{"id":"W2066392492","doi":"10.1111/medu.12490","title":"In‐training evaluations: developing an automated screening tool to measure report quality","year":2014,"lang":"en","type":"article","venue":"Medical Education","topic":"Innovations in Medical Education","field":"Medicine","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ottawa Hospital; University of Ottawa","funders":"","keywords":"Measure (data warehouse); Quality (philosophy); Medical education; Computer science; Medical physics; Training (meteorology); MEDLINE; Medicine; Psychology; Data mining","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009168893,0.0001707908,0.0003358184,0.0004919751,0.0001532966,0.00003667303,0.000187369,0.000260857,0.000518846],"category_scores_gemma":[0.07449276,0.0001672977,0.00003942247,0.001491032,0.00007698325,0.0003051263,0.0000355528,0.0004692394,0.00007057551],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004545652,"about_ca_system_score_gemma":0.005366149,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001938631,"about_ca_topic_score_gemma":0.00005129986,"domain_scores_codex":[0.9960489,0.0003176688,0.001109326,0.0004955094,0.001677289,0.0003513329],"domain_scores_gemma":[0.9978139,0.0001319239,0.0002258941,0.0006336142,0.0009805999,0.0002140402],"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":[0.00004592294,0.0005839611,0.01433409,0.0001365502,0.00002163228,0.000009277353,0.004574273,0.00002889818,0.0003713397,0.0047342,0.0332222,0.9419376],"study_design_scores_gemma":[0.001838362,0.0002184354,0.8110566,0.002435707,0.00007467081,0.0006172213,0.004441866,0.05294083,0.0002852537,0.001499838,0.1239311,0.0006600824],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8128226,0.00002597682,0.09965776,0.08246578,0.001867341,0.0007606728,4.45774e-7,0.0003773714,0.002022042],"genre_scores_gemma":[0.7896332,0.000002652272,0.15455,0.05348354,0.001187308,0.0003703439,0.0003970832,0.00003370017,0.0003422182],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9412776,"threshold_uncertainty_score":0.9519318,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1173736023270483,"score_gpt":0.4999297432818502,"score_spread":0.382556140954802,"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."}}