{"id":"W6948010449","doi":"10.48448/jx10-s248","title":"NADI 2020: The First Nuanced Arabic Dialect Identification Shared Task","year":2020,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Task (project management); Identification (biology); Arabic; Task analysis","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"],"consensus_categories":[],"category_scores_codex":[0.0006383971,0.0003728548,0.0003340554,0.0003190413,0.000572625,0.0008504247,0.005110289,0.00015596,0.0001526292],"category_scores_gemma":[0.0004931339,0.0002726904,0.0001038489,0.003032348,0.0008642279,0.0009531789,0.0007868377,0.0004595749,0.000434838],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001684803,"about_ca_system_score_gemma":0.0004746645,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009002229,"about_ca_topic_score_gemma":0.0001432501,"domain_scores_codex":[0.99671,0.00005292677,0.0004309432,0.001260786,0.0009732496,0.000572094],"domain_scores_gemma":[0.9974614,0.0001154852,0.0004848062,0.001587346,0.0001648246,0.0001861238],"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":[0.000009057931,0.00009623136,0.00005995455,0.00009617429,0.00003853549,0.00005482199,0.0006578198,0.00002573777,0.007054068,0.02037034,0.8191134,0.1524238],"study_design_scores_gemma":[0.0002058459,0.0001245756,0.0003373598,0.0001754473,0.00002126749,0.00002257579,0.00002249054,0.01900989,0.008002373,0.007810215,0.9636158,0.0006522111],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000003612198,0.00112145,0.9519076,0.006343799,0.0008816864,0.0008239917,0.0000400251,0.001295633,0.03758214],"genre_scores_gemma":[0.1328065,0.006123924,0.4426752,0.02225675,0.005925264,0.0007936888,0.000320402,0.001441441,0.3876569],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5092325,"threshold_uncertainty_score":0.9999725,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0154975812623318,"score_gpt":0.2797347093895835,"score_spread":0.2642371281272517,"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."}}