{"id":"W4411934141","doi":"10.1162/tacl_a_00759","title":"A Comparative Approach for Auditing Multilingual Phonetic Transcript Archives","year":2025,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Computer science; Audit; Natural language processing; Linguistics; Speech recognition; Data science; Artificial intelligence; World Wide Web; Accounting; Business","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.000279952,0.0001136531,0.0002294776,0.0001431088,0.0004108097,0.00005736129,0.0004006492,0.00006160774,0.000002206402],"category_scores_gemma":[0.0009694858,0.000104933,0.0003026233,0.0003175176,0.00004748826,0.00003762528,0.000008974721,0.000101494,7.271597e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008338026,"about_ca_system_score_gemma":0.0001882804,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005179694,"about_ca_topic_score_gemma":0.000004361287,"domain_scores_codex":[0.9989284,0.00007520547,0.0003906063,0.000217972,0.0002217075,0.0001661146],"domain_scores_gemma":[0.996176,0.002657177,0.0002760736,0.00014659,0.0007164948,0.00002767563],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000182405,0.001264987,0.0004004257,0.0004717041,0.001167542,1.416845e-7,0.005709879,0.6580609,0.0009451272,0.2933827,0.001534511,0.03687964],"study_design_scores_gemma":[0.001014834,0.00003819625,0.0009533112,0.00003854898,0.0001196358,5.059355e-7,0.0001714408,0.9388521,0.006983152,0.0483165,0.003387515,0.0001242887],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.000379382,0.0000273218,0.9929854,0.0003037706,0.000813693,0.0006261557,0.0002319399,0.00006548437,0.004566829],"genre_scores_gemma":[0.5785294,0.000001190477,0.4203424,0.00008290379,0.00005274732,0.00007776819,0.00002470258,0.000004551825,0.0008843202],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.57815,"threshold_uncertainty_score":0.4279042,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03049783272393018,"score_gpt":0.2948096777967044,"score_spread":0.2643118450727742,"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."}}