{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1569944,0.003208248,0.01433923,0.01233193,0.0008506694,0.006482226,0.004307874,0.002182736,0.001710672],"category_scores_gemma":[0.3911814,0.001964922,0.03975581,0.01126354,0.00230853,0.005236434,0.003169201,0.002894884,0.0002140418],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004970467,"about_ca_system_score_gemma":0.005785631,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006157157,"about_ca_topic_score_gemma":0.01035251,"domain_scores_codex":[0.8246144,0.1119284,0.03956908,0.008198451,0.01480504,0.0008846289],"domain_scores_gemma":[0.6065734,0.3342241,0.02556903,0.0187192,0.01404329,0.0008709473],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"meta_analysis","study_design_gemma":"meta_analysis","study_design_scores_codex":[0.001380233,0.00004416532,0.008096296,0.2169404,0.7289261,0.0001290453,0.0009382486,0.0006800748,0.0003201911,0.0008016152,0.0008352158,0.04090842],"study_design_scores_gemma":[0.0007520349,0.000667019,0.009264308,0.06802141,0.9107859,0.000172118,0.0004297189,0.0005933147,0.0007853201,0.002001567,0.006430806,0.000096601],"study_design_candidate":"meta_analysis","study_design_consensus":"meta_analysis","genre_codex":"review","genre_gemma":"empirical","genre_scores_codex":[0.01732506,0.9678293,0.009367925,0.001242771,0.0008801899,0.001461072,0.0008934905,0.0001187081,0.0008814466],"genre_scores_gemma":[0.5769219,0.3788173,0.03214547,0.002398479,0.0006064837,0.006424193,0.001829189,0.0003264086,0.0005305325],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8430056,"threshold_uncertainty_score":0.8302758,"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."}}