SPB Git

spb/wp26_uqo

Public
7.7 KB · 32 lines csv
1run_id,arm,committee,n_turns,n_properties,cited_share_valid,share_turns_all_ids_valid,adj_share_within_40,share_turns_adj_ok,point_in_hull,hull_deviation_justified,quantile_sane,summary_words,summary_within_limit,validation_retries,packet_hash_match,iqr_log_round0,iqr_log_final,convergence,anchoring_index,share_toward_median2final_E_single_llm_mixed_random_mid,E_single_llm,mixed_random,80,80,1.0,1.0,0.9539285714285715,0.9,1.0,0.0,1.0,76.7625,1.0,0.0,1.0,,,,,3final_F_independent_mixed_random_mid,F_independent,mixed_random,960,80,1.0,1.0,0.9831706942082986,0.709375,0.9944289693593314,0.005571030640668524,0.990625,77.53229166666667,1.0,0.0,1.0,0.086128751357532,0.086128751357532,1.0,,4final_G_debate_r2_mixed_random_mid,G_debate_r2,mixed_random,2856,80,1.0,1.0,0.9880948665358777,0.7205882352941176,0.99812734082397,0.0018726591760299626,0.9877450980392157,77.82002801120449,1.0,0.0010504201680672268,1.0,0.08807682247963038,0.03814487616315234,0.5493003401709176,0.7132526065986224,0.45104166666666675final_H_debate_skeptic_r2_mixed_random_mid,H_debate_skeptic,mixed_random,2654,80,1.0,1.0,0.9922290041068902,0.7174076865109269,0.9984607491021037,0.0015392508978963571,0.9849284099472494,78.01092690278824,1.0,0.0011303692539562924,1.0,0.09158946316324416,,,,6final_I_placebo_r2_mixed_random_mid,I_placebo,mixed_random,2832,80,1.0,1.0,0.9807322551662174,0.7108050847457628,0.994811320754717,0.005188679245283019,0.9876412429378532,72.37146892655367,1.0,0.0007062146892655367,1.0,0.08687408017408682,0.040879757274712845,0.6120472770308627,0.751030261717586,0.42916666666666677final_J_cost_matched_mixed_random_mid,J_cost_matched,mixed_random,1040,80,1.0,1.0,0.9654510073260073,0.9173076923076923,0.9971153846153846,0.0028846153846153848,0.9961538461538462,76.3923076923077,1.0,0.0009615384615384616,1.0,0.014094513861668712,,,,8final_small_E_single_llm_mixed_random_small,E_single_llm,mixed_random,300,300,1.0,1.0,0.9915548098434005,0.9766666666666667,0.9932885906040269,0.006711409395973154,0.9966666666666667,76.98,1.0,0.016666666666666666,1.0,,,,,9final_small_F_independent_mixed_random_small,F_independent,mixed_random,3600,300,1.0,1.0,0.985478540491659,0.7155555555555555,0.9958770614692654,0.004122938530734633,0.9975,77.58111111111111,0.9997222222222222,0.024722222222222222,1.0,0.08799243559538626,0.08799243559538626,1.0,,10final_small_G_debate_r2_mixed_random_small,G_debate_r2,mixed_random,10740,300,1.0,1.0,0.9862487624565845,0.7019553072625698,0.9964212678936605,0.0035787321063394683,0.9953445065176909,79.61955307262569,0.999534450651769,0.024581005586592177,1.0,0.08727294745268495,0.03371045320262234,0.4752227169747357,0.676739290074005,0.520833333333333411holdout_E_single_llm_mixed_random_mid,E_single_llm,mixed_random,60,60,1.0,1.0,0.9966666666666666,0.9833333333333333,1.0,0.0,1.0,74.28333333333333,1.0,0.03333333333333333,1.0,,,,,12holdout_F_independent_mixed_random_mid,F_independent,mixed_random,720,60,1.0,1.0,0.9947602181368415,0.7319444444444444,0.9981447124304267,0.0018552875695732839,0.9944444444444445,77.70555555555555,1.0,0.009722222222222222,1.0,0.07512327094157438,0.07512327094157438,1.0,,13holdout_G_debate_r2_mixed_random_mid,G_debate_r2,mixed_random,2147,60,1.0,1.0,0.9917807508815599,0.7284583139264089,1.0,0.0,0.9916162086632511,77.47927340475081,1.0,0.0013972985561248254,1.0,0.07333397874417326,0.037391912560166524,0.5282580415137724,0.6996159147090963,0.46452020202020214prospective_E_single_llm_mixed_random_mid,E_single_llm,mixed_random,40,40,1.0,1.0,0.9949999999999999,0.975,0.975,0.025,1.0,71.4,1.0,0.0,1.0,,,,,15prospective_F_independent_mixed_random_mid,F_independent,mixed_random,479,40,1.0,1.0,0.9809192200557102,0.7035490605427975,0.9916434540389972,0.008356545961002786,1.0,76.97286012526096,1.0,0.0020876826722338203,1.0,0.0768384477574859,0.0768384477574859,1.0,,16prospective_G_debate_r2_mixed_random_mid,G_debate_r2,mixed_random,1404,40,1.0,1.0,0.9826126619230067,0.7065527065527065,0.9875478927203065,0.012452107279693486,0.9992877492877493,77.4928774928775,1.0,0.002136752136752137,1.0,0.08184706625974277,0.040836084217946045,0.6162437865096527,0.7570145340506012,0.452083333333333317validation_E_single_llm_all_anthropic_mid,E_single_llm,all_anthropic,40,40,1.0,1.0,1.0,1.0,1.0,0.0,1.0,63.025,1.0,0.0,1.0,,,,,18validation_E_single_llm_all_openai_mid,E_single_llm,all_openai,40,40,1.0,1.0,0.9854166666666666,0.95,0.975,0.025,1.0,83.325,1.0,0.0,1.0,,,,,19validation_E_single_llm_mixed_random_mid,E_single_llm,mixed_random,40,40,1.0,1.0,0.95625,0.9,1.0,0.0,1.0,75.925,1.0,0.0,1.0,,,,,20validation_F_independent_all_anthropic_mid,F_independent,all_anthropic,480,40,1.0,1.0,0.9954166666666667,0.7375,1.0,0.0,0.9916666666666667,68.1625,1.0,0.004166666666666667,1.0,0.057767385897232515,0.057767385897232515,1.0,,21validation_F_independent_all_openai_mid,F_independent,all_openai,480,40,1.0,1.0,0.9793896713615023,0.7104166666666667,0.9943661971830986,0.005633802816901409,0.9979166666666667,86.01666666666667,1.0,0.0,1.0,0.041102559006384445,0.041102559006384445,1.0,,22validation_F_independent_mixed_random_mid,F_independent,mixed_random,480,40,1.0,1.0,0.9871973929236499,0.73125,0.994413407821229,0.00558659217877095,1.0,77.41666666666667,1.0,0.0020833333333333333,1.0,0.06373610964840518,0.06373610964840518,1.0,,23validation_G_debate_r1_mixed_random_mid,G_debate_r1,mixed_random,960,40,1.0,1.0,0.9880852898262369,0.7270833333333333,0.9986072423398329,0.001392757660167131,0.9958333333333333,78.1375,1.0,0.0010416666666666667,1.0,0.06860823466162573,0.04256456927353649,0.6641061711084988,0.6716946015329783,0.427083333333333324validation_G_debate_r2_all_anthropic_mid,G_debate_r2,all_anthropic,1428,40,1.0,1.0,0.9991907874260817,0.7478991596638656,1.0,0.0,0.9929971988795518,68.51680672268908,1.0,0.0014005602240896359,1.0,0.056172129277550595,0.017664708927771368,0.45698419044273847,0.9696643951960786,0.52525validation_G_debate_r2_all_openai_mid,G_debate_r2,all_openai,1104,40,1.0,1.0,0.9856544239755919,0.7192028985507246,0.9914841849148418,0.00851581508515815,0.9981884057971014,86.70289855072464,1.0,0.0,1.0,0.041744862372300726,0.03833072776209083,0.943547792353898,0.383787626632117,0.07526validation_G_debate_r2_mixed_random_mid,G_debate_r2,mixed_random,1440,40,1.0,1.0,0.9783983490880044,0.7125,0.9990680335507922,0.0009319664492078285,1.0,77.72291666666666,1.0,0.0006944444444444445,1.0,0.0702289743058849,0.03439595065793903,0.5599911648661037,0.6730913417565307,0.441666666666666727validation_G_debate_r4_mixed_random_mid,G_debate_r4,mixed_random,1020,20,1.0,1.0,0.9916225749559082,0.7264705882352941,0.9986772486772487,0.0013227513227513227,1.0,77.65588235294118,1.0,0.0,1.0,0.05730395706919964,0.02417353399940918,0.4689033504367745,0.780791339232074,0.429166666666666728validation_G_fullview_r2_mixed_random_mid,G_fullview,mixed_random,1416,40,1.0,1.0,0.983890851549275,0.882768361581921,0.9969088098918083,0.0030911901081916537,0.9929378531073446,77.5042372881356,1.0,0.002824858757062147,1.0,0.07236702703357575,0.027588101545402654,0.5204716014455759,0.6514492597835508,0.516666666666666729validation_H_debate_skeptic_r2_mixed_random_mid,H_debate_skeptic,mixed_random,1360,40,1.0,1.0,0.9936307721877853,0.7169117647058824,0.9989909182643795,0.0010090817356205853,0.9977941176470588,77.56911764705882,1.0,0.0007352941176470588,1.0,0.07420871831762557,,,,30validation_I_placebo_r2_mixed_random_mid,I_placebo,mixed_random,1404,40,1.0,1.0,0.9965865384615386,0.7343304843304843,0.9990384615384615,0.0,0.9971509971509972,72.52777777777777,1.0,0.002849002849002849,1.0,0.07323331797888052,0.035011885204309666,0.5772124371720999,0.7756733358961002,0.435416666666666731validation_J_cost_matched_mixed_random_mid,J_cost_matched,mixed_random,520,40,1.0,1.0,0.9780896794515471,0.9346153846153846,0.9785992217898832,0.021400778210116732,1.0,76.41923076923077,1.0,0.0019230769230769232,1.0,0.014917220108813644,,,,32
Files · main
Menu

Theme