{"id":"W2504431993","doi":"10.1145/2948068","title":"The Convergence Behavior of Naive Bayes on Large Sparse Datasets","year":2016,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Naive Bayes classifier; Computer science; Machine learning; Missing data; Bayes' theorem; Artificial intelligence; Convergence (economics); Data mining; Bayesian probability; 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":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0003985704,0.0002252012,0.0002082974,0.0001054803,0.0003257267,0.0001497741,0.00716618,0.00008459675,0.00008766792],"category_scores_gemma":[0.0002119865,0.000138702,0.00006730847,0.0003405692,0.0002152511,0.002663482,0.0003387483,0.0001821051,0.0003999763],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006625922,"about_ca_system_score_gemma":0.000146029,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005219463,"about_ca_topic_score_gemma":0.0002123773,"domain_scores_codex":[0.9979154,0.000157279,0.0004140522,0.0008604411,0.0003308211,0.000321951],"domain_scores_gemma":[0.9897711,0.001223949,0.0001862768,0.00865044,0.0000859293,0.00008229438],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002863266,0.004466416,0.001416089,0.00003639912,0.0002943533,0.00002310288,0.0005697454,0.000003496656,0.039795,0.06181991,0.1256411,0.765648],"study_design_scores_gemma":[0.002299,0.0005847816,0.02056398,0.0006308384,0.0002110732,0.00001063036,0.0002140488,0.002315516,0.6187772,0.009784552,0.343364,0.001244325],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002477889,0.000121114,0.925047,0.0008988146,0.0007544235,0.0003304932,0.07009839,0.0001645097,0.0001073568],"genre_scores_gemma":[0.9836447,0.0008412626,0.01224919,0.00012187,0.00005436516,0.0001614189,0.002341851,0.00002537274,0.0005599458],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9811668,"threshold_uncertainty_score":0.9982055,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05267241250637728,"score_gpt":0.3180910509676954,"score_spread":0.2654186384613181,"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."}}