{"id":"W3158589498","doi":"10.18653/v1/2021.nlp4if-1.9","title":"AraStance: A Multi-Country and Multi-Domain Dataset of Arabic Stance Detection for Fact Checking","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; King Abdulaziz City for Science and Technology; Hamad Bin Khalifa University; Compute Canada","keywords":"Disinformation; Computer science; Misinformation; Task (project management); Arabic; Set (abstract data type); Domain (mathematical analysis); Benchmark (surveying); Natural language processing; Artificial intelligence; German; Scale (ratio); Machine learning; Data science; Social media; Computer security; World Wide Web; Linguistics; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0005265689,0.0002720128,0.0004265915,0.00010602,0.00009142668,0.0002197793,0.0006546334,0.0002193558,0.000004632688],"category_scores_gemma":[0.00009692619,0.0002705717,0.00007626427,0.0001321778,0.0000437904,0.0003522149,0.001011715,0.0003581397,5.472273e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009519993,"about_ca_system_score_gemma":0.0001509523,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002213702,"about_ca_topic_score_gemma":0.0008677934,"domain_scores_codex":[0.997841,0.00005919172,0.0005252328,0.001015492,0.0002629621,0.0002961248],"domain_scores_gemma":[0.9983352,0.00009988965,0.0003394914,0.0009983296,0.0001544611,0.00007263153],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002477936,0.001521109,0.008089008,0.01483121,0.001011765,0.0001352795,0.01427638,0.06950814,0.1251287,0.009451866,0.0005975551,0.7552012],"study_design_scores_gemma":[0.0008188687,0.00001752905,0.001107485,0.0002851754,0.00001435275,0.000008862326,0.0001982486,0.9870158,0.009248801,0.0006025216,0.0003491156,0.0003332463],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06297647,0.0008343053,0.9343707,0.00003510824,0.0006077578,0.0005391533,0.00054747,0.00008028279,0.000008759714],"genre_scores_gemma":[0.382629,0.00007411635,0.6169114,0.00006307755,0.00004372721,0.0000628585,0.0001756689,0.00001280026,0.00002739037],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9175076,"threshold_uncertainty_score":0.9999747,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05182885206336371,"score_gpt":0.3053056938476754,"score_spread":0.2534768417843117,"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."}}