{"id":"W4399593952","doi":"10.1002/sim.10138","title":"Non‐parametric inference on calibration of predicted risks","year":2024,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Advanced Statistical Process Monitoring","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Canadian Institutes of Health Research","keywords":"Inference; Calibration; Parametric statistics; Computer science; Statistics; Econometrics; Parametric model; Mathematics; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":true,"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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00146887,0.0001427476,0.0003841369,0.0008783735,0.00003727323,0.00004212005,0.0003566118,0.00006966386,0.0003497779],"category_scores_gemma":[0.04342823,0.00009920493,0.00001577565,0.00258074,0.0003218846,0.0001563867,0.00005558535,0.0003803747,0.00003271623],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006961619,"about_ca_system_score_gemma":0.000107507,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000981573,"about_ca_topic_score_gemma":0.0000247313,"domain_scores_codex":[0.9966141,0.00009068097,0.0009719815,0.0004367956,0.001671132,0.0002152875],"domain_scores_gemma":[0.9864392,0.01267922,0.0001563756,0.0003341988,0.0002840685,0.0001069589],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001790244,0.0001503408,0.03002961,0.0003610917,0.00003419637,0.0003665476,0.002402279,0.01830319,0.0006614484,0.4133654,0.02248871,0.5116582],"study_design_scores_gemma":[0.000363294,0.0004856693,0.03029576,0.0004472149,0.00001700444,0.000001577775,0.0002667463,0.4365055,0.0003163251,0.5305965,0.0005879807,0.0001165006],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007526961,0.0002111728,0.9878922,0.0002110063,0.001139581,0.0001711611,0.0003343343,0.00003729467,0.002476302],"genre_scores_gemma":[0.9702957,0.0000654536,0.02908979,0.00004557867,0.0001659918,0.00001242065,0.00002721586,0.00001368972,0.0002841542],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9627687,"threshold_uncertainty_score":0.9646294,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1888057989843291,"score_gpt":0.5166805173376785,"score_spread":0.3278747183533494,"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."}}