{"id":"W3128610517","doi":"10.1016/j.stueduc.2021.100977","title":"The long-term washback effects of the National Matriculation English Test on college English learning in China: Tertiary student perspectives","year":2021,"lang":"en","type":"article","venue":"Studies In Educational Evaluation","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":31,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Matriculation; Active listening; Competence (human resources); Psychology; Test (biology); College English; Curriculum; Perception; Mathematics education; China; Medical education; Pedagogy; Medicine; Political science","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":[0.002655667,0.0001183874,0.0001480522,0.0001058725,0.000732247,0.00005354341,0.0002329547,0.00005561558,0.00005094493],"category_scores_gemma":[0.02011385,0.00008689506,0.00007141533,0.000895014,0.000279045,0.0001947896,0.0001046705,0.0002032699,0.000003099964],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001445752,"about_ca_system_score_gemma":0.0009609932,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002357298,"about_ca_topic_score_gemma":0.001280747,"domain_scores_codex":[0.9964652,0.0009977238,0.0003413808,0.0002683213,0.00173321,0.0001941352],"domain_scores_gemma":[0.9937923,0.003909969,0.000212659,0.0001067447,0.001957797,0.00002055175],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000007635882,0.0005537834,0.8097692,0.00002243506,0.00005447925,3.622915e-7,0.1735791,0.0009082835,0.00002818337,0.01403324,0.0006984872,0.0003448444],"study_design_scores_gemma":[0.0005483953,0.00002355031,0.8842094,0.0001373982,0.00002734641,1.344546e-7,0.1128406,0.00006991737,0.00004387378,0.001929078,0.00008752631,0.00008283731],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9809753,0.002069847,5.631072e-7,0.003772078,0.002308043,0.0009357651,0.000002761888,0.00001264553,0.009922994],"genre_scores_gemma":[0.9968901,0.0007253176,0.00002409624,0.00004292892,0.0009575095,0.0003014081,0.00001440337,0.000007443113,0.001036852],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07444018,"threshold_uncertainty_score":0.9881402,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03124067406168235,"score_gpt":0.419786253443572,"score_spread":0.3885455793818897,"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."}}