{"id":"W4389150341","doi":"10.1111/medu.15287","title":"Timing's not everything: Immediate and delayed feedback are equally beneficial for performance in formative multiple‐choice testing","year":2023,"lang":"en","type":"article","venue":"Medical Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"The Wilson Centre; University of Toronto","funders":"University of Melbourne","keywords":"Formative assessment; Psychology; Medical education; Medicine; Computer science; Mathematics education","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"],"consensus_categories":[],"category_scores_codex":[0.001420356,0.0001023706,0.0001508267,0.0001361635,0.0004177636,0.00007131634,0.0001951373,0.0001338973,0.00003540816],"category_scores_gemma":[0.01109383,0.0001007525,0.00002656917,0.0005650402,0.0001094529,0.0003671474,0.0000585692,0.0001737072,0.00002695269],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001256584,"about_ca_system_score_gemma":0.0007704786,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006738343,"about_ca_topic_score_gemma":0.002478361,"domain_scores_codex":[0.9984825,0.00006956682,0.0002849316,0.0002071412,0.000590656,0.0003652307],"domain_scores_gemma":[0.997606,0.001906128,0.0001445006,0.00006721531,0.0001459637,0.0001302221],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001180188,0.0003061437,0.6789207,0.0001695718,0.00002355991,0.000001739361,0.136988,0.00004056318,0.00006046361,0.000614404,0.006699132,0.1760577],"study_design_scores_gemma":[0.0009564277,0.00007909102,0.9351023,0.0002189602,0.00001608121,5.709287e-7,0.03275819,0.02287567,0.0000184418,0.0002300075,0.00753098,0.0002133184],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9907428,0.000036686,0.00006047626,0.006279228,0.0009490188,0.000433629,0.00000410947,0.00007704448,0.001416984],"genre_scores_gemma":[0.9972656,0.00009454503,0.0005269952,0.0008322325,0.0007184792,0.0001372529,0.00004162073,0.00001091488,0.0003723766],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2561816,"threshold_uncertainty_score":0.9972361,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06026460928659012,"score_gpt":0.3781464413277802,"score_spread":0.3178818320411901,"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."}}