{"id":"W2970751912","doi":"10.4000/jtei.2301","title":"Encoding Disappearing Characters: The Case of Twentieth-Century Japanese-Canadian Names","year":2019,"lang":"en","type":"article","venue":"Journal of the Text Encoding Initiative","topic":"Digital Humanities and Scholarship","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Glyph (data visualization); Unicode; Kanji; Computer science; Geocoding; Markup language; Variation (astronomy); Cover (algebra); Physiognomy; Font; World Wide Web; Chinese characters; Linguistics; Natural language processing; Artificial intelligence; Geography; Visualization; Cartography; XML; Engineering; Sociology","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008390741,0.0001778751,0.0003060221,0.0001806309,0.0005746362,0.0005149759,0.0005603677,0.00004422266,0.001030022],"category_scores_gemma":[0.0002223141,0.00009840674,0.0003288466,0.00007608502,0.0003066294,0.001179276,0.0001135543,0.0005865631,0.00003959906],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001509483,"about_ca_system_score_gemma":0.000142141,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00172375,"about_ca_topic_score_gemma":0.005830333,"domain_scores_codex":[0.9985697,0.0001535135,0.0005451736,0.0001167433,0.000280379,0.0003344609],"domain_scores_gemma":[0.9981727,0.0004105231,0.000749105,0.0002522321,0.0003049061,0.0001105102],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.0001087113,0.0001445782,0.004897962,0.0001780688,0.0006091737,0.0004800663,0.7115838,0.00005751556,0.0004134515,0.2751755,0.002278029,0.004073157],"study_design_scores_gemma":[0.001442928,0.0006224609,0.005658519,0.002340704,0.0003112447,0.001929565,0.8659503,0.000133502,0.0005779106,0.009592125,0.1106967,0.0007440393],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7928563,0.0002709341,3.12537e-7,0.0005871893,0.001948206,0.0001507837,0.00003154528,0.000006801898,0.2041479],"genre_scores_gemma":[0.9963245,0.00004290458,0.000005474083,0.0005780837,0.0005461343,0.000001895298,9.578747e-7,0.00002075802,0.002479335],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2655834,"threshold_uncertainty_score":0.9998832,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05268278347355442,"score_gpt":0.2450025990435659,"score_spread":0.1923198155700115,"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."}}