{"id":"W4407931412","doi":"10.1177/02655322251319284","title":"The relationship between English language proficiency test scores and academic achievement: A longitudinal study of two tests","year":2025,"lang":"en","type":"article","venue":"Language Testing","topic":"Higher Education Learning Practices","field":"Social Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Psychology; Language proficiency; Test (biology); Language assessment; Achievement test; Academic achievement; Mathematics education; English language; Test of English as a Foreign Language; Standardized test","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.002328164,0.0001025564,0.0001320046,0.00009088909,0.001164699,0.0001345145,0.000347256,0.00005616074,0.000008894818],"category_scores_gemma":[0.05939497,0.00008349853,0.00001636122,0.001056104,0.0002297645,0.000265949,0.0001063877,0.0004853095,0.000004470698],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000503164,"about_ca_system_score_gemma":0.0001958426,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004684316,"about_ca_topic_score_gemma":0.001946799,"domain_scores_codex":[0.9983624,0.0004655701,0.0003153876,0.0002452123,0.0003403035,0.0002711549],"domain_scores_gemma":[0.9808006,0.01849031,0.0002943639,0.0002178268,0.0001387672,0.00005815417],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000001580898,0.00006401684,0.8198246,0.00001545275,0.000008235719,0.000001833293,0.1757089,0.000003336502,0.00009713515,0.001594217,0.00001883568,0.002661781],"study_design_scores_gemma":[0.0002238726,0.00005792698,0.8783645,0.00008695196,0.00004788189,2.585959e-7,0.1208417,0.00000606608,0.00002120016,0.0001745028,0.0001020989,0.00007299994],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9916908,0.0009025748,0.00001466173,0.000652093,0.0001263449,0.0004682189,0.000002441846,0.0001423895,0.00600044],"genre_scores_gemma":[0.9974722,0.000002597353,0.0005632708,0.0000238835,0.0002798169,0.00003536675,0.000001987813,0.000009082518,0.001611793],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05853987,"threshold_uncertainty_score":0.9485282,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1073036299005186,"score_gpt":0.4529902981757598,"score_spread":0.3456866682752412,"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."}}