{"id":"W4318604573","doi":"10.1109/ssci51031.2022.10022190","title":"Training and Testing Cascades for Imbalanced Data Classification","year":2022,"lang":"en","type":"article","venue":"2022 IEEE Symposium Series on Computational Intelligence (SSCI)","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Regina","funders":"","keywords":"Cascade; Computer science; Artificial intelligence; Training set; Machine learning; Data modeling; Data mining; Data set; Class (philosophy); Set (abstract data type); Synthetic data; Test data; Recall rate; Pattern recognition (psychology); Database; Engineering","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001083425,0.0002663679,0.0002679127,0.0002683035,0.001094,0.0003446409,0.002351647,0.0000591903,0.00002031711],"category_scores_gemma":[0.0002696181,0.0003028416,0.00004534386,0.000889832,0.0001726173,0.001328925,0.0007768256,0.0003368678,0.00001016521],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001873903,"about_ca_system_score_gemma":0.0002709618,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001425193,"about_ca_topic_score_gemma":0.000005068233,"domain_scores_codex":[0.9969854,0.0001698017,0.0005848201,0.001184876,0.000678495,0.0003965559],"domain_scores_gemma":[0.9970438,0.001098069,0.0003774407,0.001111242,0.000257111,0.0001123715],"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":[0.0001506889,0.0003499728,0.0004314706,0.0001169622,0.00008928684,0.00001593916,0.003775541,0.1345998,0.02939346,0.6143514,0.01004006,0.2066855],"study_design_scores_gemma":[0.0001288476,0.0005515976,0.0006734583,0.00002411158,0.00001059116,0.0001170945,0.0009239634,0.9445354,0.004415955,0.03502974,0.01316638,0.0004228532],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001563103,0.00006149049,0.9906075,0.00441109,0.0007591667,0.0007221152,0.0006497191,0.000545019,0.0006807742],"genre_scores_gemma":[0.6922379,0.00003653483,0.3046511,0.000962518,0.0001475589,0.0006070461,0.001035623,0.00003652121,0.000285277],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8099356,"threshold_uncertainty_score":0.9999424,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1728539108943217,"score_gpt":0.3439910303025261,"score_spread":0.1711371194082045,"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."}}