{"id":"W7127321268","doi":"10.1109/rivf68649.2025.11365054","title":"GPTViet: An Open-Source Vietnamese Foundation Model from Pretraining to Domain Specialization","year":2025,"lang":"","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Alpha Technologies (Canada)","funders":"","keywords":"Vietnamese; Domain (mathematical analysis); Foundation (evidence); Work (physics); Domain-specific language; Language model","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":[0.0009691612,0.000988605,0.0004255828,0.0008035321,0.000476961,0.001385532,0.00225407,0.0008450465,0.01404161],"category_scores_gemma":[0.00409788,0.0007308069,0.001186643,0.0007482611,0.0004420156,0.002191523,0.002046537,0.002061659,0.006417702],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009564082,"about_ca_system_score_gemma":0.003065204,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02019766,"about_ca_topic_score_gemma":0.03787638,"domain_scores_codex":[0.9996291,0.0001066273,0.00003101305,0.0001119607,0.00007711896,0.00004417673],"domain_scores_gemma":[0.9991934,0.0003398561,0.00003088215,0.0001764996,0.0001889705,0.00007055866],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005904207,0.000323099,0.007221166,0.001256579,0.0003513045,0.0008493978,0.001119214,0.1836486,0.009704615,0.03047823,0.2863348,0.4781226],"study_design_scores_gemma":[0.0001492168,0.0001647784,0.001657813,0.0002688621,0.0001015918,0.000419982,0.0002988033,0.7439663,0.00876501,0.02579323,0.218329,0.00008535993],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04896761,0.001599294,0.7658092,0.002388517,0.0009979992,0.0007236853,0.03305236,0.1109697,0.03549159],"genre_scores_gemma":[0.3238944,0.001658132,0.5081555,0.001257803,0.0001506277,0.001608428,0.1165399,0.01383816,0.03289698],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02019766,"threshold_uncertainty_score":0.04697382,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1962732927277619,"score_gpt":0.4749204397940344,"score_spread":0.2786471470662724,"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."}}