{"id":"W4410839902","doi":"10.1038/s41598-025-03753-7","title":"A phenomenographic study on Chinese EFL teachers’ cognitions of positive and negative educational, social, and psychological consequences of high-stake tests","year":2025,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Phenomenography; Psychology; Cognition; Social psychology; Developmental psychology; Clinical psychology; Mathematics education; Psychiatry","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.001202802,0.0001018299,0.0002309966,0.0002531486,0.0007697543,0.000123559,0.00009643796,0.00005190844,0.00006552359],"category_scores_gemma":[0.0005122192,0.00008326335,0.00004233898,0.001032856,0.002958379,0.0001233778,0.00004735538,0.00008586889,5.839491e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002253466,"about_ca_system_score_gemma":0.0001839174,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005411753,"about_ca_topic_score_gemma":0.0004611305,"domain_scores_codex":[0.998409,0.0002155551,0.0003437499,0.0004383971,0.0004422427,0.0001510973],"domain_scores_gemma":[0.9987341,0.0004801453,0.0003057775,0.0001412062,0.0002859888,0.00005282803],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001894051,0.001489877,0.9193406,0.000009362398,0.000098832,0.000008495133,0.06511841,2.122244e-7,0.002300709,0.009884165,0.001048025,0.0006823487],"study_design_scores_gemma":[0.0002324754,0.0001421443,0.8984861,0.00003694462,0.00004450186,0.000001348842,0.03888454,1.359067e-7,0.00007047363,0.06198713,0.00004126698,0.00007290293],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9836236,0.00009263337,0.000002055933,0.001359413,0.0007600709,0.0006134668,0.00001145791,0.00001316555,0.0135241],"genre_scores_gemma":[0.9988479,0.0000135396,0.00009194514,0.00002583397,0.00002875028,0.00003561864,0.000009765814,0.000002611221,0.0009440522],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05210297,"threshold_uncertainty_score":0.999755,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05859291485390382,"score_gpt":0.4162507589408014,"score_spread":0.3576578440868975,"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."}}