{"id":"W7077899621","doi":"10.48448/x4s1-en78","title":"AfriHate: A Multilingual Collection of Hate Speech and Abusive Language Datasets for African Languages","year":2025,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Moderation; Baseline (sea); Censorship; Data collection; Language identification; Component (thermodynamics)","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":[0.001145807,0.001268046,0.0005358569,0.004059405,0.001842415,0.001082449,0.001274392,0.001606998,0.004395171],"category_scores_gemma":[0.005312437,0.0002651775,0.0007971879,0.003582336,0.0006745877,0.001763473,0.002483381,0.001173328,0.005367334],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008903935,"about_ca_system_score_gemma":0.001291753,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02224514,"about_ca_topic_score_gemma":0.05759691,"domain_scores_codex":[0.9987822,0.000314831,0.0001522293,0.0002816234,0.000269002,0.0002000924],"domain_scores_gemma":[0.9975644,0.0006833168,0.0003541458,0.0005827184,0.0005480584,0.0002672942],"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":[0.001110712,0.0006877522,0.08260554,0.003379528,0.0002991847,0.002365058,0.0054599,0.003531755,0.01509263,0.004324635,0.7138617,0.1672816],"study_design_scores_gemma":[0.0001300142,0.0002043364,0.1675035,0.0005601763,0.00009243732,0.001780496,0.0071732,0.009458903,0.007677424,0.002307194,0.8029081,0.0002041973],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.1590886,0.00233365,0.008545102,0.002082901,0.0009464953,0.0006094513,0.8042369,0.005381665,0.01677531],"genre_scores_gemma":[0.09163728,0.0005673721,0.01678443,0.0002991511,0.0001897981,0.000778648,0.8829834,0.0003494348,0.006410535],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.02224514,"threshold_uncertainty_score":0.0442313,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01190444538831699,"score_gpt":0.2905940946202544,"score_spread":0.2786896492319374,"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."}}