{"id":"W2042053856","doi":"10.1016/j.patcog.2008.03.027","title":"A dynamic overproduce-and-choose strategy for the selection of classifier ensembles","year":2008,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":152,"is_retracted":false,"has_abstract":false,"ca_institutions":"Defence Research and Development Canada; Quest University Canada; École de Technologie Supérieure","funders":"","keywords":"Classifier (UML); Computer science; Artificial intelligence; Selection (genetic algorithm); Machine learning; Population; Pattern recognition (psychology)","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":[0.0002228234,0.00007737285,0.00008176827,0.00005938491,0.0001801101,0.00003732959,0.000145056,0.0000414325,0.00001222697],"category_scores_gemma":[0.00007133473,0.00005861499,0.00003485989,0.0001285072,0.00003410119,0.000232983,0.00002828668,0.00009359542,0.000013751],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001524168,"about_ca_system_score_gemma":0.00002870615,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008139396,"about_ca_topic_score_gemma":0.00004186776,"domain_scores_codex":[0.9993036,0.00006166418,0.0001615707,0.0002475722,0.0001142926,0.0001112493],"domain_scores_gemma":[0.9993647,0.000186758,0.0001287771,0.0001960622,0.00009953366,0.00002420883],"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":[0.00001213499,0.00003642717,0.003887502,0.00003102371,0.0000132663,3.419025e-7,0.0001843792,0.00004061252,0.002412867,0.00009990422,0.00023612,0.9930454],"study_design_scores_gemma":[0.000465452,0.0001750563,0.3561128,0.00003409261,0.00002458812,0.00008239246,0.00004811609,0.6368147,0.003070634,0.001870111,0.001137396,0.0001647179],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2758564,0.00008699008,0.7227053,0.000779262,0.0001117676,0.0002185494,0.00001861832,0.00006050198,0.0001626015],"genre_scores_gemma":[0.9966234,0.000185517,0.002843224,0.00009966787,0.00004045053,0.00005450356,0.00006282827,0.000006586544,0.00008385467],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9928807,"threshold_uncertainty_score":0.239025,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05774142430184379,"score_gpt":0.2844336532926083,"score_spread":0.2266922289907645,"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."}}