{"id":"W3127624731","doi":"10.1038/s41405-021-00067-4","title":"The interrelationship between confidence and correctness in a multiple-choice assessment: pointing out misconceptions and assuring valuable questions","year":2021,"lang":"en","type":"article","venue":"BDJ Open","topic":"Clinical Reasoning and Diagnostic Skills","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Correctness; Low Confidence; Confidence interval; Psychology; Point (geometry); Mathematics education; Sample (material); Computer science; Social psychology; Statistics; Mathematics; Algorithm","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":[0.0009295067,0.00008832817,0.0002364393,0.00003105547,0.0003020072,0.0002558973,0.0001014494,0.00006384509,0.00002904285],"category_scores_gemma":[0.08094209,0.00007064802,0.00002709732,0.00013308,0.000125365,0.0001321379,0.0002614556,0.0003281789,0.000007371902],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000376046,"about_ca_system_score_gemma":0.0002202405,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001230791,"about_ca_topic_score_gemma":0.002500658,"domain_scores_codex":[0.9989389,0.0001828943,0.0003117623,0.0002670161,0.0001234958,0.0001759892],"domain_scores_gemma":[0.9583895,0.04102867,0.00008556006,0.0002459141,0.0001144148,0.0001359763],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000008922491,0.00004204238,0.9928618,0.000009357085,0.00002128694,0.00001318523,0.0003208882,0.00001180615,0.00004672252,0.0008663357,0.0002181846,0.005579472],"study_design_scores_gemma":[0.001373703,0.00004429536,0.991254,0.002142599,0.00007817856,0.00002940845,0.001050698,0.002251748,0.00003951355,0.000742987,0.0009055035,0.00008734298],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9836617,0.0007164554,0.00121694,0.005159764,0.0001848921,0.0005424468,0.00001013743,0.00003315019,0.008474524],"genre_scores_gemma":[0.9957318,0.0001234621,0.001628957,0.0001593868,0.00007717439,0.00006172545,0.00002452805,0.000009879075,0.002183037],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.08001259,"threshold_uncertainty_score":0.9267995,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1385446853540866,"score_gpt":0.4454390641274341,"score_spread":0.3068943787733475,"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."}}