{"id":"W4220985017","doi":"10.1111/vsu.13791","title":"Evaluating validity evidence for 2 instruments developed to assess students' surgical skills in a simulated environment","year":2022,"lang":"en","type":"article","venue":"Veterinary Surgery","topic":"Veterinary Practice and Education Studies","field":"Health Professions","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Prince Edward Island","funders":"","keywords":"Checklist; Content validity; Generalizability theory; Medicine; Reliability (semiconductor); Psychometrics; Clinical psychology; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.2439239,0.001215056,0.002125992,0.006166054,0.001273763,0.003891252,0.002587008,0.00394319,0.003663535],"category_scores_gemma":[0.5920367,0.001155094,0.004906639,0.00414573,0.007211112,0.004048144,0.004324768,0.002129888,0.0007151368],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004234952,"about_ca_system_score_gemma":0.007521939,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00154582,"about_ca_topic_score_gemma":0.002621652,"domain_scores_codex":[0.683538,0.185858,0.04367156,0.01117056,0.07358997,0.002171932],"domain_scores_gemma":[0.1840193,0.6835536,0.07290497,0.0137891,0.0440421,0.001690894],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0134502,0.002354536,0.6824299,0.02632375,0.01104686,0.0002408578,0.003069031,0.00134348,0.001734783,0.002828583,0.00166803,0.25351],"study_design_scores_gemma":[0.007496842,0.03383957,0.8572425,0.04672641,0.0119298,0.0009558943,0.005816722,0.007435317,0.008663977,0.005049845,0.01448065,0.0003624726],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8101957,0.1156004,0.03143698,0.007994696,0.002638739,0.008176258,0.002486907,0.0001637572,0.02130664],"genre_scores_gemma":[0.9612305,0.00857942,0.02293075,0.00166537,0.0005376386,0.003284098,0.001302914,0.00005380984,0.0004156249],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2439239,"threshold_uncertainty_score":0.9323765,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8262828402652543,"score_gpt":0.6291034980016528,"score_spread":0.1971793422636016,"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."}}