{"id":"W7082303416","doi":"10.48448/qd4a-yy90","title":"A Comparative Approach for Auditing Multilingual Phonetic Transcript Archives","year":2025,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Transcription (linguistics); Phonetic transcription; Audit; Task (project management); Language model; Statistical model; Identification (biology); Downstream (manufacturing)","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007790468,0.001013583,0.0007005429,0.008906879,0.002221618,0.004094744,0.002773366,0.001505049,0.01049318],"category_scores_gemma":[0.02951564,0.0005698063,0.0007707921,0.006907896,0.001361083,0.004033562,0.005112776,0.001511445,0.005779901],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001415743,"about_ca_system_score_gemma":0.003776027,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007057874,"about_ca_topic_score_gemma":0.02237413,"domain_scores_codex":[0.9884573,0.00393192,0.000903463,0.002026882,0.004282488,0.0003979254],"domain_scores_gemma":[0.9744974,0.004918593,0.001566971,0.007521998,0.01059766,0.0008974163],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0007606327,0.000352016,0.03778433,0.001172823,0.0003448979,0.001024438,0.006337688,0.007070826,0.09126969,0.01810899,0.02444128,0.8113325],"study_design_scores_gemma":[0.0002131573,0.001069617,0.141873,0.001034163,0.0006124355,0.005603503,0.01905305,0.1627042,0.2094842,0.04594272,0.4116765,0.0007334403],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07251813,0.001969095,0.8521418,0.002000497,0.0006445292,0.0008907705,0.01005423,0.01526234,0.04451867],"genre_scores_gemma":[0.2160114,0.0006010568,0.764168,0.0004680901,0.0001896,0.0006567634,0.008025536,0.001315429,0.008564129],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01049318,"threshold_uncertainty_score":0.0412004,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03421558061260944,"score_gpt":0.2934816207342943,"score_spread":0.2592660401216849,"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."}}