{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002743894,0.0003561832,0.0003024121,0.002132226,0.001252481,0.00163064,0.001071262,0.0003771208,0.00300542],"category_scores_gemma":[0.004237963,0.0001489924,0.0002641001,0.004497968,0.00214353,0.001937993,0.00148417,0.0006002617,0.0001894623],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005628615,"about_ca_system_score_gemma":0.009244754,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.1480384,"about_ca_topic_score_gemma":0.1801477,"domain_scores_codex":[0.998023,0.0005430849,0.0001270918,0.000276837,0.000713532,0.000316461],"domain_scores_gemma":[0.9971642,0.0009916537,0.0004146338,0.000330715,0.0006636102,0.0004351746],"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":[0.0001508692,0.0002041392,0.4535939,0.0002232732,0.00004957684,0.000536359,0.02278696,0.003009086,0.001417854,0.02128315,0.006972352,0.4897726],"study_design_scores_gemma":[0.00001623076,0.0002170542,0.9650242,0.0001053657,0.00003602103,0.0001297732,0.009693056,0.004665163,0.0008328882,0.004610606,0.01463662,0.00003309238],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9626268,0.002095842,0.001533293,0.002268816,0.0000478996,0.00004562716,0.000182188,0.00009322438,0.03110642],"genre_scores_gemma":[0.9926019,0.0004317076,0.000438538,0.00008518347,0.00001029096,0.00001337093,0.00007253385,0.00001103619,0.006335405],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1480384,"threshold_uncertainty_score":0.2943535,"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."}}