{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000490444,0.00009491274,0.000188189,0.0001350168,0.0001010801,0.00007174497,0.0008812246,0.00006185081,0.00003089737],"category_scores_gemma":[0.00006454629,0.0000914205,0.00007365838,0.000313263,0.00006575223,0.0004281502,0.00011373,0.00006996041,0.000008645485],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001786176,"about_ca_system_score_gemma":0.000009586172,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000773308,"about_ca_topic_score_gemma":6.689856e-7,"domain_scores_codex":[0.9989337,0.00009890434,0.0003547622,0.0002968795,0.0001426901,0.000173055],"domain_scores_gemma":[0.9986339,0.0001934802,0.0002124011,0.0007268288,0.0001846756,0.00004867299],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000004783272,0.0001462717,0.0001714024,0.00002019714,0.0000230888,1.204317e-7,0.00009805588,0.00001831743,0.1169905,0.4817803,0.07581368,0.3249333],"study_design_scores_gemma":[0.0002048828,0.00004944863,0.002043247,0.000006867869,0.000007955177,0.000003725697,0.00002472921,0.8941121,0.05945905,0.001866746,0.04210497,0.0001162912],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00002332595,0.00006249973,0.9927421,0.00162494,0.0001044255,0.0002613301,0.000008572213,0.0003790312,0.004793801],"genre_scores_gemma":[0.2439222,0.000008950788,0.7555695,0.0001224049,0.00001867655,0.00004422734,0.00001607453,0.000005825768,0.0002921484],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8940938,"threshold_uncertainty_score":0.372802,"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."}}