{"id":"W2624412722","doi":"10.3102/0034654316689306","title":"Rethinking the Use of Tests: A Meta-Analysis of Practice Testing","year":2017,"lang":"en","type":"article","venue":"Review of Educational Research","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":536,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Psychology; Meta-analysis; Test (biology); Best practice; Presentation (obstetrics); Mathematics education; Applied psychology; 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":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01333356,0.00005219842,0.0004587626,0.0001412096,0.0006692388,0.00008326961,0.0009011544,0.00002788055,0.0014831],"category_scores_gemma":[0.1543893,0.00003318381,0.0003584912,0.001219851,0.0007048753,0.0003956729,0.0001572289,0.0001771927,0.000007481653],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004670007,"about_ca_system_score_gemma":0.001123243,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006231942,"about_ca_topic_score_gemma":0.0004336831,"domain_scores_codex":[0.9963712,0.001128286,0.0004194855,0.0001411301,0.001776495,0.0001633773],"domain_scores_gemma":[0.9671686,0.02814018,0.0007928132,0.0006104821,0.003246295,0.00004163515],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.00002744297,0.001441232,0.2150051,0.00393856,0.07487441,8.058294e-7,0.03111603,0.00002031982,0.0003698409,0.6287912,0.03585434,0.00856071],"study_design_scores_gemma":[0.0001640399,0.0001353945,0.5232499,0.002957338,0.1197802,9.254803e-7,0.007367696,0.00008137718,0.00005583377,0.01051603,0.335398,0.0002933253],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.03606445,0.2325587,0.00001237089,0.3699527,0.0002572706,0.002796807,0.00006019995,0.000007462227,0.35829],"genre_scores_gemma":[0.8991355,0.07381168,0.01773002,0.0005213657,0.0002724349,0.0001530594,0.0000148891,0.00001342292,0.008347641],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.863071,"threshold_uncertainty_score":0.9994297,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7954275058930537,"score_gpt":0.643213236651155,"score_spread":0.1522142692418986,"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."}}