{"id":"W2364152458","doi":"","title":"Family Medicine Mandatory Assessment of Progress Results of a pilot administration of a family medicine competency-based in-training examination","year":2016,"lang":"en","type":"article","venue":"PubMed Central","topic":"Innovations in Medical Education","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"St. Michael's Hospital","funders":"","keywords":"Test (biology); Family medicine; Medicine; Medical education; Educational measurement; Construct validity; MEDLINE; Competency assessment; Psychology; Psychometrics; Curriculum; Clinical psychology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005466689,0.0004110979,0.000325233,0.0007291061,0.0005234867,0.0002958609,0.000323803,0.000275214,0.001672492],"category_scores_gemma":[0.0222267,0.0002113245,0.0003860664,0.0002420135,0.0003285025,0.0003543563,0.00071445,0.0004170072,0.0004961783],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008339587,"about_ca_system_score_gemma":0.001131864,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007977765,"about_ca_topic_score_gemma":0.01135814,"domain_scores_codex":[0.9972094,0.001052032,0.0002431674,0.0002798135,0.0009003984,0.0003151499],"domain_scores_gemma":[0.9864089,0.004400447,0.001640851,0.0007030944,0.005403173,0.001443502],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.005077478,0.004314501,0.8667988,0.0002291345,0.000186827,0.0004995074,0.005972195,0.0007216646,0.02112345,0.00006750828,0.00195426,0.09305476],"study_design_scores_gemma":[0.00007534907,0.006931771,0.9823101,0.00002122865,0.00004037694,0.0001767666,0.0004970465,0.0005755681,0.008410304,0.00001184604,0.0009317498,0.00001776739],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9982882,0.00003038324,0.0003736887,0.00003816451,0.00001040705,0.000201122,0.0001305593,0.00003345961,0.0008940616],"genre_scores_gemma":[0.9973876,0.00003306442,0.001192357,0.00002758234,0.000008095963,0.0001393921,0.0003135641,0.000009768753,0.0008884976],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007977765,"threshold_uncertainty_score":0.02891093,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06866547786686188,"score_gpt":0.3584059834605909,"score_spread":0.289740505593729,"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."}}