{"id":"W2042225150","doi":"10.1191/0265532204lt273oa","title":"Evaluation of an in-depth vocabulary knowledge measure for assessing reading performance","year":2004,"lang":"en","type":"article","venue":"Language Testing","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":237,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Test of English as a Foreign Language; Vocabulary; Reading comprehension; Reading (process); Context (archaeology); Measure (data warehouse); Test (biology); Psychology; Language proficiency; Sample (material); Vocabulary development; Mathematics education; Language assessment; Computer science; Linguistics; Teaching method","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.005204954,0.0004586938,0.0004321079,0.001784308,0.0003527467,0.0009910719,0.0008997726,0.0006165419,0.000809135],"category_scores_gemma":[0.0260272,0.0001744141,0.0004490964,0.0007387301,0.0003672121,0.001257441,0.0007220078,0.0006205713,0.0002609464],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001121133,"about_ca_system_score_gemma":0.001595734,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009828704,"about_ca_topic_score_gemma":0.03267641,"domain_scores_codex":[0.9951285,0.001304171,0.0005165302,0.0003042738,0.002522318,0.0002242592],"domain_scores_gemma":[0.9765419,0.01079436,0.004085685,0.001200044,0.006073779,0.001304202],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0007499933,0.001955929,0.8311982,0.0001957464,0.0001612497,0.000190213,0.001954512,0.001757206,0.01708511,0.0003511797,0.0005509937,0.1438496],"study_design_scores_gemma":[0.0000548773,0.003790393,0.9796784,0.00004666356,0.00006580561,0.0003343201,0.0009486981,0.005403274,0.008063748,0.0001833622,0.001395124,0.00003542263],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9945739,0.0001023362,0.002560387,0.00003932026,0.0000107754,0.0002456443,0.000177964,0.00002517858,0.002264597],"genre_scores_gemma":[0.9872411,0.0001366373,0.01083325,0.00003762513,0.00001269191,0.0003032234,0.0004538446,0.000007355715,0.000974141],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009828704,"threshold_uncertainty_score":0.0275268,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09731813955004215,"score_gpt":0.406059529447716,"score_spread":0.3087413898976738,"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."}}