{"id":"W3096953036","doi":"10.1080/0142159x.2020.1841128","title":"Exploring the connections between programmatic assessment and program evaluation within competency-based medical education programs","year":2020,"lang":"en","type":"article","venue":"Medical Teacher","topic":"Innovations in Medical Education","field":"Medicine","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Medical education; Program evaluation; Competency assessment; Evaluation methods; Self-assessment; Computer science; Medicine; Psychology; Political science; Pedagogy; Engineering","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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003983767,0.0002256579,0.0003516557,0.0001056942,0.0002739551,0.00007933964,0.0002501714,0.0002181389,0.001604569],"category_scores_gemma":[0.008542204,0.000151392,0.00007789792,0.001010221,0.0005592925,0.0001501473,0.00006770829,0.001361577,0.00003119271],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000268435,"about_ca_system_score_gemma":0.008343681,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003932641,"about_ca_topic_score_gemma":0.0000163304,"domain_scores_codex":[0.9948696,0.0004328983,0.0007677081,0.0004507398,0.003140196,0.000338807],"domain_scores_gemma":[0.9982834,0.00006954833,0.0001848457,0.0003512141,0.0004457013,0.0006652774],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001361681,0.001146435,0.1462477,0.0002226209,0.00007810355,0.000003265723,0.001280364,0.000001326723,0.000001495728,0.002372514,0.001381576,0.847251],"study_design_scores_gemma":[0.003402615,0.001499536,0.07070564,0.001545244,0.0008060631,0.00006575598,0.005478099,0.8905751,0.0000135072,0.001106534,0.02438139,0.0004204928],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7690719,0.0001045233,0.002359977,0.2220488,0.0005717175,0.004034276,2.432936e-7,0.0003565806,0.001451985],"genre_scores_gemma":[0.9744056,0.00001476898,0.01288396,0.003741872,0.001568502,0.006905156,0.0003800498,0.00004095979,0.00005906935],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8905738,"threshold_uncertainty_score":0.9998093,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1869079731289644,"score_gpt":0.4421498276901076,"score_spread":0.2552418545611432,"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."}}