SPB Git

spb/wp26_uqo

Public
3.2 KB · 23 lines csv
1split,run_id,arm,committee,n_properties,iqr_log_round0,iqr_log_final,convergence,anchoring_index,share_toward_median2validation,validation_F_independent_all_anthropic_mid,F_independent,all_anthropic,40,0.0577673858972325,0.0577673858972325,1.0,,3validation,validation_F_independent_all_openai_mid,F_independent,all_openai,40,0.0411025590063844,0.0411025590063844,1.0,,4validation,validation_F_independent_mixed_random_mid,F_independent,mixed_random,40,0.0637361096484051,0.0637361096484051,1.0,,5validation,validation_G_debate_r1_mixed_random_mid,G_debate_r1,mixed_random,40,0.0686082346616257,0.0425645692735364,0.6641061711084988,0.6716946015329783,0.42708333333333336validation,validation_G_debate_r2_all_anthropic_mid,G_debate_r2,all_anthropic,40,0.0561721292775505,0.0176647089277713,0.4569841904427384,0.9696643951960786,0.5257validation,validation_G_debate_r2_all_openai_mid,G_debate_r2,all_openai,40,0.0417448623723007,0.0383307277620908,0.943547792353898,0.383787626632117,0.0758validation,validation_G_debate_r2_mixed_random_mid,G_debate_r2,mixed_random,40,0.0702289743058849,0.034395950657939,0.5599911648661037,0.6730913417565307,0.44166666666666679validation,validation_G_debate_r4_mixed_random_mid,G_debate_r4,mixed_random,20,0.0573039570691996,0.0241735339994091,0.4689033504367745,0.780791339232074,0.429166666666666710validation,validation_G_fullview_r2_mixed_random_mid,G_fullview,mixed_random,40,0.0723670270335757,0.0275881015454026,0.5204716014455759,0.6514492597835508,0.516666666666666711validation,validation_H_debate_skeptic_r2_mixed_random_mid,H_debate_skeptic,mixed_random,40,0.0742087183176255,,,,12validation,validation_I_placebo_r2_mixed_random_mid,I_placebo,mixed_random,40,0.0732333179788805,0.0350118852043096,0.5772124371720999,0.7756733358961002,0.435416666666666713test (mid),final_F_independent_mixed_random_mid,F_independent,mixed_random,80,0.086128751357532,0.086128751357532,1.0,,14test (mid),final_G_debate_r2_mixed_random_mid,G_debate_r2,mixed_random,80,0.0880768224796303,0.0381448761631523,0.5493003401709176,0.7132526065986224,0.451041666666666715test (mid),final_H_debate_skeptic_r2_mixed_random_mid,H_debate_skeptic,mixed_random,80,0.0915894631632441,,,,16test (mid),final_I_placebo_r2_mixed_random_mid,I_placebo,mixed_random,80,0.0868740801740868,0.0408797572747128,0.6120472770308627,0.751030261717586,0.429166666666666717test (small),final_small_F_independent_mixed_random_small,F_independent,mixed_random,300,0.0879924355953862,0.0879924355953862,1.0,,18test (small),final_small_G_debate_r2_mixed_random_small,G_debate_r2,mixed_random,300,0.0872729474526849,0.0337104532026223,0.4752227169747357,0.676739290074005,0.520833333333333419holdout 2026,holdout_F_independent_mixed_random_mid,F_independent,mixed_random,60,0.0751232709415743,0.0751232709415743,1.0,,20holdout 2026,holdout_G_debate_r2_mixed_random_mid,G_debate_r2,mixed_random,60,0.0733339787441732,0.0373919125601665,0.5282580415137724,0.6996159147090963,0.46452020202020221prospective,prospective_F_independent_mixed_random_mid,F_independent,mixed_random,40,0.0768384477574859,0.0768384477574859,1.0,,22prospective,prospective_G_debate_r2_mixed_random_mid,G_debate_r2,mixed_random,40,0.0818470662597427,0.040836084217946,0.6162437865096527,0.7570145340506012,0.452083333333333323
Files · main
Menu

Theme