{"id":"W2068704925","doi":"10.1109/icmla.2013.187","title":"Selective Sampling Designs to Improve the Performance of Classification Methods","year":2013,"lang":"en","type":"article","venue":"","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Naive Bayes classifier; Sampling (signal processing); Logistic regression; Computer science; Statistics; Bayes' theorem; Data mining; Missing data; Binary classification; Artificial intelligence; Bayes error rate; Sample size determination; Machine learning; Mathematics; Bayesian probability; Bayes classifier; Support vector machine","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":[0.0005143947,0.00006970133,0.00008310704,0.00003980465,0.00008789784,0.00007903986,0.0005790144,0.00003253798,0.00001207912],"category_scores_gemma":[0.00004975693,0.00004340661,0.00002453568,0.0003360416,0.00002284136,0.0002858695,0.000091397,0.00009276845,0.00006054779],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002010674,"about_ca_system_score_gemma":0.00005362096,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007507861,"about_ca_topic_score_gemma":0.000001313079,"domain_scores_codex":[0.9992808,0.00008370965,0.0001667174,0.000206825,0.0001078964,0.000154115],"domain_scores_gemma":[0.9991041,0.0001724108,0.00005783442,0.0003853956,0.0002304339,0.00004985395],"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":[0.000002276048,0.00002186343,0.0002013976,0.000009352244,0.00000992634,1.266558e-8,0.001041734,0.0008107378,0.4017123,0.06548234,0.0003492298,0.5303589],"study_design_scores_gemma":[0.00003235503,0.0001152411,0.00705037,0.000007872728,0.000002111763,7.969555e-7,0.00004947127,0.8394623,0.1488708,0.004268494,0.00006058283,0.00007962382],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05116074,0.000009994147,0.9459602,0.0008720439,0.00008323252,0.0001981533,1.796558e-7,0.00005694259,0.00165849],"genre_scores_gemma":[0.5592263,0.000002291554,0.440394,0.0002069124,0.00001056003,0.00003590163,9.932356e-8,0.000002018327,0.0001219313],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8386516,"threshold_uncertainty_score":0.177007,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.112058794588624,"score_gpt":0.3578968239430307,"score_spread":0.2458380293544068,"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."}}