{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003479412,0.00008816005,0.0001310702,0.00007328689,0.0001076177,0.00004791001,0.0002498835,0.00003395564,0.00002025209],"category_scores_gemma":[0.0001603428,0.00007272844,0.00001527837,0.0001288299,0.00002694726,0.0003596335,0.0001714655,0.0001628081,0.00002467942],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009718973,"about_ca_system_score_gemma":0.00000507456,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001552346,"about_ca_topic_score_gemma":0.00001387478,"domain_scores_codex":[0.9991657,0.0001011622,0.0001742581,0.00019844,0.0001649102,0.0001955281],"domain_scores_gemma":[0.9992272,0.0001913479,0.0001084857,0.0003615704,0.00001467634,0.00009666545],"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":[0.00001361094,0.0006486824,0.4493899,0.00003246689,0.00001515421,5.906855e-7,0.001163332,0.0004242728,0.004616416,0.01567275,0.001939281,0.5260835],"study_design_scores_gemma":[0.0002590134,0.0001724752,0.03050174,0.00001094911,0.00000407766,0.000004256282,0.00005133198,0.9282109,0.005049039,0.00002640028,0.03558918,0.0001205991],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01436341,0.0003156257,0.9813527,0.0005121807,0.0001414519,0.0000889789,0.00003264264,0.0001632528,0.003029771],"genre_scores_gemma":[0.9485307,0.000004914464,0.05102495,0.00005663537,0.00003169346,0.000001116124,0.0002311091,0.000005085853,0.0001137908],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9341673,"threshold_uncertainty_score":0.296578,"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."}}