{"id":"W2766940338","doi":"10.1016/j.jamcollsurg.2017.07.389","title":"Assessing the Reliability and Validity of Technical Skill Assessment Tools and the Impact of Rater Training","year":2017,"lang":"en","type":"article","venue":"Journal of the American College of Surgeons","topic":"Innovations in Medical Education","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"","keywords":"Medicine; Inter-rater reliability; Reliability (semiconductor); Validity; Medical education; Medical physics; Applied psychology; Psychometrics; Rating scale; 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":[0.1458554,0.0008788782,0.0009060619,0.002217873,0.0008092556,0.001253035,0.0010212,0.001041625,0.0009453731],"category_scores_gemma":[0.3736172,0.0004382858,0.002038877,0.001440038,0.001651642,0.001940834,0.00225027,0.001237126,0.0004685133],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00132116,"about_ca_system_score_gemma":0.002365348,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001734597,"about_ca_topic_score_gemma":0.002846253,"domain_scores_codex":[0.8454044,0.09904175,0.01512731,0.007375727,0.03096385,0.002086951],"domain_scores_gemma":[0.4479875,0.4103439,0.0495053,0.02597014,0.06408294,0.002110314],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.003654151,0.001666149,0.8159662,0.0008199135,0.00167996,0.00009644487,0.005619965,0.002576296,0.003897186,0.000641402,0.001050889,0.1623313],"study_design_scores_gemma":[0.0004048059,0.01265052,0.9591801,0.0004357448,0.001143915,0.0004378158,0.001092522,0.01401651,0.006728571,0.0008727866,0.002867627,0.0001690995],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.971187,0.001692829,0.02102919,0.0003478068,0.0002355234,0.001359068,0.0002494441,0.0001156176,0.003783568],"genre_scores_gemma":[0.9769692,0.0003123291,0.02066147,0.0001540492,0.0001342046,0.0010703,0.000215671,0.00004138034,0.0004414378],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8541446,"threshold_uncertainty_score":0.7713663,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0556049049498519,"score_gpt":0.4208911937058103,"score_spread":0.3652862887559584,"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."}}