{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01131658,0.0004166438,0.0004501826,0.0003974944,0.0002182173,0.001193437,0.0006724551,0.0008641203,0.005859503],"category_scores_gemma":[0.08844522,0.0002611637,0.0004223796,0.0003097635,0.0003631818,0.001218003,0.0007512015,0.0006786612,0.0005804089],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003097254,"about_ca_system_score_gemma":0.001117277,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004562826,"about_ca_topic_score_gemma":0.0007797405,"domain_scores_codex":[0.9924644,0.004063604,0.0006828113,0.0004814821,0.002122908,0.0001849129],"domain_scores_gemma":[0.90679,0.07345378,0.01162674,0.001952287,0.002617142,0.003560016],"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":[0.02787119,0.005453929,0.130265,0.001864197,0.0002993992,0.0002262766,0.001419478,0.00139458,0.0465116,0.0006195546,0.001832376,0.7822425],"study_design_scores_gemma":[0.002381277,0.08399832,0.8333356,0.001821614,0.001050899,0.002154076,0.001368898,0.009104489,0.05283739,0.002820989,0.008904574,0.0002218778],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9846262,0.001336612,0.008594497,0.0008186712,0.0002776046,0.0002566764,0.0001033798,0.0001828899,0.003803495],"genre_scores_gemma":[0.9841733,0.0003389872,0.01399633,0.0002247916,0.00007942775,0.0001407738,0.00007542823,0.00003493127,0.0009360136],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01131658,"threshold_uncertainty_score":0.05984855,"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."}}