{"id":"W2008716813","doi":"10.1177/02655322100270020902","title":"Book Review: Chapelle, C. A., Enright, M. K. and Jamieson, J. M. (Eds) Building a validity argument for the Test of English as a Foreign LanguageTM. New York and London: Routledge, Taylor & Francis Group, 2008. 370 + xiii pp. ISBN 0-8058-5456-8 (paperback)","year":2010,"lang":"en","type":"article","venue":"Language Testing","topic":"Second Language Learning and Teaching","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Argument (complex analysis); Psychology; Media studies; Sociology; Chemistry","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001151292,0.0004436734,0.0006064206,0.00007394607,0.0008023667,0.0003095491,0.0003551946,0.0001293983,0.002957284],"category_scores_gemma":[0.008583907,0.0003212995,0.0001589003,0.0001248076,0.0002666852,0.0002818437,0.0001592805,0.0008021006,0.00001712955],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002142124,"about_ca_system_score_gemma":0.00003339619,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00363965,"about_ca_topic_score_gemma":0.001693097,"domain_scores_codex":[0.9978285,0.0001057758,0.0005898332,0.00057793,0.0003049045,0.0005930815],"domain_scores_gemma":[0.9947553,0.003806219,0.0004404046,0.0005851861,0.0002132917,0.0001995592],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001146815,0.0003908697,0.004205833,0.004110138,0.0003665026,0.00009926048,0.3057957,0.000009684885,0.0100645,0.009356162,0.320109,0.3453777],"study_design_scores_gemma":[0.001272591,0.0002623545,0.0001638814,0.0008582528,0.0003028367,0.0000695881,0.00824815,0.0005694057,0.0004161964,0.0001862984,0.9870526,0.0005978713],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"empirical","genre_scores_codex":[0.131136,0.8487833,0.0003672437,0.0004315142,0.0008085498,0.001519179,0.0001108099,0.0004269607,0.01641643],"genre_scores_gemma":[0.824583,0.008115415,0.03460341,0.03495795,0.02450156,0.0006593799,0.0003469762,0.0006830742,0.07154923],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8406678,"threshold_uncertainty_score":0.9999239,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02347074940022355,"score_gpt":0.2445379187758677,"score_spread":0.2210671693756441,"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."}}