{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03782004,0.0014651,0.004059131,0.001814737,0.001097665,0.003197282,0.003835274,0.002654585,0.001763867],"category_scores_gemma":[0.09730925,0.00122761,0.001448759,0.001425059,0.002177559,0.003766936,0.003053976,0.003087516,0.00104391],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001524446,"about_ca_system_score_gemma":0.00319015,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003225046,"about_ca_topic_score_gemma":0.003025477,"domain_scores_codex":[0.9789969,0.01407658,0.001245707,0.002543919,0.002546186,0.0005908062],"domain_scores_gemma":[0.8963272,0.08021159,0.005576243,0.008443517,0.008118928,0.001322504],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000947377,0.0005619014,0.02372519,0.0003748189,0.0004650649,0.0003592513,0.0006682599,0.6528586,0.002936346,0.03589711,0.003765562,0.2774406],"study_design_scores_gemma":[0.00002202364,0.00008109067,0.0006190293,0.00002437258,0.00001653291,0.00003691887,0.00002259915,0.9819996,0.0008080758,0.01612523,0.0002309963,0.0000134005],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02465952,0.0002216055,0.9734298,0.000243037,0.00002370063,0.0002150393,0.0001610968,0.0005665057,0.0004797498],"genre_scores_gemma":[0.4617549,0.000350399,0.5332881,0.0004837684,0.0001572991,0.0008640601,0.001726657,0.0001937034,0.001181101],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.03782004,"threshold_uncertainty_score":0.2000139,"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."}}