{"id":"W2020794294","doi":"10.1186/1472-6920-14-97","title":"Accuracy of portrayal by standardized patients: Results from four OSCE stations conducted for high stakes examinations","year":2014,"lang":"en","type":"article","venue":"BMC Medical Education","topic":"Innovations in Medical Education","field":"Medicine","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Cronbach's alpha; Objective structured clinical examination; Trainer; Rating scale; Reliability (semiconductor); Scale (ratio); Psychology; Medical education; Educational measurement; Applied psychology; Medicine; Medical physics; Psychometrics; Clinical psychology; Computer science; Curriculum; Pedagogy","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":[0.001336421,0.0001982093,0.0004121901,0.0002500803,0.0001601421,0.00002398556,0.0002069554,0.0002683582,0.000771973],"category_scores_gemma":[0.1141757,0.000183,0.00008032426,0.0005972864,0.0002413935,0.0002132598,0.00002124293,0.0002799104,0.00001356241],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002324071,"about_ca_system_score_gemma":0.004962327,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005022501,"about_ca_topic_score_gemma":0.0000769818,"domain_scores_codex":[0.9965795,0.0001939932,0.001252795,0.0004473978,0.001253507,0.0002728065],"domain_scores_gemma":[0.9930449,0.002570077,0.0007856812,0.0006489014,0.002677947,0.0002725219],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.0008184647,0.005256876,0.008713845,0.0004787019,0.0001337976,2.063036e-7,0.001957679,0.000004969426,0.001444657,0.01120512,0.6375352,0.3324505],"study_design_scores_gemma":[0.05195435,0.002580285,0.5636645,0.002846387,0.001323986,0.00001281202,0.00819297,0.01019701,0.01246795,0.01387735,0.3314651,0.001417326],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8964747,0.0000655353,0.09101246,0.00729502,0.002046127,0.001387417,0.0008340264,0.00009096137,0.0007937669],"genre_scores_gemma":[0.9134092,0.00003494809,0.06171509,0.002099755,0.0006286548,0.0003725768,0.02106044,0.00003871935,0.0006406057],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5549507,"threshold_uncertainty_score":0.893286,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02735951081956597,"score_gpt":0.3465033525339843,"score_spread":0.3191438417144183,"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."}}