{"id":"W4406043859","doi":"10.1080/15427587.2024.2448815","title":"The impact of TOEFL iBT preparation on Chinese test-takers’ perceptions of integrated speaking and writing design","year":2025,"lang":"en","type":"article","venue":"Critical Inquiry in Language Studies","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Test (biology); Test of English as a Foreign Language; Psychology; Perception; Context (archaeology); Construct validity; Language assessment; Test design; Applied psychology; Social psychology; Medical education; Mathematics education; Developmental psychology; Psychometrics; Test method; Medicine","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":[0.0008256972,0.00009164995,0.0002030704,0.00007910805,0.0003122015,0.00004297737,0.0001098748,0.00004351888,0.00002475936],"category_scores_gemma":[0.005196708,0.00005726878,0.0000548052,0.0003858839,0.001230879,0.0001099315,0.0000561479,0.0001061958,9.153274e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009096148,"about_ca_system_score_gemma":0.00006391101,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003781908,"about_ca_topic_score_gemma":0.0003878626,"domain_scores_codex":[0.9990401,0.0002290713,0.0002576793,0.0001306611,0.0001605262,0.0001819203],"domain_scores_gemma":[0.9958986,0.003776402,0.0000422503,0.00009429566,0.0001668231,0.00002164066],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.0001379447,0.0004282598,0.3528609,0.00009498596,0.0001967472,0.000008546194,0.6043819,0.00007041216,0.006153926,0.02647927,0.001123047,0.008064075],"study_design_scores_gemma":[0.0002545956,0.0002291378,0.3198544,0.0002903407,0.00002891121,2.195348e-7,0.6764436,0.0002351668,0.0001107228,0.00245501,0.000008190116,0.00008972862],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9917061,0.001554836,0.0004022898,0.0007245645,0.0001366135,0.0002253737,0.000004813101,0.00001899849,0.005226367],"genre_scores_gemma":[0.999185,0.000325442,0.0002792677,0.00002853462,0.00008059869,0.00001709124,0.000001141396,0.000003317962,0.00007958908],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07206172,"threshold_uncertainty_score":0.622132,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07430071452784202,"score_gpt":0.5133190650981386,"score_spread":0.4390183505702966,"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."}}