family,arm_a,arm_b,metric,n,n_blocks,B,value_a,value_b,diff,rel_diff,ci_lo,ci_hi,se_boot,p_boot,p_holm,dm_stat,dm_p,dm_lag primary,D_avm,G_debate_r2,mean_abs_log_error,40.0,39.0,2000.0,0.18507726135604616,0.1756280898133557,-0.009449171542690454,-0.051055280770080216,-0.048197605412221824,0.028217980446989543,0.019006736468036287,0.608,1.0,-0.39856695075672255,0.6923861396258116,3.0 primary,F_independent,G_debate_r2,mean_abs_log_error,40.0,39.0,2000.0,0.1790658698103976,0.1756280898133557,-0.0034377799970418954,-0.019198410063748943,-0.013454594898615014,0.0036899139026239803,0.0044680767034935304,0.4525,1.0,-0.8198602752754339,0.4172783878346392,3.0 primary,J_cost_matched,G_debate_r2,mean_abs_log_error,40.0,39.0,2000.0,0.1786301928342328,0.1756280898133557,-0.003002103020877084,-0.016806246319529018,-0.023516427354654718,0.013987795640802976,0.009530939058329772,0.746,1.0,-0.24199732894747122,0.8100502570171414,3.0 primary,I_placebo,G_debate_r2,mean_abs_log_error,40.0,39.0,2000.0,0.18364834891764875,0.1756280898133557,-0.008020259104293048,-0.043671827988442616,-0.022762349543844106,0.0030316416587367278,0.006747870843533264,0.2325,0.93,-1.0316204206517727,0.30860531843348254,3.0 primary_tail,I_placebo,G_debate_r2,p95_abs_log_error,40.0,39.0,2000.0,0.46321473299277605,0.4196121863595829,-0.04360254663319313,-0.09413031047497603,-0.15627898124819595,0.011232940555540694,0.04502587166981409,0.2495,,,, secondary,E_single_llm,G_debate_r2,mean_abs_log_error,40.0,39.0,2000.0,0.18152027933145048,0.1756280898133557,-0.005892189518094781,-0.03246022725282294,-0.026133635957660398,0.01201145775631421,0.009683854144559354,0.526,,-0.44618522296232493,0.6579309965735168,3.0 secondary,E_single_llm,G_debate_r2,mdape,40.0,39.0,2000.0,0.11771828687251629,0.11301644701869923,-0.004701839853817058,-0.03994145666517338,-0.06082610223890528,0.03217401112813367,0.02014233762291226,0.707,,,, secondary,E_single_llm,G_debate_r2,p95_abs_log_error,40.0,39.0,2000.0,0.4569422135828799,0.4196121863595829,-0.03733002722329698,-0.08169529125049,-0.18549354987869776,0.06453721851420091,0.061505444959746296,0.6085,,,, secondary,E_single_llm,G_debate_r2,severe_rate,40.0,39.0,2000.0,0.275,0.3,0.024999999999999967,0.09090909090909079,0.0,0.07692307692307693,0.02474064667311848,0.5805,,,, secondary,E_single_llm,G_debate_r2,coverage_90,40.0,39.0,2000.0,0.8,0.825,0.02499999999999991,0.03124999999999989,-0.05128205128205132,0.10256410256410264,0.04326506528931116,0.701,,,, secondary,E_single_llm,G_debate_r2,pinball_log,40.0,39.0,2000.0,0.061649688628035326,0.0584926960085387,-0.003156992619496625,-0.05120857363196764,-0.010875002589298181,0.002861685251866992,0.00352588473183663,0.3655,,-0.729374724345698,0.4701305280288164,3.0 secondary,H_debate_skeptic,G_debate_r2,mean_abs_log_error,40.0,39.0,2000.0,0.17507604886472028,0.1756280898133557,0.0005520409486354239,0.0031531494582790194,-0.0034895483018070605,0.005560549555244474,0.0023406996833315982,0.814,,0.18254755892412514,0.856098663687158,3.0 secondary,H_debate_skeptic,G_debate_r2,mdape,40.0,39.0,2000.0,0.11919490475681532,0.11301644701869923,-0.006178457738116094,-0.05183491484574405,-0.009511705171715734,0.0065202417948404204,0.004751472408085161,0.2255,,,, secondary,H_debate_skeptic,G_debate_r2,p95_abs_log_error,40.0,39.0,2000.0,0.4295842503760401,0.4196121863595829,-0.009972064016457172,-0.023213290542490893,-0.024763211895974236,0.023354980606209046,0.011736352614741185,0.3625,,,, secondary,H_debate_skeptic,G_debate_r2,severe_rate,40.0,39.0,2000.0,0.275,0.3,0.024999999999999967,0.09090909090909079,0.0,0.07692307692307693,0.02448883485881128,0.5775,,,, secondary,H_debate_skeptic,G_debate_r2,coverage_90,40.0,39.0,2000.0,0.825,0.825,0.0,0.0,0.0,0.0,0.0,1.0,,,, secondary,H_debate_skeptic,G_debate_r2,pinball_log,40.0,39.0,2000.0,0.05826326920763099,0.0584926960085387,0.000229426800907713,0.003937760514091853,-0.0007797043288649032,0.0015114991577933,0.0006057347074446127,0.708,,0.31290718146423735,0.7560183957662733,3.0 secondary,A_hedonic,G_debate_r2,mean_abs_log_error,40.0,39.0,2000.0,0.2109868325913999,0.1756280898133557,-0.03535874277804418,-0.16758743824796132,-0.07553507469227556,0.007350486588667127,0.021566666438304898,0.0985,,-1.4934895251049436,0.1433560734027671,3.0 secondary,A_hedonic,G_debate_r2,mdape,40.0,39.0,2000.0,0.15676872058934516,0.11301644701869923,-0.04375227357064593,-0.2790880311210473,-0.09135432313820435,0.03592098692274248,0.03472609519002285,0.223,,,, secondary,A_hedonic,G_debate_r2,p95_abs_log_error,40.0,39.0,2000.0,0.5667082462944234,0.4196121863595829,-0.14709605993484048,-0.259562236647637,-0.2341186323535247,0.06971828940065578,0.07472801119808414,0.0705,,,, secondary,A_hedonic,G_debate_r2,severe_rate,40.0,39.0,2000.0,0.275,0.3,0.024999999999999967,0.09090909090909079,-0.12499999999999997,0.17948717948717946,0.07618480774316692,0.826,,,, secondary,A_hedonic,G_debate_r2,coverage_90,40.0,39.0,2000.0,0.925,0.825,-0.10000000000000009,-0.1081081081081082,-0.24390243902439024,0.025000000000000022,0.07008236637468407,0.1755,,,, secondary,A_hedonic,G_debate_r2,pinball_log,40.0,39.0,2000.0,0.06959027071750826,0.0584926960085387,-0.011097574708969556,-0.15947020459251512,-0.023938970310060478,0.0021438475164858614,0.006769099472954388,0.098,,-1.6343813076977634,0.11022650300267474,3.0 secondary,C_gbm,G_debate_r2,mean_abs_log_error,40.0,39.0,2000.0,0.19931873073427733,0.1756280898133557,-0.02369064092092163,-0.11885807637669997,-0.06401077551137065,0.015377894520953872,0.01973599421949176,0.236,,-1.013828502139813,0.3169133198952991,3.0 secondary,C_gbm,G_debate_r2,mdape,40.0,39.0,2000.0,0.1293375384701717,0.11301644701869923,-0.01632109145147248,-0.12618990313656317,-0.08695671459117481,0.05426357311305931,0.03471778573910652,0.5905,,,, secondary,C_gbm,G_debate_r2,p95_abs_log_error,40.0,39.0,2000.0,0.5884922251125102,0.4196121863595829,-0.1688800387529273,-0.2869707220356907,-0.2684089410983369,0.09363327828047707,0.08811593675270905,0.0895,,,, secondary,C_gbm,G_debate_r2,severe_rate,40.0,39.0,2000.0,0.325,0.3,-0.025000000000000022,-0.07692307692307698,-0.1285714285714286,0.07692307692307693,0.05712600101612412,0.7045,,,, secondary,C_gbm,G_debate_r2,coverage_90,40.0,39.0,0.0,,0.825,,,,,,,,,, secondary,C_gbm,G_debate_r2,pinball_log,40.0,39.0,0.0,,0.0584926960085387,,,,,,,,,, secondary,D_avm,F_independent,mean_abs_log_error,40.0,39.0,2000.0,0.18507726135604616,0.1790658698103976,-0.006011391545648559,-0.03248044358125671,-0.04315942546515714,0.02879744523029518,0.018113025052566754,0.7305,,-0.26934956861573967,0.7890806652761322,3.0 secondary,D_avm,F_independent,mdape,40.0,39.0,2000.0,0.14662047197593708,0.1182178076253731,-0.02840266435056399,-0.1937155430465764,-0.07030949853866364,0.05217994211476418,0.033743437632296515,0.4045,,,, secondary,D_avm,F_independent,p95_abs_log_error,40.0,39.0,2000.0,0.5290695620355366,0.4430984029974624,-0.08597115903807417,-0.16249500104921866,-0.21776797308832996,0.09308076910476605,0.077362966858015,0.2655,,,, secondary,D_avm,F_independent,severe_rate,40.0,39.0,2000.0,0.275,0.3,0.024999999999999967,0.09090909090909079,-0.051282051282051266,0.12195121951219509,0.0436514949762503,0.716,,,, secondary,D_avm,F_independent,coverage_90,40.0,39.0,2000.0,0.85,0.825,-0.025000000000000022,-0.02941176470588238,-0.15384615384615385,0.10000000000000009,0.06686225738443267,0.793,,,, secondary,D_avm,F_independent,pinball_log,40.0,39.0,2000.0,0.06142131708201287,0.060008472296771566,-0.001412844785241306,-0.0230025152888663,-0.01176949494644251,0.008791420149370288,0.005130729460230032,0.7725,,-0.2548730457021017,0.8001604036523866,3.0 secondary,E_single_llm,F_independent,mean_abs_log_error,40.0,39.0,2000.0,0.18152027933145048,0.1790658698103976,-0.002454409521052886,-0.0135214066995303,-0.01675134294321997,0.011772151307922965,0.007236781037379159,0.73,,-0.2419741653094173,0.8100680779907289,3.0 secondary,E_single_llm,F_independent,mdape,40.0,39.0,2000.0,0.11771828687251629,0.1182178076253731,0.000499520752856808,0.0042433573077542905,-0.06076903486960774,0.016231278300244623,0.02022123448996578,0.9865,,,, secondary,E_single_llm,F_independent,p95_abs_log_error,40.0,39.0,2000.0,0.4569422135828799,0.4430984029974624,-0.013843810585417504,-0.03029663308379479,-0.10876823154251092,0.0366141176469732,0.04588307311694857,0.726,,,, secondary,E_single_llm,F_independent,severe_rate,40.0,39.0,2000.0,0.275,0.3,0.024999999999999967,0.09090909090909079,0.0,0.07692307692307693,0.02474064667311848,0.5805,,,, secondary,E_single_llm,F_independent,coverage_90,40.0,39.0,2000.0,0.8,0.825,0.02499999999999991,0.03124999999999989,-0.05128205128205132,0.10256410256410264,0.04326506528931116,0.701,,,, secondary,E_single_llm,F_independent,pinball_log,40.0,39.0,2000.0,0.061649688628035326,0.06000847229677157,-0.0016412163312637534,-0.026621648345477724,-0.0070005718381634515,0.003207376909408558,0.002549246893400283,0.509,,-0.4966570890377753,0.6222189519834236,3.0 secondary,G_debate_r1,G_debate_r2,mean_abs_log_error,40.0,39.0,2000.0,0.17795994858564676,0.1756280898133557,-0.0023318587722910566,-0.01310327852319424,-0.008260769822609917,0.0023383127137514745,0.002796231950092475,0.414,,-0.8609153047230045,0.39454682207890424,3.0 secondary,G_debate_r1,G_debate_r2,mdape,40.0,39.0,2000.0,0.1151532405382264,0.11301644701869923,-0.0021367935195271692,-0.01855608673746213,-0.009511705171715734,0.008968046542857988,0.00461403397512001,0.677,,,, secondary,G_debate_r1,G_debate_r2,p95_abs_log_error,40.0,39.0,2000.0,0.4195372237846765,0.4196121863595829,7.4962574906412e-05,0.0001786791985468394,-0.045330585483041475,0.009724706454914411,0.014460852316641525,0.953,,,, secondary,G_debate_r1,G_debate_r2,severe_rate,40.0,39.0,2000.0,0.3,0.3,0.0,0.0,0.0,0.0,0.0,1.0,,,, secondary,G_debate_r1,G_debate_r2,coverage_90,40.0,39.0,2000.0,0.825,0.825,0.0,0.0,0.0,0.0,0.0,1.0,,,, secondary,G_debate_r1,G_debate_r2,pinball_log,40.0,39.0,2000.0,0.059547859303411964,0.0584926960085387,-0.0010551632948732625,-0.017719583998761883,-0.002674727737456979,0.00033891065665693954,0.0008033441325398319,0.187,,-1.3302573786870802,0.1911604416851463,3.0 secondary,G_debate_r2,G_debate_r4,mean_abs_log_error,20.0,20.0,2000.0,0.16441274234245914,0.162923796912827,-0.0014889454296321547,-0.009056143753936027,-0.004935898298151665,0.0019277863391774562,0.001747002525455873,0.3895,,-0.915411009838051,0.3714484265378315,2.0 secondary,G_debate_r2,G_debate_r4,mdape,20.0,20.0,2000.0,0.10139952133713936,0.09950741701872856,-0.0018921043184108033,-0.018659893986282424,-0.012264637059118014,0.014134533051557874,0.005139760217018403,0.5795,,,, secondary,G_debate_r2,G_debate_r4,p95_abs_log_error,20.0,20.0,2000.0,0.4398322037175225,0.4218478254740278,-0.017984378243494692,-0.040889180218020064,-0.0186817680994551,0.008100600978789174,0.008650463757046364,0.185,,,, secondary,G_debate_r2,G_debate_r4,severe_rate,20.0,20.0,2000.0,0.25,0.25,0.0,0.0,0.0,0.0,0.0,1.0,,,, secondary,G_debate_r2,G_debate_r4,coverage_90,20.0,20.0,2000.0,0.8,0.8,0.0,0.0,0.0,0.0,0.0,1.0,,,, secondary,G_debate_r2,G_debate_r4,pinball_log,20.0,20.0,2000.0,0.058318166490192724,0.05835807950460511,3.991301441238354e-05,0.0006844010505559302,-0.0009011912165148072,0.000972957042559465,0.0004771699090754563,0.931,,0.08868232687354347,0.930262470476063,2.0