1arm,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,main_selection2A_hedonic,none,model,prospective_baselines,1182.0,0.2185938773916135,101233.49137871097,0.14171441878083452,0.3156089825957377,0.5356384929018659,0.7379316820814765,0.006014533222618259,0.33079526226734346,0.15905245346869712,0.1065989847715736,0.45685279187817257,0.8121827411167513,0.8730964467005076,0.9103214890016921,0.8756345177664975,1.0012939578604456,0.2454377797686806,0.07294464619544982,0.15112239422201745,0.17006864314321296,1182.0,0.0,0.0,1.5503842625514862e-05,0.0,baseline3B_hierarchical,none,model,prospective_baselines,1182.0,0.20685163007412297,95377.19235054783,0.12292834029952382,0.3124985052927351,0.5217642515944428,0.7573147183249161,0.03539984692497287,0.2910321489001692,0.16243654822335024,0.0829103214890017,0.4780033840947547,0.8367174280879864,0.8840947546531303,0.9094754653130288,0.8857868020304569,0.9980838744748973,0.2308178428117022,0.07084012220128806,0.14614863909505943,0.163938861983992,1182.0,0.0,0.0,4.031373116592743e-06,0.0,baseline4C_catboost,none,model,prospective_baselines,1182.0,0.21463808000349202,103039.70809915233,0.1382487360665976,0.32712494092013894,0.49670892389245,0.7592147421157,0.0769218312317705,0.2969543147208122,0.19712351945854484,0.06175972927241963,,,,,,,,,,,0.0,0.0,0.0,5.5690567137582094e-06,0.0,baseline5C_gbm,none,model,prospective_baselines,1182.0,0.21793871036888554,103314.08635564613,0.1421115953909055,0.32110844956498424,0.478575454351593,0.7625964069347773,0.05021093024719027,0.3240270727580372,0.18274111675126903,0.09137055837563451,,,,,,,,,,,0.0,0.0,0.0,1.5393295246546744e-05,0.0,baseline6C_xgboost,none,model,prospective_baselines,1182.0,0.22180204133421091,105344.35616936337,0.14409796216862347,0.3330404895745805,0.5043543793585383,0.8168384288964584,0.09510816429410458,0.305414551607445,0.21912013536379019,0.06006768189509306,,,,,,,,,,,0.0,0.0,0.0,8.88102790522003e-06,0.0,baseline7D_avm,none,model,prospective_baselines,1182.0,0.2024250307340938,95299.73188033383,0.12945034317709198,0.3086463002014552,0.46031507564453755,0.7395463082579299,0.03871832865971896,0.2808798646362098,0.15651438240270726,0.07191201353637902,0.4103214890016921,0.8274111675126904,0.8663282571912013,0.8993231810490694,0.8815566835871405,0.8893791351125315,0.2184186865779708,0.07146594608746076,0.1479729467965839,0.15749018787217148,1182.0,0.0,0.0,0.00031365563368303435,0.0,baseline8E_single_llm,mixed_random,median,prospective_E_single_llm_mixed_random_mid,40.0,0.18650753970155973,83022.175,0.08506682745452776,0.27495488819108443,0.49091093457069773,0.6448924880894997,0.05877583003180309,0.3,0.175,0.025,0.425,0.725,0.75,0.85,0.775,0.5579650700737118,0.2139463226171124,0.0646556358154885,0.13123674199725022,0.1422409550573188,40.0,0.020484999999999996,0.8193999999999999,16.092724999999998,6943.725,preferred9F_independent,mixed_random,median,prospective_F_independent_mixed_random_mid,40.0,0.1787261001431398,77779.83887115055,0.0878879308262499,0.26822811107227423,0.43073329344754824,0.6600587868492497,0.06087627636627051,0.275,0.175,0.025,0.5,0.775,0.8,0.875,0.825,0.5741003394033062,0.21855410899596098,0.06156762202903757,0.1258575037673835,0.13557751846817992,40.0,0.23409914999999998,9.363966,54.70235,75319.55,preferred10G_debate_r2,mixed_random,median,prospective_G_debate_r2_mixed_random_mid,40.0,0.18739539395828042,81111.36014474792,0.096109380183864,0.27806809479267924,0.48729545017873943,0.6619796463871616,0.057701636416563715,0.3,0.175,0.05,0.45,0.725,0.825,0.9,0.825,0.5707408543553014,0.21346491065014234,0.06428879557732191,0.13195556127047464,0.14222408103796638,40.0,1.4995731749999999,59.982927,244.906625,514032.075,preferred11