{"id":"W3123455859","doi":"10.33011/computel.v2i.985","title":"A Digital Corpus of St. Lawrence Island Yupik","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Pipeline (software); Spell; Indigenous language; Indigenous; Linguistics; Computer science; Sociology; Anthropology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005326945,0.0003365776,0.0003242494,0.005624846,0.001969612,0.00141248,0.0008058171,0.0005427827,0.01382086],"category_scores_gemma":[0.003233042,0.0002864308,0.0001484326,0.01115363,0.001213667,0.0007922483,0.002161917,0.0006742721,0.006079882],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003876301,"about_ca_system_score_gemma":0.005499076,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.2734634,"about_ca_topic_score_gemma":0.5344642,"domain_scores_codex":[0.9994283,0.00007725074,0.00007741107,0.000171904,0.0001691389,0.00007585128],"domain_scores_gemma":[0.9969778,0.0007730206,0.0002357924,0.000523856,0.001316764,0.0001728475],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0006987442,0.0001468788,0.02706684,0.005776265,0.00009105319,0.003874262,0.04821223,0.002550174,0.02864524,0.0149841,0.5708451,0.2971091],"study_design_scores_gemma":[0.00003144409,0.00001731581,0.1287786,0.0004422243,0.0000346048,0.0004397669,0.01029393,0.0007692116,0.004782153,0.0009466482,0.8534051,0.00005895936],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.2442718,0.002155745,0.004067203,0.0008704289,0.0002052326,0.0004710815,0.6612255,0.001331012,0.08540207],"genre_scores_gemma":[0.1746864,0.001117366,0.01439509,0.0001661735,0.00003655852,0.001029534,0.7792603,0.0008480448,0.0284606],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.2734634,"threshold_uncertainty_score":0.5437434,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01311180023878614,"score_gpt":0.2611552939209713,"score_spread":0.2480434936821852,"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."}}