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,83489.0,0.1979251606964042,95867.64933324595,0.1315979618893146,0.2912214722391947,0.4359403189941982,0.6488149138238946,-0.003652738484054442,0.2909604858125022,0.12558540646073135,0.10227694666363234,0.4798596222256824,0.8530944196241421,0.8976152547042126,0.934949514307274,0.9080357891458755,1.001459205820069,0.24555321031791527,0.06639817879889601,0.1368067310340593,0.1557286573617329,83489.0,0.0,0.0,1.2689511069686403e-06,0.0 B_hierarchical,none,model,baselines,83489.0,0.18546824946244722,90071.80772957353,0.11734243023333302,0.28386704967881665,0.4154463536868226,0.6550377569388846,0.015761042715615674,0.2524883517589144,0.12572913797027152,0.07507575848315347,0.4949514307274012,0.864988202038592,0.9066823174310388,0.9363868294026758,0.9134376983794272,0.9980834562671798,0.23081762970185607,0.06356472991202007,0.13051299224947238,0.15005407818546887,83489.0,0.0,0.0,9.546871439288114e-07,0.0 C_catboost,none,model,baselines,83489.0,0.19121337794060425,94518.06451548066,0.12420639584980409,0.2894000309302015,0.4130913315983456,0.6590975068806568,0.012002588881544969,0.2653762771143504,0.1348560888260729,0.07238079267927511,,,,,,,,,,,0.0,0.0,0.0,1.2147733112911035e-06,0.0 C_gbm,none,model,baselines,83489.0,0.19253066496579505,94552.6669343487,0.12666610869924133,0.28782510613195145,0.41801318246215613,0.6508809896230991,0.008201637345222517,0.273892369054606,0.1309992933200781,0.08383140293930937,,,,,,,,,,,0.0,0.0,0.0,2.9570991384886e-06,0.0 C_xgboost,none,model,baselines,83489.0,0.1915589848422451,95645.05107250281,0.12135427867383508,0.29540007441498034,0.4254431415148513,0.6888035412177579,0.04612140042763994,0.2608966450670148,0.15691887554049036,0.06119369018673119,,,,,,,,,,,0.0,0.0,0.0,1.0019383750646475e-06,0.0 D_avm,none,model,baselines,83489.0,0.17990472006046368,88511.94587625634,0.11242545941537896,0.2775101759187976,0.39923512815628787,0.6433706067447303,0.0023498750222177163,0.23932494101019297,0.11482949849680796,0.06991340176550204,0.4343566218304208,0.8462312400435985,0.8776365748781276,0.9256668543161375,0.9014720502102074,0.8270870792558116,0.20405216127218306,0.0609482705017001,0.12546872398931572,0.13981228012755972,83489.0,0.0,0.0,0.0002326626736333806,0.0 E_single_llm,mixed_random,inverse_variance,holdout_E_single_llm_mixed_random_mid,60.0,0.1952999223487625,96343.65000000007,0.08606270251335485,0.32037092614578466,0.605008800534372,0.8464376869734441,0.11039476057625937,0.26666666666666666,0.18333333333333332,0.05,0.4666666666666667,0.7166666666666667,0.8,0.8333333333333334,0.7833333333333333,0.49688479586848483,0.18618219756398385,0.0715305705557199,0.14329370167779357,0.15316185591812753,60.0,0.022798033333333335,1.367882,17.562116666666665,7343.45 E_single_llm,mixed_random,mean,holdout_E_single_llm_mixed_random_mid,60.0,0.1952999223487625,96343.65000000007,0.08606270251335485,0.32037092614578466,0.605008800534372,0.8464376869734441,0.11039476057625937,0.26666666666666666,0.18333333333333332,0.05,0.4666666666666667,0.7166666666666667,0.8,0.8333333333333334,0.7833333333333333,0.49688479586848483,0.18618219756398385,0.0715305705557199,0.14329370167779357,0.15316185591812753,60.0,0.022798033333333335,1.367882,17.562116666666665,7343.45 E_single_llm,mixed_random,median,holdout_E_single_llm_mixed_random_mid,60.0,0.1952999223487625,96343.65000000007,0.08606270251335485,0.32037092614578466,0.605008800534372,0.8464376869734441,0.11039476057625937,0.26666666666666666,0.18333333333333332,0.05,0.4666666666666667,0.7166666666666667,0.8,0.8333333333333334,0.7833333333333333,0.49688479586848483,0.18618219756398385,0.0715305705557199,0.14329370167779357,0.15316185591812753,60.0,0.022798033333333335,1.367882,17.562116666666665,7343.45 E_single_llm,mixed_random,mixture,holdout_E_single_llm_mixed_random_mid,60.0,0.19531455237318168,96357.49665434966,0.0860455352519035,0.32040276457618383,0.6050274021443925,0.8465618104220611,0.11051946098179481,0.26666666666666666,0.18333333333333332,0.05,0.4666666666666667,0.7166666666666667,0.8,0.8333333333333334,0.7833333333333333,0.4968970303598146,0.18617936203996577,0.07153696111659798,0.14330614759577404,0.15317796959717753,60.0,0.022798033333333335,1.367882,17.562116666666665,7343.45 E_single_llm,mixed_random,robust_bayes,holdout_E_single_llm_mixed_random_mid,60.0,0.19529992234876278,96343.65000000024,0.08606270251335574,0.32037092614578494,0.6050088005343738,0.8464376869734441,0.11039476057625942,0.26666666666666666,0.18333333333333332,0.05,0.4666666666666667,0.7166666666666667,0.8,0.8333333333333334,0.7833333333333333,0.49688479586848483,0.18618219756398385,0.0715305705557199,0.14329370167779357,0.15316185591812753,60.0,0.022798033333333335,1.367882,17.562116666666665,7343.45 E_single_llm,mixed_random,stacking,holdout_E_single_llm_mixed_random_mid,60.0,0.1952999223487625,96343.65000000007,0.08606270251335485,0.32037092614578466,0.605008800534372,0.8464376869734441,0.11039476057625937,0.26666666666666666,0.18333333333333332,0.05,0.4666666666666667,0.7166666666666667,0.8,0.8333333333333334,0.7833333333333333,0.49688479586848483,0.18618219756398385,0.0715305705557199,0.14329370167779357,0.15316185591812753,60.0,0.022798033333333335,1.367882,17.562116666666665,7343.45 E_single_llm,mixed_random,trimmed_mean_20,holdout_E_single_llm_mixed_random_mid,60.0,0.1952999223487625,96343.65000000007,0.08606270251335485,0.32037092614578466,0.605008800534372,0.8464376869734441,0.11039476057625937,0.26666666666666666,0.18333333333333332,0.05,0.4666666666666667,0.7166666666666667,0.8,0.8333333333333334,0.7833333333333333,0.49688479586848483,0.18618219756398385,0.0715305705557199,0.14329370167779357,0.15316185591812753,60.0,0.022798033333333335,1.367882,17.562116666666665,7343.45 F_independent,mixed_random,inverse_variance,holdout_F_independent_mixed_random_mid,60.0,0.1824449477877259,91587.95487292056,0.0844092362469761,0.30440861997391905,0.5500328048918561,0.7919089008737029,0.10064281473421914,0.23333333333333334,0.18333333333333332,0.05,0.5166666666666667,0.75,0.8333333333333334,0.8333333333333334,0.8166666666666667,0.5077470175934654,0.19242990314387456,0.0685949264303503,0.13756971850561459,0.14815270751704934,60.0,0.24187855,14.512713,81.19189999999999,77650.16666666667 F_independent,mixed_random,mean,holdout_F_independent_mixed_random_mid,60.0,0.18219464979762143,91510.6188750048,0.08222075717085553,0.3031389887827641,0.5431039085117185,0.7823512183781643,0.09796515298699043,0.23333333333333334,0.18333333333333332,0.05,0.5166666666666667,0.75,0.8333333333333334,0.8333333333333334,0.8166666666666667,0.5077470175934654,0.19242990314387456,0.0685949264303503,0.13756971850561459,0.14815270751704934,60.0,0.24187855,14.512713,81.19189999999999,77650.16666666667 F_independent,mixed_random,median,holdout_F_independent_mixed_random_mid,60.0,0.18587053154303357,92553.33915803811,0.08987815800321519,0.3103782493005791,0.5837464197516442,0.8051454444335208,0.10660063150501733,0.23333333333333334,0.18333333333333332,0.05,0.5166666666666667,0.75,0.8333333333333334,0.8333333333333334,0.8166666666666667,0.5077470175934654,0.19242990314387456,0.0685949264303503,0.13756971850561459,0.14815270751704934,60.0,0.24187855,14.512713,81.19189999999999,77650.16666666667 F_independent,mixed_random,mixture,holdout_F_independent_mixed_random_mid,60.0,0.1836843483513352,92497.21482400183,0.08876037121078506,0.305159254009495,0.5550770534653608,0.80012397759366,0.10380237050670325,0.23333333333333334,0.18333333333333332,0.05,0.6,0.7833333333333333,0.85,0.8833333333333333,0.8333333333333334,0.5697220720602492,0.23134737897541913,0.06708882641815847,0.13530789981909558,0.14521030500447252,60.0,0.24187855,14.512713,81.19189999999999,77650.16666666667 F_independent,mixed_random,robust_bayes,holdout_F_independent_mixed_random_mid,60.0,0.18277061134458103,91803.55560252648,0.08501411402911219,0.30490760612452344,0.5520039346576328,0.7978582769769688,0.10034571989687005,0.23333333333333334,0.18333333333333332,0.05,0.5166666666666667,0.75,0.8333333333333334,0.8333333333333334,0.8166666666666667,0.5077470175934654,0.19242990314387456,0.0685949264303503,0.13756971850561459,0.14815270751704934,60.0,0.24187855,14.512713,81.19189999999999,77650.16666666667 F_independent,mixed_random,stacking,holdout_F_independent_mixed_random_mid,60.0,0.18560025523031223,93612.15066699251,0.07717079706954594,0.30742720736657153,0.5356934425774778,0.7922788607558683,0.11003897503604494,0.25,0.18333333333333332,0.03333333333333333,0.5166666666666667,0.75,0.8333333333333334,0.8333333333333334,0.8166666666666667,0.5077470175934654,0.19242990314387456,0.0685949264303503,0.13756971850561459,0.14815270751704934,60.0,0.24187855,14.512713,81.19189999999999,77650.16666666667 F_independent,mixed_random,trimmed_mean_20,holdout_F_independent_mixed_random_mid,60.0,0.18655920951457328,93692.96807968084,0.08408658215953568,0.30979267363093443,0.5713124569752519,0.8132385429531273,0.10514196021169822,0.23333333333333334,0.18333333333333332,0.05,0.5166666666666667,0.75,0.8333333333333334,0.8333333333333334,0.8166666666666667,0.5077470175934654,0.19242990314387456,0.0685949264303503,0.13756971850561459,0.14815270751704934,60.0,0.24187855,14.512713,81.19189999999999,77650.16666666667 G_debate_r2,mixed_random,inverse_variance,holdout_G_debate_r2_mixed_random_mid,60.0,0.18572330624692715,91853.75674982132,0.08310255266228295,0.3080667019736564,0.5602590497755082,0.7957349458329517,0.09452086918962674,0.26666666666666666,0.18333333333333332,0.05,0.5333333333333333,0.7333333333333333,0.8333333333333334,0.85,0.8,0.5277165599452268,0.20027088961398498,0.06929681974680801,0.13957246034547602,0.14969257860248583,60.0,1.5782689333333335,94.69613600000001,341.5586333333333,537705.2166666667 G_debate_r2,mixed_random,mean,holdout_G_debate_r2_mixed_random_mid,60.0,0.18550987201943153,91824.11394552908,0.08491608797783329,0.30686442568913186,0.5563180226562157,0.7862483859736131,0.09208147541159123,0.26666666666666666,0.18333333333333332,0.05,0.5333333333333333,0.7333333333333333,0.8333333333333334,0.85,0.8,0.5277165599452268,0.20027088961398498,0.06929681974680801,0.13957246034547602,0.14969257860248583,60.0,1.5782689333333335,94.69613600000001,341.5586333333333,537705.2166666667 G_debate_r2,mixed_random,median,holdout_G_debate_r2_mixed_random_mid,60.0,0.1888295841931927,93534.93271751267,0.08881444397229393,0.3135314565052563,0.5874272699870523,0.82772064059921,0.10233449088265743,0.25,0.18333333333333332,0.05,0.5333333333333333,0.7333333333333333,0.8333333333333334,0.85,0.8,0.5277165599452268,0.20027088961398498,0.06929681974680801,0.13957246034547602,0.14969257860248583,60.0,1.5782689333333335,94.69613600000001,341.5586333333333,537705.2166666667 G_debate_r2,mixed_random,mixture,holdout_G_debate_r2_mixed_random_mid,60.0,0.18598199204919258,91824.48370631479,0.08604087324097515,0.30821987699208603,0.5623702773844538,0.807350581591115,0.09673752154876156,0.25,0.18333333333333332,0.05,0.5833333333333334,0.75,0.8333333333333334,0.8666666666666667,0.8166666666666667,0.5592790842127308,0.22604292864606193,0.06813902175045382,0.13749895252531943,0.1479746071458511,60.0,1.5782689333333335,94.69613600000001,341.5586333333333,537705.2166666667 G_debate_r2,mixed_random,robust_bayes,holdout_G_debate_r2_mixed_random_mid,60.0,0.18591815182865304,91991.77314594288,0.08479868333498036,0.30793202825905547,0.5598846586306407,0.8021696786542051,0.09452346279188746,0.25,0.18333333333333332,0.05,0.5333333333333333,0.7333333333333333,0.8333333333333334,0.85,0.8,0.5277165599452268,0.20027088961398498,0.06929681974680801,0.13957246034547602,0.14969257860248583,60.0,1.5782689333333335,94.69613600000001,341.5586333333333,537705.2166666667 G_debate_r2,mixed_random,stacking,holdout_G_debate_r2_mixed_random_mid,60.0,0.18927834446608272,93829.69847541988,0.08974655010370364,0.31254679764030613,0.5319638865200098,0.8032066441883463,0.098621763372924,0.26666666666666666,0.18333333333333332,0.06666666666666667,0.5333333333333333,0.7333333333333333,0.8333333333333334,0.85,0.8,0.5277165599452268,0.20027088961398498,0.06929681974680801,0.13957246034547602,0.14969257860248583,60.0,1.5782689333333335,94.69613600000001,341.5586333333333,537705.2166666667 G_debate_r2,mixed_random,trimmed_mean_20,holdout_G_debate_r2_mixed_random_mid,60.0,0.18814153594355748,92807.70655180347,0.0885328006612005,0.3117796156920275,0.5733116264498249,0.8211682459215099,0.10022785713204944,0.25,0.18333333333333332,0.05,0.5333333333333333,0.7333333333333333,0.8333333333333334,0.85,0.8,0.5277165599452268,0.20027088961398498,0.06929681974680801,0.13957246034547602,0.14969257860248583,60.0,1.5782689333333335,94.69613600000001,341.5586333333333,537705.2166666667