SPB Git

spb/wp26_uqo

Public
6.3 KB · 32 lines csv
1split,run_id,arm,committee,n_properties,n_turns,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_match2test (mid),final_E_single_llm_mixed_random_mid,E_single_llm,mixed_random,80,80,1.0,1.0,0.9539285714285716,0.9,1.0,0.0,1.0,76.7625,1.0,0.0,1.03test (mid),final_F_independent_mixed_random_mid,F_independent,mixed_random,80,960,1.0,1.0,0.9831706942082986,0.709375,0.9944289693593314,0.0055710306406685,0.990625,77.53229166666667,1.0,0.0,1.04test (mid),final_G_debate_r2_mixed_random_mid,G_debate_r2,mixed_random,80,2856,1.0,1.0,0.9880948665358776,0.7205882352941176,0.99812734082397,0.0018726591760299,0.9877450980392156,77.82002801120449,1.0,0.0010504201680672,1.05test (mid),final_H_debate_skeptic_r2_mixed_random_mid,H_debate_skeptic,mixed_random,80,2654,1.0,1.0,0.9922290041068902,0.7174076865109269,0.9984607491021036,0.0015392508978963,0.9849284099472494,78.01092690278824,1.0,0.0011303692539562,1.06test (mid),final_I_placebo_r2_mixed_random_mid,I_placebo,mixed_random,80,2832,1.0,1.0,0.9807322551662174,0.7108050847457628,0.994811320754717,0.005188679245283,0.9876412429378532,72.37146892655367,1.0,0.0007062146892655,1.07test (mid),final_J_cost_matched_mixed_random_mid,J_cost_matched,mixed_random,80,1040,1.0,1.0,0.9654510073260072,0.9173076923076924,0.9971153846153846,0.0028846153846153,0.9961538461538462,76.3923076923077,1.0,0.0009615384615384,1.08test (small),final_small_E_single_llm_mixed_random_small,E_single_llm,mixed_random,300,300,1.0,1.0,0.9915548098434004,0.9766666666666668,0.9932885906040269,0.0067114093959731,0.9966666666666668,76.98,1.0,0.0166666666666666,1.09test (small),final_small_F_independent_mixed_random_small,F_independent,mixed_random,300,3600,1.0,1.0,0.985478540491659,0.7155555555555555,0.9958770614692654,0.0041229385307346,0.9975,77.58111111111111,0.9997222222222222,0.0247222222222222,1.010test (small),final_small_G_debate_r2_mixed_random_small,G_debate_r2,mixed_random,300,10740,1.0,1.0,0.9862487624565844,0.7019553072625698,0.9964212678936604,0.0035787321063394,0.9953445065176908,79.61955307262569,0.999534450651769,0.0245810055865921,1.011holdout 2026,holdout_E_single_llm_mixed_random_mid,E_single_llm,mixed_random,60,60,1.0,1.0,0.9966666666666666,0.9833333333333332,1.0,0.0,1.0,74.28333333333333,1.0,0.0333333333333333,1.012holdout 2026,holdout_F_independent_mixed_random_mid,F_independent,mixed_random,60,720,1.0,1.0,0.9947602181368416,0.7319444444444444,0.9981447124304268,0.0018552875695732,0.9944444444444444,77.70555555555555,1.0,0.0097222222222222,1.013holdout 2026,holdout_G_debate_r2_mixed_random_mid,G_debate_r2,mixed_random,60,2147,1.0,1.0,0.99178075088156,0.7284583139264089,1.0,0.0,0.9916162086632512,77.47927340475081,1.0,0.0013972985561248,1.014prospective,prospective_E_single_llm_mixed_random_mid,E_single_llm,mixed_random,40,40,1.0,1.0,0.995,0.975,0.975,0.025,1.0,71.4,1.0,0.0,1.015prospective,prospective_F_independent_mixed_random_mid,F_independent,mixed_random,40,479,1.0,1.0,0.9809192200557102,0.7035490605427975,0.9916434540389972,0.0083565459610027,1.0,76.97286012526096,1.0,0.0020876826722338,1.016prospective,prospective_G_debate_r2_mixed_random_mid,G_debate_r2,mixed_random,40,1404,1.0,1.0,0.9826126619230068,0.7065527065527065,0.9875478927203064,0.0124521072796934,0.9992877492877492,77.4928774928775,1.0,0.0021367521367521,1.017validation,validation_E_single_llm_all_anthropic_mid,E_single_llm,all_anthropic,40,40,1.0,1.0,1.0,1.0,1.0,0.0,1.0,63.025,1.0,0.0,1.018validation,validation_E_single_llm_all_openai_mid,E_single_llm,all_openai,40,40,1.0,1.0,0.9854166666666666,0.95,0.975,0.025,1.0,83.325,1.0,0.0,1.019validation,validation_E_single_llm_mixed_random_mid,E_single_llm,mixed_random,40,40,1.0,1.0,0.95625,0.9,1.0,0.0,1.0,75.925,1.0,0.0,1.020validation,validation_F_independent_all_anthropic_mid,F_independent,all_anthropic,40,480,1.0,1.0,0.9954166666666668,0.7375,1.0,0.0,0.9916666666666668,68.1625,1.0,0.0041666666666666,1.021validation,validation_F_independent_all_openai_mid,F_independent,all_openai,40,480,1.0,1.0,0.9793896713615023,0.7104166666666667,0.9943661971830986,0.0056338028169014,0.9979166666666668,86.01666666666667,1.0,0.0,1.022validation,validation_F_independent_mixed_random_mid,F_independent,mixed_random,40,480,1.0,1.0,0.98719739292365,0.73125,0.994413407821229,0.0055865921787709,1.0,77.41666666666667,1.0,0.0020833333333333,1.023validation,validation_G_debate_r1_mixed_random_mid,G_debate_r1,mixed_random,40,960,1.0,1.0,0.9880852898262368,0.7270833333333333,0.9986072423398328,0.0013927576601671,0.9958333333333332,78.1375,1.0,0.0010416666666666,1.024validation,validation_G_debate_r2_all_anthropic_mid,G_debate_r2,all_anthropic,40,1428,1.0,1.0,0.9991907874260816,0.7478991596638656,1.0,0.0,0.9929971988795518,68.51680672268908,1.0,0.0014005602240896,1.025validation,validation_G_debate_r2_all_openai_mid,G_debate_r2,all_openai,40,1104,1.0,1.0,0.985654423975592,0.7192028985507246,0.9914841849148418,0.0085158150851581,0.9981884057971014,86.70289855072464,1.0,0.0,1.026validation,validation_G_debate_r2_mixed_random_mid,G_debate_r2,mixed_random,40,1440,1.0,1.0,0.9783983490880044,0.7125,0.9990680335507922,0.0009319664492078,1.0,77.72291666666666,1.0,0.0006944444444444,1.027validation,validation_G_debate_r4_mixed_random_mid,G_debate_r4,mixed_random,20,1020,1.0,1.0,0.9916225749559082,0.7264705882352941,0.9986772486772488,0.0013227513227513,1.0,77.65588235294118,1.0,0.0,1.028validation,validation_G_fullview_r2_mixed_random_mid,G_fullview,mixed_random,40,1416,1.0,1.0,0.983890851549275,0.882768361581921,0.9969088098918084,0.0030911901081916,0.9929378531073446,77.5042372881356,1.0,0.0028248587570621,1.029validation,validation_H_debate_skeptic_r2_mixed_random_mid,H_debate_skeptic,mixed_random,40,1360,1.0,1.0,0.9936307721877852,0.7169117647058824,0.9989909182643796,0.0010090817356205,0.9977941176470588,77.56911764705882,1.0,0.000735294117647,1.030validation,validation_I_placebo_r2_mixed_random_mid,I_placebo,mixed_random,40,1404,1.0,1.0,0.9965865384615386,0.7343304843304843,0.9990384615384617,0.0,0.9971509971509972,72.52777777777777,1.0,0.0028490028490028,1.031validation,validation_J_cost_matched_mixed_random_mid,J_cost_matched,mixed_random,40,520,1.0,1.0,0.9780896794515472,0.9346153846153846,0.9785992217898832,0.0214007782101167,1.0,76.41923076923077,1.0,0.0019230769230769,1.032
Files · main
Menu

Theme