{"id":"W2126443908","doi":"","title":"Bayesian Comparison of Machine Learning Algorithms on Single and Multiple Datasets","year":2012,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"","keywords":"Computer science; Sign test; Machine learning; Wilcoxon signed-rank test; Algorithm; Bayesian probability; Key (lock); Artificial intelligence; Set (abstract data type); Test data; Bayesian network; Mathematics; Statistics; Mann–Whitney U test","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":[0.08660308,0.002010091,0.003413013,0.01088281,0.001357502,0.006314355,0.004331167,0.004240327,0.003438439],"category_scores_gemma":[0.3129503,0.0009931996,0.002558863,0.005513464,0.003943511,0.01051768,0.007002489,0.004871433,0.001394333],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002078549,"about_ca_system_score_gemma":0.002941608,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007124484,"about_ca_topic_score_gemma":0.0009669744,"domain_scores_codex":[0.8751965,0.08076112,0.005781987,0.007909025,0.02849451,0.001856867],"domain_scores_gemma":[0.6558962,0.2848149,0.01642081,0.02411318,0.01620083,0.00255407],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001851872,0.0008122972,0.03282371,0.001263457,0.00293893,0.0002635697,0.0006586752,0.2042288,0.005729091,0.1989387,0.006713559,0.5437773],"study_design_scores_gemma":[0.0001622064,0.001231066,0.008764045,0.0002418131,0.0002462355,0.0004492249,0.0002025864,0.7076403,0.006018496,0.2701827,0.004666543,0.0001949202],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01586797,0.000837429,0.9798151,0.0003493423,0.0001605858,0.0001627663,0.0001917135,0.0004131362,0.002202006],"genre_scores_gemma":[0.3268909,0.0007732531,0.6671077,0.0004217516,0.0005514813,0.001108883,0.001411652,0.0004864435,0.001247828],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.08660308,"threshold_uncertainty_score":0.4580063,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03976322648787854,"score_gpt":0.3023984921882241,"score_spread":0.2626352657003456,"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."}}