Added results

ag-sc · Jul 5, 2024 · 6ee1d3d · 6ee1d3d
1 parent 180b463
commit 6ee1d3d
Show file tree

Hide file tree

Showing 62 changed files with 1,393,667 additions and 0 deletions.
diff --git a/results/GPT/finetuned-gpt-3.5-turbo/QALD9_finetuned-gpt-3.5-turbo_0-shot_prompt1_test.csv b/results/GPT/finetuned-gpt-3.5-turbo/QALD9_finetuned-gpt-3.5-turbo_0-shot_prompt1_test.csv
diff --git a/...GPT/finetuned-gpt-3.5-turbo/QALD9_finetuned-gpt-3.5-turbo_0-shot_prompt1_test_lexicon.csv b/...GPT/finetuned-gpt-3.5-turbo/QALD9_finetuned-gpt-3.5-turbo_0-shot_prompt1_test_lexicon.csv
diff --git a/results/GPT/finetuned-gpt-3.5-turbo/QALD9_finetuned-gpt-3.5-turbo_0-shot_prompt2_test.csv b/results/GPT/finetuned-gpt-3.5-turbo/QALD9_finetuned-gpt-3.5-turbo_0-shot_prompt2_test.csv
diff --git a/...GPT/finetuned-gpt-3.5-turbo/QALD9_finetuned-gpt-3.5-turbo_0-shot_prompt2_test_lexicon.csv b/...GPT/finetuned-gpt-3.5-turbo/QALD9_finetuned-gpt-3.5-turbo_0-shot_prompt2_test_lexicon.csv
diff --git a/results/GPT/finetuned-gpt-3.5-turbo/QALD9_finetuned-gpt-3.5-turbo_0-shot_prompt3_test.csv b/results/GPT/finetuned-gpt-3.5-turbo/QALD9_finetuned-gpt-3.5-turbo_0-shot_prompt3_test.csv
diff --git a/...GPT/finetuned-gpt-3.5-turbo/QALD9_finetuned-gpt-3.5-turbo_0-shot_prompt3_test_lexicon.csv b/...GPT/finetuned-gpt-3.5-turbo/QALD9_finetuned-gpt-3.5-turbo_0-shot_prompt3_test_lexicon.csv
diff --git a/results/GPT/finetuned-gpt-3.5-turbo/QALD9_finetuned-gpt-3.5-turbo_0-shot_prompt4_test.csv b/results/GPT/finetuned-gpt-3.5-turbo/QALD9_finetuned-gpt-3.5-turbo_0-shot_prompt4_test.csv
diff --git a/...GPT/finetuned-gpt-3.5-turbo/QALD9_finetuned-gpt-3.5-turbo_0-shot_prompt4_test_lexicon.csv b/...GPT/finetuned-gpt-3.5-turbo/QALD9_finetuned-gpt-3.5-turbo_0-shot_prompt4_test_lexicon.csv
diff --git a/results/GPT/finetuned-gpt-3.5-turbo/QALD9_finetuned-gpt-3.5-turbo_0-shot_prompt5_test.csv b/results/GPT/finetuned-gpt-3.5-turbo/QALD9_finetuned-gpt-3.5-turbo_0-shot_prompt5_test.csv
diff --git a/...GPT/finetuned-gpt-3.5-turbo/QALD9_finetuned-gpt-3.5-turbo_0-shot_prompt5_test_lexicon.csv b/...GPT/finetuned-gpt-3.5-turbo/QALD9_finetuned-gpt-3.5-turbo_0-shot_prompt5_test_lexicon.csv
diff --git a/results/GPT/finetuned-gpt-3.5-turbo/datasets/test_prompt1.jsonl b/results/GPT/finetuned-gpt-3.5-turbo/datasets/test_prompt1.jsonl
diff --git a/results/GPT/finetuned-gpt-3.5-turbo/datasets/test_prompt1_lexicon.jsonl b/results/GPT/finetuned-gpt-3.5-turbo/datasets/test_prompt1_lexicon.jsonl
diff --git a/results/GPT/finetuned-gpt-3.5-turbo/datasets/test_prompt2.jsonl b/results/GPT/finetuned-gpt-3.5-turbo/datasets/test_prompt2.jsonl
diff --git a/results/GPT/finetuned-gpt-3.5-turbo/datasets/test_prompt2_lexicon.jsonl b/results/GPT/finetuned-gpt-3.5-turbo/datasets/test_prompt2_lexicon.jsonl
diff --git a/results/GPT/finetuned-gpt-3.5-turbo/datasets/test_prompt3.jsonl b/results/GPT/finetuned-gpt-3.5-turbo/datasets/test_prompt3.jsonl
diff --git a/results/GPT/finetuned-gpt-3.5-turbo/datasets/test_prompt3_lexicon.jsonl b/results/GPT/finetuned-gpt-3.5-turbo/datasets/test_prompt3_lexicon.jsonl
diff --git a/results/GPT/finetuned-gpt-3.5-turbo/datasets/test_prompt4.jsonl b/results/GPT/finetuned-gpt-3.5-turbo/datasets/test_prompt4.jsonl
diff --git a/results/GPT/finetuned-gpt-3.5-turbo/datasets/test_prompt4_lexicon.jsonl b/results/GPT/finetuned-gpt-3.5-turbo/datasets/test_prompt4_lexicon.jsonl
diff --git a/results/GPT/finetuned-gpt-3.5-turbo/datasets/test_prompt5.jsonl b/results/GPT/finetuned-gpt-3.5-turbo/datasets/test_prompt5.jsonl
diff --git a/results/GPT/finetuned-gpt-3.5-turbo/datasets/test_prompt5_lexicon.jsonl b/results/GPT/finetuned-gpt-3.5-turbo/datasets/test_prompt5_lexicon.jsonl
diff --git a/results/GPT/finetuned-gpt-3.5-turbo/datasets/train_prompt1.jsonl b/results/GPT/finetuned-gpt-3.5-turbo/datasets/train_prompt1.jsonl
diff --git a/results/GPT/finetuned-gpt-3.5-turbo/datasets/train_prompt1_lexicon.jsonl b/results/GPT/finetuned-gpt-3.5-turbo/datasets/train_prompt1_lexicon.jsonl
diff --git a/results/GPT/finetuned-gpt-3.5-turbo/datasets/train_prompt2.jsonl b/results/GPT/finetuned-gpt-3.5-turbo/datasets/train_prompt2.jsonl
diff --git a/results/GPT/finetuned-gpt-3.5-turbo/datasets/train_prompt2_lexicon.jsonl b/results/GPT/finetuned-gpt-3.5-turbo/datasets/train_prompt2_lexicon.jsonl
diff --git a/results/GPT/finetuned-gpt-3.5-turbo/datasets/train_prompt3.jsonl b/results/GPT/finetuned-gpt-3.5-turbo/datasets/train_prompt3.jsonl
diff --git a/results/GPT/finetuned-gpt-3.5-turbo/datasets/train_prompt3_lexicon.jsonl b/results/GPT/finetuned-gpt-3.5-turbo/datasets/train_prompt3_lexicon.jsonl
diff --git a/results/GPT/finetuned-gpt-3.5-turbo/datasets/train_prompt4.jsonl b/results/GPT/finetuned-gpt-3.5-turbo/datasets/train_prompt4.jsonl
diff --git a/results/GPT/finetuned-gpt-3.5-turbo/datasets/train_prompt4_lexicon.jsonl b/results/GPT/finetuned-gpt-3.5-turbo/datasets/train_prompt4_lexicon.jsonl
diff --git a/results/GPT/finetuned-gpt-3.5-turbo/datasets/train_prompt5.jsonl b/results/GPT/finetuned-gpt-3.5-turbo/datasets/train_prompt5.jsonl
diff --git a/results/GPT/finetuned-gpt-3.5-turbo/datasets/train_prompt5_lexicon.jsonl b/results/GPT/finetuned-gpt-3.5-turbo/datasets/train_prompt5_lexicon.jsonl
diff --git a/results/GPT/finetuned-gpt-3.5-turbo/datasets/valid_prompt1.jsonl b/results/GPT/finetuned-gpt-3.5-turbo/datasets/valid_prompt1.jsonl
diff --git a/results/GPT/finetuned-gpt-3.5-turbo/datasets/valid_prompt1_lexicon.jsonl b/results/GPT/finetuned-gpt-3.5-turbo/datasets/valid_prompt1_lexicon.jsonl
diff --git a/results/GPT/finetuned-gpt-3.5-turbo/datasets/valid_prompt2.jsonl b/results/GPT/finetuned-gpt-3.5-turbo/datasets/valid_prompt2.jsonl
diff --git a/results/GPT/finetuned-gpt-3.5-turbo/datasets/valid_prompt2_lexicon.jsonl b/results/GPT/finetuned-gpt-3.5-turbo/datasets/valid_prompt2_lexicon.jsonl
diff --git a/results/GPT/finetuned-gpt-3.5-turbo/datasets/valid_prompt3.jsonl b/results/GPT/finetuned-gpt-3.5-turbo/datasets/valid_prompt3.jsonl
diff --git a/results/GPT/finetuned-gpt-3.5-turbo/datasets/valid_prompt3_lexicon.jsonl b/results/GPT/finetuned-gpt-3.5-turbo/datasets/valid_prompt3_lexicon.jsonl
diff --git a/results/GPT/finetuned-gpt-3.5-turbo/datasets/valid_prompt4.jsonl b/results/GPT/finetuned-gpt-3.5-turbo/datasets/valid_prompt4.jsonl
diff --git a/results/GPT/finetuned-gpt-3.5-turbo/datasets/valid_prompt4_lexicon.jsonl b/results/GPT/finetuned-gpt-3.5-turbo/datasets/valid_prompt4_lexicon.jsonl
diff --git a/results/GPT/finetuned-gpt-3.5-turbo/datasets/valid_prompt5.jsonl b/results/GPT/finetuned-gpt-3.5-turbo/datasets/valid_prompt5.jsonl
diff --git a/results/GPT/finetuned-gpt-3.5-turbo/datasets/valid_prompt5_lexicon.jsonl b/results/GPT/finetuned-gpt-3.5-turbo/datasets/valid_prompt5_lexicon.jsonl
diff --git a/results/GPT/gpt-3.5-turbo/QALD9_gpt-3.5-turbo_0-shot_test.csv b/results/GPT/gpt-3.5-turbo/QALD9_gpt-3.5-turbo_0-shot_test.csv
diff --git a/results/GPT/gpt-3.5-turbo/QALD9_gpt-3.5-turbo_0-shot_test_lexicon.csv b/results/GPT/gpt-3.5-turbo/QALD9_gpt-3.5-turbo_0-shot_test_lexicon.csv
diff --git a/results/GPT/gpt-3.5-turbo/QALD9_gpt-3.5-turbo_0-shot_train.csv b/results/GPT/gpt-3.5-turbo/QALD9_gpt-3.5-turbo_0-shot_train.csv
diff --git a/results/GPT/gpt-3.5-turbo/QALD9_gpt-3.5-turbo_0-shot_train_lexicon.csv b/results/GPT/gpt-3.5-turbo/QALD9_gpt-3.5-turbo_0-shot_train_lexicon.csv
diff --git a/results/GPT/gpt-4/QALD9_gpt-4_0-shot_test.csv b/results/GPT/gpt-4/QALD9_gpt-4_0-shot_test.csv
diff --git a/results/GPT/gpt-4/QALD9_gpt-4_0-shot_test_lexicon.csv b/results/GPT/gpt-4/QALD9_gpt-4_0-shot_test_lexicon.csv
diff --git a/results/GPT/gpt-4/QALD9_gpt-4_0-shot_train.csv b/results/GPT/gpt-4/QALD9_gpt-4_0-shot_train.csv
diff --git a/results/GPT/gpt-4/QALD9_gpt-4_0-shot_train_lexicon.csv b/results/GPT/gpt-4/QALD9_gpt-4_0-shot_train_lexicon.csv
diff --git a/results/NeoDUDES/29376s-all-train/all-generated-queries-train.csv.zst b/results/NeoDUDES/29376s-all-train/all-generated-queries-train.csv.zst
diff --git a/results/NeoDUDES/29376s-all-train/chosen-queries-per-strategy-train.csv b/results/NeoDUDES/29376s-all-train/chosen-queries-per-strategy-train.csv
diff --git a/results/NeoDUDES/29376s-all-train/strategy-total-eval-train.csv b/results/NeoDUDES/29376s-all-train/strategy-total-eval-train.csv
@@ -0,0 +1,90 @@
+"Strategy","Micro F1","Micro TP","Micro FP","Micro FN","Micro EM","Micro Precision","Micro Recall","Macro F1","Macro Precision","Macro Recall"
+"BestScoreEval","0,685346733668342",8524,1311,6516,145,"0,86670055922725","0,566755319148936","0,382261006228723","0,386424967640807","0,398045708951882"
+"LLMMostWinsEval_0_0.0","0,165987448039775",4073,29963,10967,122,"0,119667410976613","0,270811170212766","0,325366508401639","0,328172222839548","0,36202121564206"
+"LLMMostWinsEval_0_0.1","0,218986891437016",4001,17500,11039,122,"0,186084368168922","0,266023936170213","0,323823166310113","0,326144560330641","0,354991512881033"
+"LLMMostWinsEval_0_0.25","0,247499374843711",3959,12993,11081,125,"0,233541764983483","0,263231382978723","0,333966836519941","0,337384623820406","0,359861197380347"
+"LLMMostWinsEval_0_0.5","0,268510610340976",4087,11315,10953,124,"0,265355148681989","0,271742021276596","0,331210828438958","0,335429923605021","0,359512798133642"
+"LLMMostWinsEval_0_0.75","0,265229836672841",3938,10717,11102,122,"0,268713749573524","0,261835106382979","0,325026508017797","0,329885022481599","0,347510770029919"
+"LLMMostWinsEval_0_0.9","0,303387334315169",3914,6848,11126,119,"0,363687047017283","0,260239361702128","0,318770109177905","0,324267778568707","0,339822779008595"
+"LLMAccumEval_0_sigmoid","0,257885327544375",4039,12245,11001,125,"0,248034880864652","0,268550531914894","0,332820374070796","0,335712542382242","0,36008566427148"
+"LLMAccumEval_0_logits","0,257827710574192",4039,12252,11001,126,"0,247928303971518","0,268550531914894","0,334805936656314","0,337920691021767","0,355147392666542"
+"LLMMostWinsEval_1_0.0","0,269374448142362",3966,10440,11074,114,"0,275301957517701","0,263696808510638","0,304687093449226","0,307679940118861","0,327462667194623"
+"LLMMostWinsEval_1_0.1","0,291322388598232",4037,8638,11003,119,"0,318500986193294","0,268417553191489","0,317447407571822","0,319299124802778","0,339876933312592"
+"LLMMostWinsEval_1_0.25","0,28925679065434",4036,8830,11004,121,"0,31369501010415","0,268351063829787","0,322120870260364","0,324016960248425","0,344687330652808"
+"LLMMostWinsEval_1_0.5","0,339468126373863",3938,4223,11102,120,"0,482538904546012","0,261835106382979","0,317261951311722","0,320322319072941","0,328682122682754"
+"LLMMostWinsEval_1_0.75","0,342266766744669",3876,3733,11164,120,"0,509396766986463","0,257712765957447","0,315530045630369","0,317853183270472","0,327348428891639"
+"LLMMostWinsEval_1_0.9","0,357677202169441",3825,2523,11215,116,"0,602551984877127","0,254321808510638","0,305013968486206","0,307615088868952","0,312533614076824"
+"LLMAccumEval_1_sigmoid","0,299503193754436",4009,7722,11031,121,"0,341744096837439","0,26655585106383","0,321200921938363","0,324640441192482","0,337613558826996"
+"LLMAccumEval_1_logits","0,266984347595883",4034,11145,11006,125,"0,265761907899071","0,268218085106383","0,329528734409134","0,330293169615012","0,351546041215222"
+"LLMMostWinsEval_2_0.0","0,306108229465046",3954,6840,11086,112,"0,366314619232907","0,262898936170213","0,299874868826942","0,303042749677626","0,320329608209712"
+"LLMMostWinsEval_2_0.1","0,353083217815141",3948,3375,11092,116,"0,539123310118804","0,2625","0,309335327670813","0,313528313327153","0,317913947099763"
+"LLMMostWinsEval_2_0.25","0,363931989222336",3917,2569,11123,116,"0,603916127042862","0,260438829787234","0,311203509785908","0,314869705833205","0,322852218704701"
+"LLMMostWinsEval_2_0.5","0,371384045972533",3813,1681,11227,116,"0,694029850746269","0,253523936170213","0,306634125136808","0,308790394198337","0,31495702514221"
+"LLMMostWinsEval_2_0.75","0,648366949118829",8149,1948,6891,121,"0,807071407348717","0,541821808510638","0,317027675952437","0,318099400820005","0,330737335366965"
+"LLMMostWinsEval_2_0.9","0,639331397630072",8147,2299,6893,120,"0,779915757227647","0,541688829787234","0,314064712989474","0,31535591659504","0,325799063762027"
+"LLMAccumEval_2_sigmoid","0,369242518256885",3868,2043,11172,119,"0,654373202503807","0,25718085106383","0,314228936392752","0,317063666862507","0,327554190208511"
+"LLMAccumEval_2_logits","0,367775831873905",3885,2202,11155,123,"0,638245441103992","0,258311170212766","0,322158531063252","0,322503269420265","0,336401926834026"
+"LLMMostWinsEval_3_0.0","0,228370221327968",4086,16658,10954,122,"0,196972618588508","0,271675531914894","0,323401584977872","0,32653221444582","0,349376247441536"
+"LLMMostWinsEval_3_0.1","0,291823358762222",4074,8807,10966,120,"0,316279791941619","0,270877659574468","0,316476029664387","0,319118783486247","0,339705465548532"
+"LLMMostWinsEval_3_0.25","0,304744046502906",4063,7562,10977,119,"0,349505376344086","0,270146276595745","0,317715712238655","0,322228311243486","0,339376247441536"
+"LLMMostWinsEval_3_0.5","0,277269624573379",4062,10198,10978,117,"0,284852734922861","0,270079787234043","0,314760501664397","0,319763057730015","0,338553202174046"
+"LLMMostWinsEval_3_0.75","0,291625759063307",4010,8451,11030,115,"0,321804028569136","0,266622340425532","0,308914770659272","0,31321929699141","0,325904900054845"
+"LLMMostWinsEval_3_0.9","0,305992122672173",4001,7110,11039,113,"0,360093600936009","0,266023936170213","0,302433075547684","0,306009593595317","0,321021498134406"
+"LLMAccumEval_3_sigmoid","0,300025973062224",4043,7868,10997,124,"0,339434136512467","0,268816489361702","0,329111252622202","0,33344918362634","0,343617123993416"
+"LLMAccumEval_3_logits","0,297844210217048",4055,8134,10985,126,"0,332677003855936","0,269614361702128","0,335914737203465","0,340594137437961","0,345861792904752"
+"LLMMostWinsEval_4_0.0","0,206872193349816",4100,20498,10940,124,"0,166680217903895","0,272606382978723","0,323097006850843","0,325380345941872","0,355807847391655"
+"LLMMostWinsEval_4_0.1","0,223053197587139",4086,17511,10954,122,"0,18919294346437","0,271675531914894","0,319730003483839","0,321638655533515","0,350869575786716"
+"LLMMostWinsEval_4_0.25","0,231832925510727",4074,16032,10966,117,"0,202626081766637","0,270877659574468","0,313702132607726","0,318521359400096","0,342940906376565"
+"LLMMostWinsEval_4_0.5","0,497806358555202",8283,9955,6757,118,"0,45416164053076","0,550731382978723","0,317247552039026","0,322133082947989","0,341022337976516"
+"LLMMostWinsEval_4_0.75","0,274906266738083",4106,10726,10934,114,"0,276833872707659","0,273005319148936","0,308844213428417","0,312646434871274","0,330843171659783"
+"LLMMostWinsEval_4_0.9","0,276927182360986",4151,10788,10889,111,"0,277863310797242","0,275997340425532","0,300229909737861","0,304487625230983","0,321085336901948"
+"LLMAccumEval_4_sigmoid","0,275332408566499",4069,10448,10971,122,"0,280292071364607","0,270545212765957","0,322091659866183","0,32537539476799","0,342618546980132"
+"LLMAccumEval_4_logits","0,304804520116795",4019,7312,11021,123,"0,354690671608861","0,267220744680851","0,32591015521297","0,328912275553136","0,343769415362639"
+"LLMMostWinsEval_5_0.0","0,13302034428795",4165,43417,10875,109,"0,0875331007523854","0,276928191489362","0,293210684019692","0,296326312043283","0,336797203180132"
+"LLMMostWinsEval_5_0.1","0,13496952353236",4174,42637,10866,116,"0,0891670761145885","0,277526595744681","0,312772785838803","0,316042199208401","0,351387551103813"
+"LLMMostWinsEval_5_0.25","0,148221309629014",4277,38394,10763,126,"0,100232007686719","0,284375","0,337838416994284","0,340930545662373","0,383486316535912"
+"LLMMostWinsEval_5_0.5","0,155265994666868",4105,33732,10935,123,"0,108491688030235","0,272938829787234","0,33099311487794","0,335856959567217","0,371824183593176"
+"LLMMostWinsEval_5_0.75","0,400145260864302",8264,18001,6776,123,"0,314639253759756","0,549468085106383","0,328973773456225","0,334425920027708","0,35947850458083"
+"LLMMostWinsEval_5_0.9","0,408298508938948",8256,17145,6784,122,"0,325026573756939","0,548936170212766","0,326279783169642","0,331839022082941","0,352997023099349"
+"LLMAccumEval_5_sigmoid","0,146232724030317",4264,39014,10776,125,"0,0985258098803087","0,283510638297872","0,331301612135124","0,334722192116731","0,375809548859144"
+"LLMAccumEval_5_logits","0,145165813643694",4141,37871,10899,126,"0,0985670760735028","0,275332446808511","0,335143745778739","0,338284341351048","0,375258527027519"
+"LLMMostWinsEval_6_0.0","0,446437124155181",8389,14153,6651,118,"0,372149764883329","0,557779255319149","0,313419393258965","0,316878055699837","0,339484116253109"
+"LLMMostWinsEval_6_0.1","0,428923667886527",8263,15226,6777,124,"0,351781685044063","0,549401595744681","0,32930522352104","0,33260662548245","0,354298931067923"
+"LLMMostWinsEval_6_0.25","0,470849122807018",8387,12198,6653,126,"0,407432596550887","0,557646276595745","0,334346770734864","0,336724006638819","0,360554075100845"
+"LLMMostWinsEval_6_0.5","0,536437978258728",8167,7242,6873,121,"0,530014926341748","0,543018617021277","0,323020961982397","0,328042851505633","0,337557294150518"
+"LLMMostWinsEval_6_0.75","0,55372293490803",8158,6268,6882,122,"0,565506723970609","0,542420212765957","0,323178818427884","0,328842769806269","0,331850846962589"
+"LLMMostWinsEval_6_0.9","0,321969383533306",3891,5239,11149,123,"0,426177437020811","0,258710106382979","0,325179669854022","0,33101261642056","0,331805122225506"
+"LLMAccumEval_6_sigmoid","0,277846864451945",3910,9195,11130,127,"0,298359404807325","0,259973404255319","0,332773845681641","0,336480875714266","0,346890128668537"
+"LLMAccumEval_6_logits","0,243147711769813",3921,13291,11119,125,"0,227806181733674","0,260704787234043","0,329481664611682","0,332777172010562","0,344420992866068"
+"LLMMostWinsEval_7_0.0","0,195127748068925",4105,22930,10935,120,"0,151840207138894","0,272938829787234","0,316551166567279","0,318544832157396","0,345432488868148"
+"LLMMostWinsEval_7_0.1","0,191071304589322",4128,24041,10912,121,"0,146544073272037","0,274468085106383","0,322530081865761","0,328110487302143","0,352810758213688"
+"LLMMostWinsEval_7_0.25","0,195761808926246",4134,23061,10906,120,"0,152013237727523","0,274867021276596","0,322826067238915","0,328865313350088","0,35781761692425"
+"LLMMostWinsEval_7_0.5","0,281172656604037",4033,9614,11007,119,"0,29552282552942","0,268151595744681","0,319313324952228","0,323683852191212","0,341849447225739"
+"LLMMostWinsEval_7_0.75","0,574704607425016",8220,5346,6820,122,"0,605926581158779","0,546542553191489","0,326415673860188","0,330929376615098","0,341849447225739"
+"LLMMostWinsEval_7_0.9","0,636946138014058",8201,2510,6839,117,"0,765661469517319","0,545279255319149","0,314002966428323","0,318503731272786","0,326988907673842"
+"LLMAccumEval_7_sigmoid","0,214099760491513",4112,19260,10928,125,"0,175937018654801","0,273404255319149","0,334247035903934","0,340387682890189","0,360012404304223"
+"LLMAccumEval_7_logits","0,189169343735659",4122,24418,10918,126,"0,144428871758935","0,27406914893617","0,336359371431275","0,34266007809572","0,359806642987351"
+"LLMMostWinsEval_8_0.0","0,287996498522814",3948,8429,11092,120,"0,318978750908944","0,2625","0,314361363369775","0,315237578458957","0,334512026660806"
+"LLMMostWinsEval_8_0.1","0,369517183019134",3930,2301,11110,119,"0,630717380837747","0,261303191489362","0,311336179096951","0,312424684445747","0,322120622911377"
+"LLMMostWinsEval_8_0.25","0,377608288962441",3936,1871,11104,116,"0,677802651971758","0,261702127659574","0,307138648232754","0,309955548643278","0,317182351306439"
+"LLMMostWinsEval_8_0.5","0,372866730584851",3889,1931,11151,113,"0,668213058419244","0,258577127659574","0,302080457940161","0,304577920437353","0,311352447328387"
+"LLMMostWinsEval_8_0.75","0,379676267788156",3882,1527,11158,114,"0,71769273433167","0,25811170212766","0,304250804480713","0,308790394198337","0,311846274488881"
+"LLMMostWinsEval_8_0.9","0,377763553104535",3836,1433,11204,114,"0,728031884608085","0,255053191489362","0,304250804480713","0,308790394198337","0,311846274488881"
+"LLMAccumEval_8_sigmoid","0,380050751512785",3894,1558,11146,118,"0,714233308877476","0,258909574468085","0,313657036109166","0,317432369506979","0,321434751855136"
+"LLMAccumEval_8_logits","0,373907703934628",3958,2173,11082,123,"0,645571684880117","0,263164893617021","0,32383367500202","0,32489758292569","0,337689895888058"
+"LLMMostWinsEval_9_0.0","0,247169181263471",4071,13830,10969,116,"0,22741746271158","0,270678191489362","0,308575570436826","0,310968551484603","0,339239073230288"
+"LLMMostWinsEval_9_0.1","0,242467043314501",4120,14824,10920,121,"0,217483108108108","0,273936170212766","0,323030504951753","0,325549633626759","0,351228099293388"
+"LLMMostWinsEval_9_0.25","0,261035313001605",3903,10961,11137,123,"0,26258073196986","0,259507978723404","0,325243783110219","0,329070924302849","0,339258254369996"
+"LLMMostWinsEval_9_0.5","0,311341909595185",3957,6422,11083,122,"0,381250602177474","0,263098404255319","0,324991206818755","0,328801088246155","0,342605305124454"
+"LLMMostWinsEval_9_0.75","0,363027399171978",3902,2555,11138,117,"0,604305404986836","0,259441489361702","0,311234010674093","0,316625449734542","0,321974303752712"
+"LLMMostWinsEval_9_0.9","0,370141135649646",3947,2340,11093,117,"0,627803403849213","0,262433510638298","0,313450554008261","0,318915518714359","0,325815181667664"
+"LLMAccumEval_9_sigmoid","0,278222972023056",3958,9454,11082,124,"0,295108857739338","0,263164893617021","0,32849093064749","0,331975741046793","0,347715044493453"
+"LLMAccumEval_9_logits","0,231895921648882",3966,15199,11074,125,"0,206939733889903","0,263696808510638","0,330454191170628","0,333116931867554","0,3469948798844"
+"LLMMostWinsEval_None_0.0","0,207525075098009",4076,20166,10964,123,"0,168137942413992","0,271010638297872","0,32633730257165","0,328954524296163","0,35715901337245"
+"LLMMostWinsEval_None_0.1","0,229073114565343",3979,15721,11061,126,"0,201979695431472","0,264561170212766","0,332514354819784","0,335552182553647","0,359628149174919"
+"LLMMostWinsEval_None_0.25","0,268995633187773",4004,10726,11036,125,"0,271826205023761","0,266223404255319","0,330866493237126","0,33366913642388","0,352877782989525"
+"LLMMostWinsEval_None_0.5","0,304445544931622",3996,7215,11044,124,"0,356435643564356","0,265691489361702","0,328928681922684","0,332342453186096","0,34617183461691"
+"LLMMostWinsEval_None_0.75","0,309600221878838",3907,6292,11133,125,"0,383076772232572","0,259773936170213","0,330346170965607","0,334096285353902","0,342776772888515"
+"LLMMostWinsEval_None_0.9","0,305769908731247",3903,6586,11137,122,"0,372104109066641","0,259507978723404","0,322938763558199","0,326688877946494","0,335369365481107"
+"LLMAccumEval_None_sigmoid","0,283222237980428",3994,9170,11046,123,"0,3034032209055","0,265558510638298","0,325533737707351","0,329225237391926","0,341233563011972"
+"LLMAccumEval_None_logits","0,311622170055306",3916,6177,11124,126,"0,387991677400178","0,260372340425532","0,331585637945814","0,33400550830234","0,343721404388702"
diff --git a/results/NeoDUDES/3h-all-test/all-generated-queries-test.csv.zst b/results/NeoDUDES/3h-all-test/all-generated-queries-test.csv.zst