{"id":"W2537151320","doi":"10.1016/j.jsurg.2016.08.017","title":"Utility of a Validated Rating Scale for Self-Assessment in Microsurgical Training","year":2016,"lang":"en","type":"article","venue":"Journal of surgical education","topic":"Surgical Simulation and Training","field":"Medicine","cited_by":19,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Preceptor; Knot tying; Inter-rater reliability; Self-assessment; Rating scale; Medicine; Physical therapy; Tying; Psychology; Medical education; Surgery; Computer science; Developmental psychology","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":[0.001301528,0.0000947315,0.0004317231,0.0001699899,0.00003018559,0.00001043679,0.00005734167,0.00009135967,0.0003189363],"category_scores_gemma":[0.0001860902,0.00005887739,0.0002067905,0.000236592,0.00004415978,0.0001339285,0.000009529451,0.000167447,9.873489e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009314752,"about_ca_system_score_gemma":0.0009200087,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004011426,"about_ca_topic_score_gemma":0.000001299696,"domain_scores_codex":[0.9984124,0.0001015217,0.000896137,0.0001301514,0.0002864114,0.0001733915],"domain_scores_gemma":[0.9980626,0.0008382432,0.0004146698,0.00008989293,0.0004229604,0.0001716492],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.003193537,0.004319781,0.5043326,0.0002866175,0.000138166,0.00005020924,0.003322233,0.00002863149,0.01274978,0.001655751,0.0002623735,0.4696603],"study_design_scores_gemma":[0.04239333,0.001204113,0.8591788,0.00251227,0.0002545092,0.0007924291,0.004400925,0.003196591,0.009190738,0.001694474,0.07480711,0.0003746795],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9940111,0.00006934366,0.001036447,0.002115388,0.000255759,0.000217,0.000002767451,0.0000110886,0.002281132],"genre_scores_gemma":[0.9921042,0.00004688277,0.007496213,0.00005453093,0.0002175334,0.000006059514,0.000004500017,0.000009527638,0.00006060314],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4692856,"threshold_uncertainty_score":0.3492129,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04717359042701361,"score_gpt":0.3832415723585543,"score_spread":0.3360679819315406,"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."}}