{"id":"W3049364633","doi":"10.1007/s40037-020-00606-z","title":"Beyond right or wrong: More effective feedback for formative multiple-choice tests","year":2020,"lang":"en","type":"article","venue":"Perspectives on Medical Education","topic":"Memory Processes and Influences","field":"Neuroscience","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"The Wilson Centre; University of Toronto","funders":"","keywords":"Formative assessment; Multiple choice; Computer science; Medical education; Medical physics; Management science; Psychology; Medicine; Mathematics education; Mathematics; Statistics; Engineering","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":[0.01431287,0.001032557,0.0008088698,0.0008372336,0.0002530171,0.001302272,0.001046367,0.0008656135,0.007711543],"category_scores_gemma":[0.09137177,0.000253279,0.0004236345,0.0004245536,0.0003810895,0.001353333,0.0009704821,0.0007561759,0.001153902],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004109081,"about_ca_system_score_gemma":0.0007851443,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005010862,"about_ca_topic_score_gemma":0.0007407527,"domain_scores_codex":[0.988557,0.00674559,0.0006913659,0.0007077737,0.003038376,0.0002598571],"domain_scores_gemma":[0.8985283,0.08531297,0.005927835,0.003685386,0.004954616,0.001590935],"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":[0.00696151,0.00406227,0.03615987,0.001161497,0.0001071395,0.0002356401,0.001966417,0.002229795,0.04196319,0.0005392479,0.002490737,0.9021228],"study_design_scores_gemma":[0.006720691,0.07807983,0.5633129,0.002888902,0.0009445242,0.003785711,0.002351238,0.05823189,0.2299949,0.01044419,0.04255152,0.0006936724],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9231834,0.0006423832,0.0681554,0.0008602393,0.0001393772,0.001136616,0.0002842946,0.001088624,0.004509587],"genre_scores_gemma":[0.839809,0.0004301357,0.1561477,0.000379147,0.0001555684,0.0009180171,0.0002899021,0.0001245882,0.001745886],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01431287,"threshold_uncertainty_score":0.07569456,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02888549548732569,"score_gpt":0.3561502694130367,"score_spread":0.327264773925711,"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."}}