{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005700863,0.0002800191,0.0007134087,0.001204328,0.000957604,0.0002058151,0.0005012124,0.0001999813,0.0008259972],"category_scores_gemma":[0.0008119964,0.0002398357,0.0001524561,0.002938811,0.001085783,0.001045471,0.0004544411,0.0008204043,0.000006477201],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006623521,"about_ca_system_score_gemma":0.0003653829,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003222762,"about_ca_topic_score_gemma":0.00421031,"domain_scores_codex":[0.9922923,0.004274209,0.0005018188,0.0007823506,0.001371942,0.0007773353],"domain_scores_gemma":[0.9965599,0.001325817,0.0001930627,0.0002202748,0.001426381,0.0002745469],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"observational","study_design_scores_codex":[0.000354689,0.001056037,0.4154256,0.00004187544,0.002346711,0.00002885633,0.5476269,0.0002923447,0.02574639,0.001453434,0.0004305175,0.005196645],"study_design_scores_gemma":[0.000914013,0.0001724971,0.720435,0.00007424169,0.0004075425,5.836537e-7,0.2710301,0.002552542,0.003696519,0.0001331351,0.0003631049,0.0002206772],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.992117,0.001307431,0.0001957662,0.001400632,0.0002438279,0.0007382965,0.00007536852,0.00006795088,0.003853651],"genre_scores_gemma":[0.9927993,0.003471605,0.001741119,0.00001515837,0.0001575563,0.0002701096,0.00007017438,0.00002123427,0.001453759],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3050094,"threshold_uncertainty_score":0.9780215,"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."}}