{"id":"W4404782299","doi":"10.18653/v1/2024.emnlp-main.1211","title":"Casablanca: Data and Models for Multidialectal Arabic Speech Recognition","year":2024,"lang":"en","type":"article","venue":"","topic":"Language, Linguistics, Cultural Analysis","field":"Arts and Humanities","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Alliance de recherche numérique du Canada; Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Arabic; Computer science; Speech recognition; Natural language processing; Artificial intelligence; Linguistics","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001186872,0.00009919751,0.0001225644,0.0000524505,0.0001409832,0.0003814484,0.0001041007,0.00002696966,0.001148917],"category_scores_gemma":[0.0001134342,0.00006571303,0.00004338045,0.00002318255,0.00006486189,0.000333569,0.0000652134,0.00005939512,0.000104787],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001381686,"about_ca_system_score_gemma":0.00001264629,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009457485,"about_ca_topic_score_gemma":0.007055142,"domain_scores_codex":[0.9993365,0.00001018546,0.0001451724,0.0002921848,0.00008013572,0.0001357762],"domain_scores_gemma":[0.9995657,0.0000972837,0.000018143,0.0001732581,0.0001087233,0.00003692023],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008578201,0.0001482762,0.00002317327,0.001013625,0.001052175,0.0001739802,0.06727589,0.00002554066,0.0005724642,0.4048688,0.1951965,0.3295638],"study_design_scores_gemma":[0.0003897352,0.00008187655,0.000003343733,0.0001028731,0.000555508,0.00002520708,0.006439217,0.6338128,0.000470349,0.1432343,0.2143779,0.0005068995],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.3734908,0.008525895,0.02891471,0.004297433,0.006286784,0.002363633,0.01411058,0.002186732,0.5598235],"genre_scores_gemma":[0.9642888,0.0000660664,0.004072434,0.0001843906,0.00314015,0.00001655556,0.001539934,0.000021854,0.02666979],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6337873,"threshold_uncertainty_score":0.9997641,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1317035454805794,"score_gpt":0.2873272728672311,"score_spread":0.1556237273866518,"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."}}