{"id":"W4389025005","doi":"10.1096/fasebj.30.1_supplement.776.7","title":"Collaborative Testing Improves Performance on Long Answer Questions, and Maintains Long‐Term Retention of Course Material","year":2016,"lang":"en","type":"article","venue":"The FASEB Journal","topic":"Innovative Teaching Methods","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"","keywords":"Test (biology); Term (time); Psychology; Significant difference; Knowledge retention; Class (philosophy); Retention rate; Medicine; Mathematics education; Medical education; Computer science; Internal medicine; Artificial intelligence; Biology; Physics","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":[0.004586702,0.00009232733,0.0001259335,0.00006672022,0.0009082027,0.00009709189,0.0001729631,0.00005234781,0.00005319703],"category_scores_gemma":[0.0008809178,0.00005139611,0.00002291066,0.0002527403,0.0005583171,0.0003336178,0.00003056141,0.0002030746,0.000003073022],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001261175,"about_ca_system_score_gemma":0.0002311419,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004560717,"about_ca_topic_score_gemma":0.00004542963,"domain_scores_codex":[0.9981034,0.001028898,0.0002422939,0.0001062235,0.0002925289,0.0002266114],"domain_scores_gemma":[0.9987433,0.0003508888,0.0003500244,0.0001055119,0.0003934338,0.00005684081],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0002212652,0.00006420314,0.253232,0.00001530658,0.00004988198,0.00001180438,0.005971787,0.000003297992,0.6428893,0.008171438,0.00009716504,0.08927255],"study_design_scores_gemma":[0.0004845472,0.0003814768,0.9387426,0.0004535197,0.00003693314,0.00003754719,0.001658095,0.00001747765,0.05650628,0.0015036,0.00003824842,0.0001396145],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9939502,0.00002673459,0.003026831,0.0009152674,0.000572434,0.000156089,0.00001528348,0.00002090471,0.001316217],"genre_scores_gemma":[0.9959333,0.00006626436,0.003034911,0.00003952,0.0005072146,0.000003001304,6.309731e-7,0.000008909759,0.0004062604],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6855106,"threshold_uncertainty_score":0.6985252,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03289744061921753,"score_gpt":0.3427438702001923,"score_spread":0.3098464295809747,"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."}}