{"id":"W4411021933","doi":"10.5770/cgj.28.795","title":"Validity and Utility of the CanMEDS “Resident as Teacher Multisource Feedback” Assessment Tool for Resident-led Structured Teaching","year":2025,"lang":"en","type":"article","venue":"Canadian Geriatrics Journal","topic":"Innovations in Medical Education","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"University of Toronto","keywords":"Inter-rater reliability; Narrative; Medicine; Cronbach's alpha; Medical education; Consistency (knowledge bases); Thematic analysis; Summative assessment; Psychology; Formative assessment; Pedagogy; Qualitative research; Rating scale; Clinical psychology; Psychometrics; Computer science","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":true,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002127855,0.0001402092,0.0002637546,0.0003946277,0.0005998508,0.00008419719,0.0002163198,0.0001685001,0.0002386061],"category_scores_gemma":[0.005040467,0.0001090639,0.0001021589,0.0004110748,0.0001090054,0.00007475919,0.00004113249,0.0009193617,4.688348e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009490555,"about_ca_system_score_gemma":0.004766462,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01357094,"about_ca_topic_score_gemma":0.0081629,"domain_scores_codex":[0.9983283,0.0001978309,0.0005706083,0.0001993441,0.0003825947,0.0003213504],"domain_scores_gemma":[0.9985875,0.0001278259,0.0002690065,0.000348229,0.0004412516,0.0002261943],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000122709,0.00008959026,0.6644359,0.0003650331,0.0001950655,0.00001618275,0.002616231,0.00002015885,0.001084502,0.003002257,0.2631778,0.06487457],"study_design_scores_gemma":[0.00152314,0.00006098766,0.9568399,0.0001360274,0.0002581157,0.0001228814,0.001517092,0.0009242235,0.0002575321,0.002854117,0.03538524,0.0001207023],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9823835,0.0001399435,0.002216694,0.01116773,0.001708156,0.0006807026,0.00002184927,0.00000832829,0.001673096],"genre_scores_gemma":[0.9893294,0.00001938473,0.006584934,0.001250729,0.0004415823,0.00001715732,0.0000125727,0.00001468725,0.002329537],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2924041,"threshold_uncertainty_score":0.9929978,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01543480388978014,"score_gpt":0.3325171091913414,"score_spread":0.3170823053015612,"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."}}