{"id":"W4400584230","doi":"10.1002/cjs.11815","title":"Robust estimation of loss‐based measures of model performance under covariate shift","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of General Medical Sciences; National Institutes of Health; National Cancer Institute; National Heart, Lung, and Blood Institute; U.S. National Library of Medicine; Patient-Centered Outcomes Research Institute","keywords":"Covariate; Statistics; Estimation; Econometrics; Computer science; Mathematics; Engineering","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"},{"model":"grok","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"},{"model":"opus","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"}],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007211415,0.0001172465,0.0003304577,0.0002480576,0.00004321893,0.00003539665,0.0001612916,0.0000658666,0.0001486339],"category_scores_gemma":[0.001639976,0.0001012601,0.00005191989,0.0001783533,0.0001847483,0.00008333886,0.000005616756,0.0002158672,0.000002162815],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009745199,"about_ca_system_score_gemma":0.002144294,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003578446,"about_ca_topic_score_gemma":0.0007080077,"domain_scores_codex":[0.9986562,0.00006669237,0.0007003975,0.00008692979,0.0003012444,0.0001886061],"domain_scores_gemma":[0.9978483,0.001027981,0.0002975568,0.0001358155,0.0004322629,0.0002580486],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002250508,0.0000209822,0.0002354752,0.0008848128,0.00007000198,0.00004753555,0.0004405679,0.1785985,0.00004995115,0.8009499,0.001720735,0.01695894],"study_design_scores_gemma":[0.0001445584,0.0001182714,0.00109178,0.0004213411,0.000106329,0.00001220103,0.00002092941,0.6203493,0.0003259109,0.3773101,0.00002209413,0.00007717501],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01733136,0.0001372013,0.9809647,0.0001141512,0.0002178507,0.00006322564,0.0008761234,0.000004401249,0.0002910038],"genre_scores_gemma":[0.5288519,0.000009280311,0.471075,0.00001846375,0.00001532012,4.973658e-7,0.000002506809,0.00001141227,0.00001555118],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5115206,"threshold_uncertainty_score":0.4129268,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2748110263819734,"score_gpt":0.3443083888726723,"score_spread":0.06949736249069888,"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."}}