{"id":"W2130231021","doi":"10.1136/qshc.2006.020750","title":"Development and testing of an assessment instrument for the formative peer review of significant event analyses","year":2007,"lang":"en","type":"article","venue":"BMJ Quality & Safety","topic":"Innovations in Medical Education","field":"Medicine","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Formative assessment; Reliability (semiconductor); Content validity; Global Positioning System; Variance (accounting); Validity; Quality (philosophy); Computer science; Applied psychology; Medicine; Statistics; Psychology; Psychometrics; Mathematics; Clinical psychology; Telecommunications","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":["metaresearch"],"category_scores_codex":[0.3084365,0.001423293,0.001650572,0.007621877,0.002526526,0.00442381,0.00453532,0.00170312,0.002740039],"category_scores_gemma":[0.4055311,0.001166798,0.002517641,0.004283381,0.002466415,0.004797441,0.004278298,0.002659735,0.00159619],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004652005,"about_ca_system_score_gemma":0.02100157,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001627019,"about_ca_topic_score_gemma":0.002357982,"domain_scores_codex":[0.7018589,0.1822735,0.03816244,0.007393951,0.06713132,0.00317989],"domain_scores_gemma":[0.437843,0.2718379,0.03424478,0.03973135,0.2102752,0.006067742],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001672813,0.005190979,0.1200666,0.003982757,0.0003480125,0.0002990004,0.01937111,0.003997737,0.01064624,0.005432701,0.01067036,0.8183218],"study_design_scores_gemma":[0.003401475,0.03308742,0.626694,0.008492739,0.001053464,0.001635794,0.03001448,0.09227103,0.04917084,0.01432117,0.1386442,0.001213296],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2833022,0.00067738,0.5026553,0.002779918,0.0011572,0.1844923,0.00167784,0.003394462,0.01986331],"genre_scores_gemma":[0.1813524,0.0003582408,0.7067978,0.0004212108,0.0001935465,0.1081694,0.001061226,0.0001852605,0.001461085],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6915635,"threshold_uncertainty_score":0.8528209,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2557529337648178,"score_gpt":0.5672406763948009,"score_spread":0.3114877426299831,"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."}}