{"id":"W6947908880","doi":"10.48448/090r-bw49","title":"WSC+: Enhancing The Winograd Schema Challenge Using Tree-of-Experts","year":2024,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Brock University","funders":"","keywords":"Schema (genetic algorithms); Overconfidence effect; Benchmark (surveying); Language model","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002094734,0.0006506697,0.0006587423,0.001731731,0.0002987031,0.0002571044,0.002024829,0.0003245028,0.0007823972],"category_scores_gemma":[0.0002780809,0.0004440996,0.0002027102,0.003147101,0.003455691,0.0002857248,0.000729051,0.0005736532,0.002497427],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004155907,"about_ca_system_score_gemma":0.001137585,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007476484,"about_ca_topic_score_gemma":0.002749518,"domain_scores_codex":[0.9949287,0.0000989567,0.0006848655,0.001313656,0.001939289,0.001034537],"domain_scores_gemma":[0.9973444,0.0001043847,0.0005856502,0.001552334,0.0001911585,0.0002220628],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004570167,0.001088112,0.00007883548,0.001693116,0.0006854511,0.0002581863,0.01139089,0.000249911,0.4846379,0.03183881,0.3932187,0.07481436],"study_design_scores_gemma":[0.0008558679,0.0003413731,0.00001276878,0.006905737,0.0005541915,0.0002029578,0.006176585,0.06121624,0.03164471,0.003460136,0.8860214,0.002607974],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.002351227,0.0250966,0.003201535,0.0007908357,0.003830048,0.001484281,0.0001745314,0.001521657,0.9615493],"genre_scores_gemma":[0.5032199,0.0006503317,0.04141653,0.000461642,0.005565566,0.00009808954,0.0000583222,0.00644037,0.4420893],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.51946,"threshold_uncertainty_score":0.9998011,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05551896162194712,"score_gpt":0.343597653360824,"score_spread":0.2880786917388768,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}