{"id":"W4383620205","doi":"10.1007/s10601-023-09348-1","title":"SAT-based optimal classification trees for non-binary data","year":2023,"lang":"en","type":"article","venue":"Constraints","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"Vector Institute; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Microsoft Research","keywords":"Interpretability; Computer science; Overfitting; Pruning; Machine learning; Artificial intelligence; Decision tree; Categorical variable; Heuristic; Incremental decision tree; Binary decision diagram; Heuristics; Data mining; Decision tree learning; Algorithm; Artificial neural network","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":[0.0006171273,0.0001342827,0.0001416512,0.0001954104,0.000142901,0.0001437155,0.00235567,0.00008713615,0.0000183261],"category_scores_gemma":[0.0002416806,0.0001385206,0.00004076391,0.0005387778,0.0002329742,0.0006256591,0.0003453909,0.00009066887,0.0002495404],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004207915,"about_ca_system_score_gemma":0.000252215,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001750321,"about_ca_topic_score_gemma":0.000001794078,"domain_scores_codex":[0.9985288,0.00003666573,0.0002678274,0.0006590469,0.0002062305,0.0003013686],"domain_scores_gemma":[0.9973133,0.0002679709,0.0001290055,0.002104192,0.0001068855,0.00007864819],"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":[0.00002604817,0.000172896,0.001108794,0.00007816513,0.00003455864,0.00002005405,0.0001921504,0.00007826277,0.08357356,0.06579575,0.2510221,0.5978977],"study_design_scores_gemma":[0.0004740576,0.00006451203,0.02644898,0.00003478625,0.000007285498,0.000004194183,0.0000632122,0.9468794,0.006969035,0.0008680752,0.01794692,0.0002394981],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002089283,0.000006467184,0.9916302,0.003022293,0.0002404025,0.0004999892,0.0005572353,0.001157463,0.000796655],"genre_scores_gemma":[0.7230383,0.000006680978,0.2739247,0.0002666005,0.00005730419,0.0001708317,0.002357627,0.00001490176,0.0001630369],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9468012,"threshold_uncertainty_score":0.5648708,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1147390700826188,"score_gpt":0.345109813977273,"score_spread":0.2303707438946542,"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."}}