{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008241626,0.0008935209,0.0007599272,0.007489355,0.002016329,0.003396112,0.00252374,0.001333731,0.007476762],"category_scores_gemma":[0.0327965,0.0006214657,0.000655517,0.00462818,0.001108615,0.003320325,0.004956577,0.001255126,0.003299051],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001287349,"about_ca_system_score_gemma":0.003037369,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005928961,"about_ca_topic_score_gemma":0.01548088,"domain_scores_codex":[0.9881666,0.004668763,0.0009603114,0.00195156,0.003811687,0.0004409437],"domain_scores_gemma":[0.96839,0.007780415,0.001823026,0.007962522,0.01306484,0.0009791758],"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":[0.001232138,0.000418661,0.03264702,0.0009832545,0.0002872203,0.001355582,0.007050565,0.009237997,0.1090874,0.009038255,0.01117677,0.817485],"study_design_scores_gemma":[0.0003046301,0.0016339,0.1267012,0.0009056668,0.0007534023,0.005274907,0.01965096,0.368171,0.2681974,0.03018671,0.17757,0.0006501582],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1700148,0.001585816,0.7810168,0.001330037,0.000449969,0.001110275,0.005237091,0.01466807,0.02458709],"genre_scores_gemma":[0.3551533,0.0003789694,0.6346353,0.0002273929,0.0001461762,0.0005043009,0.003885173,0.0009503952,0.004119077],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008241626,"threshold_uncertainty_score":0.04358637,"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."}}