{"id":"W3003854185","doi":"10.1002/cjs.11633","title":"Assessing the calibration of subdistribution hazard models in discrete time","year":2021,"lang":"en","type":"preprint","venue":"Canadian Journal of Statistics","topic":"Statistical Methods in Epidemiology","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Censoring (clinical trials); Covariate; Calibration; Hazard; Generalization; Statistics; Event (particle physics); Computer science; Econometrics; 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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.003102233,0.0002307357,0.0009332859,0.0002360854,0.00007621251,0.0001393118,0.0004333831,0.0003375589,0.0001551149],"category_scores_gemma":[0.02437409,0.0001876328,0.0001202688,0.0001801358,0.0003427753,0.0001649671,0.00008372279,0.001258885,5.253378e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000506392,"about_ca_system_score_gemma":0.003722582,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002311201,"about_ca_topic_score_gemma":0.008720317,"domain_scores_codex":[0.9959574,0.001526076,0.001655985,0.0002052185,0.000297696,0.0003576209],"domain_scores_gemma":[0.9901395,0.00696467,0.00153123,0.000386602,0.0006742371,0.0003038005],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00003185121,0.00006614628,0.003913603,0.001202306,0.0003572152,0.001224479,0.002302223,0.02972412,0.0001695587,0.9311857,0.01943314,0.01038967],"study_design_scores_gemma":[0.0001539981,0.00003567663,0.002355771,0.0006080033,0.0001641447,0.00006828956,0.0003038695,0.173669,0.00006985153,0.8223878,0.00002648785,0.0001570307],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01746804,0.000312966,0.9786518,0.0005433962,0.0006847315,0.0001847511,0.001950117,0.000003347926,0.000200907],"genre_scores_gemma":[0.3032651,0.00003914177,0.6963094,0.00006282603,0.0001292832,0.000004095336,0.0001326631,0.00003131581,0.00002619126],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2857971,"threshold_uncertainty_score":0.983844,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1772214023177138,"score_gpt":0.4187768192035156,"score_spread":0.2415554168858018,"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."}}