{"id":"W4399724720","doi":"10.31234/osf.io/dw89q","title":"Calibration Feedback with the Practical Scoring Rule Does Not Improve Calibration of Confidence","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Quality and Safety in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Defence Research and Development Canada; Université du Québec à Montréal","funders":"","keywords":"Calibration; Computer science; Confidence interval; Statistics; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004874622,0.0006294036,0.0007964384,0.0003621712,0.0002456234,0.0006877899,0.001068718,0.0008757047,0.007696805],"category_scores_gemma":[0.06124912,0.0002816052,0.0003422678,0.0002886023,0.0007376288,0.001382212,0.001039719,0.001062549,0.001345019],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002965961,"about_ca_system_score_gemma":0.0006861963,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008041246,"about_ca_topic_score_gemma":0.0007735654,"domain_scores_codex":[0.9957771,0.001675269,0.0003936765,0.0007976851,0.001141134,0.0002151845],"domain_scores_gemma":[0.9427267,0.03935074,0.006568814,0.007996883,0.001846428,0.001510487],"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":[0.01400653,0.009710507,0.03244198,0.001620936,0.0003025377,0.0001083821,0.00222989,0.01200661,0.1186339,0.001970263,0.004741017,0.8022274],"study_design_scores_gemma":[0.006563332,0.1243927,0.492475,0.001527874,0.0009843619,0.00103971,0.002008163,0.1399798,0.1695101,0.02445539,0.03641023,0.0006533687],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9594002,0.0002982141,0.03045105,0.0004840293,0.0001535052,0.0003622916,0.0001252146,0.001041997,0.007683483],"genre_scores_gemma":[0.9692077,0.0001430852,0.02707455,0.0002792104,0.00005531275,0.0003450086,0.0001783764,0.00009044852,0.002626352],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007696805,"threshold_uncertainty_score":0.02577972,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1186135678698076,"score_gpt":0.4545305730201225,"score_spread":0.3359170051503148,"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."}}