{"id":"W4411835307","doi":"10.4995/head25.2025.20058","title":"Language Proficiency Evaluation in the Age of AI: The Resurgence of Oral Production Skill","year":2025,"lang":"en","type":"article","venue":"","topic":"Interpreting and Communication in Healthcare","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"The Scarborough Hospital; University of Toronto","funders":"","keywords":"Production (economics); Computer science; Artificial intelligence; Natural language processing; Linguistics; Economics; Philosophy","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":[0.01120814,0.0002806521,0.000453832,0.001575948,0.0007882039,0.002443072,0.0007550198,0.001155672,0.001920893],"category_scores_gemma":[0.0475317,0.0001037064,0.000245217,0.0007878968,0.002169797,0.004040729,0.002240947,0.001806252,0.0004542096],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001514352,"about_ca_system_score_gemma":0.002560908,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007203828,"about_ca_topic_score_gemma":0.00836041,"domain_scores_codex":[0.9935123,0.002780802,0.000555369,0.0004404097,0.002231267,0.0004799326],"domain_scores_gemma":[0.9674075,0.01878468,0.004027799,0.0008515145,0.007514396,0.001414086],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003383373,0.0001473301,0.2891091,0.001123456,0.00005202074,0.001650287,0.04075195,0.0003221589,0.007028978,0.003106454,0.005056141,0.6513138],"study_design_scores_gemma":[0.00001829948,0.001769848,0.8086509,0.002226933,0.000110022,0.0087563,0.0953991,0.001619451,0.01072156,0.009673674,0.06086518,0.0001888272],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9229851,0.01858461,0.01249411,0.01970033,0.001106666,0.00007221889,0.0001421014,0.0001404888,0.02477441],"genre_scores_gemma":[0.9889911,0.003465887,0.004303372,0.001551701,0.0002973492,0.00002799117,0.00002827595,0.00003601198,0.001298267],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01120814,"threshold_uncertainty_score":0.05927503,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.10389549193103,"score_gpt":0.5336507637461866,"score_spread":0.4297552718151566,"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."}}