{"id":"W2584820851","doi":"10.1111/medu.13221","title":"Should learners reason one step at a time? A randomised trial of two diagnostic scheme designs","year":2017,"lang":"en","type":"article","venue":"Medical Education","topic":"Clinical Reasoning and Diagnostic Skills","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University; Western University","funders":"","keywords":"Medical diagnosis; Auscultation; Scheme (mathematics); Cognition; Medicine; Computer science; Algorithm; Artificial intelligence; Mathematics; Radiology","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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001598903,0.0001585704,0.0006079227,0.00006917583,0.0001607009,0.00002760881,0.0002435576,0.0002440459,0.002589639],"category_scores_gemma":[0.5794691,0.0001296027,0.0002012085,0.00007820829,0.0003702976,0.00005482014,0.00008138051,0.0003300007,0.0002715589],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008965707,"about_ca_system_score_gemma":0.001920608,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004199723,"about_ca_topic_score_gemma":0.00002210627,"domain_scores_codex":[0.9977036,0.0001535237,0.0005829415,0.0003367981,0.0009579976,0.0002651829],"domain_scores_gemma":[0.9837829,0.01418323,0.0004183885,0.0008366284,0.0001864164,0.0005924745],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"randomized_trial","study_design_scores_codex":[0.1817241,0.01793295,0.06124436,0.0002816005,0.0005251748,0.00008119375,0.0009713066,0.000002708919,0.00178557,0.001129218,0.1966616,0.5376602],"study_design_scores_gemma":[0.906468,0.003448058,0.05605336,0.01308494,0.001543749,0.0001023462,0.0001493019,0.003283109,0.002546317,0.0005987437,0.0120765,0.0006455617],"study_design_candidate":"randomized_trial","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9714299,0.000332699,0.0002615791,0.01729307,0.0009844218,0.001245724,0.000003132849,0.00005031126,0.00839913],"genre_scores_gemma":[0.9895935,0.0002998082,0.002279528,0.001423203,0.001214302,0.0002207974,0.0001110055,0.00003048561,0.004827345],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7247439,"threshold_uncertainty_score":0.9983221,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06677853953739667,"score_gpt":0.4145278522515871,"score_spread":0.3477493127141904,"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."}}