{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0009655377,0.0001110473,0.0001188323,0.0000888387,0.0009532226,0.0001115393,0.0003842894,0.00005532264,0.00007885817],"category_scores_gemma":[0.03555979,0.00009147055,0.00002704573,0.001128732,0.0001181554,0.0001222962,0.00006277621,0.000233851,0.00005939662],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009257929,"about_ca_system_score_gemma":0.0002977969,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0610561,"about_ca_topic_score_gemma":0.01353228,"domain_scores_codex":[0.9986054,0.0001898932,0.0002345989,0.0002051478,0.0002678884,0.0004971278],"domain_scores_gemma":[0.9978673,0.001551022,0.00008655296,0.0002198012,0.000106766,0.0001684935],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"observational","study_design_scores_codex":[0.000002479984,0.00002764066,0.08376308,0.000006508226,0.000001947626,0.00004572174,0.8534475,0.00003453374,0.0004868277,0.0004217965,0.0002865836,0.06147538],"study_design_scores_gemma":[0.0008019304,0.00008541813,0.4806236,0.0003289129,0.00001345924,0.00002905023,0.4647095,0.001137606,0.0009347451,0.000149304,0.05025275,0.0009337381],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8010755,0.0002265084,0.000002933243,0.0005168193,0.0002680528,0.0001837448,0.000002374435,0.0002081385,0.1975159],"genre_scores_gemma":[0.9903392,0.000005412271,0.003070153,0.0005809875,0.00137789,0.00002179936,0.000002244072,0.00001677681,0.004585589],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3968606,"threshold_uncertainty_score":0.9725641,"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."}}