{"id":"W4416610221","doi":"10.48550/arxiv.2505.23170","title":"ZIPA: A family of efficient models for multilingual phone 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":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung","keywords":"Phone; Leverage (statistics); Training set; Set (abstract data type); Noisy data; Data set","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"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":[0.0005149897,0.0003007852,0.0005089727,0.0003325704,0.00009548022,0.00005884908,0.0008969325,0.0003161542,0.00001950376],"category_scores_gemma":[0.0002932042,0.0003063996,0.0003826182,0.0002751111,0.00005915399,0.00009959267,0.0007095406,0.0003094676,0.00006534732],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007440661,"about_ca_system_score_gemma":0.0003236369,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008724482,"about_ca_topic_score_gemma":0.000009663052,"domain_scores_codex":[0.9978344,0.00009553342,0.0006080913,0.0008304897,0.000308901,0.00032261],"domain_scores_gemma":[0.9977643,0.0004330859,0.000338117,0.0007953983,0.000576898,0.0000921699],"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":[0.0001842685,0.001443717,0.0008128338,0.001350384,0.0004299132,0.00002246311,0.003114567,0.01067235,0.007122477,0.0008891832,0.001482968,0.9724749],"study_design_scores_gemma":[0.001336287,0.00008773596,0.002361199,0.001134398,0.0001332378,0.000004531595,0.0001991029,0.8343546,0.1464073,0.01274052,0.0004888522,0.0007522405],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5406844,0.0001919147,0.4541692,0.0001505949,0.001193272,0.0006434298,0.000196733,0.0001741054,0.002596282],"genre_scores_gemma":[0.8624151,0.0001138217,0.1359042,0.0004644277,0.0001458795,0.0003192767,0.00008795213,0.00002098272,0.0005283811],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9717227,"threshold_uncertainty_score":0.9999388,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1281203376629262,"score_gpt":0.3082748997877475,"score_spread":0.1801545621248213,"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."}}