SPB Git

spb/wp26_uqo

Public
7.7 KB · 59 lines csv
1round,value,ci_lo,ci_hi,arm,committee,metric,n,run_id20,0.18013984964265023,0.12703886542864445,0.2444743120346185,G_debate_r1,mixed_random,ae_median,40,validation_G_debate_r1_mixed_random_mid30,0.17710168720776923,0.12729362781185716,0.23870402258567094,G_debate_r1,mixed_random,ae_mean,40,validation_G_debate_r1_mixed_random_mid40,0.06860823466162573,0.04834455645485157,0.09520321178478872,G_debate_r1,mixed_random,iqr,40,validation_G_debate_r1_mixed_random_mid51,0.17795994858564676,0.12616612518499098,0.24061000367559798,G_debate_r1,mixed_random,ae_median,40,validation_G_debate_r1_mixed_random_mid61,0.17458239393120428,0.12524012956856645,0.23581746802643053,G_debate_r1,mixed_random,ae_mean,40,validation_G_debate_r1_mixed_random_mid71,0.04256456927353649,0.030601439703394396,0.05832857612708406,G_debate_r1,mixed_random,iqr,40,validation_G_debate_r1_mixed_random_mid80,0.18067192682616512,0.12903587747023693,0.2445902023126168,G_debate_r2,all_anthropic,ae_median,40,validation_G_debate_r2_all_anthropic_mid90,0.18184217011863563,0.13088226453357518,0.2455428815413961,G_debate_r2,all_anthropic,ae_mean,40,validation_G_debate_r2_all_anthropic_mid100,0.056172129277550595,0.0374641829526177,0.07967182149408289,G_debate_r2,all_anthropic,iqr,40,validation_G_debate_r2_all_anthropic_mid111,0.17873202673484917,0.12770771658810282,0.2416066710749308,G_debate_r2,all_anthropic,ae_median,40,validation_G_debate_r2_all_anthropic_mid121,0.17579541443784827,0.12463625259949275,0.2379896656005587,G_debate_r2,all_anthropic,ae_mean,40,validation_G_debate_r2_all_anthropic_mid131,0.02582393147832014,0.018569964702163905,0.03480802870251866,G_debate_r2,all_anthropic,iqr,40,validation_G_debate_r2_all_anthropic_mid142,0.17801480954173238,0.1273602789854808,0.24081605277228266,G_debate_r2,all_anthropic,ae_median,40,validation_G_debate_r2_all_anthropic_mid152,0.17676409053399827,0.12557437687365627,0.2390507084076553,G_debate_r2,all_anthropic,ae_mean,40,validation_G_debate_r2_all_anthropic_mid162,0.017664708927771368,0.013053748463155384,0.022903112530999324,G_debate_r2,all_anthropic,iqr,40,validation_G_debate_r2_all_anthropic_mid170,0.1772919655759168,0.12364221347405994,0.24158064912468544,G_debate_r2,all_openai,ae_median,40,validation_G_debate_r2_all_openai_mid180,0.17286627998156803,0.12119505520954733,0.23474931938153998,G_debate_r2,all_openai,ae_mean,40,validation_G_debate_r2_all_openai_mid190,0.041744862372300726,0.0334679831293259,0.05207052195720665,G_debate_r2,all_openai,iqr,40,validation_G_debate_r2_all_openai_mid201,0.17781789573303777,0.12411770513546037,0.24200425479311535,G_debate_r2,all_openai,ae_median,40,validation_G_debate_r2_all_openai_mid211,0.17384994137658602,0.12283017289330443,0.23555604655487683,G_debate_r2,all_openai,ae_mean,40,validation_G_debate_r2_all_openai_mid221,0.038666454671042016,0.03123227671244657,0.04782349272578449,G_debate_r2,all_openai,iqr,40,validation_G_debate_r2_all_openai_mid232,0.177978154338401,0.12435626097000133,0.2420081635395876,G_debate_r2,all_openai,ae_median,40,validation_G_debate_r2_all_openai_mid242,0.17435764068395865,0.12337973758268789,0.2360706418176341,G_debate_r2,all_openai,ae_mean,40,validation_G_debate_r2_all_openai_mid252,0.03833072776209083,0.031027090084238318,0.04751166593729795,G_debate_r2,all_openai,iqr,40,validation_G_debate_r2_all_openai_mid260,0.17987945613240383,0.12786326758346916,0.2429974904034653,G_debate_r2,mixed_random,ae_median,40,validation_G_debate_r2_mixed_random_mid270,0.17800207265197984,0.12934213630958627,0.2388537803186402,G_debate_r2,mixed_random,ae_mean,40,validation_G_debate_r2_mixed_random_mid280,0.0702289743058849,0.049388194589421994,0.09834570959640124,G_debate_r2,mixed_random,iqr,40,validation_G_debate_r2_mixed_random_mid291,0.17829652494048348,0.1272373821801898,0.23985783253456164,G_debate_r2,mixed_random,ae_median,40,validation_G_debate_r2_mixed_random_mid301,0.17353439890432204,0.12541747354604355,0.23413083636898757,G_debate_r2,mixed_random,ae_mean,40,validation_G_debate_r2_mixed_random_mid311,0.04366420395871447,0.03129516675139347,0.06086443485053188,G_debate_r2,mixed_random,iqr,40,validation_G_debate_r2_mixed_random_mid322,0.1756280898133557,0.12580779121056382,0.238085005739998,G_debate_r2,mixed_random,ae_median,40,validation_G_debate_r2_mixed_random_mid332,0.17334113396819112,0.12558365500235125,0.23334629510640814,G_debate_r2,mixed_random,ae_mean,40,validation_G_debate_r2_mixed_random_mid342,0.03439595065793903,0.026593289820915543,0.04368519375944554,G_debate_r2,mixed_random,iqr,40,validation_G_debate_r2_mixed_random_mid350,0.1622320322619208,0.08237326054339525,0.26742412169976326,G_debate_r4,mixed_random,ae_median,20,validation_G_debate_r4_mixed_random_mid360,0.16801315099233483,0.0872358304256904,0.27294850266234577,G_debate_r4,mixed_random,ae_mean,20,validation_G_debate_r4_mixed_random_mid370,0.05730395706919964,0.040013472419636126,0.07636088018410696,G_debate_r4,mixed_random,iqr,20,validation_G_debate_r4_mixed_random_mid381,0.16316622235601627,0.08308111813749855,0.26604981819917256,G_debate_r4,mixed_random,ae_median,20,validation_G_debate_r4_mixed_random_mid391,0.16129495555762557,0.08237114343428689,0.26418969338791004,G_debate_r4,mixed_random,ae_mean,20,validation_G_debate_r4_mixed_random_mid401,0.03224524847162051,0.023722123313206625,0.04242484183657401,G_debate_r4,mixed_random,iqr,20,validation_G_debate_r4_mixed_random_mid412,0.16331831156785306,0.0827759484272835,0.2664458955239808,G_debate_r4,mixed_random,ae_median,20,validation_G_debate_r4_mixed_random_mid422,0.16103189287391279,0.08165187255735645,0.2640234544626639,G_debate_r4,mixed_random,ae_mean,20,validation_G_debate_r4_mixed_random_mid432,0.02589659282383492,0.018745857164738505,0.03461580765356233,G_debate_r4,mixed_random,iqr,20,validation_G_debate_r4_mixed_random_mid443,0.16303074234450765,0.08258772355374445,0.2659764793892237,G_debate_r4,mixed_random,ae_median,20,validation_G_debate_r4_mixed_random_mid453,0.16118243036684704,0.08188581260894716,0.2644579881836077,G_debate_r4,mixed_random,ae_mean,20,validation_G_debate_r4_mixed_random_mid463,0.025053049482697886,0.017908865397342814,0.03350318882677551,G_debate_r4,mixed_random,iqr,20,validation_G_debate_r4_mixed_random_mid474,0.162923796912827,0.08197109514128353,0.26624700993125855,G_debate_r4,mixed_random,ae_median,20,validation_G_debate_r4_mixed_random_mid484,0.16140325884651102,0.08227623621684292,0.26464029684203616,G_debate_r4,mixed_random,ae_mean,20,validation_G_debate_r4_mixed_random_mid494,0.02417353399940918,0.016979550211372308,0.03255762268676844,G_debate_r4,mixed_random,iqr,20,validation_G_debate_r4_mixed_random_mid500,0.17287733842374076,0.12223740274669166,0.23642466903371673,G_fullview,mixed_random,ae_median,40,validation_G_fullview_r2_mixed_random_mid510,0.17745982813810207,0.12616474893250212,0.23942557248609503,G_fullview,mixed_random,ae_mean,40,validation_G_fullview_r2_mixed_random_mid520,0.07236702703357575,0.045991753878122967,0.10766665573860656,G_fullview,mixed_random,iqr,40,validation_G_fullview_r2_mixed_random_mid531,0.17392997694912432,0.12381587503119,0.23649910867128077,G_fullview,mixed_random,ae_median,40,validation_G_fullview_r2_mixed_random_mid541,0.17439849394296486,0.1253807684478345,0.23422727667942153,G_fullview,mixed_random,ae_mean,40,validation_G_fullview_r2_mixed_random_mid551,0.03615809500683853,0.024324858277674288,0.051325902918780135,G_fullview,mixed_random,iqr,40,validation_G_fullview_r2_mixed_random_mid562,0.17455906988101186,0.123973296184389,0.2367954387610734,G_fullview,mixed_random,ae_median,40,validation_G_fullview_r2_mixed_random_mid572,0.17428713534197313,0.12523792714775173,0.23432466246431388,G_fullview,mixed_random,ae_mean,40,validation_G_fullview_r2_mixed_random_mid582,0.027588101545402654,0.020172088273847394,0.036781309351777675,G_fullview,mixed_random,iqr,40,validation_G_fullview_r2_mixed_random_mid59
Files · b780d9effbc0d688f848faf14e38219f6088143b
Menu

Theme