{"id":"W3043085860","doi":"10.17613/34jx-fw32","title":"Seeing the Heiltsuk orthography from font encoding through to Unicode: A case study using convertextract","year":2018,"lang":"en","type":"article","venue":"Humanities Commons CORE (Modern Language Association / Columbia University)","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Unicode; Computer science; World Wide Web; Transliteration; Encoding (memory); Font; Orthography; Writing system; Rendering (computer graphics); Natural language processing; Artificial intelligence; Linguistics","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0004444489,0.0002604876,0.000338041,0.0002848948,0.001957876,0.0009970575,0.001574417,0.0001477338,0.0000705822],"category_scores_gemma":[0.0001364058,0.0003026042,0.0001486772,0.001151678,0.0001163183,0.001267546,0.0009546442,0.0004514643,0.000009601559],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006291515,"about_ca_system_score_gemma":0.0001349223,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.04827917,"about_ca_topic_score_gemma":0.141585,"domain_scores_codex":[0.9976491,0.0004043799,0.0003024259,0.0005949085,0.0005514941,0.0004976524],"domain_scores_gemma":[0.9975565,0.0005306794,0.0004231998,0.0009320609,0.0004698034,0.00008775984],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.0001122105,0.001269886,0.1074287,0.00005795654,0.001419161,0.01766389,0.7982847,0.00006201245,0.006630338,0.03735265,0.005226212,0.02449234],"study_design_scores_gemma":[0.009587614,0.003414192,0.009954399,0.001352365,0.00199,0.001590086,0.7642155,0.1194598,0.004775451,0.0339843,0.04178071,0.007895611],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8448067,0.0002237342,0.1502918,0.0001298676,0.0002498324,0.0007240124,0.00005482561,0.0008244006,0.002694802],"genre_scores_gemma":[0.9748774,0.00000282591,0.02306647,0.0006807644,0.0001506619,0.000005134219,0.00001230803,0.00002916038,0.001175323],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1300706,"threshold_uncertainty_score":0.9999426,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0426305788822605,"score_gpt":0.2697616665529911,"score_spread":0.2271310876707305,"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."}}