{"id":"W7102431493","doi":"","title":"AfriMTEB and AfriE5: Benchmarking and Adapting Text Embedding Models for African Languages","year":2025,"lang":"","type":"article","venue":"arXiv (Cornell University)","topic":"Hate Speech and Cyberbullying Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Institut de Valorisation des Données; Canada First Research Excellence Fund","keywords":"Embedding; Benchmarking; Component (thermodynamics); Adaptation (eye); Languages of Africa; Cluster analysis","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005168585,0.0003263018,0.0003369329,0.0004240493,0.0008900759,0.0003872243,0.0004426369,0.0001935969,0.00001106147],"category_scores_gemma":[0.00006949947,0.0003997925,0.0001115443,0.001011034,0.0001940341,0.001018603,0.0005888821,0.0002615465,0.000002923731],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001203033,"about_ca_system_score_gemma":0.0001249835,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001992327,"about_ca_topic_score_gemma":0.00008156212,"domain_scores_codex":[0.9977923,0.0001169148,0.000240853,0.001159676,0.00007916331,0.000611062],"domain_scores_gemma":[0.9986836,0.0003468342,0.0001751126,0.0004439374,0.0001398111,0.0002106954],"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":[0.0003167892,0.0001330852,0.001883753,0.0005394871,0.0003432925,0.0002414622,0.005679199,0.0935697,0.001404111,0.6953695,0.0002544904,0.2002651],"study_design_scores_gemma":[0.0008644171,0.0001842206,0.0002424585,0.000276402,0.000137267,0.00001119675,0.002914103,0.9769639,0.0003848372,0.01669418,0.0009304167,0.0003965997],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2604025,0.0007959202,0.7303802,0.0001535716,0.0003056741,0.0003724583,0.000009965553,0.0001112161,0.007468465],"genre_scores_gemma":[0.9905025,0.0003961095,0.006051301,0.00008015987,0.00008852913,0.000001685673,0.000001857098,0.00001623135,0.002861597],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8833942,"threshold_uncertainty_score":0.9998454,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03903952360992188,"score_gpt":0.1995726577564995,"score_spread":0.1605331341465776,"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."}}