{"id":"W6966430195","doi":"10.48448/3eyy-3h68","title":"Learning to Identify Top Elo Ratings with A Dueling Bandits Approach","year":2022,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Regret; Scheduling (production processes); Maximization; Variety (cybernetics); Sample (material); Convergence (economics)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004274499,0.001552443,0.00258412,0.001668551,0.0009661691,0.00220821,0.002260986,0.00216173,0.006423071],"category_scores_gemma":[0.01493678,0.001055664,0.0007519098,0.001311174,0.001528485,0.00239435,0.001867362,0.002016899,0.00218409],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00123013,"about_ca_system_score_gemma":0.001688428,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006672828,"about_ca_topic_score_gemma":0.006834948,"domain_scores_codex":[0.9977577,0.00115406,0.0001159123,0.0004288504,0.0002599811,0.0002834437],"domain_scores_gemma":[0.9931048,0.005103759,0.0006134083,0.0003510913,0.0005057557,0.0003212229],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004265114,0.0002550289,0.003782743,0.000149215,0.0001421715,0.0001445719,0.0001657104,0.8390207,0.001154153,0.02689817,0.004502455,0.1233585],"study_design_scores_gemma":[0.00001821553,0.00002597048,0.0001922474,0.00001015126,0.000008338748,0.00001360673,0.00001396629,0.9922821,0.000148458,0.007042338,0.0002360936,0.000008524357],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05170812,0.0005307065,0.9399655,0.0006695871,0.00009446094,0.0001812788,0.0001637251,0.0009296734,0.005756924],"genre_scores_gemma":[0.8012033,0.0002818244,0.1867699,0.0006014241,0.0002166226,0.0004255789,0.0005226534,0.0001912946,0.009787399],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006672828,"threshold_uncertainty_score":0.02260602,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02029795967491655,"score_gpt":0.3085787126627098,"score_spread":0.2882807529877933,"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."}}