{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01682012,0.00009550447,0.0003407539,0.00005974404,0.0001028021,0.000003373044,0.00008208442,0.0000384709,0.00002637545],"category_scores_gemma":[0.005350544,0.00006037233,0.00004855759,0.0003557201,0.0001085849,0.00006313399,0.00003534745,0.000118342,3.144316e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000180081,"about_ca_system_score_gemma":0.0006308752,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005825986,"about_ca_topic_score_gemma":0.000007291803,"domain_scores_codex":[0.9971032,0.00008886679,0.001721109,0.0001367961,0.0008039804,0.0001460515],"domain_scores_gemma":[0.996793,0.0007191929,0.0006583864,0.0002842797,0.001494116,0.00005104728],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0001844775,0.0006160518,0.005047998,0.01043399,0.0002416683,5.958221e-7,0.004405034,0.000007443769,0.002834632,0.005384338,0.001251279,0.9695925],"study_design_scores_gemma":[0.001906955,0.0005167983,0.9042415,0.008250277,0.0004443792,0.00001435094,0.02644328,0.001625058,0.02450314,0.0003551877,0.03143319,0.0002658729],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7578446,0.000744672,0.2186294,0.01726764,0.0002296764,0.00372765,0.00003084744,0.0000233807,0.001502158],"genre_scores_gemma":[0.7139458,0.000126955,0.2842456,0.001299065,0.00006557132,0.00009121562,0.0001590138,0.000007584115,0.00005928122],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9693266,"threshold_uncertainty_score":0.6405487,"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."}}