{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003130488,0.0001159232,0.0001701122,0.0001833873,0.0000918697,0.0000286197,0.0001204321,0.00008907282,0.000684517],"category_scores_gemma":[0.001180775,0.0001191045,0.00003596853,0.0003366669,0.00002430502,0.0002627604,0.00001592381,0.0001812512,0.00001850328],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001189025,"about_ca_system_score_gemma":0.0001165607,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001404246,"about_ca_topic_score_gemma":0.00006481753,"domain_scores_codex":[0.9987161,0.000245617,0.0002819153,0.0002590074,0.0002365545,0.0002608483],"domain_scores_gemma":[0.9990966,0.0001957119,0.0001609505,0.0002437646,0.0002571928,0.00004576704],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0000292533,0.0002303176,0.01357269,0.0001056226,0.0000321651,0.00003624922,0.0734766,0.003579995,0.04331007,0.000230644,0.000007649212,0.8653888],"study_design_scores_gemma":[0.01145313,0.0005833753,0.7942628,0.001905661,0.0003484047,0.0002122004,0.1017742,0.07069571,0.01734526,0.0004423854,0.00005584531,0.0009210572],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.961946,0.003043764,0.0008335939,0.0000104177,0.0001758834,0.0002867959,0.000001583915,0.0000956072,0.03360632],"genre_scores_gemma":[0.9922594,1.295822e-7,0.007199365,0.0001514823,0.0002222943,0.00005180746,0.00002797069,0.00003035981,0.00005718436],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8644677,"threshold_uncertainty_score":0.7494982,"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."}}