{"id":"W2795046142","doi":"10.36834/cmej.42286","title":"Redeveloping a workplace-based assessment program for physicians using Kane’s validity framework","year":2018,"lang":"en","type":"article","venue":"Canadian Medical Education Journal","topic":"Innovations in Medical Education","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"College of Physicians and Surgeons of Ontario","funders":"","keywords":"Formative assessment; Process (computing); Specialty; Medical education; Computer science; Knowledge management; Psychology; Medicine; Family medicine; Pedagogy","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2855033,0.0008617706,0.001310587,0.0099082,0.006327075,0.006118841,0.004051285,0.001694659,0.00161844],"category_scores_gemma":[0.3055966,0.001249006,0.002084703,0.003630334,0.00695045,0.008988682,0.01036753,0.004911731,0.000620336],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.02120064,"about_ca_system_score_gemma":0.06578346,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01670412,"about_ca_topic_score_gemma":0.03610696,"domain_scores_codex":[0.7489586,0.1768829,0.01902281,0.006870418,0.04369644,0.004568844],"domain_scores_gemma":[0.6454622,0.1870407,0.0246452,0.0292248,0.1087181,0.004908996],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0001960528,0.001221708,0.05390977,0.001629881,0.0001365713,0.0002851525,0.04624568,0.006751006,0.002371418,0.09451079,0.008403214,0.7843388],"study_design_scores_gemma":[0.0006746231,0.00432868,0.2232819,0.01299958,0.0005466458,0.001465922,0.07424616,0.1022055,0.03114236,0.3284164,0.2189298,0.001762596],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0947021,0.0007665369,0.8420428,0.01362946,0.0004422502,0.01389946,0.0002768463,0.0008284826,0.03341204],"genre_scores_gemma":[0.2169954,0.0002124258,0.7750354,0.00070626,0.00004911141,0.005229142,0.0001702326,0.00006293844,0.001539075],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9787993,"threshold_uncertainty_score":0.8811017,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04517756488486576,"score_gpt":0.4255364163158259,"score_spread":0.3803588514309602,"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."}}