{"id":"W3194429716","doi":"10.1007/978-981-16-3603-5_4","title":"Global ESOL Assessment Practices: The Washback Effect and Automated Testing in China","year":2021,"lang":"en","type":"book-chapter","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Yorkville University","funders":"","keywords":"Language assessment; German; China; Foreign language; Test (biology); Language education; Computer science; Language industry; Mathematics education; Pedagogy; Comprehension approach; Psychology; Political science; Linguistics","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":[],"consensus_categories":[],"category_scores_codex":[0.001692516,0.0003186043,0.0004190027,0.00004883023,0.0004749907,0.000542494,0.000377028,0.0003118639,0.0007708602],"category_scores_gemma":[0.0005034179,0.0002209403,0.00008823051,0.0001975493,0.0002443655,0.0002211788,0.0002766702,0.0004154204,0.00002666139],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003686612,"about_ca_system_score_gemma":0.0004963941,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003317518,"about_ca_topic_score_gemma":0.008595009,"domain_scores_codex":[0.9977234,0.000290689,0.0003324882,0.0004819016,0.0007931013,0.0003784424],"domain_scores_gemma":[0.9978336,0.001213836,0.0005177681,0.0002501652,0.00008960051,0.00009500724],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.00002661552,0.000111671,0.3115983,0.0001492488,0.0003848427,0.0002415855,0.003081281,0.00001194922,0.000008999306,0.648923,0.009687291,0.02577529],"study_design_scores_gemma":[0.002760659,0.0006105349,0.688629,0.001602257,0.0007753531,0.00003353521,0.007465474,0.004085657,0.000001849417,0.01066141,0.2812022,0.002172108],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.003944823,0.000454836,0.000007412649,0.00146246,0.000387084,0.0008412187,0.000006421629,0.0002758672,0.9926199],"genre_scores_gemma":[0.2347129,0.001317262,0.003338133,0.0005672557,0.001131705,0.00009096236,0.00006569008,0.00008110275,0.758695],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.6382616,"threshold_uncertainty_score":0.9009683,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03885743439082492,"score_gpt":0.3910353222358748,"score_spread":0.3521778878450499,"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."}}