{"id":"W4224511660","doi":"10.1111/rssb.12502","title":"Efficient Evaluation of Prediction Rules in Semi-Supervised Settings under Stratified Sampling","year":2022,"lang":"en","type":"article","venue":"Journal of the Royal Statistical Society Series B (Statistical Methodology)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"National Institute of Neurological Disorders and Stroke; National Institute of General Medical Sciences; National Heart, Lung, and Blood Institute","keywords":"Estimator; Leverage (statistics); Stratified sampling; Computer science; Missing data; Random forest; Consistency (knowledge bases); Data mining; Machine learning; Sampling (signal processing); Imputation (statistics); Regression; Artificial intelligence; Statistics; Mathematics","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":[0.01119534,0.000168873,0.0004319909,0.00006614783,0.0003602984,0.00006156411,0.000770568,0.00009399228,0.0002501002],"category_scores_gemma":[0.005053965,0.0001284638,0.0001464357,0.0004008244,0.000279109,0.00009425525,0.000390623,0.0009646818,0.000001473431],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003293837,"about_ca_system_score_gemma":0.0003612408,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005465195,"about_ca_topic_score_gemma":0.000004728536,"domain_scores_codex":[0.9925376,0.004418754,0.001043898,0.0003254635,0.001371175,0.0003031101],"domain_scores_gemma":[0.9941959,0.004337928,0.000653746,0.000351901,0.0003507423,0.0001097789],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002719114,0.0003951927,0.001953558,0.0001118858,0.0001340288,0.000005753274,0.002233319,0.5121683,0.001887194,0.4304525,0.002507671,0.04787865],"study_design_scores_gemma":[0.0007608485,0.0003245468,0.112666,0.00002667131,0.0001155806,0.00003890166,0.0009780939,0.8030494,0.00006930336,0.08156548,0.0002853519,0.0001198953],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04754557,0.00008872868,0.9487002,0.002335463,0.0006175849,0.000225309,0.0003790603,0.00001937641,0.00008870148],"genre_scores_gemma":[0.4086274,0.000004169128,0.5910873,0.0001581119,0.0000516369,0.00001485288,0.00003007913,0.000009198731,0.00001729604],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3610818,"threshold_uncertainty_score":0.6050434,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09762707363528889,"score_gpt":0.3569091399639306,"score_spread":0.2592820663286418,"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."}}