{"id":"W1919031954","doi":"10.1109/icdm.2001.989495","title":"Comparisons of classification methods for screening potential compounds","year":2002,"lang":"en","type":"article","venue":"","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Pruning; Computer science; Machine learning; Data mining; Sampling (signal processing); Training set; Artificial intelligence; Set (abstract data type); Data set; Class (philosophy)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007760005,0.001618482,0.001729021,0.008418054,0.0005425018,0.001126987,0.001623462,0.001281096,0.002751793],"category_scores_gemma":[0.02184238,0.0002497397,0.001226154,0.003810229,0.0003867812,0.002070393,0.0009599038,0.0009305541,0.00139973],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001036662,"about_ca_system_score_gemma":0.001015362,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002507906,"about_ca_topic_score_gemma":0.002795549,"domain_scores_codex":[0.9950516,0.001378729,0.0004548187,0.0004796221,0.002410967,0.000224409],"domain_scores_gemma":[0.9674147,0.02437085,0.001151164,0.001886747,0.004603239,0.000573251],"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":[0.001558578,0.0004590496,0.01779938,0.0007463645,0.0006721937,0.00007575698,0.0001051394,0.0908229,0.00171603,0.001800036,0.006848161,0.8773964],"study_design_scores_gemma":[0.0003022579,0.001183114,0.01762356,0.000166748,0.0004390041,0.0003029999,0.0002258728,0.960304,0.007689915,0.005628987,0.006051844,0.00008168824],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.5044122,0.03574809,0.4079891,0.004023326,0.001405419,0.001132776,0.005240576,0.009335686,0.03071285],"genre_scores_gemma":[0.7905248,0.007583018,0.1861308,0.0005082353,0.000463027,0.0005368941,0.006840159,0.0004545858,0.006958429],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.008418054,"threshold_uncertainty_score":0.04103929,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1264652803102443,"score_gpt":0.380750297055729,"score_spread":0.2542850167454848,"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."}}