{"id":"W3092705373","doi":"10.48550/arxiv.2010.09443","title":"Efficient Estimation and Evaluation of Prediction Rules in Semi-Supervised Settings under Stratified Sampling","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Estimator; Leverage (statistics); Computer science; Missing data; Random forest; Data mining; Consistency (knowledge bases); Stratified sampling; Machine learning; Sampling (signal processing); Imputation (statistics); Artificial intelligence; Brier score; Regression; 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":[0.03323056,0.001482107,0.003691057,0.001798018,0.001068882,0.003064218,0.003831286,0.002660525,0.001702206],"category_scores_gemma":[0.09615514,0.001271574,0.001345346,0.001456894,0.002325427,0.003561746,0.003070612,0.003048416,0.001001858],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001633677,"about_ca_system_score_gemma":0.00308506,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003792155,"about_ca_topic_score_gemma":0.003587299,"domain_scores_codex":[0.9800122,0.01376942,0.001106855,0.002455902,0.00213067,0.0005248739],"domain_scores_gemma":[0.9019226,0.07574444,0.005353193,0.008694466,0.007128054,0.001157181],"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":[0.0007804276,0.0005551669,0.02491306,0.0003869771,0.000427994,0.0003102237,0.0006075537,0.6726088,0.002684962,0.03816818,0.003655792,0.2549009],"study_design_scores_gemma":[0.00002022002,0.00006216195,0.0006982464,0.00002280255,0.00001431234,0.00003194167,0.00002088554,0.9818502,0.0007088655,0.01634702,0.000211387,0.00001196],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0251452,0.000227429,0.9729455,0.0002508798,0.00002205969,0.0002068008,0.000164533,0.0005350751,0.0005024758],"genre_scores_gemma":[0.478243,0.0003824912,0.5170412,0.0003965888,0.0001473239,0.0007999636,0.00171693,0.0001721135,0.001100414],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.03323056,"threshold_uncertainty_score":0.1757421,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1236536886627107,"score_gpt":0.2469224183527546,"score_spread":0.1232687296900438,"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."}}