{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004341999,0.000335476,0.000449967,0.000421127,0.0003564926,0.0002031986,0.00231742,0.0001438632,0.00005092517],"category_scores_gemma":[0.0002128921,0.0003021022,0.0001086335,0.0007374922,0.0009053361,0.0001183819,0.0003219377,0.000293915,0.000008836493],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003024198,"about_ca_system_score_gemma":0.0008059584,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004372437,"about_ca_topic_score_gemma":0.00001619964,"domain_scores_codex":[0.9975279,0.0000431646,0.000304623,0.001134317,0.0003600095,0.0006299833],"domain_scores_gemma":[0.9986415,0.000218762,0.0002366429,0.0006530355,0.0001199073,0.0001301799],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009192654,0.002265351,0.0001127397,0.004322631,0.0005974131,0.00005802215,0.02851787,0.01838325,0.07134108,0.2819307,0.2771003,0.3152787],"study_design_scores_gemma":[0.0006387686,0.00008097862,0.00001512799,0.0002533959,0.00002658148,0.00001223185,0.0005946307,0.8006536,0.009086786,0.006145442,0.1818899,0.0006025383],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000005106054,0.0001853678,0.5444506,0.0002591606,0.0002565889,0.0003596072,0.00002079864,0.0002103022,0.4542525],"genre_scores_gemma":[0.03747178,0.00001292129,0.5510894,0.0002308824,0.0002611199,0.00008466328,0.00004768131,0.00001983099,0.4107817],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7822703,"threshold_uncertainty_score":0.9999431,"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."}}