{"id":"W3154515585","doi":"10.1111/risa.13725","title":"What is a Good Calibration Question?","year":2021,"lang":"en","type":"article","venue":"Risk Analysis","topic":"Forecasting Techniques and Applications","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Calibration; Set (abstract data type); Sample (material); Computer science; Reliability (semiconductor); Domain (mathematical analysis); Artificial intelligence; Machine learning; Statistics; Data mining; Mathematics","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001136646,0.00007596055,0.0002084257,0.0002570999,0.0002071847,0.0007502136,0.0002729004,0.00005845819,0.001681126],"category_scores_gemma":[0.0005279388,0.00005988315,0.0003058277,0.004504913,0.00003117636,0.0004445065,0.00008093582,0.00008614223,0.0002165568],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002012207,"about_ca_system_score_gemma":0.00004323953,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002239177,"about_ca_topic_score_gemma":0.0005623662,"domain_scores_codex":[0.9982593,0.0001878612,0.0003851676,0.0004208345,0.0006327283,0.000114103],"domain_scores_gemma":[0.9981994,0.0003192318,0.0002122016,0.0008291281,0.0003700544,0.00006999836],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000006191491,0.0003049031,0.6218389,0.000003180974,0.001213082,0.00001781693,0.001445624,0.006902162,0.0006765993,0.0622348,0.06332892,0.2420278],"study_design_scores_gemma":[0.0001218771,0.00002344887,0.05528561,0.00001440946,0.00173792,0.000004967414,0.001257179,0.5704415,0.01016771,0.2824301,0.07820843,0.0003068752],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2704975,0.0007286131,0.7192121,0.006617337,0.0001181001,0.0001009314,0.00006885665,0.0001802966,0.002476268],"genre_scores_gemma":[0.9783317,0.000700618,0.01442185,0.0003465494,0.00005822686,0.00002227047,0.00004069335,0.000005865243,0.006072212],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7078342,"threshold_uncertainty_score":0.9992315,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05990817643048678,"score_gpt":0.4026853487622595,"score_spread":0.3427771723317727,"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."}}