{"id":"W3213458975","doi":"10.1162/tacl_a_00419","title":"<scp>ParsiNLU</scp>: A Suite of Language Understanding Challenges for Persian","year":2021,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"Microsoft (Canada); International Medias Data Services (Canada)","funders":"","keywords":"Computer science; Natural language understanding; Natural language processing; Suite; Benchmark (surveying); Artificial intelligence; Persian; Natural language; Linguistics","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":[],"consensus_categories":[],"category_scores_codex":[0.0003230425,0.00007847394,0.0001624632,0.00006850228,0.0001815772,0.0000290339,0.0002612984,0.00006853254,9.174919e-7],"category_scores_gemma":[0.002072148,0.00007971112,0.0002105552,0.0001902889,0.00001917119,0.00004565814,0.00001574799,0.00007239422,3.767705e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001984848,"about_ca_system_score_gemma":0.0001923109,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005962239,"about_ca_topic_score_gemma":0.00001970116,"domain_scores_codex":[0.9990283,0.00004564069,0.0003003686,0.0001764726,0.0003039461,0.0001452741],"domain_scores_gemma":[0.9963433,0.002255487,0.000309124,0.0001749412,0.0008892635,0.00002789067],"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":[0.000004644088,0.0001472854,0.0002860556,0.0002324545,0.0002289346,2.470431e-7,0.006186066,0.2768342,0.000110148,0.7147368,0.0001339006,0.001099342],"study_design_scores_gemma":[0.001307549,0.00008435754,0.001288887,0.0001188676,0.0001841204,0.000002659366,0.003221129,0.8253283,0.002388423,0.1633043,0.002663555,0.000107826],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001672856,0.0002023314,0.9955479,0.0006329029,0.0007424006,0.0002166483,0.0001448069,0.00003172466,0.0008084133],"genre_scores_gemma":[0.8897815,0.00001004854,0.1095411,0.0000337926,0.00009859251,0.00001106632,0.00001648383,0.000008743681,0.0004986054],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8881087,"threshold_uncertainty_score":0.3250525,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05384418972214958,"score_gpt":0.281614772268062,"score_spread":0.2277705825459125,"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."}}