{"id":"W3183541999","doi":"10.1002/prp2.833","title":"Answering questions in a co‐created formative exam question bank improves summative exam performance, while students perceive benefits from answering, authoring, and peer discussion: A mixed methods analysis of PeerWise","year":2021,"lang":"en","type":"article","venue":"Pharmacology Research & Perspectives","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Summative assessment; Formative assessment; Test (biology); Medical education; Multiple choice; Peer assessment; Class (philosophy); Psychology; Mathematics education; Computer science; Medicine; Internal medicine; Artificial intelligence","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":[0.02213337,0.0004363766,0.0005249497,0.001117271,0.001053827,0.002248863,0.0009804995,0.0006726256,0.002727011],"category_scores_gemma":[0.04848852,0.0003705213,0.001517456,0.0007400418,0.0007534106,0.001087096,0.001574835,0.0007032724,0.000468899],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001226946,"about_ca_system_score_gemma":0.003497158,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001905298,"about_ca_topic_score_gemma":0.004876623,"domain_scores_codex":[0.9843559,0.009338977,0.001626989,0.001116436,0.002829807,0.0007319273],"domain_scores_gemma":[0.9578112,0.02523145,0.006553674,0.00244621,0.006308625,0.001648787],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.004583695,0.009443257,0.6073354,0.001854398,0.001837089,0.0002101159,0.04596496,0.0009651156,0.01223446,0.002080207,0.002212747,0.3112785],"study_design_scores_gemma":[0.0003961563,0.01778612,0.9091272,0.0009069098,0.001596463,0.0002756867,0.02204369,0.004207032,0.02337499,0.001682115,0.01841622,0.0001874545],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9927677,0.0002473958,0.004441394,0.0001789483,0.00002958156,0.0006823197,0.0002784609,0.00003251026,0.0013417],"genre_scores_gemma":[0.9881608,0.0001665607,0.00753744,0.000165548,0.00002346684,0.002003761,0.0002391907,0.00002347472,0.001679666],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02213337,"threshold_uncertainty_score":0.1170538,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0832141660436603,"score_gpt":0.5168632575806068,"score_spread":0.4336490915369465,"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."}}