{"id":"W4388997485","doi":"10.1016/j.jsurg.2023.10.001","title":"Development of a Tool to Assess Surgical Resident Competence On-Call: The Western University Call Assessment Tool (WUCAT)","year":2023,"lang":"en","type":"article","venue":"Journal of surgical education","topic":"Innovations in Medical Education","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"London Health Sciences Centre; Western University","funders":"Canadian Institutes of Health Research; Western University","keywords":"Formative assessment; Generalizability theory; Competence (human resources); Summative assessment; Medical education; Medicine; Internal consistency; Psychology; Nursing; Patient satisfaction","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.008164234,0.0006587125,0.0007275369,0.004238686,0.0006452857,0.001975696,0.001100037,0.0007314075,0.003209321],"category_scores_gemma":[0.0301019,0.0003699667,0.001164116,0.001555286,0.0003191062,0.001940229,0.002433452,0.001306664,0.001745885],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001022363,"about_ca_system_score_gemma":0.004381444,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005162997,"about_ca_topic_score_gemma":0.01068516,"domain_scores_codex":[0.9950787,0.001369206,0.001019446,0.0002538333,0.001985493,0.0002932983],"domain_scores_gemma":[0.9804115,0.006898154,0.002174243,0.0006076721,0.008775312,0.001133129],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005642992,0.001247952,0.304557,0.0007757113,0.0002785555,0.0002613543,0.002213946,0.001437558,0.004338759,0.002395678,0.0418814,0.6400477],"study_design_scores_gemma":[0.0003512636,0.001879751,0.8758458,0.001812021,0.0004516056,0.001631045,0.004209887,0.02344816,0.00964895,0.003356104,0.07694328,0.0004220703],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8175025,0.001408806,0.1067988,0.003315272,0.001346576,0.01368025,0.01233033,0.004261633,0.03935583],"genre_scores_gemma":[0.6370024,0.0009741479,0.3224005,0.001266752,0.0001907615,0.01494421,0.01149289,0.0005696418,0.01115876],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008164234,"threshold_uncertainty_score":0.04317707,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04667661739479628,"score_gpt":0.3796237397971542,"score_spread":0.332947122402358,"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."}}