{"id":"W2920932416","doi":"10.1016/j.jss.2019.02.006","title":"The Resident Report Card: A Tool for Operative Feedback and Evaluation of Technical Skills","year":2019,"lang":"en","type":"article","venue":"Journal of Surgical Research","topic":"Surgical Simulation and Training","field":"Medicine","cited_by":20,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Formative assessment; Cohort; Medicine; Curriculum; Medical education; Medical physics; Hum; Family medicine; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01735934,0.00005984153,0.0003036226,0.0001152438,0.00009560366,0.00003670812,0.00007986333,0.0000815824,0.0002008218],"category_scores_gemma":[0.004225384,0.00003173985,0.0001449676,0.0002268914,0.0001558231,0.0000724804,0.00004772018,0.0004383412,0.000004244134],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001356237,"about_ca_system_score_gemma":0.0004157986,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006124338,"about_ca_topic_score_gemma":0.000002057041,"domain_scores_codex":[0.996665,0.000356079,0.0006237344,0.0001267158,0.002027727,0.0002007272],"domain_scores_gemma":[0.9923612,0.004159504,0.0001693512,0.0001646076,0.003006246,0.0001390391],"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":[0.03641853,0.001998536,0.2676873,0.0005154045,0.001528183,0.003362784,0.002827483,0.001722437,0.02496549,0.02265739,0.006058292,0.6302582],"study_design_scores_gemma":[0.05826327,0.009572331,0.6915838,0.001685026,0.0004195078,0.007454492,0.003379898,0.01136644,0.006519373,0.007331935,0.2020645,0.0003595014],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9861361,0.0004896367,0.00001203561,0.002537493,0.00007113234,0.0007019512,0.000001133919,0.000002601175,0.01004787],"genre_scores_gemma":[0.9984363,0.0002067404,0.000137022,0.00001250517,0.0001401654,0.00001080941,0.000001643604,0.00000743535,0.001047393],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6298987,"threshold_uncertainty_score":0.6016437,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1312943573604302,"score_gpt":0.5112539235385435,"score_spread":0.3799595661781133,"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."}}