{"id":"W4387700453","doi":"10.36834/cmej.75876","title":"The Quality of Assessment for Learning score for evaluating written feedback in anesthesiology postgraduate medical education: a generalizability and decision study","year":2023,"lang":"en","type":"article","venue":"Canadian Medical Education Journal","topic":"Innovations in Medical Education","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University; University of Saskatchewan","funders":"","keywords":"Generalizability theory; Narrative; Quality (philosophy); Medical education; Reliability (semiconductor); Psychology; Graduate medical education; Medicine; Developmental psychology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1521205,0.0009296639,0.002150211,0.004877021,0.001132062,0.00156329,0.001640632,0.001916298,0.002093915],"category_scores_gemma":[0.2599488,0.0006271396,0.005041036,0.004077632,0.00333876,0.002449997,0.00268765,0.001326925,0.0003682216],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002074713,"about_ca_system_score_gemma":0.001576532,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001015691,"about_ca_topic_score_gemma":0.00133665,"domain_scores_codex":[0.8068374,0.1285393,0.02057314,0.007785552,0.03499069,0.001273828],"domain_scores_gemma":[0.620113,0.2932682,0.03861098,0.01587751,0.02806295,0.004067465],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.005903988,0.0007911549,0.9536619,0.0004726815,0.002969196,0.00008383311,0.001845327,0.001048985,0.0006340345,0.00052828,0.0007891373,0.03127158],"study_design_scores_gemma":[0.002589385,0.01943113,0.9395737,0.0004323456,0.002273363,0.0004832413,0.002263348,0.02552493,0.002967815,0.001413865,0.00284724,0.0001997394],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9730584,0.001067133,0.01739825,0.0003664544,0.0002099514,0.004427704,0.0005069336,0.00008200272,0.002883276],"genre_scores_gemma":[0.9892385,0.0001026451,0.007713323,0.00008800129,0.00004481808,0.002334092,0.0002539592,0.00003144619,0.0001932296],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8478795,"threshold_uncertainty_score":0.8044995,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07790103128073553,"score_gpt":0.4861602049242974,"score_spread":0.4082591736435619,"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."}}