{"id":"W2023067667","doi":"10.1017/s0269888910000329","title":"Discretization as the enabling technique for the Naïve Bayes and semi-Naïve Bayes-based classification","year":2010,"lang":"en","type":"article","venue":"The Knowledge Engineering Review","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Killam Trusts","keywords":"Discretization; Computer science; Scalability; Naive Bayes classifier; Machine learning; Artificial intelligence; Maximization; Data mining; Classifier (UML); Bayes' theorem; Estimator; Algorithm; Mathematics; Bayesian probability; Mathematical optimization; Statistics; Support vector machine","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001802614,0.000189109,0.0001834441,0.00003732653,0.0003238789,0.0001761491,0.0009747427,0.00007132721,0.00000614738],"category_scores_gemma":[0.0006036004,0.00009299239,0.00008411976,0.0004084122,0.00006662907,0.0001392299,0.0001106615,0.0003864849,0.00001618409],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002031389,"about_ca_system_score_gemma":0.00008652141,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005471597,"about_ca_topic_score_gemma":0.000006345785,"domain_scores_codex":[0.9990214,0.00007134906,0.0002680992,0.0002840921,0.0001331103,0.0002219489],"domain_scores_gemma":[0.9979151,0.0009469779,0.00009882923,0.0008257373,0.0001611055,0.00005226824],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00000697934,0.00006877394,0.00002949178,0.002966907,0.00006867875,7.913472e-7,0.001320748,0.002015705,0.04423323,0.5096719,0.001728199,0.4378886],"study_design_scores_gemma":[0.00008583062,0.00003230041,0.0001442018,0.0013435,0.0000662449,0.00001912497,0.000009407604,0.940798,0.003588984,0.001704252,0.05199295,0.0002151351],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0001239401,0.03579262,0.9567856,0.005617721,0.0003072603,0.001024584,0.000001966536,0.0001625298,0.00018379],"genre_scores_gemma":[0.9666213,0.01214122,0.01850336,0.0007070067,0.0003761292,0.001395862,0.000008794299,0.00004692449,0.0001994047],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9664974,"threshold_uncertainty_score":0.379212,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02308276804678729,"score_gpt":0.2851675183899761,"score_spread":0.2620847503431888,"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."}}