{"id":"W2170595610","doi":"10.1109/tkde.2004.1269594","title":"CAIM discretization algorithm","year":2004,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Rough Sets and Fuzzy Logic","field":"Computer Science","cited_by":449,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Discretization; Discretization of continuous features; Algorithm; Computer science; Decision tree; Class (philosophy); Tree (set theory); ID3 algorithm; Decision tree learning; Artificial intelligence; Incremental decision tree; Mathematics; Discretization error","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":[0.00008238421,0.0001110388,0.00008980783,0.00009643594,0.0001095878,0.00009593235,0.000430515,0.00004379451,0.000003741072],"category_scores_gemma":[0.000002060777,0.0001008455,0.00001906935,0.0002514163,0.00001250175,0.0006093589,0.00001012696,0.0001177165,0.00003622699],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002568005,"about_ca_system_score_gemma":0.00002514163,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001608122,"about_ca_topic_score_gemma":0.000010767,"domain_scores_codex":[0.9993352,0.000006462973,0.0001111867,0.0003137255,0.00007646952,0.0001569031],"domain_scores_gemma":[0.9992934,0.00002634264,0.00001275563,0.0005708373,0.00001795738,0.00007865595],"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":[0.00000273193,0.000229134,0.000002130127,0.00004578897,0.00004125589,0.00001803307,0.0009046309,0.1070795,0.0004470738,0.006167661,0.0001817095,0.8848804],"study_design_scores_gemma":[0.0004442349,0.00007185344,0.00009079916,0.00004781183,0.00001326432,0.00003114247,0.00001115708,0.9899884,0.001983302,0.0003001074,0.006777542,0.0002403583],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0002059428,0.0002697047,0.9982048,0.0001340667,0.0005470757,0.00006929399,0.00004589841,0.0001879981,0.000335196],"genre_scores_gemma":[0.7816358,0.0002981079,0.2178026,0.00004897859,0.00009864548,0.00001324652,0.00002947491,0.00001676625,0.00005638506],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.88464,"threshold_uncertainty_score":0.4112361,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01997980423624899,"score_gpt":0.2493373957629373,"score_spread":0.2293575915266883,"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."}}