{"id":"W1989494794","doi":"10.1142/s0218001408006703","title":"USING INSTANCE CLONING TO IMPROVE NAIVE BAYES FOR RANKING","year":2008,"lang":"en","type":"article","venue":"International Journal of Pattern Recognition and Artificial Intelligence","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Naive Bayes classifier; Machine learning; Artificial intelligence; Ranking (information retrieval); Computer science; Bayes' theorem; Bayes error rate; Data mining; Bayesian probability; Support vector machine; Bayes classifier","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":[0.0003657807,0.0001188236,0.000161141,0.0002328968,0.0001397529,0.0001833684,0.0004905315,0.00004734544,0.00001507993],"category_scores_gemma":[0.0001811909,0.00011435,0.00008890565,0.0001209463,0.00004893037,0.0005667069,0.00008306843,0.0001524378,0.00001407761],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004975679,"about_ca_system_score_gemma":0.00008209476,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002542154,"about_ca_topic_score_gemma":0.000008016369,"domain_scores_codex":[0.9986843,0.00003762226,0.0005548343,0.0002254839,0.0003265459,0.0001711549],"domain_scores_gemma":[0.9983422,0.0001471921,0.0003015338,0.00008278197,0.001010487,0.0001157911],"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":[0.00007366636,0.0000630688,0.0002193287,0.000007825242,0.00004491968,0.00005585034,0.001792212,0.0007635421,0.0164532,0.001848291,0.00002290534,0.9786552],"study_design_scores_gemma":[0.0003647149,0.0007142157,0.0003019883,0.0009712389,0.00003218855,0.001337388,0.0006211709,0.5295759,0.2938621,0.1710887,0.000430918,0.0006995348],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.234085,0.00005108485,0.7639673,0.0006288402,0.001127959,0.00007847238,0.00001464761,0.0000145918,0.0000320866],"genre_scores_gemma":[0.9168123,0.00007404028,0.08183515,0.0008379295,0.0004194477,0.000004642076,0.000001939375,0.000007527288,0.000007047573],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9779556,"threshold_uncertainty_score":0.4663059,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2080090107044039,"score_gpt":0.356634389687509,"score_spread":0.1486253789831051,"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."}}