{"id":"W7130589557","doi":"10.1109/fllm67465.2025.11390927","title":"Fact Checking in Low Resource Languages: Creating Translation-Based Datasets and Benchmarking for Farsi","year":2025,"lang":"","type":"article","venue":"","topic":"Misinformation and Its Impacts","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Benchmarking; Benchmark (surveying); Language model; Resource (disambiguation); Misinformation","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007858141,0.001905628,0.000859452,0.004483436,0.001596288,0.001965535,0.003077229,0.002346739,0.003535737],"category_scores_gemma":[0.02793683,0.0004375189,0.001573393,0.003514411,0.002260896,0.004693707,0.003914554,0.002536934,0.003980718],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001916986,"about_ca_system_score_gemma":0.002408233,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01752623,"about_ca_topic_score_gemma":0.01958399,"domain_scores_codex":[0.9936298,0.00267846,0.0006688684,0.001394515,0.001268094,0.0003601955],"domain_scores_gemma":[0.9842592,0.005337756,0.001056404,0.005828201,0.002810774,0.0007076137],"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":[0.002578257,0.003950714,0.07239663,0.005176163,0.001126854,0.002426808,0.003458533,0.1155722,0.01828373,0.02094699,0.3728949,0.3811882],"study_design_scores_gemma":[0.0009075282,0.002247992,0.06763212,0.001775226,0.0004366652,0.002796919,0.005636973,0.5432529,0.04895067,0.02742893,0.2983563,0.000577785],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6382075,0.00590642,0.1035803,0.005128684,0.002699054,0.00241931,0.16039,0.04704373,0.03462495],"genre_scores_gemma":[0.4110404,0.0008861287,0.112494,0.001070989,0.0002185445,0.001060626,0.4666381,0.00139771,0.005193491],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01752623,"threshold_uncertainty_score":0.04155833,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02729240955561052,"score_gpt":0.3536231891676906,"score_spread":0.3263307796120801,"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."}}