{"id":"W4402671457","doi":"10.18653/v1/2024.arabicnlp-1.79","title":"NADI 2024: The Fifth Nuanced Arabic Dialect Identification Shared Task","year":2024,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":12,"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; UK Research and Innovation","keywords":"Arabic; Identification (biology); Task (project management); Computer science; Linguistics; Natural language processing; Artificial intelligence; Philosophy; Engineering","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0003378799,0.0001036365,0.0000753438,0.00009071115,0.0001287799,0.00110404,0.00115637,0.00004898256,0.0001014309],"category_scores_gemma":[0.00008518866,0.00006180765,0.00005485292,0.0007560111,0.00003620062,0.0007603381,0.0001698921,0.0001994206,0.0002489809],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005205268,"about_ca_system_score_gemma":0.00007044734,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004943696,"about_ca_topic_score_gemma":0.00002335507,"domain_scores_codex":[0.9990031,0.00004475563,0.0001667645,0.0003768778,0.0002246053,0.000183966],"domain_scores_gemma":[0.9992051,0.000111477,0.00003522836,0.0005539783,0.00006015786,0.00003410539],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000004332999,0.00002982483,0.0000314563,0.0001201484,0.00003850583,0.00005872098,0.00380701,0.000006475633,0.08816281,0.3898009,0.1504133,0.3675265],"study_design_scores_gemma":[0.0001630461,0.00008732687,0.001174533,0.0003332104,0.0000350006,0.0001099429,0.00005147096,0.2255221,0.1707321,0.5046771,0.09631325,0.0008009135],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001329556,0.009278866,0.9767721,0.007087082,0.0009931294,0.0002502212,0.000004369165,0.002173845,0.002110794],"genre_scores_gemma":[0.9170219,0.00003131913,0.07292038,0.0005769655,0.0001247063,0.0000632825,0.000006223398,0.00001165529,0.00924354],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9156924,"threshold_uncertainty_score":0.9999329,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01126245484664217,"score_gpt":0.2741339424653891,"score_spread":0.2628714876187469,"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."}}