{"id":"W2971231166","doi":"10.1111/medu.13935","title":"Beyond ‘driving’: The relationship between assessment, performance and learning","year":2019,"lang":"en","type":"article","venue":"Medical Education","topic":"Innovations in Medical Education","field":"Medicine","cited_by":84,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Formative assessment; Curriculum; Assessment for learning; Mythology; Psychology; Summative assessment; Medical education; Computer science; Mathematics education; Pedagogy; Medicine","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":[],"consensus_categories":[],"category_scores_codex":[0.02164452,0.0004618893,0.0004362982,0.001878182,0.001147804,0.008411773,0.001417054,0.002046761,0.006471962],"category_scores_gemma":[0.1345128,0.0002450254,0.0002995601,0.002344826,0.01115211,0.007400488,0.005024982,0.003599995,0.001001201],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002463219,"about_ca_system_score_gemma":0.003211758,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002257479,"about_ca_topic_score_gemma":0.001473519,"domain_scores_codex":[0.9684245,0.02139524,0.001345978,0.002617224,0.005433938,0.0007832031],"domain_scores_gemma":[0.7922211,0.1640092,0.01902694,0.004614022,0.01476401,0.005364787],"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":[0.0005272971,0.0006420789,0.2144469,0.00204139,0.0002826099,0.0004313929,0.04497619,0.002541475,0.000924195,0.2788728,0.02238129,0.4319325],"study_design_scores_gemma":[0.00007853572,0.001868791,0.4568232,0.005261759,0.0002126438,0.001380485,0.03474875,0.009142346,0.001616721,0.3725643,0.1158487,0.0004538803],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.379107,0.05813306,0.09522244,0.1662572,0.003088801,0.000509427,0.00050299,0.0009451213,0.296234],"genre_scores_gemma":[0.9819067,0.002853601,0.008195092,0.00298337,0.0005588045,0.0001913112,0.00006623016,0.0001074561,0.003137524],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02164452,"threshold_uncertainty_score":0.1144685,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01711462559164947,"score_gpt":0.3671892593153332,"score_spread":0.3500746337236837,"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."}}