{"id":"W2134278381","doi":"10.1177/0265532207083743","title":"The key to success: English language testing in China","year":2008,"lang":"en","type":"article","venue":"Language Testing","topic":"Multilingual Education and Policy","field":"Social Sciences","cited_by":242,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"Ministry of Education, India; Ministry of Earth Sciences","keywords":"Language assessment; China; Context (archaeology); Psychology; English language; Test (biology); Linguistics; Test of English as a Foreign Language; Language proficiency; Chinese language; Mathematics education; History","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01096668,0.0002848776,0.0004112139,0.002144826,0.003949618,0.005014567,0.001094131,0.001288224,0.00429056],"category_scores_gemma":[0.02320735,0.0002176699,0.0001887109,0.004364367,0.008342939,0.004767886,0.003733133,0.001998505,0.0003395263],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.007463609,"about_ca_system_score_gemma":0.03821543,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.08723613,"about_ca_topic_score_gemma":0.06559477,"domain_scores_codex":[0.9929419,0.002335205,0.0004975031,0.0004724337,0.002289023,0.001464019],"domain_scores_gemma":[0.9778613,0.008931503,0.003178519,0.0007986427,0.003905594,0.005324371],"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":[0.0001530115,0.0003269259,0.3462199,0.001287101,0.00004655093,0.003073614,0.04190045,0.001301723,0.001824679,0.1946201,0.03007205,0.3791739],"study_design_scores_gemma":[0.00006000548,0.0004483749,0.7214758,0.001610371,0.00007416737,0.0009092859,0.05818735,0.00280512,0.003204133,0.05148752,0.1595466,0.0001913222],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6194819,0.01485494,0.002672177,0.2125484,0.0006924016,0.0002303369,0.0002426285,0.0001161739,0.1491611],"genre_scores_gemma":[0.9883155,0.002913266,0.0006792504,0.003271846,0.0001216478,0.00005595314,0.00006687543,0.00001101544,0.004564708],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.08723613,"threshold_uncertainty_score":0.1734567,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0648421376261999,"score_gpt":0.4101903691881555,"score_spread":0.3453482315619556,"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."}}