SPB Git

spb/wp26_uqo

Public
7.8 KB · 20 lines csv
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,96935.0,0.19056946791554397,88962.27824737069,0.1261383454209658,0.28558909065239446,0.41217115040667923,0.6412362730233914,0.013618583750248209,0.27002630628771856,0.1287357507608191,0.08413885593438902,0.4888017743848971,0.8692216433692681,0.9093516273791716,0.939103522979316,0.9168102336617321,1.0014592058200693,0.24555321031791522,0.06486018198817049,0.13348682019697516,0.1501137234238583,96935.0,0.0,0.0,1.2269304174544202e-06,0.0,baseline3A_hedonic_spatial,none,model,baselines,8988.0,0.20801062571921,76181.33292825938,0.15423514740326177,0.2791547951511308,0.41696715895971975,0.5518892814973193,-0.07831028054625164,0.35947930574098796,0.09368046283934134,0.16410769915442813,0.42289719626168226,0.834334668446818,0.8862928348909658,0.9520471740097909,0.920115709835336,1.0123270107304705,0.24066525604295294,0.06499381018038751,0.1344786264212238,0.16156206116416721,8988.0,0.0,0.0,0.0,0.0,baseline4B_hierarchical,none,model,baselines,96935.0,0.18187600949116897,84924.99753834389,0.11536119525433386,0.28115274073334334,0.4018910028084978,0.6451615863727795,0.02579966245896181,0.24189405271573736,0.12750812400061898,0.06588951359158199,0.49925207613349154,0.8742765770877392,0.9132305152937535,0.9391963687006757,0.9173466756073657,0.9980834562671799,0.2308176297018561,0.0627534591803314,0.1287244897844472,0.14669742731244337,96935.0,0.0,0.0,9.187243098888168e-07,0.0,baseline5C_catboost,none,model,baselines,96935.0,0.1767604987174085,82153.26960725641,0.11131931731533751,0.27754825339154376,0.3746070321538506,0.6395025802936867,0.021168232529879198,0.22585237530303812,0.12150410068602673,0.05535668231289008,,,,,,,,,,,0.0,0.0,0.0,1.196263392896917e-06,0.0,baseline6C_gbm,none,model,baselines,96935.0,0.1792328866925307,83227.26022960231,0.11430491041298885,0.27764742605575565,0.38789861816190174,0.6298385851156596,0.02271069042338858,0.237881054314747,0.12405219992778665,0.06522927735080208,,,,,,,,,,,0.0,0.0,0.0,2.9650431629751662e-06,0.0,baseline7C_gbm_spatial,none,model,baselines,8988.0,0.1763518946028651,65411.639113262514,0.1276167585876265,0.2577771782026851,0.35790597417131614,0.5374279261245916,0.04955299823898542,0.24087672452158435,0.1451935914552737,0.05651980418335559,,,,,,,,,,,0.0,0.0,0.0,0.0,0.0,baseline8C_xgboost,none,model,baselines,96935.0,0.18017295155532076,85231.63019666045,0.11175024350649343,0.28571963176832177,0.392321604651832,0.6676807786962894,0.055103480801067965,0.2307319337700521,0.14467426626089647,0.05036364574199206,,,,,,,,,,,0.0,0.0,0.0,9.557852377807515e-07,0.0,baseline9D_avm,none,model,baselines,96935.0,0.17147330557935556,80059.33959627434,0.10540693711793758,0.270442687315783,0.3728942418667227,0.622153490812197,0.00977004534424576,0.21807396709134988,0.11040387888791459,0.059369680713880435,0.44638159591478827,0.867612317532367,0.8964048073451282,0.9362356218084283,0.9154381802238614,0.8299789424600684,0.20253600335733868,0.058061790733292575,0.11937702126416304,0.13328827572889537,96935.0,0.0,0.0,0.00022600315588784827,0.0,baseline10D_avm_spatial,none,model,baselines,8988.0,0.16067798066287955,57680.926081571255,0.105282280102996,0.24842508174893368,0.3447192094830329,0.5267760726725146,0.04456846168044138,0.20371606586559857,0.12483311081441922,0.04739652870493992,0.4247886070315977,0.8556964842011571,0.9065420560747663,0.9382510013351135,0.913440142412105,0.7413633841862405,0.22717502337747256,0.057574522493242075,0.11977535032197303,0.12090212597345742,8988.0,0.0,0.0,0.0,0.0,baseline11E_single_llm,mixed_random,median,final_E_single_llm_mixed_random_mid,80.0,0.1655996928706865,76060.34999999999,0.10682121154412122,0.24969726544870055,0.35389917173016394,0.5075374999263345,0.012833498499068896,0.2375,0.125,0.05,0.4625,0.7625,0.8875,0.9125,0.875,0.5620513641013618,0.20791660733677383,0.05498016624076081,0.11369002039596085,0.12261394559835186,80.0,0.0218719625,1.749757,19.7346875,6596.4125,preferred12E_single_llm_small,mixed_random,median,final_small_E_single_llm_mixed_random_small,300.0,0.18203351780088417,90124.74333333333,0.104388433055005,0.28714632299934145,0.40580466700827766,0.6338112828456033,0.037789439529514746,0.2733333333333333,0.16666666666666666,0.07,0.4166666666666667,0.67,0.7766666666666666,0.8133333333333334,0.7733333333333333,0.46366476380721733,0.18630864832375102,0.06376093481149013,0.12947522568908337,0.13938160747337083,300.0,0.0017041766666666665,0.511253,19.08168,8132.62,preferred13F_independent,mixed_random,median,final_F_independent_mixed_random_mid,80.0,0.15871028571985762,76763.9646233391,0.09051480582055721,0.23951744377938194,0.3141870403398491,0.4990352168129302,0.0033337688954587106,0.2125,0.0875,0.075,0.5125,0.775,0.8875,0.9,0.875,0.589534685295042,0.22049220464963773,0.05280055387313411,0.10915656731708497,0.11796097384669946,80.0,0.23228025,18.58242,79.1258125,73947.1625,preferred14F_independent_small,mixed_random,median,final_small_F_independent_mixed_random_small,300.0,0.1760399627264085,86595.7530120812,0.10009683423575366,0.28099870472078226,0.4173909383398498,0.5717959856627008,0.03527863680924263,0.25666666666666665,0.15333333333333332,0.056666666666666664,0.42,0.68,0.7866666666666666,0.84,0.7766666666666666,0.4509501851141239,0.18482294377204256,0.06095368488054293,0.12432946275353003,0.13389218151457494,300.0,0.01875933,5.627799,78.47935666666667,89503.81333333334,preferred15G_debate_r2,mixed_random,median,final_G_debate_r2_mixed_random_mid,80.0,0.1575785832187693,73765.25269372298,0.08652249890782016,0.24345526990510352,0.30688308911761475,0.4930899944960976,-0.0035708238551207527,0.225,0.1,0.0875,0.475,0.7875,0.8875,0.9,0.875,0.6022991979979221,0.21985709238344864,0.05294019168832402,0.10906447077468003,0.11895621254259167,80.0,1.521668475,121.733478,336.19342500000005,521126.9375,preferred16G_debate_r2_small,mixed_random,median,final_small_G_debate_r2_mixed_random_small,300.0,0.1802127691886514,88861.48736469213,0.10620271149954386,0.2832582650822766,0.41298057267289984,0.6023681931284645,0.027614100901086895,0.28,0.15666666666666668,0.06666666666666667,0.4266666666666667,0.7033333333333334,0.8066666666666666,0.86,0.8033333333333333,0.48901672945581914,0.19595442333572888,0.06158245661843142,0.12625527904514225,0.13537372118025423,300.0,0.12528112,37.584336,358.38188333333335,667794.92,preferred17H_debate_skeptic,mixed_random,median,final_H_debate_skeptic_r2_mixed_random_mid,80.0,0.15764573155979728,73923.03469579441,0.09222966587408982,0.24188736019509047,0.32154543451937906,0.49293028995382515,-0.0016640163135728026,0.225,0.1,0.0875,0.525,0.8,0.875,0.9125,0.875,0.6044958653160023,0.21932310745495479,0.05278575981203985,0.10903992121363464,0.11817986929824657,80.0,1.3501288875,108.010311,304.8450875,459056.7875,preferred18I_placebo,mixed_random,median,final_I_placebo_r2_mixed_random_mid,80.0,0.15739760350653925,75094.83911232911,0.09280867956572036,0.23946202509195602,0.32067538049194744,0.49748578082971523,0.0037941026894839245,0.2125,0.075,0.075,0.4875,0.8125,0.8875,0.8875,0.875,0.5901626269268021,0.21841221145371836,0.05249152435026898,0.10823454723262338,0.11696429176625758,80.0,1.3973111875000002,111.784895,268.12165,491998.425,preferred19J_cost_matched,mixed_random,median,final_J_cost_matched_mixed_random_mid,80.0,0.1633342294817131,75760.35,0.11803751803751789,0.2486924463276386,0.34728360163289307,0.4969832640370402,0.009405787879217864,0.25,0.125,0.05,0.475,0.7875,0.8625,0.9,0.875,0.5608868161548359,0.20770547076981663,0.054426142741055575,0.1124438130892246,0.12082804500872428,80.0,0.25540555,20.432444,93.8318125,91937.3875,preferred20
Files · b780d9effbc0d688f848faf14e38219f6088143b
Menu

Theme