{"id":"W2131225292","doi":"10.1109/ride.1997.583715","title":"Generalization and decision tree induction: efficient classification in data mining","year":2002,"lang":"en","type":"article","venue":"","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":118,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Scalability; Decision tree; Data mining; Abstraction; Generalization; Relevance (law); Machine learning; Artificial intelligence; Database; Mathematics","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":[0.0002062974,0.00005713488,0.00005608875,0.0001039413,0.00008246272,0.0001422995,0.0005089474,0.00003246203,0.00001746894],"category_scores_gemma":[0.00003193632,0.00005192681,0.000004817027,0.0004909181,0.00001807927,0.0004300975,0.0002790472,0.00003911784,0.0000218207],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001707767,"about_ca_system_score_gemma":0.000006356934,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002096365,"about_ca_topic_score_gemma":0.00004440214,"domain_scores_codex":[0.9991951,0.0000140791,0.0001669093,0.0003975318,0.0001309325,0.0000954487],"domain_scores_gemma":[0.9990836,0.00004475989,0.00004206031,0.0007682816,0.00002331762,0.00003797616],"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":[2.672208e-7,0.00004641241,0.0002665451,9.92869e-7,8.461159e-7,4.519611e-7,0.000203926,0.0001678621,0.000170128,0.00936118,0.004710427,0.9850709],"study_design_scores_gemma":[0.0001425187,0.000006978693,0.0111857,0.000008274734,0.000001244963,0.000007580329,0.00004875894,0.9835901,0.00002811622,0.0001634211,0.004751231,0.00006610891],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08001295,0.00009872755,0.9170102,0.00108182,0.000091642,0.00007956991,0.00000420187,0.00006328395,0.001557638],"genre_scores_gemma":[0.2965929,0.00008148015,0.7028828,0.0001010703,0.00005173019,0.00001421522,0.00005465528,0.000004525821,0.0002167025],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9850048,"threshold_uncertainty_score":0.2117514,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1137594219951989,"score_gpt":0.2990887928556513,"score_spread":0.1853293708604524,"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."}}