{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00161317,0.0001016997,0.0001524602,0.0001304885,0.0002746,0.00002985932,0.0001146603,0.0001591802,0.000809163],"category_scores_gemma":[0.007097002,0.00007254407,0.00002517377,0.0004855152,0.0001534388,0.0001473256,0.00004045131,0.001158075,0.0001500048],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001276793,"about_ca_system_score_gemma":0.001355645,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001511095,"about_ca_topic_score_gemma":0.000001021217,"domain_scores_codex":[0.9984732,0.0001151918,0.0003150828,0.0002202425,0.0006938466,0.0001824092],"domain_scores_gemma":[0.9988595,0.0005152191,0.0001155436,0.0002746742,0.000150982,0.00008404482],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000002667898,0.00006871529,0.8847256,0.00008504499,0.00000868704,1.037926e-7,0.0003565072,5.514939e-7,0.00000901447,0.002752578,0.01171526,0.1002752],"study_design_scores_gemma":[0.0003127044,0.00009348984,0.9538662,0.0002149904,0.00003967412,0.00002806046,0.0007008786,0.001349068,0.000005704645,0.0003520591,0.04296181,0.00007540041],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.946035,0.00006188118,0.0002992581,0.03680314,0.0007956697,0.0003572027,1.500004e-7,0.00004997197,0.01559772],"genre_scores_gemma":[0.9870317,0.00002466987,0.001556963,0.004879417,0.0006567411,0.00005695434,0.0001293068,0.00001658736,0.005647643],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1001998,"threshold_uncertainty_score":0.8859767,"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."}}