{"id":"W3027176385","doi":"10.1002/pst.2029","title":"Investigating the appropriateness of different concordance measures in a time‐to‐event setting","year":2020,"lang":"en","type":"article","venue":"Pharmaceutical Statistics","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Censoring (clinical trials); Concordance; Statistic; Statistics; Comparability; Parametric statistics; Event (particle physics); Mathematics; Econometrics; Computer science; Medicine; Internal medicine","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":[0.0006136419,0.0001613432,0.0002455973,0.00003477615,0.00009664072,0.0001022144,0.001088143,0.00003176046,0.00004327225],"category_scores_gemma":[0.001598195,0.0001206842,0.00003273886,0.0005593526,0.0001406611,0.0001111689,0.0004830397,0.0003012466,0.0001396225],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005750311,"about_ca_system_score_gemma":0.00007355522,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003591736,"about_ca_topic_score_gemma":0.00001008024,"domain_scores_codex":[0.9978687,0.000281722,0.0005370351,0.0003489674,0.0005660398,0.0003975434],"domain_scores_gemma":[0.9983719,0.000846347,0.000123499,0.0002385908,0.0001317329,0.0002879201],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009010491,0.0004776324,0.02020402,0.0005105974,0.00008887471,0.0001137011,0.01835917,0.02485757,0.1102403,0.3406437,0.003211975,0.4812023],"study_design_scores_gemma":[0.0001777719,0.00008765964,0.001786686,0.00005815148,0.00001201971,0.000002174344,0.00009568452,0.8794835,0.1047043,0.01183934,0.001554665,0.0001980501],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04491257,0.00006723049,0.9477887,0.006489872,0.0000904796,0.0004123222,0.00002468901,0.00005855154,0.0001556247],"genre_scores_gemma":[0.9504816,0.000009044712,0.04622839,0.003160485,0.00005865377,0.00003343026,0.000002055926,0.00001283224,0.00001349434],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.905569,"threshold_uncertainty_score":0.4921359,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08646133817187293,"score_gpt":0.3480782208862438,"score_spread":0.2616168827143709,"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."}}