{"id":"W4414689770","doi":"10.63878/qrjs470","title":"EVALUATING LANGUAGE SKILLS IN HIGHER EDUCATION: POTENTIAL ISSUES AND OUTCOMES","year":2025,"lang":"fr","type":"article","venue":"Qualitative Research Journal for Social Studies","topic":"Second Language Learning and Teaching","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Language assessment; Practicum; Formative assessment; Variety (cybernetics); Language proficiency; English language; Language education; Language industry; Language acquisition","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.01022656,0.0002027356,0.0005156904,0.000465215,0.004419221,0.000609355,0.0001566428,0.00009795735,0.0006692718],"category_scores_gemma":[0.003699741,0.0001722837,0.0001699748,0.0001687382,0.001219168,0.0002888405,0.0001379915,0.001187643,0.00001058195],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003765107,"about_ca_system_score_gemma":0.0002855877,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002690068,"about_ca_topic_score_gemma":0.0006572073,"domain_scores_codex":[0.9940596,0.004043955,0.0005075833,0.000264451,0.0005204232,0.0006040423],"domain_scores_gemma":[0.9946772,0.004002823,0.0001600836,0.00006904173,0.001025313,0.00006555379],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.00003975624,0.0001722485,0.000222681,0.0003619705,0.0005472681,0.000009931575,0.5656042,0.000001827099,0.00001014516,0.2977428,0.01622408,0.1190631],"study_design_scores_gemma":[0.0007957203,0.0002197171,0.002723266,0.0006804788,0.00006101279,0.000002125583,0.8229861,0.000007254446,0.000003924801,0.05475537,0.1176094,0.0001555877],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"other","genre_scores_codex":[0.521245,0.3724716,0.000009015935,0.09270544,0.003570326,0.0003955372,0.00004927851,0.00001563433,0.009538144],"genre_scores_gemma":[0.3251443,0.002545106,0.0005286742,0.0004984758,0.003641505,0.00009982539,0.000007502428,0.0000252612,0.6675094],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6579713,"threshold_uncertainty_score":0.9968769,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4084033049460129,"score_gpt":0.6561818798565727,"score_spread":0.2477785749105598,"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."}}