{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003050433,0.000265185,0.0004047446,0.0003561844,0.0001810002,0.00006166555,0.0008797178,0.00009549064,0.00002088518],"category_scores_gemma":[0.004633181,0.0001797441,0.0001999648,0.0005173601,0.0001006634,0.0003170335,0.0002544672,0.000914966,0.00001571874],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001463301,"about_ca_system_score_gemma":0.0001716467,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001265121,"about_ca_topic_score_gemma":0.00000253809,"domain_scores_codex":[0.9973931,0.0007306121,0.0004250737,0.0004117884,0.0006297564,0.0004097118],"domain_scores_gemma":[0.9962454,0.002362683,0.0003005138,0.0008741569,0.00008462794,0.0001326373],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"observational","study_design_scores_codex":[0.0005702051,0.0009245236,0.03802664,0.0003744864,0.0003465833,0.0001388666,0.539666,0.01063275,0.1175593,0.01016248,0.007039335,0.2745588],"study_design_scores_gemma":[0.007659421,0.009579353,0.5887513,0.009083998,0.000200319,0.00007173723,0.07170776,0.2075556,0.09837905,0.002353245,0.001574903,0.003083306],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9961543,0.00009837867,0.0006199464,0.0002019416,0.0006690085,0.0002775815,0.00001285407,0.0002518804,0.001714105],"genre_scores_gemma":[0.9918993,0.00002920681,0.007413899,0.0001328149,0.000275913,0.00001793901,0.00002366969,0.00003427824,0.0001730174],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5507247,"threshold_uncertainty_score":0.7329752,"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."}}