{"id":"W4404162510","doi":"10.1002/ffo2.199","title":"Calibration Feedback With the Practical Scoring Rule Does Not Improve Calibration of Confidence","year":2024,"lang":"en","type":"article","venue":"Futures & Foresight Science","topic":"Clinical Reasoning and Diagnostic Skills","field":"Medicine","cited_by":1,"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; Artificial intelligence; Statistics; Machine learning; 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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0009255787,0.0001198351,0.0001761216,0.00007873857,0.0002096905,0.00020282,0.0001752015,0.00006450522,0.00007906881],"category_scores_gemma":[0.009128929,0.00005289452,0.00005653059,0.0005286289,0.0008884646,0.0005031114,0.00005836189,0.00025132,0.000007697248],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004695315,"about_ca_system_score_gemma":0.0009476974,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001368721,"about_ca_topic_score_gemma":0.00007104751,"domain_scores_codex":[0.998102,0.00003396846,0.0002545322,0.0004016247,0.0009560843,0.0002518063],"domain_scores_gemma":[0.9955817,0.003624318,0.00009233335,0.0003434816,0.0002023989,0.0001557169],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001914557,0.0004799365,0.01165852,0.0005202367,0.0001429047,0.0003804548,0.006185783,0.0004327633,0.5589635,0.3746764,0.01811623,0.02652869],"study_design_scores_gemma":[0.001016739,0.001366089,0.04623613,0.003008995,0.0003055403,0.0001827846,0.001239029,0.07517798,0.8651105,0.004318492,0.001667652,0.0003700386],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9318054,0.0004968853,0.03050779,0.03280462,0.001415199,0.0007787393,0.00002752433,0.0001678006,0.001996058],"genre_scores_gemma":[0.9961412,0.00003489752,0.002041579,0.0006265573,0.0004544739,0.00002017653,0.000004838645,0.00001108332,0.0006651793],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3703579,"threshold_uncertainty_score":0.9992176,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01930742933790456,"score_gpt":0.328052727097001,"score_spread":0.3087452977590964,"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."}}