{"id":"W6966594921","doi":"10.48448/r8pp-6056","title":"NADI 2024: The Fifth Nuanced Arabic Dialect Identification Shared Task","year":2024,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Arabic; Task (project management); Identification (biology); Machine translation; Modern Standard Arabic","routes":{"ca_aff":true,"ca_fund":false,"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":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00230422,0.0005849028,0.0004329238,0.001501375,0.0004378893,0.001310259,0.002906576,0.0002717466,0.005138368],"category_scores_gemma":[0.0006798164,0.0004123084,0.0001569654,0.004972442,0.002509682,0.0004179494,0.0004063474,0.0007999553,0.08818528],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006536313,"about_ca_system_score_gemma":0.00125031,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006063333,"about_ca_topic_score_gemma":0.002586236,"domain_scores_codex":[0.9946863,0.0001421357,0.0006029142,0.001754742,0.001857385,0.0009565367],"domain_scores_gemma":[0.9968997,0.0001061915,0.0005550633,0.001965525,0.0002367764,0.0002367347],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000006246524,0.00005233293,0.0000142669,0.00007343759,0.00005005721,0.00001379048,0.0004998362,0.0000402757,0.0172268,0.002463159,0.9769796,0.002580191],"study_design_scores_gemma":[0.000250425,0.00004925489,0.0003226454,0.0005060681,0.0001737675,0.00002682629,0.0001814877,0.009738785,0.0004597719,0.005328341,0.9821791,0.0007834951],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.0005725413,0.01010935,0.002252673,0.003200333,0.01457356,0.003904667,0.003474515,0.003345305,0.958567],"genre_scores_gemma":[0.05606506,0.0001019074,0.0007591575,0.0002924814,0.001347172,0.0001946756,0.0002993008,0.001272521,0.9396677],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.08304691,"threshold_uncertainty_score":0.9998329,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02365089562541785,"score_gpt":0.3077806918928366,"score_spread":0.2841297962674188,"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."}}