{"id":"W4390026249","doi":"10.1353/dic.2023.a915069","title":"Designing Corpus-Creation Tools for Language Revitalization","year":2023,"lang":"en","type":"article","venue":"Dictionaries","topic":"Discourse Analysis in Language Studies","field":"Arts and Humanities","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Documentation; Computer science; Set (abstract data type); Adaptation (eye); Linguistics; Spoken language; Corpus linguistics; Process (computing); Natural language processing; Psychology; Programming language","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":[],"consensus_categories":[],"category_scores_codex":[0.0001648945,0.00008286723,0.0001146932,0.0001232258,0.0005714307,0.0003191057,0.00005688663,0.00001830884,0.0003546562],"category_scores_gemma":[0.0003287937,0.00007326248,0.00007183052,0.00008977332,0.0001472626,0.0004617427,0.00002095593,0.00002602271,0.0001022526],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001970617,"about_ca_system_score_gemma":0.00001244444,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004255298,"about_ca_topic_score_gemma":0.0002458813,"domain_scores_codex":[0.9994261,0.00001912946,0.0001503016,0.0001358734,0.0001351374,0.0001335033],"domain_scores_gemma":[0.9994903,0.0002059325,0.00006349464,0.0001002956,0.0001248241,0.00001511985],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001456813,0.00001817963,0.0001966178,0.00003939944,0.0001401326,0.000002743107,0.07258172,0.0003275487,0.0001725559,0.8813043,0.02722699,0.01797524],"study_design_scores_gemma":[0.0003629185,0.0001008536,0.0007179699,0.00009700644,0.0002992917,0.000001548621,0.2735465,0.002497804,0.001293107,0.01754741,0.7031452,0.0003903953],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.123631,0.007359966,0.1515726,0.008433391,0.005844878,0.002842029,0.001322813,0.005223753,0.6937695],"genre_scores_gemma":[0.9656572,0.0001073026,0.0004608786,0.0002143809,0.001266696,0.0002433924,0.001368032,0.00002764804,0.03065448],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8637569,"threshold_uncertainty_score":0.4395041,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04584676063739353,"score_gpt":0.2999979899117502,"score_spread":0.2541512292743567,"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."}}