{"id":"W3004481391","doi":"10.1080/10401334.2019.1708365","title":"The Quality of Assessment of Learning (Qual) Score: Validity Evidence for a Scoring System Aimed at Rating Short, Workplace-Based Comments on Trainee Performance","year":2020,"lang":"en","type":"article","venue":"Teaching and Learning in Medicine","topic":"Innovations in Medical Education","field":"Medicine","cited_by":54,"is_retracted":false,"has_abstract":true,"ca_institutions":"Impact; McMaster University","funders":"","keywords":"Quality (philosophy); Psychology; Medical education; Scoring system; Medicine; Applied psychology; Internal medicine","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1856294,0.0008187341,0.002479672,0.008529317,0.001358166,0.003145746,0.001977025,0.001684903,0.002810541],"category_scores_gemma":[0.386199,0.0005843313,0.00474377,0.00644926,0.003424262,0.00359985,0.003132914,0.001652411,0.000481782],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003102762,"about_ca_system_score_gemma":0.004877861,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001841331,"about_ca_topic_score_gemma":0.003941895,"domain_scores_codex":[0.7701257,0.1337856,0.03704504,0.006904998,0.05127368,0.0008648526],"domain_scores_gemma":[0.4100572,0.4202691,0.09481017,0.01743608,0.05472148,0.002705884],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.003595211,0.0006637169,0.62377,0.02901502,0.01304744,0.00007429205,0.003535874,0.001617236,0.001356966,0.006695949,0.007493717,0.3091347],"study_design_scores_gemma":[0.001674426,0.008044482,0.8670151,0.03335099,0.008389417,0.000960573,0.005918207,0.01511462,0.005316683,0.01400041,0.03962133,0.0005937507],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5698527,0.1315487,0.1898192,0.0110364,0.002694593,0.01401945,0.01063776,0.0006295914,0.06976158],"genre_scores_gemma":[0.9156093,0.007233914,0.06620403,0.001281517,0.0003619056,0.006217179,0.002226565,0.000102825,0.0007627162],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8143706,"threshold_uncertainty_score":0.9817136,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2124900937935385,"score_gpt":0.4522771206867789,"score_spread":0.2397870268932404,"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."}}