{"id":"W4410358712","doi":"10.1080/29984475.2025.2501997","title":"Protocol for a Systematic Review of the Impact of Test Preparation Practices on L2 Test Performance and Language Proficiency","year":2025,"lang":"en","type":"review","venue":"Research Synthesis in Applied Linguistics","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke; Western University","funders":"","keywords":"Protocol (science); Test (biology); Computer science; Test preparation; Medicine; Engineering; Biology; Manufacturing engineering","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"],"consensus_categories":[],"category_scores_codex":[0.009082586,0.0002277124,0.001409746,0.0002697582,0.0002622406,0.00006652352,0.0008169725,0.000179077,0.00001422143],"category_scores_gemma":[0.2111604,0.0001314371,0.0002203637,0.001145503,0.0003259507,0.00001695751,0.0001560413,0.00037344,0.000002675427],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003123366,"about_ca_system_score_gemma":0.002042772,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001066497,"about_ca_topic_score_gemma":0.00002903388,"domain_scores_codex":[0.9965168,0.0007676702,0.0009783136,0.0003235291,0.001060788,0.000352853],"domain_scores_gemma":[0.9687243,0.02854184,0.001668846,0.0005252584,0.0004926525,0.00004711209],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","study_design_scores_codex":[0.00001498064,0.000337882,0.0001497218,0.9907719,0.00003814188,2.688541e-7,0.0005941041,2.677456e-7,0.00000103294,0.001964009,0.0002653027,0.005862318],"study_design_scores_gemma":[0.0001161803,0.000212061,0.00002724522,0.9758402,0.0003254426,1.722489e-7,0.0005401401,0.00004329642,0.0000200152,0.00004216559,0.02267023,0.0001628605],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","genre_codex":"protocol","genre_gemma":"review","genre_scores_codex":[0.000004204814,0.3683255,0.000001613264,0.00002159898,0.00004647377,0.5038844,0.0001105072,0.00001925101,0.1275865],"genre_scores_gemma":[0.00102957,0.724506,0.0001471219,0.000002527518,0.0001416559,0.2737674,0.000003199022,0.00001626975,0.0003862702],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.3561806,"threshold_uncertainty_score":0.7954843,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1636298798766739,"score_gpt":0.5843519821444451,"score_spread":0.4207221022677712,"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."}}