{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009156913,0.0001538568,0.0001879114,0.0002289703,0.00007180317,0.00007679813,0.0003781366,0.0001550311,0.000005676525],"category_scores_gemma":[0.0001486866,0.000182826,0.00004150948,0.000357242,0.0000433054,0.0001634119,0.0003970361,0.0003377783,0.000004936455],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00015193,"about_ca_system_score_gemma":0.0001833363,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001141006,"about_ca_topic_score_gemma":0.00001579547,"domain_scores_codex":[0.9984343,0.0002865469,0.0002522792,0.0007134023,0.0001914881,0.0001219629],"domain_scores_gemma":[0.9988996,0.0001118672,0.0002871767,0.0004702703,0.0001695068,0.00006156793],"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":[0.00001210093,0.00003765836,0.002031759,0.000104294,0.00001334943,0.000001160862,0.0004917163,0.9610248,0.0004218082,0.03026896,0.000006930904,0.005585503],"study_design_scores_gemma":[0.0004528272,0.00002296429,0.05278608,0.0001321811,0.00005494404,7.07346e-7,0.0001251984,0.9283897,0.00005703766,0.01784887,0.000003595373,0.0001259412],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.510419,0.00002338968,0.48887,0.0001843838,0.00006595253,0.0002060139,0.00001825714,0.00005969054,0.0001533351],"genre_scores_gemma":[0.9929434,0.00001980944,0.006769564,0.00001843785,0.0000171238,0.000001734642,0.0002148487,0.00000682371,0.000008244459],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4825244,"threshold_uncertainty_score":0.7455429,"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."}}