{"id":"W4417423602","doi":"10.48550/arxiv.2507.10827","title":"Supporting SENĆOTEN Language Documentation Efforts with Automatic Speech Recognition","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Pipeline (software); Documentation; Vocabulary; Word error rate; Language model; Constructed language; Set (abstract data type); Speech technology","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005508203,0.000345116,0.000391889,0.0003299149,0.0001456076,0.0003305725,0.0006356903,0.0002297853,0.0004676541],"category_scores_gemma":[0.0001577719,0.0003130364,0.0001494691,0.0003740437,0.00003807984,0.0005311082,0.0005153149,0.0004415965,0.0005003284],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001352754,"about_ca_system_score_gemma":0.000225705,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001980826,"about_ca_topic_score_gemma":0.00007206324,"domain_scores_codex":[0.9976574,0.0001553571,0.0005503129,0.0007990793,0.0004328507,0.0004049619],"domain_scores_gemma":[0.9982419,0.0001864607,0.00049332,0.0007881289,0.0001763477,0.0001138511],"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":[0.000009984256,0.00009991824,0.02038185,0.0004180109,0.0001504015,0.0003054688,0.001424956,0.00001078472,0.0004388124,0.00003869855,0.0007176173,0.9760035],"study_design_scores_gemma":[0.005340566,0.0006497207,0.2798203,0.01216547,0.001404889,0.0009519635,0.004096291,0.1316854,0.5330811,0.02094872,0.002913275,0.006942343],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9464171,0.0000543364,0.04172966,0.0007611192,0.0006611809,0.0006722279,0.00003104316,0.0008045484,0.008868773],"genre_scores_gemma":[0.707741,0.00004798495,0.2866275,0.001417926,0.0002404045,0.00024091,0.0004388806,0.00003966997,0.003205805],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9690611,"threshold_uncertainty_score":0.9999322,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03055018748211533,"score_gpt":0.3052722171440733,"score_spread":0.274722029661958,"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."}}