arm,committee,aggregation,run_id,n,mean_abs_log_error,mae_cad,mdape,rmse_log,p90_abs_log_error,p95_abs_log_error,bias_log,severe_rate,over_rate,under_rate,coverage_50,coverage_80,coverage_90,coverage_95,coverage_90_normal_fit,mean_log_width_90,mean_log_width_50,pinball_log,crps_log,crps_log_normal_fit,n_with_interval,cost_usd_mean,cost_usd_total,latency_s_mean,tokens_mean A_hedonic,none,model,baselines,72132.0,0.1965395654036433,84618.06466949593,0.12458481659610149,0.29585039474850394,0.45082916805567363,0.6797019882820978,0.008296036496991234,0.27984805634115234,0.13119004048133975,0.08926689957300504,0.5,0.8548910331059724,0.8999889092219819,0.9297260577829535,0.9039261354183996,1.0014592058200693,0.24555321031791516,0.06672412219936037,0.13727502334713804,0.15607153606320923,72132.0,0.0,0.0,1.2664570928544177e-06,0.0 B_hierarchical,none,model,baselines,72132.0,0.1901013943871288,81929.37283629781,0.11585438292713085,0.29330325862839796,0.4440281866344344,0.686948384046076,0.0211892113840668,0.25901125713968837,0.1338241002606333,0.07450230133643874,0.5,0.8566239671712971,0.8999889092219819,0.9301003715410636,0.9046886264071424,0.9980834562671801,0.23081762970185607,0.06536651899962224,0.13424430517421074,0.15397016749584871,72132.0,0.0,0.0,9.276655991557834e-07,0.0 C_catboost,none,model,baselines,72132.0,0.1728449166688981,73856.1000451516,0.0985819201286563,0.2836864452089413,0.39564407609373636,0.6907546505071392,0.03929236431380833,0.21206953917817334,0.12798757832861976,0.04595741141241058,,,,,,,,,,,0.0,0.0,0.0,1.1639165004978922e-06,0.0 C_gbm,none,model,baselines,72132.0,0.1825518199096673,78141.03408972699,0.1122073819947288,0.2825595961606405,0.412170054862151,0.6592591403539668,0.007895772145622577,0.24550823490267842,0.11980812954028724,0.07124438529362835,,,,,,,,,,,0.0,0.0,0.0,3.1204493156457797e-06,0.0 C_xgboost,none,model,baselines,72132.0,0.1812049738521171,78659.43914081779,0.10515994992690059,0.29267409548683754,0.42416748020295236,0.7135442308264949,0.05402146562614569,0.22784617090888926,0.1436394388066323,0.05080962679531969,,,,,,,,,,,0.0,0.0,0.0,1.0671662090602171e-06,0.0 D_avm,none,model,baselines,72132.0,0.18014167592470398,77392.32261709639,0.109260247594546,0.2804998618844654,0.4066930669992761,0.6588447692888497,0.004485868645034657,0.23828536571840514,0.11643930571729606,0.0676676093827982,0.49053124826706596,0.8731769533632784,0.9000166361670271,0.9366716575167748,0.9174984750180225,0.8771581497110039,0.21881853210707025,0.058817415312322284,0.12091151574756318,0.13987930306239327,72132.0,0.0,0.0,0.00023210158056101757,0.0 E_single_llm,all_anthropic,inverse_variance,validation_E_single_llm_all_anthropic_mid,40.0,0.19440952121173222,70096.37500000003,0.12578486875965073,0.27964863819105834,0.4230669733785428,0.5021808849963472,0.062035792539286,0.3,0.2,0.075,0.4,0.75,0.825,0.825,0.825,0.5891290800061362,0.23033446105917466,0.06658104844311068,0.1361903925907264,0.14698414464434723,40.0,0.018847625,0.753905,8.570174999999999,7393.875 E_single_llm,all_anthropic,mean,validation_E_single_llm_all_anthropic_mid,40.0,0.19440952121173222,70096.37500000003,0.12578486875965073,0.27964863819105834,0.4230669733785428,0.5021808849963472,0.062035792539286,0.3,0.2,0.075,0.4,0.75,0.825,0.825,0.825,0.5891290800061362,0.23033446105917466,0.06658104844311068,0.1361903925907264,0.14698414464434723,40.0,0.018847625,0.753905,8.570174999999999,7393.875 E_single_llm,all_anthropic,median,validation_E_single_llm_all_anthropic_mid,40.0,0.19440952121173222,70096.37500000003,0.12578486875965073,0.27964863819105834,0.4230669733785428,0.5021808849963472,0.062035792539286,0.3,0.2,0.075,0.4,0.75,0.825,0.825,0.825,0.5891290800061362,0.23033446105917466,0.06658104844311068,0.1361903925907264,0.14698414464434723,40.0,0.018847625,0.753905,8.570174999999999,7393.875 E_single_llm,all_anthropic,mixture,validation_E_single_llm_all_anthropic_mid,40.0,0.19440040912791576,70099.62547230546,0.12586746471571564,0.27965835331451167,0.42259147969615013,0.5022488618188709,0.06218347047095283,0.3,0.2,0.075,0.4,0.75,0.825,0.825,0.825,0.5890832530125412,0.23037097311766536,0.0665834128772862,0.13619005031233172,0.14698995720591318,40.0,0.018847625,0.753905,8.570174999999999,7393.875 E_single_llm,all_anthropic,robust_bayes,validation_E_single_llm_all_anthropic_mid,40.0,0.19440952121173236,70096.37500000015,0.1257848687596525,0.2796486381910584,0.42306697337854265,0.5021808849963472,0.06203579253928595,0.3,0.2,0.075,0.4,0.75,0.825,0.825,0.825,0.5891290800061362,0.23033446105917466,0.06658104844311068,0.1361903925907264,0.14698414464434723,40.0,0.018847625,0.753905,8.570174999999999,7393.875 E_single_llm,all_anthropic,stacking,validation_E_single_llm_all_anthropic_mid,40.0,0.19440952121173222,70096.37500000003,0.12578486875965073,0.27964863819105834,0.4230669733785428,0.5021808849963472,0.062035792539286,0.3,0.2,0.075,0.4,0.75,0.825,0.825,0.825,0.5891290800061362,0.23033446105917466,0.06658104844311068,0.1361903925907264,0.14698414464434723,40.0,0.018847625,0.753905,8.570174999999999,7393.875 E_single_llm,all_anthropic,trimmed_mean_20,validation_E_single_llm_all_anthropic_mid,40.0,0.19440952121173222,70096.37500000003,0.12578486875965073,0.27964863819105834,0.4230669733785428,0.5021808849963472,0.062035792539286,0.3,0.2,0.075,0.4,0.75,0.825,0.825,0.825,0.5891290800061362,0.23033446105917466,0.06658104844311068,0.1361903925907264,0.14698414464434723,40.0,0.018847625,0.753905,8.570174999999999,7393.875 E_single_llm,all_openai,inverse_variance,validation_E_single_llm_all_openai_mid,40.0,0.17692013372797666,64249.27500000007,0.13080054274084174,0.2571954424968813,0.36581956653142045,0.45839159042654243,0.08020733580117216,0.3,0.175,0.05,0.375,0.675,0.8,0.825,0.775,0.4863282504503171,0.1788152092538598,0.06142503470393694,0.1251931330297071,0.134709855251505,40.0,0.019288725,0.771549,24.55775,5760.075 E_single_llm,all_openai,mean,validation_E_single_llm_all_openai_mid,40.0,0.17692013372797666,64249.27500000007,0.13080054274084174,0.2571954424968813,0.36581956653142045,0.45839159042654243,0.08020733580117216,0.3,0.175,0.05,0.375,0.675,0.8,0.825,0.775,0.4863282504503171,0.1788152092538598,0.06142503470393694,0.1251931330297071,0.134709855251505,40.0,0.019288725,0.771549,24.55775,5760.075 E_single_llm,all_openai,median,validation_E_single_llm_all_openai_mid,40.0,0.17692013372797666,64249.27500000007,0.13080054274084174,0.2571954424968813,0.36581956653142045,0.45839159042654243,0.08020733580117216,0.3,0.175,0.05,0.375,0.675,0.8,0.825,0.775,0.4863282504503171,0.1788152092538598,0.06142503470393694,0.1251931330297071,0.134709855251505,40.0,0.019288725,0.771549,24.55775,5760.075 E_single_llm,all_openai,mixture,validation_E_single_llm_all_openai_mid,40.0,0.17695449657892995,64270.438759853925,0.13094333662922986,0.2572176949424017,0.36585700426015977,0.45842092764630704,0.08034194422642424,0.3,0.175,0.025,0.375,0.675,0.8,0.825,0.775,0.4863613356513671,0.1788560560684782,0.061434210570264304,0.12521259671160148,0.1347232054976105,40.0,0.019288725,0.771549,24.55775,5760.075 E_single_llm,all_openai,robust_bayes,validation_E_single_llm_all_openai_mid,40.0,0.17692013372797671,64249.27500000012,0.13080054274084274,0.25719544249688137,0.365819566531422,0.45839159042654076,0.08020733580117204,0.3,0.175,0.05,0.375,0.675,0.8,0.825,0.775,0.4863282504503171,0.1788152092538598,0.06142503470393694,0.1251931330297071,0.134709855251505,40.0,0.019288725,0.771549,24.55775,5760.075 E_single_llm,all_openai,stacking,validation_E_single_llm_all_openai_mid,40.0,0.17692013372797666,64249.27500000007,0.13080054274084174,0.2571954424968813,0.36581956653142045,0.45839159042654243,0.08020733580117216,0.3,0.175,0.05,0.375,0.675,0.8,0.825,0.775,0.4863282504503171,0.1788152092538598,0.06142503470393694,0.1251931330297071,0.134709855251505,40.0,0.019288725,0.771549,24.55775,5760.075 E_single_llm,all_openai,trimmed_mean_20,validation_E_single_llm_all_openai_mid,40.0,0.17692013372797666,64249.27500000007,0.13080054274084174,0.2571954424968813,0.36581956653142045,0.45839159042654243,0.08020733580117216,0.3,0.175,0.05,0.375,0.675,0.8,0.825,0.775,0.4863282504503171,0.1788152092538598,0.06142503470393694,0.1251931330297071,0.134709855251505,40.0,0.019288725,0.771549,24.55775,5760.075 E_single_llm,mixed_random,inverse_variance,validation_E_single_llm_mixed_random_mid,40.0,0.18152027933145048,64424.27500000002,0.11771828687251629,0.25889233799108785,0.4187760165520603,0.4569422135828799,0.0645299564214473,0.275,0.175,0.05,0.35,0.675,0.8,0.825,0.8,0.49258150706308346,0.18558222278248185,0.061649688628035326,0.12590793671557535,0.13581195687770178,40.0,0.02063125,0.82525,19.624624999999998,6381.425 E_single_llm,mixed_random,mean,validation_E_single_llm_mixed_random_mid,40.0,0.18152027933145048,64424.27500000002,0.11771828687251629,0.25889233799108785,0.4187760165520603,0.4569422135828799,0.0645299564214473,0.275,0.175,0.05,0.35,0.675,0.8,0.825,0.8,0.49258150706308346,0.18558222278248185,0.061649688628035326,0.12590793671557535,0.13581195687770178,40.0,0.02063125,0.82525,19.624624999999998,6381.425 E_single_llm,mixed_random,median,validation_E_single_llm_mixed_random_mid,40.0,0.18152027933145048,64424.27500000002,0.11771828687251629,0.25889233799108785,0.4187760165520603,0.4569422135828799,0.0645299564214473,0.275,0.175,0.05,0.35,0.675,0.8,0.825,0.8,0.49258150706308346,0.18558222278248185,0.061649688628035326,0.12590793671557535,0.13581195687770178,40.0,0.02063125,0.82525,19.624624999999998,6381.425 E_single_llm,mixed_random,mixture,validation_E_single_llm_mixed_random_mid,40.0,0.18153679804460796,64437.58496757387,0.1177834964205326,0.2588971488960126,0.4185620516830753,0.4570457353965029,0.06468811453936056,0.275,0.175,0.05,0.35,0.675,0.8,0.825,0.8,0.4925693619124537,0.18556734695569257,0.061656830553347454,0.12592064214120025,0.1358225644098699,40.0,0.02063125,0.82525,19.624624999999998,6381.425 E_single_llm,mixed_random,robust_bayes,validation_E_single_llm_mixed_random_mid,40.0,0.18152027933145048,64424.275,0.11771828687251451,0.25889233799108796,0.4187760165520603,0.45694221358287823,0.0645299564214473,0.275,0.175,0.05,0.35,0.675,0.8,0.825,0.8,0.49258150706308346,0.18558222278248185,0.061649688628035326,0.12590793671557535,0.13581195687770178,40.0,0.02063125,0.82525,19.624624999999998,6381.425 E_single_llm,mixed_random,stacking,validation_E_single_llm_mixed_random_mid,40.0,0.18152027933145048,64424.27500000002,0.11771828687251629,0.25889233799108785,0.4187760165520603,0.4569422135828799,0.0645299564214473,0.275,0.175,0.05,0.35,0.675,0.8,0.825,0.8,0.49258150706308346,0.18558222278248185,0.061649688628035326,0.12590793671557535,0.13581195687770178,40.0,0.02063125,0.82525,19.624624999999998,6381.425 E_single_llm,mixed_random,trimmed_mean_20,validation_E_single_llm_mixed_random_mid,40.0,0.18152027933145048,64424.27500000002,0.11771828687251629,0.25889233799108785,0.4187760165520603,0.4569422135828799,0.0645299564214473,0.275,0.175,0.05,0.35,0.675,0.8,0.825,0.8,0.49258150706308346,0.18558222278248185,0.061649688628035326,0.12590793671557535,0.13581195687770178,40.0,0.02063125,0.82525,19.624624999999998,6381.425 F_independent,all_anthropic,inverse_variance,validation_F_independent_all_anthropic_mid,40.0,0.18278060606708119,65607.71369381648,0.13577323086007792,0.25667133354218297,0.39745929423274373,0.44830410806163706,0.05016093266409505,0.275,0.175,0.075,0.35,0.775,0.825,0.85,0.825,0.5812748948353057,0.22879274824296786,0.06061519562824609,0.12460845193456302,0.13452910702981752,40.0,0.21183892499999998,8.473557,53.198074999999996,81950.075 F_independent,all_anthropic,mean,validation_F_independent_all_anthropic_mid,40.0,0.18278060606708119,65607.71369381648,0.13577323086008058,0.2566713335421831,0.3974592942327435,0.4483041080616338,0.05016093266409558,0.275,0.175,0.075,0.35,0.775,0.825,0.85,0.825,0.5812748948353057,0.22879274824296786,0.06061519562824609,0.12460845193456302,0.13452910702981752,40.0,0.21183892499999998,8.473557,53.198074999999996,81950.075 F_independent,all_anthropic,median,validation_F_independent_all_anthropic_mid,40.0,0.18244900816472454,65720.42714390045,0.12684969107873695,0.2584744785830561,0.4178931516047502,0.4542490497249704,0.04887043993727334,0.275,0.175,0.075,0.35,0.775,0.825,0.85,0.825,0.5812748948353057,0.22879274824296786,0.06061519562824609,0.12460845193456302,0.13452910702981752,40.0,0.21183892499999998,8.473557,53.198074999999996,81950.075 F_independent,all_anthropic,mixture,validation_F_independent_all_anthropic_mid,40.0,0.18215151480770167,65317.80072070402,0.13284907700023646,0.2555093600151698,0.4069486926839973,0.43109641688649086,0.049544955457844916,0.275,0.175,0.075,0.425,0.8,0.85,0.9,0.85,0.6276338018249337,0.2586624778689334,0.0603896834334682,0.12400748609915242,0.13464105060553444,40.0,0.21183892499999998,8.473557,53.198074999999996,81950.075 F_independent,all_anthropic,robust_bayes,validation_F_independent_all_anthropic_mid,40.0,0.18155180920436204,65266.055629739,0.12621126090485463,0.2567062387416248,0.4145553583002483,0.4377362866530085,0.04911925011404557,0.275,0.175,0.075,0.35,0.775,0.825,0.85,0.825,0.5812748948353057,0.22879274824296786,0.06061519562824609,0.12460845193456302,0.13452910702981752,40.0,0.21183892499999998,8.473557,53.198074999999996,81950.075 F_independent,all_anthropic,stacking,validation_F_independent_all_anthropic_mid,40.0,0.18278060606708119,65607.71369381648,0.13577323086007792,0.25667133354218297,0.39745929423274373,0.44830410806163706,0.05016093266409505,0.275,0.175,0.075,0.35,0.775,0.825,0.85,0.825,0.5812748948353057,0.22879274824296786,0.06061519562824609,0.12460845193456302,0.13452910702981752,40.0,0.21183892499999998,8.473557,53.198074999999996,81950.075 F_independent,all_anthropic,trimmed_mean_20,validation_F_independent_all_anthropic_mid,40.0,0.1811240109662954,65117.25094705647,0.12839821529457668,0.256803683985244,0.4145625069212855,0.43714547226724193,0.048712368035983736,0.275,0.175,0.075,0.35,0.775,0.825,0.85,0.825,0.5812748948353057,0.22879274824296786,0.06061519562824609,0.12460845193456302,0.13452910702981752,40.0,0.21183892499999998,8.473557,53.198074999999996,81950.075 F_independent,all_openai,inverse_variance,validation_F_independent_all_openai_mid,40.0,0.17268334187387152,61210.64560933602,0.10683948583068698,0.2485200226689296,0.39581011142924755,0.4261627297476767,0.049599039678706755,0.275,0.175,0.075,0.375,0.675,0.825,0.825,0.825,0.506774921009673,0.18422640016182973,0.06030949549579219,0.12386008409668484,0.13252758712193638,40.0,0.216257075,8.650283,163.21880000000002,61940.675 F_independent,all_openai,mean,validation_F_independent_all_openai_mid,40.0,0.17268334187387127,61210.64560933594,0.10683948583068542,0.24852002266892925,0.39581011142924755,0.4261627297476766,0.049599039678706935,0.275,0.175,0.075,0.375,0.675,0.825,0.825,0.825,0.506774921009673,0.18422640016182973,0.06030949549579219,0.12386008409668484,0.13252758712193638,40.0,0.216257075,8.650283,163.21880000000002,61940.675 F_independent,all_openai,median,validation_F_independent_all_openai_mid,40.0,0.17759954787690502,63425.307145606355,0.11525437643678921,0.25794494427433595,0.3600192220519424,0.4631120578944551,0.07261949403999121,0.3,0.2,0.075,0.375,0.675,0.825,0.825,0.825,0.506774921009673,0.18422640016182973,0.06030949549579219,0.12386008409668484,0.13252758712193638,40.0,0.216257075,8.650283,163.21880000000002,61940.675 F_independent,all_openai,mixture,validation_F_independent_all_openai_mid,40.0,0.17411756281480623,61588.96466238955,0.11650018759744007,0.2532463107203084,0.3848565553162857,0.4536859612826568,0.06288148695091818,0.3,0.2,0.05,0.5,0.775,0.85,0.875,0.825,0.5971017602321211,0.2289936678407646,0.056760385747821177,0.11787532824818894,0.12767572324648122,40.0,0.216257075,8.650283,163.21880000000002,61940.675 F_independent,all_openai,robust_bayes,validation_F_independent_all_openai_mid,40.0,0.17746560442394016,63088.23534029677,0.11218068082333882,0.25713290594631855,0.3600394649724263,0.462326320479375,0.07177078826199593,0.3,0.2,0.05,0.375,0.675,0.825,0.825,0.825,0.506774921009673,0.18422640016182973,0.06030949549579219,0.12386008409668484,0.13252758712193638,40.0,0.216257075,8.650283,163.21880000000002,61940.675 F_independent,all_openai,stacking,validation_F_independent_all_openai_mid,40.0,0.17268334187387152,61210.64560933602,0.10683948583068698,0.2485200226689296,0.39581011142924755,0.4261627297476767,0.049599039678706755,0.275,0.175,0.075,0.375,0.675,0.825,0.825,0.825,0.506774921009673,0.18422640016182973,0.06030949549579219,0.12386008409668484,0.13252758712193638,40.0,0.216257075,8.650283,163.21880000000002,61940.675 F_independent,all_openai,trimmed_mean_20,validation_F_independent_all_openai_mid,40.0,0.17598222696773042,62518.59937105955,0.11342176970867446,0.25565447117350154,0.36585933181713215,0.4602428597217295,0.0682218479262536,0.3,0.2,0.05,0.375,0.675,0.825,0.825,0.825,0.506774921009673,0.18422640016182973,0.06030949549579219,0.12386008409668484,0.13252758712193638,40.0,0.216257075,8.650283,163.21880000000002,61940.675 F_independent,mixed_random,inverse_variance,validation_F_independent_mixed_random_mid,40.0,0.17745073961663332,63405.50452584473,0.12091628345900929,0.250859950674828,0.37723935559828287,0.40525754484296367,0.0503132352387274,0.275,0.175,0.075,0.375,0.775,0.825,0.85,0.85,0.5408930118658547,0.2043421741840586,0.06000847229677157,0.12308959755950158,0.1325705082421022,40.0,0.226941825,9.077673,84.739975,71977.175 F_independent,mixed_random,mean,validation_F_independent_mixed_random_mid,40.0,0.17745073961663374,63405.50452584488,0.12091628345901184,0.2508599506748285,0.37723935559828287,0.40525754484296533,0.05031323523872842,0.275,0.175,0.075,0.375,0.775,0.825,0.85,0.85,0.5408930118658547,0.2043421741840586,0.06000847229677157,0.12308959755950158,0.1325705082421022,40.0,0.226941825,9.077673,84.739975,71977.175 F_independent,mixed_random,median,validation_F_independent_mixed_random_mid,40.0,0.1790658698103976,63379.75228429295,0.1182178076253731,0.25481088480064895,0.3849386526672,0.4430984029974624,0.06473147588294807,0.3,0.2,0.075,0.375,0.775,0.825,0.85,0.85,0.5408930118658547,0.2043421741840586,0.06000847229677157,0.12308959755950158,0.1325705082421022,40.0,0.226941825,9.077673,84.739975,71977.175 F_independent,mixed_random,mixture,validation_F_independent_mixed_random_mid,40.0,0.17873205325605,63609.49195750149,0.11974323253599262,0.2525204022007258,0.37316885495603797,0.4276132672920004,0.057697423440457564,0.3,0.2,0.075,0.45,0.8,0.85,0.875,0.85,0.6205340209470288,0.24672158444110998,0.05819791232875654,0.12014659649707275,0.12988863906687242,40.0,0.226941825,9.077673,84.739975,71977.175 F_independent,mixed_random,robust_bayes,validation_F_independent_mixed_random_mid,40.0,0.1784902242979851,63586.549368704866,0.11850491177640943,0.25241636776699883,0.3679180017890623,0.432192036478237,0.061588995630435586,0.3,0.2,0.075,0.375,0.775,0.825,0.85,0.85,0.5408930118658547,0.2043421741840586,0.06000847229677157,0.12308959755950158,0.1325705082421022,40.0,0.226941825,9.077673,84.739975,71977.175 F_independent,mixed_random,stacking,validation_F_independent_mixed_random_mid,40.0,0.17745073961663332,63405.50452584473,0.12091628345900929,0.250859950674828,0.37723935559828287,0.40525754484296367,0.0503132352387274,0.275,0.175,0.075,0.375,0.775,0.825,0.85,0.85,0.5408930118658547,0.2043421741840586,0.06000847229677157,0.12308959755950158,0.1325705082421022,40.0,0.226941825,9.077673,84.739975,71977.175 F_independent,mixed_random,trimmed_mean_20,validation_F_independent_mixed_random_mid,40.0,0.17815280060910516,63444.333625654996,0.11913639942472437,0.2521565995934818,0.35916451675008987,0.43103702213836964,0.060524680473131684,0.3,0.2,0.075,0.375,0.775,0.825,0.85,0.85,0.5408930118658547,0.2043421741840586,0.06000847229677157,0.12308959755950158,0.1325705082421022,40.0,0.226941825,9.077673,84.739975,71977.175 G_debate_r1,mixed_random,inverse_variance,validation_G_debate_r1_mixed_random_mid,40.0,0.17458239393120434,62160.45377239968,0.12011586630260651,0.24826594003751534,0.38485932931953054,0.39389333614734223,0.04574128137474616,0.275,0.175,0.075,0.375,0.775,0.825,0.85,0.85,0.553242311977879,0.2061828219757214,0.059547859303411964,0.12220193403171549,0.1308303326633853,40.0,0.8772890499999999,35.091561999999996,252.17132500000002,294497.45 G_debate_r1,mixed_random,mean,validation_G_debate_r1_mixed_random_mid,40.0,0.17458239393120428,62160.453772399655,0.12011586630260723,0.2482659400375151,0.3848593293195318,0.39389333614733724,0.04574128137474709,0.275,0.175,0.075,0.375,0.775,0.825,0.85,0.85,0.553242311977879,0.2061828219757214,0.059547859303411964,0.12220193403171549,0.1308303326633853,40.0,0.8772890499999999,35.091561999999996,252.17132500000002,294497.45 G_debate_r1,mixed_random,median,validation_G_debate_r1_mixed_random_mid,40.0,0.17795994858564676,63018.52623555394,0.1151532405382264,0.25441101373771824,0.3774047996100212,0.4195372237846765,0.05929379950426648,0.3,0.2,0.075,0.375,0.775,0.825,0.85,0.85,0.553242311977879,0.2061828219757214,0.059547859303411964,0.12220193403171549,0.1308303326633853,40.0,0.8772890499999999,35.091561999999996,252.17132500000002,294497.45 G_debate_r1,mixed_random,mixture,validation_G_debate_r1_mixed_random_mid,40.0,0.17656957833245115,62681.900475992436,0.11586013117343114,0.2509705976901622,0.38505154596416136,0.41549588822861944,0.05335512353568812,0.3,0.2,0.075,0.45,0.8,0.825,0.85,0.85,0.5961316448756216,0.23522531699044347,0.05743875681856334,0.11854656932024903,0.12811129187050624,40.0,0.8772890499999999,35.091561999999996,252.17132500000002,294497.45 G_debate_r1,mixed_random,robust_bayes,validation_G_debate_r1_mixed_random_mid,40.0,0.17754007997497037,63041.90944623152,0.11303105965277171,0.2526504121499491,0.36120733225470925,0.42252298100794394,0.058466962507187546,0.3,0.2,0.075,0.375,0.775,0.825,0.85,0.85,0.553242311977879,0.2061828219757214,0.059547859303411964,0.12220193403171549,0.1308303326633853,40.0,0.8772890499999999,35.091561999999996,252.17132500000002,294497.45 G_debate_r1,mixed_random,stacking,validation_G_debate_r1_mixed_random_mid,40.0,0.17458239393120434,62160.45377239968,0.12011586630260651,0.24826594003751534,0.38485932931953054,0.39389333614734223,0.04574128137474616,0.275,0.175,0.075,0.375,0.775,0.825,0.85,0.85,0.553242311977879,0.2061828219757214,0.059547859303411964,0.12220193403171549,0.1308303326633853,40.0,0.8772890499999999,35.091561999999996,252.17132500000002,294497.45 G_debate_r1,mixed_random,trimmed_mean_20,validation_G_debate_r1_mixed_random_mid,40.0,0.17677478606017924,62812.77919698553,0.11268779467193962,0.2519489113925953,0.36064560398659756,0.42130131163162127,0.057614103198410135,0.3,0.2,0.075,0.375,0.775,0.825,0.85,0.85,0.553242311977879,0.2061828219757214,0.059547859303411964,0.12220193403171549,0.1308303326633853,40.0,0.8772890499999999,35.091561999999996,252.17132500000002,294497.45 G_debate_r2,all_anthropic,inverse_variance,validation_G_debate_r2_all_anthropic_mid,40.0,0.17676409053399858,63696.32205406708,0.12480968239183327,0.25013492344656585,0.413155773832575,0.4365798873496922,0.04112289903518884,0.275,0.175,0.075,0.375,0.775,0.825,0.85,0.85,0.5818959946645964,0.21425551229612663,0.05935972846833857,0.12191700728496076,0.13236113712434655,40.0,1.5341821,61.367284,301.671375,572619.075 G_debate_r2,all_anthropic,mean,validation_G_debate_r2_all_anthropic_mid,40.0,0.17676409053399827,63696.322054066906,0.12480968239183149,0.2501349234465658,0.41315577383257324,0.43657988734969067,0.04112289903518977,0.275,0.175,0.075,0.375,0.775,0.825,0.85,0.85,0.5818959946645964,0.21425551229612663,0.05935972846833857,0.12191700728496076,0.13236113712434655,40.0,1.5341821,61.367284,301.671375,572619.075 G_debate_r2,all_anthropic,median,validation_G_debate_r2_all_anthropic_mid,40.0,0.17801480954173238,64334.033646128686,0.12547438399563154,0.2507630165384472,0.4187308319084803,0.43306883918285155,0.04318920995839046,0.275,0.175,0.075,0.375,0.775,0.825,0.85,0.85,0.5818959946645964,0.21425551229612663,0.05935972846833857,0.12191700728496076,0.13236113712434655,40.0,1.5341821,61.367284,301.671375,572619.075 G_debate_r2,all_anthropic,mixture,validation_G_debate_r2_all_anthropic_mid,40.0,0.17710224868801686,63812.36192549276,0.12476430686911855,0.2503502835721656,0.41582946725495074,0.4380038598414856,0.040937859366653305,0.275,0.175,0.075,0.4,0.775,0.825,0.85,0.85,0.5820226379453489,0.22573008626100832,0.05902435712244408,0.12112183309147564,0.1317313687482192,40.0,1.5341821,61.367284,301.671375,572619.075 G_debate_r2,all_anthropic,robust_bayes,validation_G_debate_r2_all_anthropic_mid,40.0,0.17735433584046384,63914.08279468885,0.12562427351567007,0.25058479817548457,0.4166781623413378,0.4355818071400362,0.04235129484466027,0.275,0.175,0.075,0.375,0.775,0.825,0.85,0.85,0.5818959946645964,0.21425551229612663,0.05935972846833857,0.12191700728496076,0.13236113712434655,40.0,1.5341821,61.367284,301.671375,572619.075 G_debate_r2,all_anthropic,stacking,validation_G_debate_r2_all_anthropic_mid,40.0,0.17676409053399858,63696.32205406708,0.12480968239183327,0.25013492344656585,0.413155773832575,0.4365798873496922,0.04112289903518884,0.275,0.175,0.075,0.375,0.775,0.825,0.85,0.85,0.5818959946645964,0.21425551229612663,0.05935972846833857,0.12191700728496076,0.13236113712434655,40.0,1.5341821,61.367284,301.671375,572619.075 G_debate_r2,all_anthropic,trimmed_mean_20,validation_G_debate_r2_all_anthropic_mid,40.0,0.17771639054191227,64006.892896261896,0.12612953369816438,0.2508745572172245,0.41810172779057153,0.43417664035184117,0.0424422519760709,0.275,0.175,0.075,0.375,0.775,0.825,0.85,0.85,0.5818959946645964,0.21425551229612663,0.05935972846833857,0.12191700728496076,0.13236113712434655,40.0,1.5341821,61.367284,301.671375,572619.075 G_debate_r2,all_openai,inverse_variance,validation_G_debate_r2_all_openai_mid,40.0,0.17435764068395873,62107.189833644035,0.1293193806891531,0.24963711566201585,0.3895814402906094,0.423455630189954,0.0476615184843181,0.25,0.15,0.075,0.45,0.7,0.825,0.85,0.825,0.5146706893386478,0.1970472864295345,0.060149529387758915,0.12367436969959274,0.13236698306997724,40.0,0.9951711,39.806844,574.302975,302118.875 G_debate_r2,all_openai,mean,validation_G_debate_r2_all_openai_mid,40.0,0.17435764068395865,62107.18983364396,0.12931938068915227,0.24963711566201593,0.389581440290608,0.42345563018995575,0.04766151848431881,0.25,0.15,0.075,0.45,0.7,0.825,0.85,0.825,0.5146706893386478,0.1970472864295345,0.060149529387758915,0.12367436969959274,0.13236698306997724,40.0,0.9951711,39.806844,574.302975,302118.875 G_debate_r2,all_openai,median,validation_G_debate_r2_all_openai_mid,40.0,0.177978154338401,63346.02983905128,0.11623376623376591,0.2584721665525666,0.36581956653142045,0.4596462808284196,0.07413742256134781,0.3,0.2,0.075,0.45,0.7,0.825,0.85,0.825,0.5146706893386478,0.1970472864295345,0.060149529387758915,0.12367436969959274,0.13236698306997724,40.0,0.9951711,39.806844,574.302975,302118.875 G_debate_r2,all_openai,mixture,validation_G_debate_r2_all_openai_mid,40.0,0.17486417751487315,62009.62234079898,0.12193846754534493,0.25412439019397515,0.3758422928759487,0.45038106747563966,0.06164996807217711,0.3,0.2,0.075,0.475,0.775,0.85,0.875,0.825,0.5967731230726896,0.23583639097840942,0.05692732283358961,0.11821774447324573,0.12825493685885267,40.0,0.9951711,39.806844,574.302975,302118.875 G_debate_r2,all_openai,robust_bayes,validation_G_debate_r2_all_openai_mid,40.0,0.1768126839176853,62839.568048295354,0.11285972230758917,0.2571014789182955,0.36194964928580153,0.46127823000805146,0.07284050421807269,0.3,0.2,0.05,0.45,0.7,0.825,0.85,0.825,0.5146706893386478,0.1970472864295345,0.060149529387758915,0.12367436969959274,0.13236698306997724,40.0,0.9951711,39.806844,574.302975,302118.875 G_debate_r2,all_openai,stacking,validation_G_debate_r2_all_openai_mid,40.0,0.17435764068395873,62107.189833644035,0.1293193806891531,0.24963711566201585,0.3895814402906094,0.423455630189954,0.0476615184843181,0.25,0.15,0.075,0.45,0.7,0.825,0.85,0.825,0.5146706893386478,0.1970472864295345,0.060149529387758915,0.12367436969959274,0.13236698306997724,40.0,0.9951711,39.806844,574.302975,302118.875 G_debate_r2,all_openai,trimmed_mean_20,validation_G_debate_r2_all_openai_mid,40.0,0.17569332306443847,62422.00369363953,0.11355991639885776,0.2557516186541747,0.3502491288571331,0.4601144741716483,0.06940841152902344,0.3,0.2,0.075,0.45,0.7,0.825,0.85,0.825,0.5146706893386478,0.1970472864295345,0.060149529387758915,0.12367436969959274,0.13236698306997724,40.0,0.9951711,39.806844,574.302975,302118.875 G_debate_r2,mixed_random,inverse_variance,validation_G_debate_r2_mixed_random_mid,40.0,0.17334113396819104,62465.56047304491,0.11834856787769005,0.24555088058041927,0.3510530442814116,0.39955142428359985,0.04427420441404815,0.3,0.2,0.075,0.4,0.775,0.825,0.85,0.85,0.5532873913268457,0.2083823848403315,0.0584926960085387,0.12011392781495281,0.12949084722172702,40.0,1.5011856,60.047424,402.28795,514935.75 G_debate_r2,mixed_random,mean,validation_G_debate_r2_mixed_random_mid,40.0,0.17334113396819112,62465.56047304494,0.11834856787768827,0.24555088058041966,0.35105304428141,0.39955142428359824,0.044274204414049126,0.3,0.2,0.075,0.4,0.775,0.825,0.85,0.85,0.5532873913268457,0.2083823848403315,0.0584926960085387,0.12011392781495281,0.12949084722172702,40.0,1.5011856,60.047424,402.28795,514935.75 G_debate_r2,mixed_random,median,validation_G_debate_r2_mixed_random_mid,40.0,0.1756280898133557,62715.31128401967,0.11301644701869923,0.2498878914959799,0.3695659962600122,0.4196121863595829,0.05587774779005326,0.3,0.2,0.075,0.4,0.775,0.825,0.85,0.85,0.5532873913268457,0.2083823848403315,0.0584926960085387,0.12011392781495281,0.12949084722172702,40.0,1.5011856,60.047424,402.28795,514935.75 G_debate_r2,mixed_random,mixture,validation_G_debate_r2_mixed_random_mid,40.0,0.17436657911531564,62579.360265703595,0.11511617223648879,0.24744459031489976,0.35234097518806107,0.41651548337467514,0.05137521298400829,0.3,0.2,0.075,0.425,0.775,0.85,0.875,0.85,0.5894525593084495,0.234745354328451,0.056553306529148584,0.11686721784795015,0.12677336840418177,40.0,1.5011856,60.047424,402.28795,514935.75 G_debate_r2,mixed_random,robust_bayes,validation_G_debate_r2_mixed_random_mid,40.0,0.1752954875414956,62768.425675850456,0.11511507452193653,0.2491567963232755,0.35148098751278195,0.42451617456529595,0.05689852618937086,0.3,0.2,0.075,0.4,0.775,0.825,0.85,0.85,0.5532873913268457,0.2083823848403315,0.0584926960085387,0.12011392781495281,0.12949084722172702,40.0,1.5011856,60.047424,402.28795,514935.75 G_debate_r2,mixed_random,stacking,validation_G_debate_r2_mixed_random_mid,40.0,0.17334113396819104,62465.56047304491,0.11834856787769005,0.24555088058041927,0.3510530442814116,0.39955142428359985,0.04427420441404815,0.3,0.2,0.075,0.4,0.775,0.825,0.85,0.85,0.5532873913268457,0.2083823848403315,0.0584926960085387,0.12011392781495281,0.12949084722172702,40.0,1.5011856,60.047424,402.28795,514935.75 G_debate_r2,mixed_random,trimmed_mean_20,validation_G_debate_r2_mixed_random_mid,40.0,0.1747621571025683,62623.16810914037,0.11521249391105359,0.24859883693535953,0.3500858276303181,0.4235955292617443,0.05602206711158515,0.3,0.2,0.075,0.4,0.775,0.825,0.85,0.85,0.5532873913268457,0.2083823848403315,0.0584926960085387,0.12011392781495281,0.12949084722172702,40.0,1.5011856,60.047424,402.28795,514935.75 G_debate_r4,mixed_random,inverse_variance,validation_G_debate_r4_mixed_random_mid,20.0,0.16140325884651147,64724.124036541405,0.10102521423099531,0.2673908332968777,0.34215216640736273,0.4329526014447851,0.03331175503573256,0.25,0.15,0.05,0.5,0.8,0.8,0.85,0.85,0.5212220295888049,0.19413848468675016,0.05835807950460511,0.11773196786749804,0.12678630110264916,20.0,2.27124095,45.424819,575.30435,776035.55 G_debate_r4,mixed_random,mean,validation_G_debate_r4_mixed_random_mid,20.0,0.16140325884651102,64724.12403654117,0.10102521423099531,0.26739083329687724,0.3421521664073658,0.4329526014447833,0.033311755035733005,0.25,0.15,0.05,0.5,0.8,0.8,0.85,0.85,0.5212220295888049,0.19413848468675016,0.05835807950460511,0.11773196786749804,0.12678630110264916,20.0,2.27124095,45.424819,575.30435,776035.55 G_debate_r4,mixed_random,median,validation_G_debate_r4_mixed_random_mid,20.0,0.162923796912827,65062.61611941088,0.09950741701872856,0.26974890377983857,0.34899220412608867,0.4218478254740278,0.041768743864376304,0.25,0.15,0.05,0.5,0.8,0.8,0.85,0.85,0.5212220295888049,0.19413848468675016,0.05835807950460511,0.11773196786749804,0.12678630110264916,20.0,2.27124095,45.424819,575.30435,776035.55 G_debate_r4,mixed_random,mixture,validation_G_debate_r4_mixed_random_mid,20.0,0.16093570783289152,64458.22757348347,0.09859942118025833,0.2675587649905172,0.3422272565594624,0.42700809427420616,0.036901927746349816,0.25,0.15,0.05,0.5,0.8,0.85,0.85,0.85,0.5396304402718809,0.2164209082328207,0.057651815853223945,0.11607766842673095,0.12644005111832338,20.0,2.27124095,45.424819,575.30435,776035.55 G_debate_r4,mixed_random,robust_bayes,validation_G_debate_r4_mixed_random_mid,20.0,0.1617260111995436,64522.578802257296,0.09852281010532526,0.26847635666681674,0.34416177924274993,0.4213015487454706,0.04167793220370255,0.25,0.15,0.05,0.5,0.8,0.8,0.85,0.85,0.5212220295888049,0.19413848468675016,0.05835807950460511,0.11773196786749804,0.12678630110264916,20.0,2.27124095,45.424819,575.30435,776035.55 G_debate_r4,mixed_random,stacking,validation_G_debate_r4_mixed_random_mid,20.0,0.16140325884651147,64724.124036541405,0.10102521423099531,0.2673908332968777,0.34215216640736273,0.4329526014447851,0.03331175503573256,0.25,0.15,0.05,0.5,0.8,0.8,0.85,0.85,0.5212220295888049,0.19413848468675016,0.05835807950460511,0.11773196786749804,0.12678630110264916,20.0,2.27124095,45.424819,575.30435,776035.55 G_debate_r4,mixed_random,trimmed_mean_20,validation_G_debate_r4_mixed_random_mid,20.0,0.16084209981813052,64399.88430580185,0.0993091393022062,0.2676232414108568,0.3453378387591553,0.42350415765236815,0.04031753235454172,0.25,0.15,0.05,0.5,0.8,0.8,0.85,0.85,0.5212220295888049,0.19413848468675016,0.05835807950460511,0.11773196786749804,0.12678630110264916,20.0,2.27124095,45.424819,575.30435,776035.55 G_fullview,mixed_random,inverse_variance,validation_G_fullview_r2_mixed_random_mid,40.0,0.1742871353419732,62839.09683177837,0.11242389075338349,0.24671939562273645,0.3455641102918453,0.40794908297623583,0.04691634179151296,0.3,0.2,0.075,0.45,0.75,0.85,0.85,0.85,0.5603430627189794,0.2099207967431838,0.05867413901500088,0.12005991831375887,0.13029890884589462,40.0,1.595248275,63.809931000000006,411.53305,545942.85 G_fullview,mixed_random,mean,validation_G_fullview_r2_mixed_random_mid,40.0,0.17428713534197313,62839.096831778275,0.11242389075338449,0.24671939562273648,0.3455641102918487,0.4079490829762342,0.04691634179151376,0.3,0.2,0.075,0.45,0.75,0.85,0.85,0.85,0.5603430627189794,0.2099207967431838,0.05867413901500088,0.12005991831375887,0.13029890884589462,40.0,1.595248275,63.809931000000006,411.53305,545942.85 G_fullview,mixed_random,median,validation_G_fullview_r2_mixed_random_mid,40.0,0.17455906988101186,62350.606382406644,0.11277815929702345,0.2502707687805322,0.34627991324610125,0.42477737493805917,0.05856397260812209,0.3,0.2,0.075,0.45,0.75,0.85,0.85,0.85,0.5603430627189794,0.2099207967431838,0.05867413901500088,0.12005991831375887,0.13029890884589462,40.0,1.595248275,63.809931000000006,411.53305,545942.85 G_fullview,mixed_random,mixture,validation_G_fullview_r2_mixed_random_mid,40.0,0.17552831012009767,63196.58737145446,0.1160232246793742,0.24881865946056242,0.3474735975312687,0.41681371229771524,0.05407910806007328,0.3,0.2,0.075,0.475,0.775,0.85,0.85,0.85,0.5913158594759329,0.2313922199297446,0.05733296610743693,0.11826307704243737,0.12793201689611133,40.0,1.595248275,63.809931000000006,411.53305,545942.85 G_fullview,mixed_random,robust_bayes,validation_G_fullview_r2_mixed_random_mid,40.0,0.17540648224852778,62867.06804850765,0.1144794269812413,0.25024150621557495,0.34486901639423834,0.42571244646508083,0.058365770975713625,0.3,0.2,0.075,0.45,0.75,0.85,0.85,0.85,0.5603430627189794,0.2099207967431838,0.05867413901500088,0.12005991831375887,0.13029890884589462,40.0,1.595248275,63.809931000000006,411.53305,545942.85 G_fullview,mixed_random,stacking,validation_G_fullview_r2_mixed_random_mid,40.0,0.1742871353419732,62839.09683177837,0.11242389075338349,0.24671939562273645,0.3455641102918453,0.40794908297623583,0.04691634179151296,0.3,0.2,0.075,0.45,0.75,0.85,0.85,0.85,0.5603430627189794,0.2099207967431838,0.05867413901500088,0.12005991831375887,0.13029890884589462,40.0,1.595248275,63.809931000000006,411.53305,545942.85 G_fullview,mixed_random,trimmed_mean_20,validation_G_fullview_r2_mixed_random_mid,40.0,0.17554844534528602,62954.14646526143,0.11545567406990687,0.25025736013099975,0.3438822966490407,0.42507075852072285,0.057746817236835835,0.3,0.2,0.075,0.45,0.75,0.85,0.85,0.85,0.5603430627189794,0.2099207967431838,0.05867413901500088,0.12005991831375887,0.13029890884589462,40.0,1.595248275,63.809931000000006,411.53305,545942.85 H_debate_skeptic,mixed_random,inverse_variance,validation_H_debate_skeptic_r2_mixed_random_mid,40.0,0.171666562801716,61682.334328630604,0.12154885530892873,0.2451780726836604,0.3651177777950775,0.42343809866546006,0.041744037843842285,0.275,0.175,0.075,0.425,0.775,0.825,0.85,0.85,0.5566340323649109,0.20889035515813942,0.05826326920763099,0.11946414569311034,0.12901324124879726,40.0,1.3739639499999998,54.958558,383.2318,464505.8 H_debate_skeptic,mixed_random,mean,validation_H_debate_skeptic_r2_mixed_random_mid,40.0,0.17166656280171563,61682.33432863038,0.12154885530892895,0.24517807268366007,0.3651177777950757,0.4234380986654567,0.041744037843843174,0.275,0.175,0.075,0.425,0.775,0.825,0.85,0.85,0.5566340323649109,0.20889035515813942,0.05826326920763099,0.11946414569311034,0.12901324124879726,40.0,1.3739639499999998,54.958558,383.2318,464505.8 H_debate_skeptic,mixed_random,median,validation_H_debate_skeptic_r2_mixed_random_mid,40.0,0.17507604886472028,62649.305615045814,0.11919490475681532,0.2496981235058179,0.3501022141078921,0.4295842503760401,0.055489643704223955,0.275,0.175,0.075,0.425,0.775,0.825,0.85,0.85,0.5566340323649109,0.20889035515813942,0.05826326920763099,0.11946414569311034,0.12901324124879726,40.0,1.3739639499999998,54.958558,383.2318,464505.8 H_debate_skeptic,mixed_random,mixture,validation_H_debate_skeptic_r2_mixed_random_mid,40.0,0.1727955026123562,61937.03805065611,0.11782561047958945,0.24718316807860855,0.3699457350363155,0.42331333172615593,0.048854761706124926,0.275,0.175,0.075,0.45,0.8,0.825,0.85,0.85,0.5934527108787158,0.23356320490494764,0.05671528904819778,0.11693561172357006,0.12702690330892605,40.0,1.3739639499999998,54.958558,383.2318,464505.8 H_debate_skeptic,mixed_random,robust_bayes,validation_H_debate_skeptic_r2_mixed_random_mid,40.0,0.17382937768475112,62239.71813031864,0.11621975605742502,0.24870010924952177,0.3526527533100688,0.4332289024758447,0.05463211113253132,0.275,0.175,0.075,0.425,0.775,0.825,0.85,0.85,0.5566340323649109,0.20889035515813942,0.05826326920763099,0.11946414569311034,0.12901324124879726,40.0,1.3739639499999998,54.958558,383.2318,464505.8 H_debate_skeptic,mixed_random,stacking,validation_H_debate_skeptic_r2_mixed_random_mid,40.0,0.171666562801716,61682.334328630604,0.12154885530892873,0.2451780726836604,0.3651177777950775,0.42343809866546006,0.041744037843842285,0.275,0.175,0.075,0.425,0.775,0.825,0.85,0.85,0.5566340323649109,0.20889035515813942,0.05826326920763099,0.11946414569311034,0.12901324124879726,40.0,1.3739639499999998,54.958558,383.2318,464505.8 H_debate_skeptic,mixed_random,trimmed_mean_20,validation_H_debate_skeptic_r2_mixed_random_mid,40.0,0.17330042141150281,62131.23356221981,0.11641290179670188,0.24800518446905845,0.35250459041477233,0.4303822616433471,0.05339544807326426,0.275,0.175,0.075,0.425,0.775,0.825,0.85,0.85,0.5566340323649109,0.20889035515813942,0.05826326920763099,0.11946414569311034,0.12901324124879726,40.0,1.3739639499999998,54.958558,383.2318,464505.8 I_placebo,mixed_random,inverse_variance,validation_I_placebo_r2_mixed_random_mid,40.0,0.1821553563708192,64340.81944267696,0.10720357489559729,0.2604625591344496,0.4047032296033161,0.454825005700491,0.05977674961337733,0.3,0.2,0.075,0.4,0.725,0.825,0.85,0.825,0.5411090984988302,0.20194654184923327,0.06132616552830002,0.12624478183212742,0.13551761270766066,40.0,1.3518994,54.075976,317.830125,476453.75 I_placebo,mixed_random,mean,validation_I_placebo_r2_mixed_random_mid,40.0,0.18215535637081892,64340.819442676846,0.10720357489559545,0.2604625591344493,0.40470322960331434,0.4548250057004928,0.05977674961337805,0.3,0.2,0.075,0.4,0.725,0.825,0.85,0.825,0.5411090984988302,0.20194654184923327,0.06132616552830002,0.12624478183212742,0.13551761270766066,40.0,1.3518994,54.075976,317.830125,476453.75 I_placebo,mixed_random,median,validation_I_placebo_r2_mixed_random_mid,40.0,0.18364834891764875,64127.433942059244,0.10627766766390445,0.2636646044070842,0.4225461388678291,0.46321473299277605,0.06377672270646344,0.3,0.2,0.075,0.4,0.725,0.825,0.85,0.825,0.5411090984988302,0.20194654184923327,0.06132616552830002,0.12624478183212742,0.13551761270766066,40.0,1.3518994,54.075976,317.830125,476453.75 I_placebo,mixed_random,mixture,validation_I_placebo_r2_mixed_random_mid,40.0,0.18227339943919113,64271.925106485745,0.10776348297120997,0.2604665276592777,0.40559433343072215,0.4490498868790683,0.06189325599708129,0.3,0.2,0.075,0.425,0.725,0.85,0.85,0.825,0.560600907448743,0.22432009436913597,0.060500323355157745,0.12450371797543609,0.13413429015114078,40.0,1.3518994,54.075976,317.830125,476453.75 I_placebo,mixed_random,robust_bayes,validation_I_placebo_r2_mixed_random_mid,40.0,0.1831406346331495,64314.92839031585,0.10674576671052138,0.26201133223868295,0.4092335676332111,0.45920357733198847,0.06328545472395945,0.3,0.2,0.075,0.4,0.725,0.825,0.85,0.825,0.5411090984988302,0.20194654184923327,0.06132616552830002,0.12624478183212742,0.13551761270766066,40.0,1.3518994,54.075976,317.830125,476453.75 I_placebo,mixed_random,stacking,validation_I_placebo_r2_mixed_random_mid,40.0,0.1821553563708192,64340.81944267696,0.10720357489559729,0.2604625591344496,0.4047032296033161,0.454825005700491,0.05977674961337733,0.3,0.2,0.075,0.4,0.725,0.825,0.85,0.825,0.5411090984988302,0.20194654184923327,0.06132616552830002,0.12624478183212742,0.13551761270766066,40.0,1.3518994,54.075976,317.830125,476453.75 I_placebo,mixed_random,trimmed_mean_20,validation_I_placebo_r2_mixed_random_mid,40.0,0.18294805263749114,64252.64908456961,0.10738342864855699,0.26163926103085633,0.4093599776311525,0.4522307518122827,0.06305220352250349,0.3,0.2,0.075,0.4,0.725,0.825,0.85,0.825,0.5411090984988302,0.20194654184923327,0.06132616552830002,0.12624478183212742,0.13551761270766066,40.0,1.3518994,54.075976,317.830125,476453.75 J_cost_matched,mixed_random,inverse_variance,validation_J_cost_matched_mixed_random_mid,40.0,0.17805664643368174,63436.68294943987,0.1161581982135475,0.25744196300054945,0.38226567392850525,0.4640820478362119,0.07063506753886717,0.275,0.175,0.05,0.35,0.775,0.825,0.825,0.825,0.4973532976535132,0.18829261759382593,0.06040781794666894,0.12323079544390189,0.13259201026007866,40.0,0.252280725,10.091229,107.91307500000002,89421.5 J_cost_matched,mixed_random,mean,validation_J_cost_matched_mixed_random_mid,40.0,0.1780566464336816,63436.68294943978,0.11615819821354734,0.25744196300054945,0.38226567392850364,0.46408204783621,0.07063506753886668,0.275,0.175,0.05,0.35,0.775,0.825,0.825,0.825,0.4973532976535132,0.18829261759382593,0.06040781794666894,0.12323079544390189,0.13259201026007866,40.0,0.252280725,10.091229,107.91307500000002,89421.5 J_cost_matched,mixed_random,median,validation_J_cost_matched_mixed_random_mid,40.0,0.1786301928342328,63449.275,0.11757350812077205,0.25739474710023774,0.3853149136344805,0.4755091706540879,0.07045289661192915,0.275,0.175,0.05,0.35,0.775,0.825,0.825,0.825,0.4973532976535132,0.18829261759382593,0.06040781794666894,0.12323079544390189,0.13259201026007866,40.0,0.252280725,10.091229,107.91307500000002,89421.5 J_cost_matched,mixed_random,mixture,validation_J_cost_matched_mixed_random_mid,40.0,0.17800416304617755,63425.60499909041,0.11629845994345889,0.2572843250568837,0.3829434607234558,0.46232919664465505,0.07067239896506261,0.275,0.175,0.05,0.35,0.75,0.825,0.825,0.825,0.4953416196565318,0.19619046738970303,0.06018790331911337,0.12260409692398673,0.1326747345972354,40.0,0.252280725,10.091229,107.91307500000002,89421.5 J_cost_matched,mixed_random,robust_bayes,validation_J_cost_matched_mixed_random_mid,40.0,0.1783056567720674,63495.224956438164,0.11639111608338581,0.2576784504251368,0.3846831730041131,0.46790407611082196,0.07047765439630864,0.275,0.175,0.05,0.35,0.775,0.825,0.825,0.825,0.4973532976535132,0.18829261759382593,0.06040781794666894,0.12323079544390189,0.13259201026007866,40.0,0.252280725,10.091229,107.91307500000002,89421.5 J_cost_matched,mixed_random,samples_mean,validation_J_cost_matched_mixed_random_mid,40.0,0.1784525752512315,63532.71709582086,0.11641721152599876,0.2579756805603611,0.38258231843348023,0.46831396157416905,0.07056316277441299,0.275,0.175,0.05,0.35,0.775,0.825,0.825,0.825,0.4973532976535132,0.18829261759382593,0.06040781794666894,0.12323079544390189,0.13259201026007866,40.0,0.252280725,10.091229,107.91307500000002,89421.5 J_cost_matched,mixed_random,samples_median,validation_J_cost_matched_mixed_random_mid,40.0,0.1795204419812224,63753.00697030623,0.11757350812077205,0.25839172991074966,0.3853149136344805,0.4755091706540879,0.06928350729989993,0.275,0.175,0.05,0.35,0.775,0.825,0.825,0.825,0.4973532976535132,0.18829261759382593,0.06040781794666894,0.12323079544390189,0.13259201026007866,40.0,0.252280725,10.091229,107.91307500000002,89421.5 J_cost_matched,mixed_random,self_refine,validation_J_cost_matched_mixed_random_mid,40.0,0.17330550062308198,62324.275,0.11365465320918755,0.2516110769146089,0.38391327363861466,0.4496475445996452,0.07149792471230745,0.25,0.15,0.05,0.35,0.775,0.825,0.825,0.825,0.4973532976535132,0.18829261759382593,0.06040781794666894,0.12323079544390189,0.13259201026007866,40.0,0.252280725,10.091229,107.91307500000002,89421.5 J_cost_matched,mixed_random,stacking,validation_J_cost_matched_mixed_random_mid,40.0,0.17805664643368174,63436.68294943987,0.1161581982135475,0.25744196300054945,0.38226567392850525,0.4640820478362119,0.07063506753886717,0.275,0.175,0.05,0.35,0.775,0.825,0.825,0.825,0.4973532976535132,0.18829261759382593,0.06040781794666894,0.12323079544390189,0.13259201026007866,40.0,0.252280725,10.091229,107.91307500000002,89421.5 J_cost_matched,mixed_random,trimmed_mean_20,validation_J_cost_matched_mixed_random_mid,40.0,0.1783599612510292,63530.56908292555,0.11704190515119256,0.25774490553645973,0.3854793328769568,0.46979874185963166,0.07017642940419799,0.275,0.175,0.05,0.35,0.775,0.825,0.825,0.825,0.4973532976535132,0.18829261759382593,0.06040781794666894,0.12323079544390189,0.13259201026007866,40.0,0.252280725,10.091229,107.91307500000002,89421.5