{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005351755,0.0005382253,0.0008489548,0.001084798,0.0005352788,0.001435268,0.001230446,0.0007775271,0.001428497],"category_scores_gemma":[0.02101693,0.0005285743,0.0008329211,0.001197803,0.001323905,0.002248556,0.001162924,0.001839453,0.0005241028],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001006666,"about_ca_system_score_gemma":0.00110984,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00210464,"about_ca_topic_score_gemma":0.002252148,"domain_scores_codex":[0.995865,0.002009702,0.0003195032,0.0005002139,0.001188862,0.0001168368],"domain_scores_gemma":[0.9889684,0.007272339,0.0007106341,0.001890025,0.001018343,0.0001402514],"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":[0.0003707094,0.0001077905,0.006298957,0.0003528641,0.0001422714,0.0001588588,0.0005308243,0.3751697,0.01022013,0.1188998,0.00347448,0.4842737],"study_design_scores_gemma":[0.00002760337,0.00005841199,0.000703885,0.00007040967,0.00001608929,0.00009750389,0.00005669372,0.934547,0.003805692,0.05785465,0.002744045,0.00001805689],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01001565,0.0003258285,0.9881643,0.0002181014,0.00003660872,0.00004386767,0.00005759833,0.0002534484,0.0008845846],"genre_scores_gemma":[0.2525603,0.0002883646,0.7460379,0.0001558374,0.00006385607,0.0001516481,0.0001827865,0.00004984159,0.0005096128],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005351755,"threshold_uncertainty_score":0.02830309,"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."}}