{"id":"W4396590733","doi":"10.1007/s00146-024-01945-9","title":"GPT-4-Trinis: assessing GPT-4’s communicative competence in the English-speaking majority world","year":2024,"lang":"en","type":"article","venue":"AI & Society","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Victoria; McMaster University; University of Toronto","funders":"Social Sciences and Humanities Research Council","keywords":"Communicative competence; Psychology; Communicative language teaching; Competence (human resources); Linguistics; Communication; Pedagogy; Philosophy; Social psychology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.002347586,0.001033759,0.0005786598,0.001758278,0.0007806832,0.00206538,0.001158389,0.00132846,0.01105113],"category_scores_gemma":[0.01959815,0.0003497922,0.0008371231,0.0006326176,0.000950261,0.00216174,0.003555489,0.001655305,0.004924999],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001024393,"about_ca_system_score_gemma":0.001556033,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01026666,"about_ca_topic_score_gemma":0.01284438,"domain_scores_codex":[0.9977877,0.0005233226,0.0002692804,0.0002908046,0.0008748213,0.0002539825],"domain_scores_gemma":[0.9897702,0.003352429,0.001287027,0.001043921,0.003269571,0.00127683],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003053731,0.002278124,0.638283,0.001022933,0.0004880315,0.001438251,0.02899652,0.003265659,0.0249387,0.002811965,0.05414756,0.2392755],"study_design_scores_gemma":[0.0002185146,0.002107911,0.941898,0.0002182626,0.0002227641,0.00139507,0.008841264,0.005364746,0.009145169,0.002444758,0.02795036,0.0001930177],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.966352,0.00006549741,0.001917502,0.0001578722,0.00006736309,0.0007037962,0.0036756,0.0005344186,0.02652587],"genre_scores_gemma":[0.957341,0.0001159648,0.008994968,0.0002030296,0.00003311811,0.003199443,0.0089085,0.0002799862,0.02092415],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01105113,"threshold_uncertainty_score":0.03696978,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03340947328450353,"score_gpt":0.3192342277502775,"score_spread":0.2858247544657739,"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."}}