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,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,baseline3B_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,baseline4C_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,baseline5C_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,baseline6C_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,baseline7D_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,baseline8E_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,preferred9F_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,preferred10G_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,preferred11G_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,preferred12G_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,preferred13G_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,preferred14H_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,preferred15I_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,preferred16J_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,preferred17