{"id":"W4382796332","doi":"10.5539/elt.v16n7p103","title":"On the Impact of Teacher-Made Vocabulary Tests vs. Standardized Vocabulary Tests on Reading Comprehension Performance of Iraqi Intermediate EFL Learners","year":2023,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Educational Methods and Media Use","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Vocabulary; Reading comprehension; Psychology; Mathematics education; Test (biology); Reading (process); Comprehension; Standardized test; Vocabulary development; Pedagogy; Teaching method; Linguistics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001364622,0.0002941248,0.0003019529,0.0002391196,0.0001739192,0.0003378337,0.0002042446,0.0002369719,0.002525465],"category_scores_gemma":[0.01116929,0.00008281788,0.0003745583,0.0001466451,0.0002528659,0.0003163443,0.0002932677,0.0003664984,0.0003379754],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001964893,"about_ca_system_score_gemma":0.0003536108,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00117489,"about_ca_topic_score_gemma":0.001953899,"domain_scores_codex":[0.9987227,0.0006481336,0.0000999601,0.0001262588,0.0002932485,0.0001095709],"domain_scores_gemma":[0.9903263,0.006554227,0.00132013,0.0002832972,0.0008283154,0.0006877446],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.01034497,0.01166973,0.5294347,0.000788542,0.0004100412,0.0008339253,0.01507821,0.001350032,0.05849988,0.0002263183,0.001459966,0.3699037],"study_design_scores_gemma":[0.0001911934,0.03036813,0.9418074,0.00008277524,0.0001868264,0.0003053289,0.00425755,0.000678411,0.01957956,0.0001108414,0.002397788,0.00003406234],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9989649,0.00007974816,0.00006855708,0.00002893978,0.000007151827,0.00001430972,0.00001499912,0.000005581286,0.0008157252],"genre_scores_gemma":[0.9987226,0.000104891,0.0004093102,0.00002165974,0.000009702301,0.00002592356,0.00004622489,0.000004423264,0.0006552821],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002525465,"threshold_uncertainty_score":0.008448541,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02099404228223429,"score_gpt":0.3261173978408372,"score_spread":0.3051233555586029,"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."}}