{"id":"W4383815387","doi":"10.56230/osotl.16","title":"Does it matter when it happens? Assessing whether formative quizzes at different timepoints in a course are predictive of final exam grades","year":2023,"lang":"en","type":"article","venue":"Open Scholarship of Teaching and Learning","topic":"Evaluation of Teaching Practices","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Summative assessment; Formative assessment; Academic achievement; Psychology; Medical education; Predictive value; Mathematics education; Medicine; Internal medicine","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.01525258,0.0001826894,0.0004169772,0.0002160039,0.001408117,0.0005766994,0.000541606,0.0001316177,0.0003933012],"category_scores_gemma":[0.005590251,0.0001351605,0.00006598315,0.0001580899,0.0002100445,0.003086339,0.0004993712,0.001657647,0.00004228689],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001291141,"about_ca_system_score_gemma":0.0000772074,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003024081,"about_ca_topic_score_gemma":0.002464009,"domain_scores_codex":[0.9914895,0.00656869,0.000500721,0.0003518861,0.0007446439,0.0003445018],"domain_scores_gemma":[0.9965852,0.00211593,0.0009180188,0.0001806318,0.0001047704,0.0000954656],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00009648166,0.0001042082,0.8052152,0.00006816206,0.00005848042,0.00000362381,0.1888618,0.0003417598,0.000395778,0.0002151866,0.0004723675,0.004166952],"study_design_scores_gemma":[0.0006956621,0.0001148651,0.81534,0.001588593,0.00006429222,0.000001761328,0.1768213,0.0006368721,0.0001250588,0.001264801,0.00312239,0.0002243466],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.97022,0.00005086812,0.00005815083,0.0147136,0.0001152208,0.0003432146,0.000005538516,0.00004557118,0.01444782],"genre_scores_gemma":[0.9914115,0.00002501146,0.001348554,0.0001898367,0.00004485978,0.00002146545,0.00001112688,0.00002240657,0.006925225],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02119149,"threshold_uncertainty_score":0.9998919,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1625747681532041,"score_gpt":0.4553232299467115,"score_spread":0.2927484617935074,"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."}}