{"id":"W2275644176","doi":"10.1080/10401334.2015.1107483","title":"Continued Validation of the O-SCORE (Ottawa Surgical Competency Operating Room Evaluation): Use in the Simulated Environment","year":2016,"lang":"en","type":"article","venue":"Teaching and Learning in Medicine","topic":"Surgical Simulation and Training","field":"Medicine","cited_by":69,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Network for Innovation in Education; University of Ottawa","funders":"","keywords":"Checklist; Competence (human resources); Construct validity; Rating scale; Medicine; Orthopedic surgery; Physical therapy; Summative assessment; Psychometrics; Medical education; Psychology; Medical physics; Surgery; Clinical psychology; Formative assessment; Social psychology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006113811,0.0001048875,0.0002604185,0.00008242007,0.0001589747,0.000009948188,0.00006972469,0.00005927914,0.0002199153],"category_scores_gemma":[0.004236334,0.00004492658,0.00003283178,0.0001271555,0.000112453,0.00006449352,0.00002350026,0.0006932928,0.000001789809],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004514637,"about_ca_system_score_gemma":0.00002606033,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002417214,"about_ca_topic_score_gemma":0.00001221999,"domain_scores_codex":[0.9969738,0.001772909,0.0004319201,0.0001848877,0.0004899643,0.0001464774],"domain_scores_gemma":[0.9969992,0.002638906,0.0001308043,0.0001611903,0.00003091883,0.00003898956],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00006200941,0.00007340936,0.9243644,0.00001424645,0.00001366341,0.00001418678,0.006640204,0.01467385,0.001034296,0.0004041093,0.00000978865,0.05269578],"study_design_scores_gemma":[0.0111478,0.0002186564,0.9305592,0.001217224,0.00006509355,0.00002583556,0.001792927,0.04860701,0.00004604091,0.00006071704,0.006167537,0.00009194291],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9935708,0.0001232348,0.0001021652,0.003846038,0.00004480643,0.0003434719,3.172783e-7,0.00001804765,0.001951111],"genre_scores_gemma":[0.999327,0.00001338145,0.0001000445,0.0002071259,0.00007492258,0.000005592471,0.00001220655,0.000008832003,0.0002508943],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05260384,"threshold_uncertainty_score":0.5071593,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05090694704738861,"score_gpt":0.322860002834169,"score_spread":0.2719530557867804,"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."}}