{"id":"W7091186536","doi":"","title":"Happiness is Sharing a Vocabulary: A Study of Transliteration Methods","year":2025,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Division of Human Resource Development; Institute for Information and Communications Technology Promotion; Korea Institute for Advancement of Technology; Ministry of Science and ICT, South Korea; Institute for Computing, Information and Cognitive Systems; Ministry of Trade, Industry and Energy","keywords":"Transliteration; Inference; Security token; Natural language; Scripting language; Factor (programming language); Romanization","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01529195,0.0008844964,0.0009854875,0.001421561,0.001293753,0.003973492,0.002383437,0.001345092,0.004740351],"category_scores_gemma":[0.05128877,0.000709356,0.001074177,0.001609718,0.002864168,0.01502184,0.004281515,0.002059789,0.002013876],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001545265,"about_ca_system_score_gemma":0.001153876,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003376423,"about_ca_topic_score_gemma":0.001775489,"domain_scores_codex":[0.9906827,0.006330218,0.0003798764,0.001505534,0.0008379529,0.0002636743],"domain_scores_gemma":[0.9602539,0.03184684,0.001558302,0.004191515,0.001753425,0.000395998],"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":[0.001037251,0.0004262846,0.03087374,0.0009738407,0.0005237553,0.0006135385,0.01533361,0.08435208,0.0118446,0.2062204,0.006305311,0.6414955],"study_design_scores_gemma":[0.000168892,0.0005902164,0.0074371,0.000344096,0.0002556323,0.001090567,0.006206314,0.7611275,0.0149898,0.1778237,0.0298323,0.0001338593],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2298668,0.003836296,0.7338563,0.003077039,0.0001988641,0.0003101455,0.0003251438,0.001205655,0.02732382],"genre_scores_gemma":[0.8763363,0.001923105,0.1108309,0.0005021698,0.0002208724,0.0003331259,0.0007999898,0.001278636,0.007774763],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01529195,"threshold_uncertainty_score":0.08087248,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05675399168167274,"score_gpt":0.261661071452346,"score_spread":0.2049070797706732,"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."}}