{"id":"W4294351388","doi":"10.36834/cmej.74860","title":"Validity evidence for the Quality of Assessment for Learning score: a quality metric for supervisor comments in Competency Based Medical Education","year":2022,"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":"McMaster University; Impact; University of Ottawa; University of Calgary; University of Saskatchewan","funders":"McMaster University; University of Saskatchewan","keywords":"Generalizability theory; Competence (human resources); Supervisor; Cronbach's alpha; Narrative; Psychology; Medical education; Variance (accounting); Medicine; Clinical psychology; Social psychology; Psychometrics; Management; Accounting; Developmental psychology","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":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.022798,0.0001888052,0.0005026067,0.0008717821,0.0009983503,0.00004530147,0.0006606648,0.000205636,0.007726864],"category_scores_gemma":[0.2361925,0.0001625462,0.000250086,0.001362883,0.0002198009,0.0001460812,0.00003796739,0.001464008,9.347693e-7],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002690536,"about_ca_system_score_gemma":0.2645219,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00682369,"about_ca_topic_score_gemma":0.005644348,"domain_scores_codex":[0.9942575,0.000948418,0.001706992,0.0003579109,0.002213819,0.0005154082],"domain_scores_gemma":[0.9839641,0.007347788,0.001233648,0.0007046637,0.003425891,0.003323857],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.000665218,0.004515136,0.1400795,0.00182141,0.0001452949,0.000001814637,0.001863265,0.000154206,0.00004802355,0.03104929,0.2738303,0.5458265],"study_design_scores_gemma":[0.01245329,0.00242933,0.4933717,0.002475036,0.000479997,0.0002475724,0.02792857,0.08262242,0.00005355376,0.01129875,0.3658049,0.0008349541],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.1906991,0.001345097,0.09347841,0.6993328,0.009324688,0.005484179,0.00008557986,0.00002675122,0.0002233481],"genre_scores_gemma":[0.8933207,0.00008976142,0.03420384,0.06611722,0.001430889,0.003957159,0.0006022752,0.00004328971,0.00023482],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7026216,"threshold_uncertainty_score":0.99979,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1675569394145632,"score_gpt":0.4977005813903227,"score_spread":0.3301436419757596,"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."}}