{"id":"W3198343911","doi":"10.1002/cjs.11772","title":"Optimal multiwave validation of secondary use data with outcome and exposure misclassification","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of Environmental Health Sciences; National Institute of Allergy and Infectious Diseases; National Heart, Lung, and Blood Institute; University of North Carolina at Chapel Hill; National Institutes of Health; Vanderbilt University; Patient-Centered Outcomes Research Institute","keywords":"Estimator; Computer science; Variance (accounting); Outcome (game theory); Optimal design; Observational study; Data mining; Mathematical optimization; Grid; Resource (disambiguation); Machine learning; Statistics; Mathematics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003848736,0.00009395049,0.0002127316,0.0002241441,0.00005104653,0.00004411313,0.0001946884,0.00005227364,0.00003262117],"category_scores_gemma":[0.00143896,0.00008128312,0.00001070412,0.0001484946,0.0001275735,0.000362304,0.00002143887,0.0001862632,0.00000129726],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000567256,"about_ca_system_score_gemma":0.0004747659,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002750461,"about_ca_topic_score_gemma":0.002871665,"domain_scores_codex":[0.9990892,0.00004005279,0.0004584074,0.0001038082,0.0001600648,0.0001484182],"domain_scores_gemma":[0.9981523,0.0005096155,0.0004546992,0.0003003179,0.0003708246,0.000212269],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003197156,0.0001758804,0.4487385,0.002197481,0.0008225583,0.002548392,0.01193616,0.001746845,0.006744951,0.2821741,0.149839,0.09275646],"study_design_scores_gemma":[0.00793599,0.005301041,0.5197447,0.002556693,0.001907063,0.002083969,0.01578791,0.03373748,0.02178526,0.3624266,0.0236397,0.003093604],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.477311,0.00003069669,0.5199289,0.0001460873,0.00007412182,0.0001584601,0.00226998,0.00002267431,0.0000581268],"genre_scores_gemma":[0.5648977,0.00002172151,0.4348289,0.00001303719,0.00001999387,9.918808e-7,0.0001112162,0.00001734015,0.00008911324],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.1261993,"threshold_uncertainty_score":0.3314629,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3119308867935993,"score_gpt":0.3904439519980124,"score_spread":0.07851306520441315,"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."}}