.852660894393921, "0.3/sync": 2.8664493560791016, "0.5/async": 2.857696771621704} True reliability_validation
19 C5 0.5 0.0 0.0 0.0 2.858191132545471 {"0.0/natural": 2.837888717651367, "0.3/single": 2.8408918380737305, "0.3/sync": 2.865405321121216, "0.5/async": 2.8885786533355713} False reliability_validation
20 C5 0.5 0.05 0.05 0.05 2.858053147792816 {"0.0/natural": 2.83787202835083, "0.3/single": 2.8407843112945557, "0.3/sync": 2.8655388355255127, "0.5/async": 2.888017416000366} False reliability_validation
21 C5 0.5 0.1 0.0 0.0 2.858084976673126 {"0.0/natural": 2.8378803730010986, "0.3/single": 2.8407742977142334, "0.3/sync": 2.8655664920806885, "0.5/async": 2.8881187438964844} False reliability_validation
22 C5 0.3 0.05 0.05 0.05 2.857841432094574 {"0.0/natural": 2.8378095626831055, "0.3/single": 2.839801549911499, "0.3/sync": 2.8676390647888184, "0.5/async": 2.886115550994873} True reliability_validation
23 C5 0.7 0.05 0.05 0.05 2.8592984676361084 {"0.0/natural": 2.8379809856414795, "0.3/single": 2.8421387672424316, "0.3/sync": 2.865103244781494, "0.5/async": 2.8919708728790283} False reliability_validation
24 C6 0.5 0.0 0.0 0.0 2.8277538418769836 {"0.0/natural": 2.8142545223236084, "0.3/single": 2.816837787628174, "0.3/sync": 2.844792127609253, "0.5/async": 2.8351309299468994} False reliability_validation
25 C6 0.5 0.05 0.05 0.05 2.827627658843994 {"0.0/natural": 2.8141915798187256, "0.3/single": 2.816967725753784, "0.3/sync": 2.8447818756103516, "0.5/async": 2.8345694541931152} False reliability_validation
26 C6 0.5 0.1 0.0 0.0 2.8276638984680176 {"0.0/natural": 2.814206123352051, "0.3/single": 2.817033052444458, "0.3/sync": 2.8448281288146973, "0.5/async": 2.8345882892608643} False reliability_validation
27 C6 0.3 0.05 0.05 0.05 2.827383041381836 {"0.0/natural": 2.8139631748199463, "0.3/single": 2.818815231323242, "0.3/sync": 2.8443305492401123, "0.5/async": 2.832423210144043} True reliability_validation
28 C6 0.7 0.05 0.05 0.05 2.8284868597984314 {"0.0/natural": 2.8144543170928955, "0.3/single": 2.815439224243164, "0.3/sync": 2.8442962169647217, "0.5/async": 2.8397576808929443} False reliability_validation
29 C6_no_distance 0.5 0.0 0.0 0.0 2.8592775464057922 {"0.0/natural": 2.846463441848755, "0.3/single": 2.839015483856201, "0.3/sync": 2.851423501968384, "0.5/async": 2.900207757949829} True reliability_validation
30 C6_no_distance 0.5 0.1 0.0 0.0 2.859361946582794 {"0.0/natural": 2.8463997840881348, "0.3/single": 2.8394994735717773, "0.3/sync": 2.8509953022003174, "0.5/async": 2.9005532264709473} False reliability_validation
31 C6_no_reconstruction 0.5 0.0 0.0 0.0 2.814443826675415 {"0.0/natural": 2.797691583633423, "0.3/single": 2.7918920516967773, "0.3/sync": 2.818723678588867, "0.5/async": 2.8494679927825928} False reliability_validation
32 C6_no_reconstruction 0.5 0.05 0.05 0.05 2.8139390349388123 {"0.0/natural": 2.7977092266082764, "0.3/single": 2.7918813228607178, "0.3/sync": 2.8184382915496826, "0.5/async": 2.8477272987365723} False reliability_validation
33 C6_no_reconstruction 0.5 0.1 0.0 0.0 2.813948094844818 {"0.0/natural": 2.7976696491241455, "0.3/single": 2.791857957839966, "0.3/sync": 2.8183655738830566, "0.5/async": 2.8478991985321045} False reliability_validation
34 C6_no_reconstruction 0.3 0.05 0.05 0.05 2.811177134513855 {"0.0/natural": 2.79757022857666, "0.3/single": 2.7916157245635986, "0.3/sync": 2.816753625869751, "0.5/async": 2.83876895904541} True reliability_validation
35 C6_no_reconstruction 0.7 0.05 0.05 0.05 2.8178954124450684 {"0.0/natural": 2.7978579998016357, "0.3/single": 2.792189121246338, "0.3/sync": 2.8217227458953857, "0.5/async": 2.859811782836914} False reliability_validation
36 C6_pointmask 0.5 0.0 0.0 0.0 2.8172501921653748 {"0.0/natural": 2.7916030883789062, "0.3/single": 2.7908267974853516, "0.3/sync": 2.8246986865997314, "0.5/async": 2.8618721961975098} False reliability_validation
37 C6_pointmask 0.5 0.05 0.05 0.05 2.8165746927261353 {"0.0/natural": 2.791574001312256, "0.3/single": 2.790780544281006, "0.3/sync": 2.823692560195923, "0.5/async": 2.8602516651153564} False reliability_validation
38 C6_pointmask 0.5 0.1 0.0 0.0 2.8165820837020874 {"0.0/natural": 2.791569232940674, "0.3/single": 2.7907233238220215, "0.3/sync": 2.82354998588562, "0.5/async": 2.860485792160034} False reliability_validation
39 C6_pointmask 0.3 0.05 0.05 0.05 2.8119084239006042 {"0.0/natural": 2.7913870811462402, "0.3/single": 2.790656089782715, "0.3/sync": 2.814664602279663, "0.5/async": 2.850925922393799} True reliability_validation
40 C6_pointmask 0.7 0.05 0.05 0.05 2.821407377719879 {"0.0/natural": 2.791775703430176, "0.3/single": 2.791663885116577, "0.3/sync": 2.8317697048187256, "0.5/async": 2.870420217514038} False reliability_validation
41 C7_distill 0.5 0.0 0.0 0.0 2.8871994614601135 {"0.0/natural": 2.871961832046509, "0.3/single": 2.8787894248962402, "0.3/sync": 2.902831792831421, "0.5/async": 2.895214796066284} False reliability_validation
42 C7_distill 0.5 0.05 0.05 0.05 2.887099504470825 {"0.0/natural": 2.8719308376312256, "0.3/single": 2.8785901069641113, "0.3/sync": 2.902597427368164, "0.5/async": 2.8952796459198} True reliability_validation
43 C7_distill 0.5 0.1 0.0 0.0 2.8871177434921265 {"0.0/natural": 2.871976137161255, "0.3/single": 2.878659248352051, "0.3/sync": 2.902616262435913, "0.5/async": 2.895219326019287} False reliability_validation
44 C7_distill 0.3 0.05 0.05 0.05 2.8883190751075745 {"0.0/natural": 2.8715980052948, "0.3/single": 2.8790061473846436, "0.3/sync": 2.9035727977752686, "0.5/async": 2.899099349975586} False reliability_validation
45 C7_distill 0.7 0.05 0.05 0.05 2.888582468032837 {"0.0/natural": 2.8725264072418213, "0.3/single": 2.87967848777771, "0.3/sync": 2.905454635620117, "0.5/async": 2.896670341491699} False reliability_validation
46 C7_group 0.5 0.0 0.0 0.0 2.9084319472312927 {"0.0/natural": 2.888453960418701, "0.3/single": 2.8795268535614014, "0.3/sync": 2.932856798171997, "0.5/async": 2.9328901767730713} False reliability_validation 0.05 0.1 False C7_group_lambda0.05_tau0.10
47 C7_group 0.5 0.05 0.05 0.05 2.9081557989120483 {"0.0/natural": 2.8884048461914062, "0.3/single": 2.879855155944824, "0.3/sync": 2.932080030441284, "0.5/async": 2.9322831630706787} False reliability_validation 0.05 0.1 False C7_group_lambda0.05_tau0.10
48 C7_group 0.5 0.1 0.0 0.0 2.908179998397827 {"0.0/natural": 2.888439893722534, "0.3/single": 2.8799004554748535, "0.3/sync": 2.9319827556610107, "0.5/async": 2.93239688873291} False reliability_validation 0.05 0.1 False C7_group_lambda0.05_tau0.10
49 C7_group 0.3 0.05 0.05 0.05 2.9074912071228027 {"0.0/natural": 2.8882105350494385, "0.3/single": 2.8837697505950928, "0.3/sync": 2.92631459236145, "0.5/async": 2.9316699504852295} False reliability_validation 0.05 0.1 False C7_group_lambda0.05_tau0.10
50 C7_group 0.7 0.05 0.05 0.05 2.9103721976280212 {"0.0/natural": 2.888576030731201, "0.3/single": 2.8777272701263428, "0.3/sync": 2.9382715225219727, "0.5/async": 2.9369139671325684} False reliability_validation 0.05 0.1 False C7_group_lambda0.05_tau0.10
51 C7_group 0.5 0.0 0.0 0.0 2.937848687171936 {"0.0/natural": 2.90403151512146, "0.3/single": 2.9019672870635986, "0.3/sync": 2.9718685150146484, "0.5/async": 2.973527431488037} False reliability_validation 0.1 0.05 False C7_group_lambda0.10_tau0.05
52 C7_group 0.5 0.05 0.05 0.05 2.937710404396057 {"0.0/natural": 2.9039723873138428, "0.3/single": 2.9019112586975098, "0.3/sync": 2.9715962409973145, "0.5/async": 2.9733617305755615} False reliability_validation 0.1 0.05 False C7_group_lambda0.10_tau0.05
53 C7_group 0.5 0.1 0.0 0.0 2.937703788280487 {"0.0/natural": 2.9039785861968994, "0.3/single": 2.901944160461426, "0.3/sync": 2.971575975418091, "0.5/async": 2.9733164310455322} False reliability_validation 0.1 0.05 False C7_group_lambda0.10_tau0.05
54 C7_group 0.3 0.05 0.05 0.05 2.93798565864563 {"0.0/natural": 2.9036080837249756, "0.3/single": 2.9026758670806885, "0.3/sync": 2.970571994781494, "0.5/async": 2.9750866889953613} False reliability_validation 0.1 0.05 False C7_group_lambda0.10_tau0.05
55 C7_group 0.7 0.05 0.05 0.05 2.939401626586914 {"0.0/natural": 2.9043807983398438, "0.3/single": 2.90256404876709, "0.3/sync": 2.9743330478668213, "0.5/async": 2.9763286113739014} False reliability_validation 0.1 0.05 False C7_group_lambda0.10_tau0.05
56 C7_group 0.5 0.0 0.0 0.0 2.887659251689911 {"0.0/natural": 2.8679378032684326, "0.3/single": 2.866154193878174, "0.3/sync": 2.889091968536377, "0.5/async": 2.92745304107666} True reliability_validation 0.1 0.1 True C7_group_lambda0.10_tau0.10
57 C7_group 0.5 0.05 0.05 0.05 2.8877416253089905 {"0.0/natural": 2.8679301738739014, "0.3/single": 2.8663411140441895, "0.3/sync": 2.8891632556915283, "0.5/async": 2.9275319576263428} False reliability_validation 0.1 0.1 True C7_group_lambda0.10_tau0.10
58 C7_group 0.5 0.1 0.0 0.0 2.88775235414505 {"0.0/natural": 2.867924213409424, "0.3/single": 2.8663671016693115, "0.3/sync": 2.889188051223755, "0.5/async": 2.92753005027771} False reliability_validation 0.1 0.1 True C7_group_lambda0.10_tau0.10
59 C7_group 0.3 0.05 0.05 0.05 2.8894190192222595 {"0.0/natural": 2.867828130722046, "0.3/single": 2.868374824523926, "0.3/sync": 2.8905928134918213, "0.5/async": 2.930880308151245} False reliability_validation 0.1 0.1 True C7_group_lambda0.10_tau0.10
60 C7_group 0.7 0.05 0.05 0.05 2.887662351131439 {"0.0/natural": 2.8680334091186523, "0.3/single": 2.8651366233825684, "0.3/sync": 2.889106273651123, "0.5/async": 2.928373098373413} False reliability_validation 0.1 0.1 True C7_group_lambda0.10_tau0.10
61 C7_group 0.5 0.0 0.0 0.0 2.9051475524902344 {"0.0/natural": 2.882009983062744, "0.3/single": 2.8719751834869385, "0.3/sync": 2.9277143478393555, "0.5/async": 2.9388906955718994} False reliability_validation 0.1 0.2 False C7_group_lambda0.10_tau0.20
62 C7_group 0.5 0.05 0.05 0.05 2.9047818183898926 {"0.0/natural": 2.8819169998168945, "0.3/single": 2.8721556663513184, "0.3/sync": 2.9272356033325195, "0.5/async": 2.937819004058838} False reliability_validation 0.1 0.2 False C7_group_lambda0.10_tau0.20
63 C7_group 0.5 0.1 0.0 0.0 2.904840886592865 {"0.0/natural": 2.8819549083709717, "0.3/single": 2.8721954822540283, "0.3/sync": 2.9272100925445557, "0.5/async": 2.9380030632019043} False reliability_validation 0.1 0.2 False C7_group_lambda0.10_tau0.20
64 C7_group 0.3 0.05 0.05 0.05 2.903527617454529 {"0.0/natural": 2.8815088272094727, "0.3/single": 2.8748013973236084, "0.3/sync": 2.9242103099823, "0.5/async": 2.9335899353027344} False reliability_validation 0.1 0.2 False C7_group_lambda0.10_tau0.20
65 C7_group 0.7 0.05 0.05 0.05 2.907408356666565 {"0.0/natural": 2.8823306560516357, "0.3/single": 2.8710365295410156, "0.3/sync": 2.9312281608581543, "0.5/async": 2.945038080215454} False reliability_validation 0.1 0.2 False C7_group_lambda0.10_tau0.20
66 C7_group 0.5 0.0 0.0 0.0 2.9365825057029724 {"0.0/natural": 2.9062917232513428, "0.3/single": 2.898517370223999, "0.3/sync": 2.957914352416992, "0.5/async": 2.9836065769195557} False reliability_validation 0.2 0.1 False C7_group_lambda0.20_tau0.10
67 C7_group 0.5 0.05 0.05 0.05 2.9361995458602905 {"0.0/natural": 2.9062345027923584, "0.3/single": 2.8984618186950684, "0.3/sync": 2.957249641418457, "0.5/async": 2.9828522205352783} False reliability_validation 0.2 0.1 False C7_group_lambda0.20_tau0.10
68 C7_group 0.5 0.1 0.0 0.0 2.936208724975586 {"0.0/natural": 2.906248092651367, "0.3/single": 2.898481845855713, "0.3/sync": 2.9571707248687744, "0.5/async": 2.9829342365264893} False reliability_validation 0.2 0.1 False C7_group_lambda0.20_tau0.10
69 C7_group 0.3 0.05 0.05 0.05 2.934680759906769 {"0.0/natural": 2.9059057235717773, "0.3/single": 2.8992602825164795, "0.3/sync": 2.95295786857605, "0.5/async": 2.9805991649627686} False reliability_validation 0.2 0.1 False C7_group_lambda0.20_tau0.10
70 C7_group 0.7 0.05 0.05 0.05 2.93935626745224 {"0.0/natural": 2.9065608978271484, "0.3/single": 2.899205207824707, "0.3/sync": 2.9629967212677, "0.5/async": 2.9886622428894043} False reliability_validation 0.2 0.1 False C7_group_lambda0.20_tau0.10
@@ -0,0 +1,422 @@
{
"seed": 20260924,
"text_encoder": "official precomputed text field; encoder revision not supplied",
"training_configuration": {
"student_epoch_limit": 12,
"imputer_epochs": 8,
"batch_size": 128,
"early_stopping_patience": 3,
"device": "cuda",
"device_name": "NVIDIA GeForce RTX 5070 Ti",
"optimizer": "AdamW",
"student_learning_rate": 0.0003,
"student_weight_decay": 0.001,
"imputer_learning_rate": 0.0003,
"imputer_weight_decay": 0.0001,
"early_stopping_metric": "mean untempered selection_nll over fixed group-disjoint internal training scenarios",
"inner_selection_scenarios": [
"0.0/natural",
"0.3/single",
"0.3/sync",
"0.5/async"
],
"inner_selection_source_video_groups": 76
},
"training_input": "E题数据/附件2-数据集特征文件/unaligned_50.pkl",
"input_version": "unaligned_50",
"q1_alignment_adapter": {
"train": {
"method": "shared_interval_overlap_on_normalized_progress",
"coordinate_mode": "relative",
"physical_time_alignment": false,
"samples": 3395,
"vision_length_conflict_samples": 618,
"vision_tail_ambiguous_samples": 618,
"nonzero_text_rows_outside_attention": 86078,
"observed_target_rows": {
"text": 169750,
"audio": 169750,
"vision": 163302
},
"mean_target_coverage": {
"text": 1.0,
"audio": 1.0,
"vision": 0.9540337701314328
},
"quality_fields_available": false,
"word_or_frame_timestamps_available": false
},
"valid": {
"method": "shared_interval_overlap_on_normalized_progress",
"coordinate_mode": "relative",
"physical_time_alignment": false,
"samples": 728,
"vision_length_conflict_samples": 141,
"vision_tail_ambiguous_samples": 141,
"nonzero_text_rows_outside_attention": 17772,
"observed_target_rows": {
"text": 36400,
"audio": 36400,
"vision": 35315
},
"mean_target_coverage": {
"text": 1.0,
"audio": 1.0,
"vision": 0.96090314748523
},
"quality_fields_available": false,
"word_or_frame_timestamps_available": false
},
"test": {
"method": "shared_interval_overlap_on_normalized_progress",
"coordinate_mode": "relative",
"physical_time_alignment": false,
"samples": 727,
"vision_length_conflict_samples": 131,
"vision_tail_ambiguous_samples": 131,
"nonzero_text_rows_outside_attention": 18041,
"observed_target_rows": {
"text": 36350,
"audio": 36350,
"vision": 35034
},
"mean_target_coverage": {
"text": 1.0,
"audio": 1.0,
"vision": 0.9549938172651288
},
"quality_fields_available": false,
"word_or_frame_timestamps_available": false
}
},
"training_sha256": "77eda14a06be9749a96c52ae45470c7cffcfa7219011eae391d231a0664c3762",
"official_group_overlap": {
"train_valid": 0,
"train_test": 0,
"valid_test": 0
},
"official_splits": {
"train": {
"n": 3395,
"source_video_groups": 1528
},
"valid": {
"n": 728,
"source_video_groups": 239
},
"test": {
"n": 727,
"source_video_groups": 381
}
},
"internal_train_holdouts": {
"fit": {
"n": 3030,
"video_groups": 1375
},
"reliability_selection": {
"n": 190,
"video_groups": 76
},
"temperature_calibration": {
"n": 175,
"video_groups": 77
},
"all_group_disjoint": true
},
"feature_standardization": "fit-only observed rows, per-dimension; fixed for valid/test/attachment3",
"missing_mask": "official text attention and source lengths plus row observation; normalized-progress overlap preserves empty bins; q*=1 only where visible, J_Q=0",
"observation_quality": {
"quality_score_fields_present": false,
"quality_available_flag_present": false,
"fallback": "q*=1 and J_Q=0 for visible rows; R_eff=R",
"quality_noise_mapping_ablation": "not identifiable on unaligned_50 because no row quality score varies"
},
"imputer": {
"type": "structured linear Gaussian shared-private state space",
"state_dims": {
"shared": 8,
"private_each": 4
},
"posterior": "block-tridiagonal equivalent Kalman information filter + RTS smoother",
"sampling": "joint latent trajectories and missing emissions; observed features copied exactly",
"fit_objective": "train-only observed Gaussian marginal likelihood including log determinants",
"epochs": 8,
"frozen_before_teacher_student": true
},
"architecture": {
"projection": 32,
"bigru_hidden_each_direction": 16,
"cross_source_layers": 1,
"cross_time_read": true,
"rank": 4,
"reliability_gru": "directional hidden decay; reset applied before candidate map; update gate multiplied by rho",
"final_gate": "rho times bounded content score plus positive null prior",
"output": "neutral point mass plus sign-specific Beta magnitudes; K-path probabilities mixed before decoding"
},
"reliability_hyperparameters": {
"selected_per_model_on": "group-disjoint internal training reliability-validation slice",
"candidate_values": [
[
0.5,
0.0,
0.0,
0.0
],
[
0.5,
0.05,
0.05,
0.05
],
[
0.5,
0.1,
0.0,
0.0
],
[
0.3,
0.05,
0.05,
0.05
],
[
0.7,
0.05,
0.05,
0.05
]
],
"validation_scenarios": [
"0.0/natural",
"0.3/single",
"0.3/sync",
"0.5/async"
],
"selected_by_model": {
"teacher": [
0.3,
0.05,
0.05,
0.05
],
"C1": [
0.5,
0.05,
0.05,
0.05
],
"C2": [
0.5,
0.05,
0.05,
0.05
],
"C3": [
0.5,
0.0,
0.0,
0.0
],
"C4": [
0.7,
0.05,
0.05,
0.05
],
"C5": [
0.3,
0.05,
0.05,
0.05
],
"C6": [
0.3,
0.05,
0.05,
0.05
],
"C6_no_distance": [
0.5,
0.0,
0.0,
0.0
],
"C6_no_reconstruction": [
0.3,
0.05,
0.05,
0.05
],
"C6_pointmask": [
0.3,
0.05,
0.05,
0.05
],
"C7_distill": [
0.5,
0.05,
0.05,
0.05
],
"C7_group": [
0.5,
0.0,
0.0,
0.0
]
}
},
"group_risk_hyperparameters": {
"selection": "lambda_group and group_temperature jointly selected with reliability hyperparameters on fixed group-disjoint internal training scenarios",
"candidate_values": [
[
0.05,
0.1
],
[
0.1,
0.05
],
[
0.1,
0.1
],
[
0.1,
0.2
],
[
0.2,
0.1
]
],
"selected": [
0.1,
0.1
],
"selection_split": "reliability_validation"
},
"loss": {
"supervision": "negative log mixture of Beta interval masses plus scaled Huber mean term",
"delta_u": 0.027777499999999997,
"delta_u_source": "half the minimum positive spacing of nonzero absolute labels in fit only",
"lambda_y": 1.0,
"lambda_distill": 0.1,
"lambda_reconstruction": 0.05,
"lambda_group_default": 0.1,
"group_temperature_default": 0.1,
"selected_group_risk": [
0.1,
0.1
],
"distill_temperature": 2.0,
"distill_retention_exponent": 1.0,
"imputer_regularization": {
"emission_l2": 0.0001,
"transition_l2": 0.0001
},
"group_and_distill_separate": true
},
"calibration": {
"method": "temperature scaling on a group-disjoint internal official-train holdout, separated from reliability selection",
"temperature": 1.122980387832455,
"valid_used_for_selection": true,
"test_used_for_selection_or_calibration": false
},
"selected_model": "C6",
"attachment3_low_information_priors": {
"class_probability_method": "fit counts + one pseudocount per class",
"class_probability_values": [
0.2786020441806792,
0.2205736894164194,
0.5008242664029015
],
"negative_beta": [
1.1441766023635864,
1.8200817108154297
],
"positive_beta": [
1.271026611328125,
2.4681642055511475
]
},
"ablation_definitions": {
"C1": "masked BiGRU; no posterior imputation, explicit reliability or source gate",
"C2": "exact Gaussian posterior mean; no joint trajectory integral",
"C3": "joint trajectory integral plus final reliability/content fusion gate",
"C4": "C3 plus bounded cross-time source attention and null source",
"C5": "C4 plus reliability-modulated BiGRU update",
"C6": "C5 plus optional rank-4 CP residual",
"C6_no_distance": "C6 with uncertainty retained but both distance/span reliability penalties fixed to zero",
"C6_no_reconstruction": "C6 trained without the auxiliary hidden-feature reconstruction loss",
"C6_pointmask": "C6 trained with independent point masking instead of contiguous spans",
"C7_distill": "C6 plus entropy/retention-weighted teacher distillation only",
"C7_group": "C6 plus smooth worst-group risk only"
},
"masking": {
"rates": [
0.0,
0.1,
0.3,
0.5,
0.7
],
"patterns": [
"single",
"sync",
"partial",
"async"
],
"preserve_at_least_fraction_per_selected_modality": 0.2,
"controlled_sweep_split": "official validation",
"identical_masks_across_models": true,
"scenario_count": 42,
"scenario_seed": 20261833,
"training_mask_rng_seed": 20261227,
"reliability_scenario_seed": 20261830,
"controlled_torch_sampling_seed": 20261476,
"paired_control_bootstrap_seed": 20261477,
"mask_audit_file": null,
"mask_audit_omitted_reason": "Row-level audit omitted from the size-limited deliverable; regenerated by rerunning final.q2.math.train.",
"additional_one_factor_controls": [
"modality T/A/V and combinations",
"start/middle/end",
"one-long/multiple-short",
"sync/partial/async"
],
"semantic_position_control": "not run: unaligned_50 does not provide audited semantic boundary indices; raw text is prohibited in student inputs"
},
"final_test_metrics": {
"n": 727,
"accuracy": 0.672627235213205,
"macro_f1": 0.5484581573154621,
"negative_support": 207,
"neutral_support": 158,
"positive_support": 362,
"negative_recall": 0.7439613526570048,
"middle_recall": 0.10126582278481013,
"positive_recall": 0.8812154696132597,
"regression_mae": 0.7100059986114502,
"regression_rmse": 0.969292458045841,
"pearson": 0.6424147486686707,
"brier": 0.4367243729993746,
"classification_nll": 0.7538501024246216,
"ece_15": 0.047142177615237854,
"selection_nll": 2.8449835777282715,
"interval_90_coverage": 0.8954607977991746,
"interval_90_mean_width": 2.48697829246521,
"predictive_variance_mean_uncalibrated": 0.6001424193382263,
"within_trajectory_variance_mean": 0.6001414060592651,
"between_trajectory_variance_mean": 1.021712705551181e-06,
"predictive_mean_mean_calibrated": 0.18709982931613922,
"predictive_variance_mean_calibrated": 0.6344733238220215
},
"test_gate_diagnostics_file": null,
"test_gate_diagnostics_omitted_reason": "Row-level audit omitted from the size-limited deliverable; regenerated by rerunning final.q2.math.train.",
"attachment3_cases": 0,
"attachment3_labeled_metrics": null,
"completed_utc": "2026-09-25T12:10:16Z"
}
@@ -0,0 +1,27 @@
{
"n": 727,
"accuracy": 0.672627235213205,
"macro_f1": 0.5484581573154621,
"negative_support": 207,
"neutral_support": 158,
"positive_support": 362,
"negative_recall": 0.7439613526570048,
"middle_recall": 0.10126582278481013,
"positive_recall": 0.8812154696132597,
"regression_mae": 0.7100059986114502,
"regression_rmse": 0.969292458045841,
"pearson": 0.6424147486686707,
"brier": 0.4367243729993746,
"classification_nll": 0.7538501024246216,
"ece_15": 0.047142177615237854,
"selection_nll": 2.8449835777282715,
"interval_90_coverage": 0.8954607977991746,
"interval_90_mean_width": 2.48697829246521,
"predictive_variance_mean_uncalibrated": 0.6001424193382263,
"within_trajectory_variance_mean": 0.6001414060592651,
"between_trajectory_variance_mean": 1.021712705551181e-06,
"predictive_mean_mean_calibrated": 0.18709982931613922,
"predictive_variance_mean_calibrated": 0.6344733238220215,
"selected_model": "C6",
"temperature": 1.122980387832455
}
@@ -0,0 +1,201 @@
stage,epoch,train_observed_nll_per_scalar,train_loss,inner_selection_nll,inner_natural_accuracy,inner_natural_macro_f1,inner_natural_mae,selection_source
structured_imputer,1,1.5532822509606679,,,,,,
structured_imputer,2,1.528148040175438,,,,,,
structured_imputer,3,1.4966334303220112,,,,,,
structured_imputer,4,1.4702217976252239,,,,,,
structured_imputer,5,1.4513782262802124,,,,,,
structured_imputer,6,1.4369136691093445,,,,,,
structured_imputer,7,1.4246017287174861,,,,,,
structured_imputer,8,1.4141698280970256,,,,,,
teacher,1,,3.462034652630488,3.3566014766693115,0.4052631578947368,0.19225967540574282,1.5161516666412354,group_disjoint_internal_scenarios
teacher,2,,3.328680286804835,3.29034423828125,0.4052631578947368,0.19225967540574282,1.324126124382019,group_disjoint_internal_scenarios
teacher,3,,3.246292660633723,3.3052875995635986,0.4052631578947368,0.19225967540574282,1.2483724355697632,group_disjoint_internal_scenarios
teacher,4,,3.2161220411459603,3.2765040397644043,0.4052631578947368,0.19225967540574282,1.2843283414840698,group_disjoint_internal_scenarios
teacher,5,,3.1693802575270333,3.212984323501587,0.4052631578947368,0.19225967540574282,1.287352204322815,group_disjoint_internal_scenarios
teacher,6,,3.1070047418276467,3.1152713298797607,0.4631578947368421,0.3023726851851852,1.155389428138733,group_disjoint_internal_scenarios
teacher,7,,3.022074888149897,3.018214225769043,0.5526315789473685,0.42452164919373797,0.909277081489563,group_disjoint_internal_scenarios
teacher,8,,2.9289448956648507,2.9519646167755127,0.5894736842105263,0.46448873962286097,0.8066921234130859,group_disjoint_internal_scenarios
teacher,9,,2.8224541743596396,2.891688346862793,0.631578947368421,0.4972827549098735,0.7159743309020996,group_disjoint_internal_scenarios
teacher,10,,2.72388419508934,2.8486835956573486,0.6578947368421053,0.5555971188335681,0.69667649269104,group_disjoint_internal_scenarios
teacher,11,,2.6484831869602203,2.832411527633667,0.6684210526315789,0.5861105609087014,0.6799808740615845,group_disjoint_internal_scenarios
teacher,12,,2.58272918065389,2.8332951068878174,0.6473684210526316,0.5827807874521221,0.6745083332061768,group_disjoint_internal_scenarios
C1,1,,3.625088413556417,3.4457728266716003,0.4052631578947368,0.19225967540574282,1.6337891817092896,group_disjoint_internal_scenarios
C1,2,,3.446867972612381,3.3080549240112305,0.4052631578947368,0.19225967540574282,1.4519895315170288,group_disjoint_internal_scenarios
C1,3,,3.298306554555893,3.2529711723327637,0.4052631578947368,0.19225967540574282,1.2774684429168701,group_disjoint_internal_scenarios
C1,4,,3.2426380018393197,3.245816707611084,0.4052631578947368,0.19225967540574282,1.2816030979156494,group_disjoint_internal_scenarios
C1,5,,3.2038341959317527,3.210524797439575,0.4052631578947368,0.19225967540574282,1.3113044500350952,group_disjoint_internal_scenarios
C1,6,,3.1642958422501883,3.1716975569725037,0.43157894736842106,0.24643380368571208,1.2311570644378662,group_disjoint_internal_scenarios
C1,7,,3.115392714738846,3.1206790804862976,0.5526315789473685,0.4230936819172113,0.9385260939598083,group_disjoint_internal_scenarios
C1,8,,3.064149796962738,3.0661433339118958,0.5842105263157895,0.4583850931677018,0.8695384860038757,group_disjoint_internal_scenarios
C1,9,,3.003529200951258,3.0254677534103394,0.6052631578947368,0.4791029561671764,0.810080349445343,group_disjoint_internal_scenarios
C1,10,,2.9559323290983834,2.9842147827148438,0.6157894736842106,0.4852838310465429,0.7587557435035706,group_disjoint_internal_scenarios
C1,11,,2.902411013841629,2.9415759444236755,0.6157894736842106,0.5008969964989866,0.7657654881477356,group_disjoint_internal_scenarios
C1,12,,2.855019211769104,2.901727080345154,0.6263157894736842,0.5366694231835751,0.7315037250518799,group_disjoint_internal_scenarios
C2,1,,3.537787844737371,3.3620360493659973,0.4052631578947368,0.19225967540574282,1.5527148246765137,group_disjoint_internal_scenarios
C2,2,,3.3904086450735726,3.266030967235565,0.4052631578947368,0.19225967540574282,1.3979792594909668,group_disjoint_internal_scenarios
C2,3,,3.2736210326353707,3.2449108958244324,0.4052631578947368,0.19225967540574282,1.2796080112457275,group_disjoint_internal_scenarios
C2,4,,3.229355643192927,3.224508762359619,0.4052631578947368,0.19225967540574282,1.293556571006775,group_disjoint_internal_scenarios
C2,5,,3.1855053901672363,3.1826480627059937,0.4052631578947368,0.19225967540574282,1.2995216846466064,group_disjoint_internal_scenarios
C2,6,,3.1340996424357095,3.1313324570655823,0.48947368421052634,0.34304341077249445,1.1094801425933838,group_disjoint_internal_scenarios
C2,7,,3.080450693766276,3.0894970893859863,0.5421052631578948,0.4115856014590192,0.9663518071174622,group_disjoint_internal_scenarios
C2,8,,3.033092975616455,3.0433709025382996,0.5789473684210527,0.4515823720792665,0.8674063682556152,group_disjoint_internal_scenarios
C2,9,,2.973719706137975,2.991317570209503,0.6052631578947368,0.4753863267795156,0.7790361046791077,group_disjoint_internal_scenarios
C2,10,,2.9355501532554626,2.9423431754112244,0.5947368421052631,0.46559829059829055,0.7608610391616821,group_disjoint_internal_scenarios
C2,11,,2.8770320216814675,2.9117713570594788,0.6,0.46507619383397963,0.7450714707374573,group_disjoint_internal_scenarios
C2,12,,2.823687126239141,2.9001985788345337,0.6,0.47456646492674553,0.72516268491745,group_disjoint_internal_scenarios
C3,1,,3.6558842261632285,3.384518265724182,0.4052631578947368,0.19225967540574282,1.559212327003479,group_disjoint_internal_scenarios
C3,2,,3.4921026726563773,3.268451452255249,0.4052631578947368,0.19225967540574282,1.3527249097824097,group_disjoint_internal_scenarios
C3,3,,3.384129673242569,3.2711148262023926,0.4052631578947368,0.19225967540574282,1.2468868494033813,group_disjoint_internal_scenarios
C3,4,,3.351481109857559,3.2908926010131836,0.4052631578947368,0.19225967540574282,1.2705941200256348,group_disjoint_internal_scenarios
C3,5,,3.3176944851875305,3.2589112520217896,0.4052631578947368,0.19225967540574282,1.282788872718811,group_disjoint_internal_scenarios
C3,6,,3.2691671550273895,3.2086825370788574,0.4052631578947368,0.19225967540574282,1.3017680644989014,group_disjoint_internal_scenarios
C3,7,,3.202888548374176,3.14694482088089,0.47368421052631576,0.3192168546499255,1.115231990814209,group_disjoint_internal_scenarios
C3,8,,3.1294551491737366,3.0830236077308655,0.5736842105263158,0.44487613884496646,0.8796601891517639,group_disjoint_internal_scenarios
C3,9,,3.0485441088676453,3.0048487782478333,0.6105263157894737,0.4795948021754473,0.7953904271125793,group_disjoint_internal_scenarios
C3,10,,2.973482757806778,2.938908636569977,0.6157894736842106,0.4797003509874797,0.7715549468994141,group_disjoint_internal_scenarios
C3,11,,2.903808911641439,2.9034862518310547,0.631578947368421,0.48848207475209765,0.7345849871635437,group_disjoint_internal_scenarios
C3,12,,2.844705899556478,2.8694076538085938,0.631578947368421,0.4899428057322794,0.6989896893501282,group_disjoint_internal_scenarios
C4,1,,3.6013375520706177,3.332814633846283,0.2736842105263158,0.17082621082621083,0.9378437399864197,group_disjoint_internal_scenarios
C4,2,,3.479383409023285,3.271034359931946,0.4052631578947368,0.19225967540574282,1.3177491426467896,group_disjoint_internal_scenarios
C4,3,,3.3795010447502136,3.285194993019104,0.4052631578947368,0.19225967540574282,1.2431234121322632,group_disjoint_internal_scenarios
C4,4,,3.3379427591959634,3.259019613265991,0.4052631578947368,0.19225967540574282,1.286502718925476,group_disjoint_internal_scenarios
C4,5,,3.29158349831899,3.1893283128738403,0.41578947368421054,0.21487471298792052,1.2786555290222168,group_disjoint_internal_scenarios
C4,6,,3.2405782540639243,3.128665268421173,0.5789473684210527,0.4518936827046156,0.9166836142539978,group_disjoint_internal_scenarios
C4,7,,3.1832628746827445,3.073520600795746,0.5736842105263158,0.4461403430475596,0.884451150894165,group_disjoint_internal_scenarios
C4,8,,3.136505603790283,3.003846764564514,0.5894736842105263,0.46306900341257445,0.8538134098052979,group_disjoint_internal_scenarios
C4,9,,3.0712250769138336,2.957157254219055,0.6263157894736842,0.4971737077289579,0.7650657296180725,group_disjoint_internal_scenarios
C4,10,,3.000265379746755,2.894549548625946,0.6263157894736842,0.4957351290684624,0.7408508062362671,group_disjoint_internal_scenarios
C4,11,,2.9216533501942954,2.8611021637916565,0.6263157894736842,0.5147248652604963,0.7227466702461243,group_disjoint_internal_scenarios
C4,12,,2.855973720550537,2.854860305786133,0.6421052631578947,0.5766158315177923,0.6649736166000366,group_disjoint_internal_scenarios
C5,1,,3.648116648197174,3.391767203807831,0.4052631578947368,0.19225967540574282,1.5741225481033325,group_disjoint_internal_scenarios
C5,2,,3.492997576793035,3.279097855091095,0.4052631578947368,0.19225967540574282,1.3879157304763794,group_disjoint_internal_scenarios
C5,3,,3.371471087137858,3.2802674770355225,0.4052631578947368,0.19225967540574282,1.2592568397521973,group_disjoint_internal_scenarios
C5,4,,3.334533045689265,3.250081419944763,0.4052631578947368,0.19225967540574282,1.313844084739685,group_disjoint_internal_scenarios
C5,5,,3.2844751278559365,3.161647081375122,0.5631578947368421,0.4363765629588414,0.9632841348648071,group_disjoint_internal_scenarios
C5,6,,3.223735253016154,3.067867398262024,0.6157894736842106,0.4870478245235527,0.8223584890365601,group_disjoint_internal_scenarios
C5,7,,3.1524856885274253,2.982391655445099,0.631578947368421,0.4990825688073395,0.7661831378936768,group_disjoint_internal_scenarios
C5,8,,3.0939479370911918,2.939557671546936,0.631578947368421,0.4997578692493947,0.7375786304473877,group_disjoint_internal_scenarios
C5,9,,3.0242554247379303,2.8982234597206116,0.6263157894736842,0.4912183908045977,0.7326452136039734,group_disjoint_internal_scenarios
C5,10,,2.963417728741964,2.873548924922943,0.6263157894736842,0.48854166666666665,0.724014937877655,group_disjoint_internal_scenarios
C5,11,,2.890074610710144,2.8580190539360046,0.6105263157894737,0.47402164435554184,0.7357648611068726,group_disjoint_internal_scenarios
C5,12,,2.8306974867979684,2.864997088909149,0.6,0.4757099720980011,0.7161284685134888,group_disjoint_internal_scenarios
C6,1,,3.5560630758603415,3.3430938720703125,0.4052631578947368,0.19225967540574282,1.4975899457931519,group_disjoint_internal_scenarios
C6,2,,3.453421543041865,3.2893688678741455,0.4052631578947368,0.19225967540574282,1.3801339864730835,group_disjoint_internal_scenarios
C6,3,,3.3749252458413443,3.283313035964966,0.4052631578947368,0.19225967540574282,1.2556867599487305,group_disjoint_internal_scenarios
C6,4,,3.3421215315659842,3.2622945308685303,0.4052631578947368,0.19225967540574282,1.2634124755859375,group_disjoint_internal_scenarios
C6,5,,3.293413112560908,3.1872403621673584,0.4052631578947368,0.19225967540574282,1.2729334831237793,group_disjoint_internal_scenarios
C6,6,,3.2178768316904702,3.0630359053611755,0.5947368421052631,0.4702380952380952,0.8375385403633118,group_disjoint_internal_scenarios
C6,7,,3.106997847557068,2.9654109477996826,0.6263157894736842,0.49602446483180423,0.7280592918395996,group_disjoint_internal_scenarios
C6,8,,2.9996988773345947,2.8977559208869934,0.6368421052631579,0.4975609756097561,0.7092863321304321,group_disjoint_internal_scenarios
C6,9,,2.899491469065348,2.8658425211906433,0.6263157894736842,0.486972286972287,0.7103310227394104,group_disjoint_internal_scenarios
C6,10,,2.836098611354828,2.8470621705055237,0.6368421052631579,0.5472151240756029,0.6935749053955078,group_disjoint_internal_scenarios
C6,11,,2.775729159514109,2.826770067214966,0.6473684210526316,0.5701847903340441,0.6837493777275085,group_disjoint_internal_scenarios
C6,12,,2.729355792204539,2.8364994525909424,0.6631578947368421,0.6057268651783106,0.6609827280044556,group_disjoint_internal_scenarios
C6_no_distance,1,,3.6177941958109536,3.4013763666152954,0.32105263157894737,0.16201859229747675,1.5172733068466187,group_disjoint_internal_scenarios
C6_no_distance,2,,3.5209619303544364,3.3226051926612854,0.5421052631578948,0.41686377768852,1.1565769910812378,group_disjoint_internal_scenarios
C6_no_distance,3,,3.412694732348124,3.2563387751579285,0.4052631578947368,0.19225967540574282,1.2960847616195679,group_disjoint_internal_scenarios
C6_no_distance,4,,3.341610232988993,3.2529987692832947,0.4052631578947368,0.19225967540574282,1.2612007856369019,group_disjoint_internal_scenarios
C6_no_distance,5,,3.278877317905426,3.161101818084717,0.5894736842105263,0.4579296277409484,0.91334068775177,group_disjoint_internal_scenarios
C6_no_distance,6,,3.1850637594858804,3.042643129825592,0.631578947368421,0.49,0.8398722410202026,group_disjoint_internal_scenarios
C6_no_distance,7,,3.065849353869756,2.9447609186172485,0.6263157894736842,0.4852110852110852,0.8017374277114868,group_disjoint_internal_scenarios
C6_no_distance,8,,2.9769005378087363,2.9019368290901184,0.631578947368421,0.4889713461142033,0.7686651945114136,group_disjoint_internal_scenarios
C6_no_distance,9,,2.90603373448054,2.880134403705597,0.6210526315789474,0.4805194805194805,0.7406255006790161,group_disjoint_internal_scenarios
C6_no_distance,10,,2.8530720472335815,2.8841158151626587,0.6210526315789474,0.4788202390033054,0.7437321543693542,group_disjoint_internal_scenarios
C6_no_distance,11,,2.796961178382238,2.8580946922302246,0.6263157894736842,0.49312670189452423,0.7221003770828247,group_disjoint_internal_scenarios
C6_no_distance,12,,2.765232632557551,2.8783057928085327,0.6368421052631579,0.5416640263323352,0.6775975227355957,group_disjoint_internal_scenarios
C6_no_reconstruction,1,,3.470627357562383,3.3347200751304626,0.4052631578947368,0.19225967540574282,1.476837158203125,group_disjoint_internal_scenarios
C6_no_reconstruction,2,,3.3288468619187674,3.2538111209869385,0.4052631578947368,0.19225967540574282,1.2974903583526611,group_disjoint_internal_scenarios
C6_no_reconstruction,3,,3.2453169425328574,3.2878774404525757,0.4052631578947368,0.19225967540574282,1.2463195323944092,group_disjoint_internal_scenarios
C6_no_reconstruction,4,,3.2214003006617227,3.2748806476593018,0.4052631578947368,0.19225967540574282,1.2813801765441895,group_disjoint_internal_scenarios
C6_no_reconstruction,5,,3.189190844694773,3.2269041538238525,0.4052631578947368,0.19225967540574282,1.2981008291244507,group_disjoint_internal_scenarios
C6_no_reconstruction,6,,3.1484953264395394,3.166981816291809,0.4473684210526316,0.2754928841885364,1.2332595586776733,group_disjoint_internal_scenarios
C6_no_reconstruction,7,,3.089041749636332,3.0948572158813477,0.5789473684210527,0.4504310344827586,0.902295708656311,group_disjoint_internal_scenarios
C6_no_reconstruction,8,,3.025175084670385,3.0188884139060974,0.6210526315789474,0.489092866451357,0.7917438745498657,group_disjoint_internal_scenarios
C6_no_reconstruction,9,,2.930894603331884,2.948912024497986,0.6210526315789474,0.48499135627848494,0.7593851089477539,group_disjoint_internal_scenarios
C6_no_reconstruction,10,,2.843903740247091,2.877197504043579,0.631578947368421,0.49062049062049057,0.700749933719635,group_disjoint_internal_scenarios
C6_no_reconstruction,11,,2.754317512114843,2.8311679363250732,0.6263157894736842,0.4962017839210822,0.7137499451637268,group_disjoint_internal_scenarios
C6_no_reconstruction,12,,2.699484477440516,2.8148857951164246,0.6473684210526316,0.5708362197925766,0.6621017456054688,group_disjoint_internal_scenarios
C6_pointmask,1,,3.675270746151606,3.418432056903839,0.4052631578947368,0.1929824561403509,1.6332911252975464,group_disjoint_internal_scenarios
C6_pointmask,2,,3.5329595804214478,3.3148856163024902,0.4052631578947368,0.19225967540574282,1.4748961925506592,group_disjoint_internal_scenarios
C6_pointmask,3,,3.3884001771608987,3.2753511667251587,0.4052631578947368,0.19225967540574282,1.2785439491271973,group_disjoint_internal_scenarios
C6_pointmask,4,,3.323949694633484,3.233676314353943,0.4052631578947368,0.19225967540574282,1.295992374420166,group_disjoint_internal_scenarios
C6_pointmask,5,,3.2646474639574685,3.1521087288856506,0.4631578947368421,0.3023726851851852,1.1706576347351074,group_disjoint_internal_scenarios
C6_pointmask,6,,3.1913488705952964,3.0605063438415527,0.5473684210526316,0.41843434343434344,0.940229058265686,group_disjoint_internal_scenarios
C6_pointmask,7,,3.1177627940972648,2.9455742835998535,0.6157894736842106,0.4875222435760553,0.7932655811309814,group_disjoint_internal_scenarios
C6_pointmask,8,,3.046340892712275,2.9041759371757507,0.6105263157894737,0.4840848615605897,0.774253785610199,group_disjoint_internal_scenarios
C6_pointmask,9,,2.961234758297602,2.8403647541999817,0.6526315789473685,0.561970651995049,0.6979454159736633,group_disjoint_internal_scenarios
C6_pointmask,10,,2.8737920025984445,2.830514669418335,0.6736842105263158,0.6283095854088634,0.6451393365859985,group_disjoint_internal_scenarios
C6_pointmask,11,,2.8031854728857675,2.8172165155410767,0.6947368421052632,0.64877769289534,0.6230531930923462,group_disjoint_internal_scenarios
C6_pointmask,12,,2.7474692165851593,2.8274717926979065,0.6842105263157895,0.6469497580608691,0.6270145773887634,group_disjoint_internal_scenarios
C7_distill,1,,3.544741004705429,3.3426119089126587,0.4052631578947368,0.19225967540574282,1.4921711683273315,group_disjoint_internal_scenarios
C7_distill,2,,3.421057472626368,3.2900941371917725,0.4052631578947368,0.19225967540574282,1.3196529150009155,group_disjoint_internal_scenarios
C7_distill,3,,3.358182022968928,3.2872865796089172,0.4052631578947368,0.19225967540574282,1.2709370851516724,group_disjoint_internal_scenarios
C7_distill,4,,3.3243547777334848,3.2372600436210632,0.4052631578947368,0.19225967540574282,1.299700140953064,group_disjoint_internal_scenarios
C7_distill,5,,3.264988531668981,3.132521629333496,0.5526315789473685,0.42452164919373797,0.9660311341285706,group_disjoint_internal_scenarios
C7_distill,6,,3.19478115439415,3.0291983485221863,0.6105263157894737,0.48260073260073266,0.8188617825508118,group_disjoint_internal_scenarios
C7_distill,7,,3.1164951622486115,2.9537498354911804,0.6368421052631579,0.5064208285758588,0.727095901966095,group_disjoint_internal_scenarios
C7_distill,8,,3.051979055007299,2.91681307554245,0.6210526315789474,0.4931657848324515,0.7496492266654968,group_disjoint_internal_scenarios
C7_distill,9,,2.9685777525107064,2.896312952041626,0.6105263157894737,0.4775074757446364,0.7416189312934875,group_disjoint_internal_scenarios
C7_distill,10,,2.9016930758953094,2.8869298100471497,0.6210526315789474,0.5304137409147704,0.7004271149635315,group_disjoint_internal_scenarios
C7_distill,11,,2.830535590648651,2.886876702308655,0.6263157894736842,0.5409901565507972,0.7052735686302185,group_disjoint_internal_scenarios
C7_distill,12,,2.788292189439138,2.8916757702827454,0.631578947368421,0.5709561765741541,0.6583392024040222,group_disjoint_internal_scenarios
C7_group_lambda0.05_tau0.10,1,,3.6699901123841605,3.3892515301704407,0.4052631578947368,0.19225967540574282,1.5651878118515015,group_disjoint_internal_scenarios
C7_group_lambda0.05_tau0.10,2,,3.522734651962916,3.285323143005371,0.4052631578947368,0.19225967540574282,1.3842427730560303,group_disjoint_internal_scenarios
C7_group_lambda0.05_tau0.10,3,,3.4277438720067344,3.2828831672668457,0.4052631578947368,0.19225967540574282,1.3060847520828247,group_disjoint_internal_scenarios
C7_group_lambda0.05_tau0.10,4,,3.364328056573868,3.2473665475845337,0.4052631578947368,0.19225967540574282,1.342193365097046,group_disjoint_internal_scenarios
C7_group_lambda0.05_tau0.10,5,,3.3265909254550934,3.1884942054748535,0.4631578947368421,0.3023726851851852,1.1814532279968262,group_disjoint_internal_scenarios
C7_group_lambda0.05_tau0.10,6,,3.286705712477366,3.0972980856895447,0.6105263157894737,0.48356377487969066,0.8808850646018982,group_disjoint_internal_scenarios
C7_group_lambda0.05_tau0.10,7,,3.2267816066741943,3.0294854640960693,0.5947368421052631,0.46817691477885653,0.886831521987915,group_disjoint_internal_scenarios
C7_group_lambda0.05_tau0.10,8,,3.189849923054377,2.9762118458747864,0.6157894736842106,0.48937616862145167,0.8175166249275208,group_disjoint_internal_scenarios
C7_group_lambda0.05_tau0.10,9,,3.146577626466751,2.944009244441986,0.6105263157894737,0.4843416953598951,0.8442237377166748,group_disjoint_internal_scenarios
C7_group_lambda0.05_tau0.10,10,,3.0875621835390725,2.920766055583954,0.6,0.4726287262872629,0.836346447467804,group_disjoint_internal_scenarios
C7_group_lambda0.05_tau0.10,11,,3.0492197473843894,2.911943554878235,0.6157894736842106,0.4852838310465429,0.7720956802368164,group_disjoint_internal_scenarios
C7_group_lambda0.05_tau0.10,12,,3.01773864030838,2.9069700241088867,0.6052631578947368,0.47309969092147314,0.786773681640625,group_disjoint_internal_scenarios
C7_group_lambda0.10_tau0.05,1,,3.7917567988236747,3.431395471096039,0.4052631578947368,0.19225967540574282,1.6089566946029663,group_disjoint_internal_scenarios
C7_group_lambda0.10_tau0.05,2,,3.6467959682146707,3.30967777967453,0.4052631578947368,0.19225967540574282,1.4272804260253906,group_disjoint_internal_scenarios
C7_group_lambda0.10_tau0.05,3,,3.5376113255818686,3.306707441806793,0.4052631578947368,0.19225967540574282,1.2905869483947754,group_disjoint_internal_scenarios
C7_group_lambda0.10_tau0.05,4,,3.456825832525889,3.2857162952423096,0.4052631578947368,0.19225967540574282,1.3240010738372803,group_disjoint_internal_scenarios
C7_group_lambda0.10_tau0.05,5,,3.4495691061019897,3.240543782711029,0.4052631578947368,0.19225967540574282,1.3067970275878906,group_disjoint_internal_scenarios
C7_group_lambda0.10_tau0.05,6,,3.443036218484243,3.1910694241523743,0.43157894736842106,0.24643380368571208,1.2924253940582275,group_disjoint_internal_scenarios
C7_group_lambda0.10_tau0.05,7,,3.3698772887388864,3.144593596458435,0.5526315789473685,0.42452164919373797,0.9700701832771301,group_disjoint_internal_scenarios
C7_group_lambda0.10_tau0.05,8,,3.331037163734436,3.073027789592743,0.5894736842105263,0.463676061929337,0.858289361000061,group_disjoint_internal_scenarios
C7_group_lambda0.10_tau0.05,9,,3.298823058605194,3.0421711802482605,0.5947368421052631,0.4696449026345933,0.827397882938385,group_disjoint_internal_scenarios
C7_group_lambda0.10_tau0.05,10,,3.2250280479590097,2.980533242225647,0.6210526315789474,0.4931657848324515,0.7491006851196289,group_disjoint_internal_scenarios
C7_group_lambda0.10_tau0.05,11,,3.178482929865519,2.9425472021102905,0.6210526315789474,0.4921348618031082,0.7286807298660278,group_disjoint_internal_scenarios
C7_group_lambda0.10_tau0.05,12,,3.122002293666204,2.936999499797821,0.6,0.47473416643377114,0.7731947898864746,group_disjoint_internal_scenarios
C7_group_lambda0.10_tau0.10,1,,3.7982660233974457,3.4424321055412292,0.41578947368421054,0.33451043338683784,0.970120370388031,group_disjoint_internal_scenarios
C7_group_lambda0.10_tau0.10,2,,3.6560287376244864,3.3182848691940308,0.4052631578947368,0.19225967540574282,1.4864188432693481,group_disjoint_internal_scenarios
C7_group_lambda0.10_tau0.10,3,,3.5502622425556183,3.271094262599945,0.4052631578947368,0.19225967540574282,1.3396120071411133,group_disjoint_internal_scenarios
C7_group_lambda0.10_tau0.10,4,,3.4411672353744507,3.282557487487793,0.4052631578947368,0.19225967540574282,1.31191086769104,group_disjoint_internal_scenarios
C7_group_lambda0.10_tau0.10,5,,3.420692811409632,3.2186851501464844,0.43157894736842106,0.24643380368571208,1.2519593238830566,group_disjoint_internal_scenarios
C7_group_lambda0.10_tau0.10,6,,3.384774992863337,3.120095133781433,0.5947368421052631,0.4600684047324364,0.9273067116737366,group_disjoint_internal_scenarios
C7_group_lambda0.10_tau0.10,7,,3.2720022002855935,3.0318233966827393,0.6105263157894737,0.4775641025641026,0.8281511664390564,group_disjoint_internal_scenarios
C7_group_lambda0.10_tau0.10,8,,3.1874267061551413,2.959826111793518,0.6263157894736842,0.48854166666666665,0.7915177345275879,group_disjoint_internal_scenarios
C7_group_lambda0.10_tau0.10,9,,3.1204189161459603,2.8964684009552,0.5894736842105263,0.4558302122347066,0.8305084109306335,group_disjoint_internal_scenarios
C7_group_lambda0.10_tau0.10,10,,3.0327975749969482,2.9093905091285706,0.6052631578947368,0.46880931453102503,0.7937615513801575,group_disjoint_internal_scenarios
C7_group_lambda0.10_tau0.10,11,,2.9967327415943146,2.8864620327949524,0.6,0.46428888635123644,0.7574557662010193,group_disjoint_internal_scenarios
C7_group_lambda0.10_tau0.10,12,,2.9405342042446136,2.8889219164848328,0.6052631578947368,0.4669717772692601,0.7580579519271851,group_disjoint_internal_scenarios
C7_group_lambda0.10_tau0.20,1,,3.7016623417536416,3.388068735599518,0.4052631578947368,0.19225967540574282,1.5812524557113647,group_disjoint_internal_scenarios
C7_group_lambda0.10_tau0.20,2,,3.5898077686627707,3.2949065566062927,0.4052631578947368,0.19225967540574282,1.4478111267089844,group_disjoint_internal_scenarios
C7_group_lambda0.10_tau0.20,3,,3.4932630161444345,3.2835686802864075,0.4052631578947368,0.19225967540574282,1.3127483129501343,group_disjoint_internal_scenarios
C7_group_lambda0.10_tau0.20,4,,3.408191959063212,3.281365990638733,0.4052631578947368,0.19225967540574282,1.3370603322982788,group_disjoint_internal_scenarios
C7_group_lambda0.10_tau0.20,5,,3.387180229028066,3.231750249862671,0.4052631578947368,0.19225967540574282,1.3287807703018188,group_disjoint_internal_scenarios
C7_group_lambda0.10_tau0.20,6,,3.367981960376104,3.1600507497787476,0.5736842105263158,0.44487613884496646,0.9737974405288696,group_disjoint_internal_scenarios
C7_group_lambda0.10_tau0.20,7,,3.2893512845039368,3.100860357284546,0.5894736842105263,0.46128364389233956,0.8847028017044067,group_disjoint_internal_scenarios
C7_group_lambda0.10_tau0.20,8,,3.2452140053113303,3.030231535434723,0.6,0.4697802197802197,0.8622543215751648,group_disjoint_internal_scenarios
C7_group_lambda0.10_tau0.20,9,,3.1978043218453727,2.9798112511634827,0.6105263157894737,0.4803591470258137,0.8322786688804626,group_disjoint_internal_scenarios
C7_group_lambda0.10_tau0.20,10,,3.117221931616465,2.945197343826294,0.6105263157894737,0.47991452991453,0.8018269538879395,group_disjoint_internal_scenarios
C7_group_lambda0.10_tau0.20,11,,3.060431480407715,2.933944344520569,0.6368421052631579,0.49956747980463395,0.7462747693061829,group_disjoint_internal_scenarios
C7_group_lambda0.10_tau0.20,12,,3.0112144152323403,2.9046136140823364,0.6210526315789474,0.48499135627848494,0.7529937624931335,group_disjoint_internal_scenarios
C7_group_lambda0.20_tau0.10,1,,3.8340122203032174,3.400073766708374,0.4052631578947368,0.19225967540574282,1.5749945640563965,group_disjoint_internal_scenarios
C7_group_lambda0.20_tau0.10,2,,3.702662537495295,3.3013370633125305,0.4052631578947368,0.19225967540574282,1.4297661781311035,group_disjoint_internal_scenarios
C7_group_lambda0.20_tau0.10,3,,3.64327542980512,3.2696509957313538,0.4052631578947368,0.19225967540574282,1.3239336013793945,group_disjoint_internal_scenarios
C7_group_lambda0.20_tau0.10,4,,3.511779417594274,3.261994481086731,0.4052631578947368,0.19225967540574282,1.3278520107269287,group_disjoint_internal_scenarios
C7_group_lambda0.20_tau0.10,5,,3.510362615187963,3.237016201019287,0.4052631578947368,0.19225967540574282,1.3181118965148926,group_disjoint_internal_scenarios
C7_group_lambda0.20_tau0.10,6,,3.5117766757806144,3.1881971955299377,0.4052631578947368,0.19225967540574282,1.3670039176940918,group_disjoint_internal_scenarios
C7_group_lambda0.20_tau0.10,7,,3.414328763882319,3.1437845826148987,0.4631578947368421,0.3023726851851852,1.165671944618225,group_disjoint_internal_scenarios
C7_group_lambda0.20_tau0.10,8,,3.363941212495168,3.085771083831787,0.5526315789473685,0.4230936819172113,0.9231602549552917,group_disjoint_internal_scenarios
C7_group_lambda0.20_tau0.10,9,,3.312815030415853,3.058401048183441,0.5894736842105263,0.4643199233716475,0.8149368166923523,group_disjoint_internal_scenarios
C7_group_lambda0.20_tau0.10,10,,3.2131250699361167,3.021866261959076,0.6,0.476140898837411,0.7716059684753418,group_disjoint_internal_scenarios
C7_group_lambda0.20_tau0.10,11,,3.154651701450348,2.950363576412201,0.6263157894736842,0.4949440900048021,0.7079406976699829,group_disjoint_internal_scenarios
C7_group_lambda0.20_tau0.10,12,,3.109651426474253,2.93612539768219,0.631578947368421,0.49446974625894596,0.7153028845787048,group_disjoint_internal_scenarios
1 stage epoch train_observed_nll_per_scalar train_loss inner_selection_nll inner_natural_accuracy inner_natural_macro_f1 inner_natural_mae selection_source
2 structured_imputer 1 1.5532822509606679
3 structured_imputer 2 1.528148040175438
4 structured_imputer 3 1.4966334303220112
5 structured_imputer 4 1.4702217976252239
6 structured_imputer 5 1.4513782262802124
7 structured_imputer 6 1.4369136691093445
8 structured_imputer 7 1.4246017287174861
9 structured_imputer 8 1.4141698280970256
10 teacher 1 3.462034652630488 3.3566014766693115 0.4052631578947368 0.19225967540574282 1.5161516666412354 group_disjoint_internal_scenarios
11 teacher 2 3.328680286804835 3.29034423828125 0.4052631578947368 0.19225967540574282 1.324126124382019 group_disjoint_internal_scenarios
12 teacher 3 3.246292660633723 3.3052875995635986 0.4052631578947368 0.19225967540574282 1.2483724355697632 group_disjoint_internal_scenarios
13 teacher 4 3.2161220411459603 3.2765040397644043 0.4052631578947368 0.19225967540574282 1.2843283414840698 group_disjoint_internal_scenarios
14 teacher 5 3.1693802575270333 3.212984323501587 0.4052631578947368 0.19225967540574282 1.287352204322815 group_disjoint_internal_scenarios
15 teacher 6 3.1070047418276467 3.1152713298797607 0.4631578947368421 0.3023726851851852 1.155389428138733 group_disjoint_internal_scenarios
16 teacher 7 3.022074888149897 3.018214225769043 0.5526315789473685 0.42452164919373797 0.909277081489563 group_disjoint_internal_scenarios
17 teacher 8 2.9289448956648507 2.9519646167755127 0.5894736842105263 0.46448873962286097 0.8066921234130859 group_disjoint_internal_scenarios
18 teacher 9 2.8224541743596396 2.891688346862793 0.631578947368421 0.4972827549098735 0.7159743309020996 group_disjoint_internal_scenarios
19 teacher 10 2.72388419508934 2.8486835956573486 0.6578947368421053 0.5555971188335681 0.69667649269104 group_disjoint_internal_scenarios
20 teacher 11 2.6484831869602203 2.832411527633667 0.6684210526315789 0.5861105609087014 0.6799808740615845 group_disjoint_internal_scenarios
21 teacher 12 2.58272918065389 2.8332951068878174 0.6473684210526316 0.5827807874521221 0.6745083332061768 group_disjoint_internal_scenarios
22 C1 1 3.625088413556417 3.4457728266716003 0.4052631578947368 0.19225967540574282 1.6337891817092896 group_disjoint_internal_scenarios
23 C1 2 3.446867972612381 3.3080549240112305 0.4052631578947368 0.19225967540574282 1.4519895315170288 group_disjoint_internal_scenarios
24 C1 3 3.298306554555893 3.2529711723327637 0.4052631578947368 0.19225967540574282 1.2774684429168701 group_disjoint_internal_scenarios
25 C1 4 3.2426380018393197 3.245816707611084 0.4052631578947368 0.19225967540574282 1.2816030979156494 group_disjoint_internal_scenarios
26 C1 5 3.2038341959317527 3.210524797439575 0.4052631578947368 0.19225967540574282 1.3113044500350952 group_disjoint_internal_scenarios
27 C1 6 3.1642958422501883 3.1716975569725037 0.43157894736842106 0.24643380368571208 1.2311570644378662 group_disjoint_internal_scenarios
28 C1 7 3.115392714738846 3.1206790804862976 0.5526315789473685 0.4230936819172113 0.9385260939598083 group_disjoint_internal_scenarios
29 C1 8 3.064149796962738 3.0661433339118958 0.5842105263157895 0.4583850931677018 0.8695384860038757 group_disjoint_internal_scenarios
30 C1 9 3.003529200951258 3.0254677534103394 0.6052631578947368 0.4791029561671764 0.810080349445343 group_disjoint_internal_scenarios
31 C1 10 2.9559323290983834 2.9842147827148438 0.6157894736842106 0.4852838310465429 0.7587557435035706 group_disjoint_internal_scenarios
32 C1 11 2.902411013841629 2.9415759444236755 0.6157894736842106 0.5008969964989866 0.7657654881477356 group_disjoint_internal_scenarios
33 C1 12 2.855019211769104 2.901727080345154 0.6263157894736842 0.5366694231835751 0.7315037250518799 group_disjoint_internal_scenarios
34 C2 1 3.537787844737371 3.3620360493659973 0.4052631578947368 0.19225967540574282 1.5527148246765137 group_disjoint_internal_scenarios
35 C2 2 3.3904086450735726 3.266030967235565 0.4052631578947368 0.19225967540574282 1.3979792594909668 group_disjoint_internal_scenarios
36 C2 3 3.2736210326353707 3.2449108958244324 0.4052631578947368 0.19225967540574282 1.2796080112457275 group_disjoint_internal_scenarios
37 C2 4 3.229355643192927 3.224508762359619 0.4052631578947368 0.19225967540574282 1.293556571006775 group_disjoint_internal_scenarios
38 C2 5 3.1855053901672363 3.1826480627059937 0.4052631578947368 0.19225967540574282 1.2995216846466064 group_disjoint_internal_scenarios
39 C2 6 3.1340996424357095 3.1313324570655823 0.48947368421052634 0.34304341077249445 1.1094801425933838 group_disjoint_internal_scenarios
40 C2 7 3.080450693766276 3.0894970893859863 0.5421052631578948 0.4115856014590192 0.9663518071174622 group_disjoint_internal_scenarios
41 C2 8 3.033092975616455 3.0433709025382996 0.5789473684210527 0.4515823720792665 0.8674063682556152 group_disjoint_internal_scenarios
42 C2 9 2.973719706137975 2.991317570209503 0.6052631578947368 0.4753863267795156 0.7790361046791077 group_disjoint_internal_scenarios
43 C2 10 2.9355501532554626 2.9423431754112244 0.5947368421052631 0.46559829059829055 0.7608610391616821 group_disjoint_internal_scenarios
44 C2 11 2.8770320216814675 2.9117713570594788 0.6 0.46507619383397963 0.7450714707374573 group_disjoint_internal_scenarios
45 C2 12 2.823687126239141 2.9001985788345337 0.6 0.47456646492674553 0.72516268491745 group_disjoint_internal_scenarios
46 C3 1 3.6558842261632285 3.384518265724182 0.4052631578947368 0.19225967540574282 1.559212327003479 group_disjoint_internal_scenarios
47 C3 2 3.4921026726563773 3.268451452255249 0.4052631578947368 0.19225967540574282 1.3527249097824097 group_disjoint_internal_scenarios
48 C3 3 3.384129673242569 3.2711148262023926 0.4052631578947368 0.19225967540574282 1.2468868494033813 group_disjoint_internal_scenarios
49 C3 4 3.351481109857559 3.2908926010131836 0.4052631578947368 0.19225967540574282 1.2705941200256348 group_disjoint_internal_scenarios
50 C3 5 3.3176944851875305 3.2589112520217896 0.4052631578947368 0.19225967540574282 1.282788872718811 group_disjoint_internal_scenarios
51 C3 6 3.2691671550273895 3.2086825370788574 0.4052631578947368 0.19225967540574282 1.3017680644989014 group_disjoint_internal_scenarios
52 C3 7 3.202888548374176 3.14694482088089 0.47368421052631576 0.3192168546499255 1.115231990814209 group_disjoint_internal_scenarios
53 C3 8 3.1294551491737366 3.0830236077308655 0.5736842105263158 0.44487613884496646 0.8796601891517639 group_disjoint_internal_scenarios
54 C3 9 3.0485441088676453 3.0048487782478333 0.6105263157894737 0.4795948021754473 0.7953904271125793 group_disjoint_internal_scenarios
55 C3 10 2.973482757806778 2.938908636569977 0.6157894736842106 0.4797003509874797 0.7715549468994141 group_disjoint_internal_scenarios
56 C3 11 2.903808911641439 2.9034862518310547 0.631578947368421 0.48848207475209765 0.7345849871635437 group_disjoint_internal_scenarios
57 C3 12 2.844705899556478 2.8694076538085938 0.631578947368421 0.4899428057322794 0.6989896893501282 group_disjoint_internal_scenarios
58 C4 1 3.6013375520706177 3.332814633846283 0.2736842105263158 0.17082621082621083 0.9378437399864197 group_disjoint_internal_scenarios
59 C4 2 3.479383409023285 3.271034359931946 0.4052631578947368 0.19225967540574282 1.3177491426467896 group_disjoint_internal_scenarios
60 C4 3 3.3795010447502136 3.285194993019104 0.4052631578947368 0.19225967540574282 1.2431234121322632 group_disjoint_internal_scenarios
61 C4 4 3.3379427591959634 3.259019613265991 0.4052631578947368 0.19225967540574282 1.286502718925476 group_disjoint_internal_scenarios
62 C4 5 3.29158349831899 3.1893283128738403 0.41578947368421054 0.21487471298792052 1.2786555290222168 group_disjoint_internal_scenarios
63 C4 6 3.2405782540639243 3.128665268421173 0.5789473684210527 0.4518936827046156 0.9166836142539978 group_disjoint_internal_scenarios
64 C4 7 3.1832628746827445 3.073520600795746 0.5736842105263158 0.4461403430475596 0.884451150894165 group_disjoint_internal_scenarios
65 C4 8 3.136505603790283 3.003846764564514 0.5894736842105263 0.46306900341257445 0.8538134098052979 group_disjoint_internal_scenarios
66 C4 9 3.0712250769138336 2.957157254219055 0.6263157894736842 0.4971737077289579 0.7650657296180725 group_disjoint_internal_scenarios
67 C4 10 3.000265379746755 2.894549548625946 0.6263157894736842 0.4957351290684624 0.7408508062362671 group_disjoint_internal_scenarios
68 C4 11 2.9216533501942954 2.8611021637916565 0.6263157894736842 0.5147248652604963 0.7227466702461243 group_disjoint_internal_scenarios
69 C4 12 2.855973720550537 2.854860305786133 0.6421052631578947 0.5766158315177923 0.6649736166000366 group_disjoint_internal_scenarios
70 C5 1 3.648116648197174 3.391767203807831 0.4052631578947368 0.19225967540574282 1.5741225481033325 group_disjoint_internal_scenarios
71 C5 2 3.492997576793035 3.279097855091095 0.4052631578947368 0.19225967540574282 1.3879157304763794 group_disjoint_internal_scenarios
72 C5 3 3.371471087137858 3.2802674770355225 0.4052631578947368 0.19225967540574282 1.2592568397521973 group_disjoint_internal_scenarios
73 C5 4 3.334533045689265 3.250081419944763 0.4052631578947368 0.19225967540574282 1.313844084739685 group_disjoint_internal_scenarios
74 C5 5 3.2844751278559365 3.161647081375122 0.5631578947368421 0.4363765629588414 0.9632841348648071 group_disjoint_internal_scenarios
75 C5 6 3.223735253016154 3.067867398262024 0.6157894736842106 0.4870478245235527 0.8223584890365601 group_disjoint_internal_scenarios
76 C5 7 3.1524856885274253 2.982391655445099 0.631578947368421 0.4990825688073395 0.7661831378936768 group_disjoint_internal_scenarios
77 C5 8 3.0939479370911918 2.939557671546936 0.631578947368421 0.4997578692493947 0.7375786304473877 group_disjoint_internal_scenarios
78 C5 9 3.0242554247379303 2.8982234597206116 0.6263157894736842 0.4912183908045977 0.7326452136039734 group_disjoint_internal_scenarios
79 C5 10 2.963417728741964 2.873548924922943 0.6263157894736842 0.48854166666666665 0.724014937877655 group_disjoint_internal_scenarios
80 C5 11 2.890074610710144 2.8580190539360046 0.6105263157894737 0.47402164435554184 0.7357648611068726 group_disjoint_internal_scenarios
81 C5 12 2.8306974867979684 2.864997088909149 0.6 0.4757099720980011 0.7161284685134888 group_disjoint_internal_scenarios
82 C6 1 3.5560630758603415 3.3430938720703125 0.4052631578947368 0.19225967540574282 1.4975899457931519 group_disjoint_internal_scenarios
83 C6 2 3.453421543041865 3.2893688678741455 0.4052631578947368 0.19225967540574282 1.3801339864730835 group_disjoint_internal_scenarios
84 C6 3 3.3749252458413443 3.283313035964966 0.4052631578947368 0.19225967540574282 1.2556867599487305 group_disjoint_internal_scenarios
85 C6 4 3.3421215315659842 3.2622945308685303 0.4052631578947368 0.19225967540574282 1.2634124755859375 group_disjoint_internal_scenarios
86 C6 5 3.293413112560908 3.1872403621673584 0.4052631578947368 0.19225967540574282 1.2729334831237793 group_disjoint_internal_scenarios
87 C6 6 3.2178768316904702 3.0630359053611755 0.5947368421052631 0.4702380952380952 0.8375385403633118 group_disjoint_internal_scenarios
88 C6 7 3.106997847557068 2.9654109477996826 0.6263157894736842 0.49602446483180423 0.7280592918395996 group_disjoint_internal_scenarios
89 C6 8 2.9996988773345947 2.8977559208869934 0.6368421052631579 0.4975609756097561 0.7092863321304321 group_disjoint_internal_scenarios
90 C6 9 2.899491469065348 2.8658425211906433 0.6263157894736842 0.486972286972287 0.7103310227394104 group_disjoint_internal_scenarios
91 C6 10 2.836098611354828 2.8470621705055237 0.6368421052631579 0.5472151240756029 0.6935749053955078 group_disjoint_internal_scenarios
92 C6 11 2.775729159514109 2.826770067214966 0.6473684210526316 0.5701847903340441 0.6837493777275085 group_disjoint_internal_scenarios
93 C6 12 2.729355792204539 2.8364994525909424 0.6631578947368421 0.6057268651783106 0.6609827280044556 group_disjoint_internal_scenarios
94 C6_no_distance 1 3.6177941958109536 3.4013763666152954 0.32105263157894737 0.16201859229747675 1.5172733068466187 group_disjoint_internal_scenarios
95 C6_no_distance 2 3.5209619303544364 3.3226051926612854 0.5421052631578948 0.41686377768852 1.1565769910812378 group_disjoint_internal_scenarios
96 C6_no_distance 3 3.412694732348124 3.2563387751579285 0.4052631578947368 0.19225967540574282 1.2960847616195679 group_disjoint_internal_scenarios
97 C6_no_distance 4 3.341610232988993 3.2529987692832947 0.4052631578947368 0.19225967540574282 1.2612007856369019 group_disjoint_internal_scenarios
98 C6_no_distance 5 3.278877317905426 3.161101818084717 0.5894736842105263 0.4579296277409484 0.91334068775177 group_disjoint_internal_scenarios
99 C6_no_distance 6 3.1850637594858804 3.042643129825592 0.631578947368421 0.49 0.8398722410202026 group_disjoint_internal_scenarios
100 C6_no_distance 7 3.065849353869756 2.9447609186172485 0.6263157894736842 0.4852110852110852 0.8017374277114868 group_disjoint_internal_scenarios
101 C6_no_distance 8 2.9769005378087363 2.9019368290901184 0.631578947368421 0.4889713461142033 0.7686651945114136 group_disjoint_internal_scenarios
102 C6_no_distance 9 2.90603373448054 2.880134403705597 0.6210526315789474 0.4805194805194805 0.7406255006790161 group_disjoint_internal_scenarios
103 C6_no_distance 10 2.8530720472335815 2.8841158151626587 0.6210526315789474 0.4788202390033054 0.7437321543693542 group_disjoint_internal_scenarios
104 C6_no_distance 11 2.796961178382238 2.8580946922302246 0.6263157894736842 0.49312670189452423 0.7221003770828247 group_disjoint_internal_scenarios
105 C6_no_distance 12 2.765232632557551 2.8783057928085327 0.6368421052631579 0.5416640263323352 0.6775975227355957 group_disjoint_internal_scenarios
106 C6_no_reconstruction 1 3.470627357562383 3.3347200751304626 0.4052631578947368 0.19225967540574282 1.476837158203125 group_disjoint_internal_scenarios
107 C6_no_reconstruction 2 3.3288468619187674 3.2538111209869385 0.4052631578947368 0.19225967540574282 1.2974903583526611 group_disjoint_internal_scenarios
108 C6_no_reconstruction 3 3.2453169425328574 3.2878774404525757 0.4052631578947368 0.19225967540574282 1.2463195323944092 group_disjoint_internal_scenarios
109 C6_no_reconstruction 4 3.2214003006617227 3.2748806476593018 0.4052631578947368 0.19225967540574282 1.2813801765441895 group_disjoint_internal_scenarios
110 C6_no_reconstruction 5 3.189190844694773 3.2269041538238525 0.4052631578947368 0.19225967540574282 1.2981008291244507 group_disjoint_internal_scenarios
111 C6_no_reconstruction 6 3.1484953264395394 3.166981816291809 0.4473684210526316 0.2754928841885364 1.2332595586776733 group_disjoint_internal_scenarios
112 C6_no_reconstruction 7 3.089041749636332 3.0948572158813477 0.5789473684210527 0.4504310344827586 0.902295708656311 group_disjoint_internal_scenarios
113 C6_no_reconstruction 8 3.025175084670385 3.0188884139060974 0.6210526315789474 0.489092866451357 0.7917438745498657 group_disjoint_internal_scenarios
114 C6_no_reconstruction 9 2.930894603331884 2.948912024497986 0.6210526315789474 0.48499135627848494 0.7593851089477539 group_disjoint_internal_scenarios
115 C6_no_reconstruction 10 2.843903740247091 2.877197504043579 0.631578947368421 0.49062049062049057 0.700749933719635 group_disjoint_internal_scenarios
116 C6_no_reconstruction 11 2.754317512114843 2.8311679363250732 0.6263157894736842 0.4962017839210822 0.7137499451637268 group_disjoint_internal_scenarios
117 C6_no_reconstruction 12 2.699484477440516 2.8148857951164246 0.6473684210526316 0.5708362197925766 0.6621017456054688 group_disjoint_internal_scenarios
118 C6_pointmask 1 3.675270746151606 3.418432056903839 0.4052631578947368 0.1929824561403509 1.6332911252975464 group_disjoint_internal_scenarios
119 C6_pointmask 2 3.5329595804214478 3.3148856163024902 0.4052631578947368 0.19225967540574282 1.4748961925506592 group_disjoint_internal_scenarios
120 C6_pointmask 3 3.3884001771608987 3.2753511667251587 0.4052631578947368 0.19225967540574282 1.2785439491271973 group_disjoint_internal_scenarios
121 C6_pointmask 4 3.323949694633484 3.233676314353943 0.4052631578947368 0.19225967540574282 1.295992374420166 group_disjoint_internal_scenarios
122 C6_pointmask 5 3.2646474639574685 3.1521087288856506 0.4631578947368421 0.3023726851851852 1.1706576347351074 group_disjoint_internal_scenarios
123 C6_pointmask 6 3.1913488705952964 3.0605063438415527 0.5473684210526316 0.41843434343434344 0.940229058265686 group_disjoint_internal_scenarios
124 C6_pointmask 7 3.1177627940972648 2.9455742835998535 0.6157894736842106 0.4875222435760553 0.7932655811309814 group_disjoint_internal_scenarios
125 C6_pointmask 8 3.046340892712275 2.9041759371757507 0.6105263157894737 0.4840848615605897 0.774253785610199 group_disjoint_internal_scenarios
126 C6_pointmask 9 2.961234758297602 2.8403647541999817 0.6526315789473685 0.561970651995049 0.6979454159736633 group_disjoint_internal_scenarios
127 C6_pointmask 10 2.8737920025984445 2.830514669418335 0.6736842105263158 0.6283095854088634 0.6451393365859985 group_disjoint_internal_scenarios
128 C6_pointmask 11 2.8031854728857675 2.8172165155410767 0.6947368421052632 0.64877769289534 0.6230531930923462 group_disjoint_internal_scenarios
129 C6_pointmask 12 2.7474692165851593 2.8274717926979065 0.6842105263157895 0.6469497580608691 0.6270145773887634 group_disjoint_internal_scenarios
130 C7_distill 1 3.544741004705429 3.3426119089126587 0.4052631578947368 0.19225967540574282 1.4921711683273315 group_disjoint_internal_scenarios
131 C7_distill 2 3.421057472626368 3.2900941371917725 0.4052631578947368 0.19225967540574282 1.3196529150009155 group_disjoint_internal_scenarios
132 C7_distill 3 3.358182022968928 3.2872865796089172 0.4052631578947368 0.19225967540574282 1.2709370851516724 group_disjoint_internal_scenarios
133 C7_distill 4 3.3243547777334848 3.2372600436210632 0.4052631578947368 0.19225967540574282 1.299700140953064 group_disjoint_internal_scenarios
134 C7_distill 5 3.264988531668981 3.132521629333496 0.5526315789473685 0.42452164919373797 0.9660311341285706 group_disjoint_internal_scenarios
135 C7_distill 6 3.19478115439415 3.0291983485221863 0.6105263157894737 0.48260073260073266 0.8188617825508118 group_disjoint_internal_scenarios
136 C7_distill 7 3.1164951622486115 2.9537498354911804 0.6368421052631579 0.5064208285758588 0.727095901966095 group_disjoint_internal_scenarios
137 C7_distill 8 3.051979055007299 2.91681307554245 0.6210526315789474 0.4931657848324515 0.7496492266654968 group_disjoint_internal_scenarios
138 C7_distill 9 2.9685777525107064 2.896312952041626 0.6105263157894737 0.4775074757446364 0.7416189312934875 group_disjoint_internal_scenarios
139 C7_distill 10 2.9016930758953094 2.8869298100471497 0.6210526315789474 0.5304137409147704 0.7004271149635315 group_disjoint_internal_scenarios
140 C7_distill 11 2.830535590648651 2.886876702308655 0.6263157894736842 0.5409901565507972 0.7052735686302185 group_disjoint_internal_scenarios
141 C7_distill 12 2.788292189439138 2.8916757702827454 0.631578947368421 0.5709561765741541 0.6583392024040222 group_disjoint_internal_scenarios
142 C7_group_lambda0.05_tau0.10 1 3.6699901123841605 3.3892515301704407 0.4052631578947368 0.19225967540574282 1.5651878118515015 group_disjoint_internal_scenarios
143 C7_group_lambda0.05_tau0.10 2 3.522734651962916 3.285323143005371 0.4052631578947368 0.19225967540574282 1.3842427730560303 group_disjoint_internal_scenarios
144 C7_group_lambda0.05_tau0.10 3 3.4277438720067344 3.2828831672668457 0.4052631578947368 0.19225967540574282 1.3060847520828247 group_disjoint_internal_scenarios
145 C7_group_lambda0.05_tau0.10 4 3.364328056573868 3.2473665475845337 0.4052631578947368 0.19225967540574282 1.342193365097046 group_disjoint_internal_scenarios
146 C7_group_lambda0.05_tau0.10 5 3.3265909254550934 3.1884942054748535 0.4631578947368421 0.3023726851851852 1.1814532279968262 group_disjoint_internal_scenarios
147 C7_group_lambda0.05_tau0.10 6 3.286705712477366 3.0972980856895447 0.6105263157894737 0.48356377487969066 0.8808850646018982 group_disjoint_internal_scenarios
148 C7_group_lambda0.05_tau0.10 7 3.2267816066741943 3.0294854640960693 0.5947368421052631 0.46817691477885653 0.886831521987915 group_disjoint_internal_scenarios
149 C7_group_lambda0.05_tau0.10 8 3.189849923054377 2.9762118458747864 0.6157894736842106 0.48937616862145167 0.8175166249275208 group_disjoint_internal_scenarios
150 C7_group_lambda0.05_tau0.10 9 3.146577626466751 2.944009244441986 0.6105263157894737 0.4843416953598951 0.8442237377166748 group_disjoint_internal_scenarios
151 C7_group_lambda0.05_tau0.10 10 3.0875621835390725 2.920766055583954 0.6 0.4726287262872629 0.836346447467804 group_disjoint_internal_scenarios
152 C7_group_lambda0.05_tau0.10 11 3.0492197473843894 2.911943554878235 0.6157894736842106 0.4852838310465429 0.7720956802368164 group_disjoint_internal_scenarios
153 C7_group_lambda0.05_tau0.10 12 3.01773864030838 2.9069700241088867 0.6052631578947368 0.47309969092147314 0.786773681640625 group_disjoint_internal_scenarios
154 C7_group_lambda0.10_tau0.05 1 3.7917567988236747 3.431395471096039 0.4052631578947368 0.19225967540574282 1.6089566946029663 group_disjoint_internal_scenarios
155 C7_group_lambda0.10_tau0.05 2 3.6467959682146707 3.30967777967453 0.4052631578947368 0.19225967540574282 1.4272804260253906 group_disjoint_internal_scenarios
156 C7_group_lambda0.10_tau0.05 3 3.5376113255818686 3.306707441806793 0.4052631578947368 0.19225967540574282 1.2905869483947754 group_disjoint_internal_scenarios
157 C7_group_lambda0.10_tau0.05 4 3.456825832525889 3.2857162952423096 0.4052631578947368 0.19225967540574282 1.3240010738372803 group_disjoint_internal_scenarios
158 C7_group_lambda0.10_tau0.05 5 3.4495691061019897 3.240543782711029 0.4052631578947368 0.19225967540574282 1.3067970275878906 group_disjoint_internal_scenarios
159 C7_group_lambda0.10_tau0.05 6 3.443036218484243 3.1910694241523743 0.43157894736842106 0.24643380368571208 1.2924253940582275 group_disjoint_internal_scenarios
160 C7_group_lambda0.10_tau0.05 7 3.3698772887388864 3.144593596458435 0.5526315789473685 0.42452164919373797 0.9700701832771301 group_disjoint_internal_scenarios
161 C7_group_lambda0.10_tau0.05 8 3.331037163734436 3.073027789592743 0.5894736842105263 0.463676061929337 0.858289361000061 group_disjoint_internal_scenarios
162 C7_group_lambda0.10_tau0.05 9 3.298823058605194 3.0421711802482605 0.5947368421052631 0.4696449026345933 0.827397882938385 group_disjoint_internal_scenarios
163 C7_group_lambda0.10_tau0.05 10 3.2250280479590097 2.980533242225647 0.6210526315789474 0.4931657848324515 0.7491006851196289 group_disjoint_internal_scenarios
164 C7_group_lambda0.10_tau0.05 11 3.178482929865519 2.9425472021102905 0.6210526315789474 0.4921348618031082 0.7286807298660278 group_disjoint_internal_scenarios
165 C7_group_lambda0.10_tau0.05 12 3.122002293666204 2.936999499797821 0.6 0.47473416643377114 0.7731947898864746 group_disjoint_internal_scenarios
166 C7_group_lambda0.10_tau0.10 1 3.7982660233974457 3.4424321055412292 0.41578947368421054 0.33451043338683784 0.970120370388031 group_disjoint_internal_scenarios
167 C7_group_lambda0.10_tau0.10 2 3.6560287376244864 3.3182848691940308 0.4052631578947368 0.19225967540574282 1.4864188432693481 group_disjoint_internal_scenarios
168 C7_group_lambda0.10_tau0.10 3 3.5502622425556183 3.271094262599945 0.4052631578947368 0.19225967540574282 1.3396120071411133 group_disjoint_internal_scenarios
169 C7_group_lambda0.10_tau0.10 4 3.4411672353744507 3.282557487487793 0.4052631578947368 0.19225967540574282 1.31191086769104 group_disjoint_internal_scenarios
170 C7_group_lambda0.10_tau0.10 5 3.420692811409632 3.2186851501464844 0.43157894736842106 0.24643380368571208 1.2519593238830566 group_disjoint_internal_scenarios
171 C7_group_lambda0.10_tau0.10 6 3.384774992863337 3.120095133781433 0.5947368421052631 0.4600684047324364 0.9273067116737366 group_disjoint_internal_scenarios
172 C7_group_lambda0.10_tau0.10 7 3.2720022002855935 3.0318233966827393 0.6105263157894737 0.4775641025641026 0.8281511664390564 group_disjoint_internal_scenarios
173 C7_group_lambda0.10_tau0.10 8 3.1874267061551413 2.959826111793518 0.6263157894736842 0.48854166666666665 0.7915177345275879 group_disjoint_internal_scenarios
174 C7_group_lambda0.10_tau0.10 9 3.1204189161459603 2.8964684009552 0.5894736842105263 0.4558302122347066 0.8305084109306335 group_disjoint_internal_scenarios
175 C7_group_lambda0.10_tau0.10 10 3.0327975749969482 2.9093905091285706 0.6052631578947368 0.46880931453102503 0.7937615513801575 group_disjoint_internal_scenarios
176 C7_group_lambda0.10_tau0.10 11 2.9967327415943146 2.8864620327949524 0.6 0.46428888635123644 0.7574557662010193 group_disjoint_internal_scenarios
177 C7_group_lambda0.10_tau0.10 12 2.9405342042446136 2.8889219164848328 0.6052631578947368 0.4669717772692601 0.7580579519271851 group_disjoint_internal_scenarios
178 C7_group_lambda0.10_tau0.20 1 3.7016623417536416 3.388068735599518 0.4052631578947368 0.19225967540574282 1.5812524557113647 group_disjoint_internal_scenarios
179 C7_group_lambda0.10_tau0.20 2 3.5898077686627707 3.2949065566062927 0.4052631578947368 0.19225967540574282 1.4478111267089844 group_disjoint_internal_scenarios
180 C7_group_lambda0.10_tau0.20 3 3.4932630161444345 3.2835686802864075 0.4052631578947368 0.19225967540574282 1.3127483129501343 group_disjoint_internal_scenarios
181 C7_group_lambda0.10_tau0.20 4 3.408191959063212 3.281365990638733 0.4052631578947368 0.19225967540574282 1.3370603322982788 group_disjoint_internal_scenarios
182 C7_group_lambda0.10_tau0.20 5 3.387180229028066 3.231750249862671 0.4052631578947368 0.19225967540574282 1.3287807703018188 group_disjoint_internal_scenarios
183 C7_group_lambda0.10_tau0.20 6 3.367981960376104 3.1600507497787476 0.5736842105263158 0.44487613884496646 0.9737974405288696 group_disjoint_internal_scenarios
184 C7_group_lambda0.10_tau0.20 7 3.2893512845039368 3.100860357284546 0.5894736842105263 0.46128364389233956 0.8847028017044067 group_disjoint_internal_scenarios
185 C7_group_lambda0.10_tau0.20 8 3.2452140053113303 3.030231535434723 0.6 0.4697802197802197 0.8622543215751648 group_disjoint_internal_scenarios
186 C7_group_lambda0.10_tau0.20 9 3.1978043218453727 2.9798112511634827 0.6105263157894737 0.4803591470258137 0.8322786688804626 group_disjoint_internal_scenarios
187 C7_group_lambda0.10_tau0.20 10 3.117221931616465 2.945197343826294 0.6105263157894737 0.47991452991453 0.8018269538879395 group_disjoint_internal_scenarios
188 C7_group_lambda0.10_tau0.20 11 3.060431480407715 2.933944344520569 0.6368421052631579 0.49956747980463395 0.7462747693061829 group_disjoint_internal_scenarios
189 C7_group_lambda0.10_tau0.20 12 3.0112144152323403 2.9046136140823364 0.6210526315789474 0.48499135627848494 0.7529937624931335 group_disjoint_internal_scenarios
190 C7_group_lambda0.20_tau0.10 1 3.8340122203032174 3.400073766708374 0.4052631578947368 0.19225967540574282 1.5749945640563965 group_disjoint_internal_scenarios
191 C7_group_lambda0.20_tau0.10 2 3.702662537495295 3.3013370633125305 0.4052631578947368 0.19225967540574282 1.4297661781311035 group_disjoint_internal_scenarios
192 C7_group_lambda0.20_tau0.10 3 3.64327542980512 3.2696509957313538 0.4052631578947368 0.19225967540574282 1.3239336013793945 group_disjoint_internal_scenarios
193 C7_group_lambda0.20_tau0.10 4 3.511779417594274 3.261994481086731 0.4052631578947368 0.19225967540574282 1.3278520107269287 group_disjoint_internal_scenarios
194 C7_group_lambda0.20_tau0.10 5 3.510362615187963 3.237016201019287 0.4052631578947368 0.19225967540574282 1.3181118965148926 group_disjoint_internal_scenarios
195 C7_group_lambda0.20_tau0.10 6 3.5117766757806144 3.1881971955299377 0.4052631578947368 0.19225967540574282 1.3670039176940918 group_disjoint_internal_scenarios
196 C7_group_lambda0.20_tau0.10 7 3.414328763882319 3.1437845826148987 0.4631578947368421 0.3023726851851852 1.165671944618225 group_disjoint_internal_scenarios
197 C7_group_lambda0.20_tau0.10 8 3.363941212495168 3.085771083831787 0.5526315789473685 0.4230936819172113 0.9231602549552917 group_disjoint_internal_scenarios
198 C7_group_lambda0.20_tau0.10 9 3.312815030415853 3.058401048183441 0.5894736842105263 0.4643199233716475 0.8149368166923523 group_disjoint_internal_scenarios
199 C7_group_lambda0.20_tau0.10 10 3.2131250699361167 3.021866261959076 0.6 0.476140898837411 0.7716059684753418 group_disjoint_internal_scenarios
200 C7_group_lambda0.20_tau0.10 11 3.154651701450348 2.950363576412201 0.6263157894736842 0.4949440900048021 0.7079406976699829 group_disjoint_internal_scenarios
201 C7_group_lambda0.20_tau0.10 12 3.109651426474253 2.93612539768219 0.631578947368421 0.49446974625894596 0.7153028845787048 group_disjoint_internal_scenarios
@@ -0,0 +1,78 @@
model,baseline,metric,point_delta,bootstrap_median_delta,ci_2_5,ci_97_5,replicates,unit
C1,C0,accuracy,-0.0027472527472527375,-0.001340239501606888,-0.0415489514789989,0.03692233632862645,300,paired source-video group resample
C1,C0,macro_f1,-0.08342531441150824,-0.0839257600579568,-0.12562870345607602,-0.04242823989116619,300,paired source-video group resample
C1,C0,mae,0.01783299446105957,0.016138792037963867,-0.02564724236726761,0.0629775285720825,300,paired source-video group resample
C1,C0,rmse,0.03289999144204303,0.031675785828170544,-0.020259642051488887,0.09688892746372023,300,paired source-video group resample
C1,C0,pearson,0.01760411262512207,0.01890239119529724,-0.03369738236069679,0.06402220875024796,300,paired source-video group resample
C1,C0,interval_90_coverage,-0.020604395604395642,-0.020156060783624363,-0.04706951966973708,0.0014244097679602268,300,paired source-video group resample
C1,C0,interval_90_mean_width,-0.8198151588439941,-0.8159161806106567,-0.8973418056964875,-0.7244095444679262,300,paired source-video group resample
C2,C0,accuracy,0.005494505494505475,0.006734034217056317,-0.03492168144435322,0.039263388113621865,300,paired source-video group resample
C2,C0,macro_f1,-0.10705130555642356,-0.10647497871020942,-0.14529034521411816,-0.07227670367224108,300,paired source-video group resample
C2,C0,mae,-0.02862834930419922,-0.02886521816253662,-0.0708615779876709,0.017617069184780107,300,paired source-video group resample
C2,C0,rmse,-0.023320158215888398,-0.024536035329587313,-0.07390452049272797,0.03574524043224036,300,paired source-video group resample
C2,C0,pearson,0.06217068433761597,0.062325745820999146,0.019706763327121735,0.10440436601638789,300,paired source-video group resample
C2,C0,interval_90_coverage,-0.028846153846153855,-0.029139374090247472,-0.05483842226931229,-0.007421393766663628,300,paired source-video group resample
C2,C0,interval_90_mean_width,-0.9512450695037842,-0.9483258724212646,-1.040887188911438,-0.8597516894340516,300,paired source-video group resample
C3,C0,accuracy,0.0,-0.0014105382526434784,-0.037480075163610405,0.03973893273401969,300,paired source-video group resample
C3,C0,macro_f1,-0.11397785982339559,-0.11550118636787543,-0.15025330407933285,-0.07573850765342569,300,paired source-video group resample
C3,C0,mae,0.0050026774406433105,0.00607532262802124,-0.038323822617530826,0.05409729927778244,300,paired source-video group resample
C3,C0,rmse,0.03632853377078282,0.034883465886420384,-0.02374622453678723,0.10238240376277774,300,paired source-video group resample
C3,C0,pearson,0.027020394802093506,0.028322190046310425,-0.024162814021110535,0.07840722724795342,300,paired source-video group resample
C3,C0,interval_90_coverage,-0.028846153846153855,-0.028296790655086446,-0.05640123255954723,-0.0027437057991513618,300,paired source-video group resample
C3,C0,interval_90_mean_width,-1.0228526592254639,-1.0194878578186035,-1.1037156105041503,-0.9390599608421326,300,paired source-video group resample
C4,C0,accuracy,-0.0357142857142857,-0.034815800464262414,-0.0772917370598698,-0.0013288600915486893,300,paired source-video group resample
C4,C0,macro_f1,-0.10368951752582078,-0.10223723410343993,-0.14512141397513129,-0.06291875743935396,300,paired source-video group resample
C4,C0,mae,0.018634796142578125,0.018803030252456665,-0.03187550157308579,0.07048249393701546,300,paired source-video group resample
C4,C0,rmse,0.0662456532801351,0.06606137343205698,-0.000771750973311937,0.13834455080325986,300,paired source-video group resample
C4,C0,pearson,-0.015321314334869385,-0.014323621988296509,-0.06995467767119408,0.045190202444791765,300,paired source-video group resample
C4,C0,interval_90_coverage,-0.05631868131868134,-0.05692091288405615,-0.08358959916190373,-0.028953700403650265,300,paired source-video group resample
C4,C0,interval_90_mean_width,-1.0491728782653809,-1.044885516166687,-1.1438844561576844,-0.9337571382522584,300,paired source-video group resample
C5,C0,accuracy,-0.008241758241758212,-0.008629674665607934,-0.044991426516953356,0.026282724151226042,300,paired source-video group resample
C5,C0,macro_f1,-0.11722314075215268,-0.11822550052537656,-0.1499375115712949,-0.08097724629441232,300,paired source-video group resample
C5,C0,mae,0.05200999975204468,0.05211746692657471,-0.0040017873048782335,0.11093356907367702,300,paired source-video group resample
C5,C0,rmse,0.07543220131984574,0.0784406160029566,0.003570230707261707,0.1612439999757444,300,paired source-video group resample
C5,C0,pearson,-0.006319224834442139,-0.008950561285018921,-0.0744188591837883,0.05456443652510638,300,paired source-video group resample
C5,C0,interval_90_coverage,-0.0357142857142857,-0.036052426258835424,-0.0611382067095792,-0.010121494473371696,300,paired source-video group resample
C5,C0,interval_90_mean_width,-0.7522284984588623,-0.7501976490020752,-0.851237690448761,-0.651238238811493,300,paired source-video group resample
C6,C0,accuracy,0.017857142857142794,0.018242022657626977,-0.015221933420851212,0.04816562201934867,300,paired source-video group resample
C6,C0,macro_f1,-0.03854345951579863,-0.03931690543571159,-0.0728723243438216,-0.001288528649975503,300,paired source-video group resample
C6,C0,mae,-0.04211997985839844,-0.041862428188323975,-0.08747663199901581,-0.0026129513978958374,300,paired source-video group resample
C6,C0,rmse,-0.02856052047731339,-0.028529750312167423,-0.07851328647353324,0.023412958789233378,300,paired source-video group resample
C6,C0,pearson,0.09151405096054077,0.09196549654006958,0.053130829334259035,0.13536421805620186,300,paired source-video group resample
C6,C0,interval_90_coverage,-0.04807692307692313,-0.048597053531264034,-0.07352282979641461,-0.02437113702623907,300,paired source-video group resample
C6,C0,interval_90_mean_width,-1.1290688514709473,-1.1257045269012451,-1.2072301983833313,-1.0356801092624666,300,paired source-video group resample
C6_no_distance,C0,accuracy,0.016483516483516425,0.015602962450278701,-0.025158176948386863,0.05368575542755869,300,paired source-video group resample
C6_no_distance,C0,macro_f1,-0.0852458400966723,-0.08818768263991761,-0.12609670666918588,-0.04349884073514668,300,paired source-video group resample
C6_no_distance,C0,mae,-0.015009105205535889,-0.014875531196594238,-0.05908146798610687,0.02703451812267302,300,paired source-video group resample
C6_no_distance,C0,rmse,-0.017103453547432368,-0.01823479256332139,-0.06720366401839234,0.03965089682585672,300,paired source-video group resample
C6_no_distance,C0,pearson,0.08881640434265137,0.08928048610687256,0.049032670259475705,0.12815435305237768,300,paired source-video group resample
C6_no_distance,C0,interval_90_coverage,-0.03708791208791207,-0.036860222829389055,-0.06295045068130059,-0.016341489525701837,300,paired source-video group resample
C6_no_distance,C0,interval_90_mean_width,-1.155916690826416,-1.1544511318206787,-1.2067680954933167,-1.0983048617839812,300,paired source-video group resample
C6_no_reconstruction,C0,accuracy,-0.006868131868131844,-0.008153393092879657,-0.04159180129850518,0.030601993085214534,300,paired source-video group resample
C6_no_reconstruction,C0,macro_f1,-0.07406662996020902,-0.07427164155320246,-0.11354473287065868,-0.028505535727230268,300,paired source-video group resample
C6_no_reconstruction,C0,mae,-0.01761627197265625,-0.018726110458374023,-0.0649495080113411,0.03427876979112624,300,paired source-video group resample
C6_no_reconstruction,C0,rmse,0.004977020946573263,0.0027477694204465775,-0.05508550586289301,0.07941780287834657,300,paired source-video group resample
C6_no_reconstruction,C0,pearson,0.04488801956176758,0.045243918895721436,-0.00925953760743141,0.09828210026025767,300,paired source-video group resample
C6_no_reconstruction,C0,interval_90_coverage,-0.04258241758241754,-0.04290758131319522,-0.06940336171756782,-0.018095951160513678,300,paired source-video group resample
C6_no_reconstruction,C0,interval_90_mean_width,-1.131732702255249,-1.1248958110809326,-1.2080435454845428,-1.0486360669136048,300,paired source-video group resample
C6_pointmask,C0,accuracy,-0.009615384615384581,-0.009738001914636085,-0.04920340824308543,0.022331564635391116,300,paired source-video group resample
C6_pointmask,C0,macro_f1,-0.054741406914747937,-0.05509936281932051,-0.09933300769039154,-0.014947960975273141,300,paired source-video group resample
C6_pointmask,C0,mae,-0.04757577180862427,-0.047405123710632324,-0.08711361587047577,-0.010291239619255097,300,paired source-video group resample
C6_pointmask,C0,rmse,-0.031789715997461165,-0.03308342959875521,-0.08183316816372967,0.02130973142654214,300,paired source-video group resample
C6_pointmask,C0,pearson,0.07724165916442871,0.07814452052116394,0.030774897336959837,0.12344256937503814,300,paired source-video group resample
C6_pointmask,C0,interval_90_coverage,-0.04532967032967039,-0.046236097755335825,-0.06903910849453329,-0.02037191114069394,300,paired source-video group resample
C6_pointmask,C0,interval_90_mean_width,-1.053518533706665,-1.050612449645996,-1.1356862008571624,-0.9624875009059907,300,paired source-video group resample
C7_distill,C0,accuracy,0.0013736263736263687,0.0,-0.03564026436677138,0.03808366113053612,300,paired source-video group resample
C7_distill,C0,macro_f1,-0.07022866473464978,-0.07150025845602764,-0.11333475377843333,-0.02820262605190197,300,paired source-video group resample
C7_distill,C0,mae,-0.024318575859069824,-0.023236483335494995,-0.06809726357460022,0.022609198093414166,300,paired source-video group resample
C7_distill,C0,rmse,-0.005145556765307591,-0.003754520280238871,-0.06475408824403364,0.06043374588794306,300,paired source-video group resample
C7_distill,C0,pearson,0.056644558906555176,0.05477696657180786,0.0036024510860443114,0.10223198831081384,300,paired source-video group resample
C7_distill,C0,interval_90_coverage,-0.0535714285714286,-0.05340785546264998,-0.08114066852367696,-0.029819319822607264,300,paired source-video group resample
C7_distill,C0,interval_90_mean_width,-1.0344364643096924,-1.0316048860549927,-1.1263263642787933,-0.9360203683376312,300,paired source-video group resample
C7_group,C0,accuracy,0.009615384615384581,0.00991596668164968,-0.026735576237341265,0.04448888522064489,300,paired source-video group resample
C7_group,C0,macro_f1,-0.10642370210014501,-0.1059487945832571,-0.14284757254188665,-0.06908091423711933,300,paired source-video group resample
C7_group,C0,mae,0.005541443824768066,0.005858421325683594,-0.03842498958110809,0.04856431335210795,300,paired source-video group resample
C7_group,C0,rmse,-0.013793035301605139,-0.013648813546030314,-0.06215944631884653,0.033087321259013286,300,paired source-video group resample
C7_group,C0,pearson,0.08217388391494751,0.08152049779891968,0.04730007201433182,0.1242825150489807,300,paired source-video group resample
C7_group,C0,interval_90_coverage,-0.03296703296703296,-0.03199443671766339,-0.05872082981670811,-0.011221050556814867,300,paired source-video group resample
C7_group,C0,interval_90_mean_width,-0.9219331741333008,-0.918962836265564,-0.9758361577987671,-0.8550595462322236,300,paired source-video group resample
1 model baseline metric point_delta bootstrap_median_delta ci_2_5 ci_97_5 replicates unit
2 C1 C0 accuracy -0.0027472527472527375 -0.001340239501606888 -0.0415489514789989 0.03692233632862645 300 paired source-video group resample
3 C1 C0 macro_f1 -0.08342531441150824 -0.0839257600579568 -0.12562870345607602 -0.04242823989116619 300 paired source-video group resample
4 C1 C0 mae 0.01783299446105957 0.016138792037963867 -0.02564724236726761 0.0629775285720825 300 paired source-video group resample
5 C1 C0 rmse 0.03289999144204303 0.031675785828170544 -0.020259642051488887 0.09688892746372023 300 paired source-video group resample
6 C1 C0 pearson 0.01760411262512207 0.01890239119529724 -0.03369738236069679 0.06402220875024796 300 paired source-video group resample
7 C1 C0 interval_90_coverage -0.020604395604395642 -0.020156060783624363 -0.04706951966973708 0.0014244097679602268 300 paired source-video group resample
8 C1 C0 interval_90_mean_width -0.8198151588439941 -0.8159161806106567 -0.8973418056964875 -0.7244095444679262 300 paired source-video group resample
9 C2 C0 accuracy 0.005494505494505475 0.006734034217056317 -0.03492168144435322 0.039263388113621865 300 paired source-video group resample
10 C2 C0 macro_f1 -0.10705130555642356 -0.10647497871020942 -0.14529034521411816 -0.07227670367224108 300 paired source-video group resample
11 C2 C0 mae -0.02862834930419922 -0.02886521816253662 -0.0708615779876709 0.017617069184780107 300 paired source-video group resample
12 C2 C0 rmse -0.023320158215888398 -0.024536035329587313 -0.07390452049272797 0.03574524043224036 300 paired source-video group resample
13 C2 C0 pearson 0.06217068433761597 0.062325745820999146 0.019706763327121735 0.10440436601638789 300 paired source-video group resample
14 C2 C0 interval_90_coverage -0.028846153846153855 -0.029139374090247472 -0.05483842226931229 -0.007421393766663628 300 paired source-video group resample
15 C2 C0 interval_90_mean_width -0.9512450695037842 -0.9483258724212646 -1.040887188911438 -0.8597516894340516 300 paired source-video group resample
16 C3 C0 accuracy 0.0 -0.0014105382526434784 -0.037480075163610405 0.03973893273401969 300 paired source-video group resample
17 C3 C0 macro_f1 -0.11397785982339559 -0.11550118636787543 -0.15025330407933285 -0.07573850765342569 300 paired source-video group resample
18 C3 C0 mae 0.0050026774406433105 0.00607532262802124 -0.038323822617530826 0.05409729927778244 300 paired source-video group resample
19 C3 C0 rmse 0.03632853377078282 0.034883465886420384 -0.02374622453678723 0.10238240376277774 300 paired source-video group resample
20 C3 C0 pearson 0.027020394802093506 0.028322190046310425 -0.024162814021110535 0.07840722724795342 300 paired source-video group resample
21 C3 C0 interval_90_coverage -0.028846153846153855 -0.028296790655086446 -0.05640123255954723 -0.0027437057991513618 300 paired source-video group resample
22 C3 C0 interval_90_mean_width -1.0228526592254639 -1.0194878578186035 -1.1037156105041503 -0.9390599608421326 300 paired source-video group resample
23 C4 C0 accuracy -0.0357142857142857 -0.034815800464262414 -0.0772917370598698 -0.0013288600915486893 300 paired source-video group resample
24 C4 C0 macro_f1 -0.10368951752582078 -0.10223723410343993 -0.14512141397513129 -0.06291875743935396 300 paired source-video group resample
25 C4 C0 mae 0.018634796142578125 0.018803030252456665 -0.03187550157308579 0.07048249393701546 300 paired source-video group resample
26 C4 C0 rmse 0.0662456532801351 0.06606137343205698 -0.000771750973311937 0.13834455080325986 300 paired source-video group resample
27 C4 C0 pearson -0.015321314334869385 -0.014323621988296509 -0.06995467767119408 0.045190202444791765 300 paired source-video group resample
28 C4 C0 interval_90_coverage -0.05631868131868134 -0.05692091288405615 -0.08358959916190373 -0.028953700403650265 300 paired source-video group resample
29 C4 C0 interval_90_mean_width -1.0491728782653809 -1.044885516166687 -1.1438844561576844 -0.9337571382522584 300 paired source-video group resample
30 C5 C0 accuracy -0.008241758241758212 -0.008629674665607934 -0.044991426516953356 0.026282724151226042 300 paired source-video group resample
31 C5 C0 macro_f1 -0.11722314075215268 -0.11822550052537656 -0.1499375115712949 -0.08097724629441232 300 paired source-video group resample
32 C5 C0 mae 0.05200999975204468 0.05211746692657471 -0.0040017873048782335 0.11093356907367702 300 paired source-video group resample
33 C5 C0 rmse 0.07543220131984574 0.0784406160029566 0.003570230707261707 0.1612439999757444 300 paired source-video group resample
34 C5 C0 pearson -0.006319224834442139 -0.008950561285018921 -0.0744188591837883 0.05456443652510638 300 paired source-video group resample
35 C5 C0 interval_90_coverage -0.0357142857142857 -0.036052426258835424 -0.0611382067095792 -0.010121494473371696 300 paired source-video group resample
36 C5 C0 interval_90_mean_width -0.7522284984588623 -0.7501976490020752 -0.851237690448761 -0.651238238811493 300 paired source-video group resample
37 C6 C0 accuracy 0.017857142857142794 0.018242022657626977 -0.015221933420851212 0.04816562201934867 300 paired source-video group resample
38 C6 C0 macro_f1 -0.03854345951579863 -0.03931690543571159 -0.0728723243438216 -0.001288528649975503 300 paired source-video group resample
39 C6 C0 mae -0.04211997985839844 -0.041862428188323975 -0.08747663199901581 -0.0026129513978958374 300 paired source-video group resample
40 C6 C0 rmse -0.02856052047731339 -0.028529750312167423 -0.07851328647353324 0.023412958789233378 300 paired source-video group resample
41 C6 C0 pearson 0.09151405096054077 0.09196549654006958 0.053130829334259035 0.13536421805620186 300 paired source-video group resample
42 C6 C0 interval_90_coverage -0.04807692307692313 -0.048597053531264034 -0.07352282979641461 -0.02437113702623907 300 paired source-video group resample
43 C6 C0 interval_90_mean_width -1.1290688514709473 -1.1257045269012451 -1.2072301983833313 -1.0356801092624666 300 paired source-video group resample
44 C6_no_distance C0 accuracy 0.016483516483516425 0.015602962450278701 -0.025158176948386863 0.05368575542755869 300 paired source-video group resample
45 C6_no_distance C0 macro_f1 -0.0852458400966723 -0.08818768263991761 -0.12609670666918588 -0.04349884073514668 300 paired source-video group resample
46 C6_no_distance C0 mae -0.015009105205535889 -0.014875531196594238 -0.05908146798610687 0.02703451812267302 300 paired source-video group resample
47 C6_no_distance C0 rmse -0.017103453547432368 -0.01823479256332139 -0.06720366401839234 0.03965089682585672 300 paired source-video group resample
48 C6_no_distance C0 pearson 0.08881640434265137 0.08928048610687256 0.049032670259475705 0.12815435305237768 300 paired source-video group resample
49 C6_no_distance C0 interval_90_coverage -0.03708791208791207 -0.036860222829389055 -0.06295045068130059 -0.016341489525701837 300 paired source-video group resample
50 C6_no_distance C0 interval_90_mean_width -1.155916690826416 -1.1544511318206787 -1.2067680954933167 -1.0983048617839812 300 paired source-video group resample
51 C6_no_reconstruction C0 accuracy -0.006868131868131844 -0.008153393092879657 -0.04159180129850518 0.030601993085214534 300 paired source-video group resample
52 C6_no_reconstruction C0 macro_f1 -0.07406662996020902 -0.07427164155320246 -0.11354473287065868 -0.028505535727230268 300 paired source-video group resample
53 C6_no_reconstruction C0 mae -0.01761627197265625 -0.018726110458374023 -0.0649495080113411 0.03427876979112624 300 paired source-video group resample
54 C6_no_reconstruction C0 rmse 0.004977020946573263 0.0027477694204465775 -0.05508550586289301 0.07941780287834657 300 paired source-video group resample
55 C6_no_reconstruction C0 pearson 0.04488801956176758 0.045243918895721436 -0.00925953760743141 0.09828210026025767 300 paired source-video group resample
56 C6_no_reconstruction C0 interval_90_coverage -0.04258241758241754 -0.04290758131319522 -0.06940336171756782 -0.018095951160513678 300 paired source-video group resample
57 C6_no_reconstruction C0 interval_90_mean_width -1.131732702255249 -1.1248958110809326 -1.2080435454845428 -1.0486360669136048 300 paired source-video group resample
58 C6_pointmask C0 accuracy -0.009615384615384581 -0.009738001914636085 -0.04920340824308543 0.022331564635391116 300 paired source-video group resample
59 C6_pointmask C0 macro_f1 -0.054741406914747937 -0.05509936281932051 -0.09933300769039154 -0.014947960975273141 300 paired source-video group resample
60 C6_pointmask C0 mae -0.04757577180862427 -0.047405123710632324 -0.08711361587047577 -0.010291239619255097 300 paired source-video group resample
61 C6_pointmask C0 rmse -0.031789715997461165 -0.03308342959875521 -0.08183316816372967 0.02130973142654214 300 paired source-video group resample
62 C6_pointmask C0 pearson 0.07724165916442871 0.07814452052116394 0.030774897336959837 0.12344256937503814 300 paired source-video group resample
63 C6_pointmask C0 interval_90_coverage -0.04532967032967039 -0.046236097755335825 -0.06903910849453329 -0.02037191114069394 300 paired source-video group resample
64 C6_pointmask C0 interval_90_mean_width -1.053518533706665 -1.050612449645996 -1.1356862008571624 -0.9624875009059907 300 paired source-video group resample
65 C7_distill C0 accuracy 0.0013736263736263687 0.0 -0.03564026436677138 0.03808366113053612 300 paired source-video group resample
66 C7_distill C0 macro_f1 -0.07022866473464978 -0.07150025845602764 -0.11333475377843333 -0.02820262605190197 300 paired source-video group resample
67 C7_distill C0 mae -0.024318575859069824 -0.023236483335494995 -0.06809726357460022 0.022609198093414166 300 paired source-video group resample
68 C7_distill C0 rmse -0.005145556765307591 -0.003754520280238871 -0.06475408824403364 0.06043374588794306 300 paired source-video group resample
69 C7_distill C0 pearson 0.056644558906555176 0.05477696657180786 0.0036024510860443114 0.10223198831081384 300 paired source-video group resample
70 C7_distill C0 interval_90_coverage -0.0535714285714286 -0.05340785546264998 -0.08114066852367696 -0.029819319822607264 300 paired source-video group resample
71 C7_distill C0 interval_90_mean_width -1.0344364643096924 -1.0316048860549927 -1.1263263642787933 -0.9360203683376312 300 paired source-video group resample
72 C7_group C0 accuracy 0.009615384615384581 0.00991596668164968 -0.026735576237341265 0.04448888522064489 300 paired source-video group resample
73 C7_group C0 macro_f1 -0.10642370210014501 -0.1059487945832571 -0.14284757254188665 -0.06908091423711933 300 paired source-video group resample
74 C7_group C0 mae 0.005541443824768066 0.005858421325683594 -0.03842498958110809 0.04856431335210795 300 paired source-video group resample
75 C7_group C0 rmse -0.013793035301605139 -0.013648813546030314 -0.06215944631884653 0.033087321259013286 300 paired source-video group resample
76 C7_group C0 pearson 0.08217388391494751 0.08152049779891968 0.04730007201433182 0.1242825150489807 300 paired source-video group resample
77 C7_group C0 interval_90_coverage -0.03296703296703296 -0.03199443671766339 -0.05872082981670811 -0.011221050556814867 300 paired source-video group resample
78 C7_group C0 interval_90_mean_width -0.9219331741333008 -0.918962836265564 -0.9758361577987671 -0.8550595462322236 300 paired source-video group resample
@@ -0,0 +1,27 @@
{
"n": 728,
"accuracy": 0.6085164835164835,
"macro_f1": 0.518781225964892,
"negative_support": 206,
"neutral_support": 184,
"positive_support": 338,
"negative_recall": 0.6796116504854369,
"middle_recall": 0.125,
"positive_recall": 0.8284023668639053,
"regression_mae": 0.6846789717674255,
"regression_rmse": 0.9208215740080159,
"pearson": 0.6101368069648743,
"brier": 0.4977383080922297,
"classification_nll": 0.8427478075027466,
"ece_15": 0.03950894476620705,
"selection_nll": 2.783693552017212,
"interval_90_coverage": 0.8873626373626373,
"interval_90_mean_width": 2.3910491466522217,
"predictive_variance_mean_uncalibrated": 0.5537729859352112,
"within_trajectory_variance_mean": 0.5537727475166321,
"between_trajectory_variance_mean": 2.9140662149984564e-07,
"predictive_mean_mean_calibrated": 0.2094990462064743,
"predictive_variance_mean_calibrated": 0.5816943049430847,
"selected_model": "C6",
"temperature": 1.122980387832455
}