{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2SFLDA2DZKJ2KOGZOXX7E4S2RT","short_pith_number":"pith:2SFLDA2D","schema_version":"1.0","canonical_sha256":"d48ab18343ca93a538d975eff2725a8cf00af0f50c9f011508abd50b429cd994","source":{"kind":"arxiv","id":"2502.19582","version":2},"attestation_state":"computed","paper":{"title":"Where Are We? Evaluating LLM Performance on African Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"AbdelRahim Elmadany, Hawau Olamide Toyin, Ife Adebara, Muhammad Abdul-Mageed, Nahom Tesfu Ghebremichael","submitted_at":"2025-02-26T21:49:54Z","abstract_excerpt":"Africa's rich linguistic heritage remains underrepresented in NLP, largely due to historical policies that favor foreign languages and create significant data inequities. In this paper, we integrate theoretical insights on Africa's language landscape with an empirical evaluation using Sahara - a comprehensive benchmark curated from large-scale, publicly accessible datasets capturing the continent's linguistic diversity. By systematically assessing the performance of leading large language models (LLMs) on Sahara, we demonstrate how policy-induced data variations directly impact model effective"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2502.19582","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-26T21:49:54Z","cross_cats_sorted":[],"title_canon_sha256":"8362cbe4ac5ef27ebcf2ee00e5ed112a5e8e4629a0c8d2624c04fa33ceb6f875","abstract_canon_sha256":"e56da4e04333e8dbb3a76091565f2e8615536ce59b90969558ff23765883a94a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:19.797450Z","signature_b64":"m+0zDJl+CgSPxvrMlYJ5gsXRgLe3zl6V6P6525i/cCmEefQOHd7ivQ/ISnE0DNF6BLQ1oHxb525TehZVlDQgDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d48ab18343ca93a538d975eff2725a8cf00af0f50c9f011508abd50b429cd994","last_reissued_at":"2026-07-05T11:15:19.796895Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:19.796895Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Where Are We? Evaluating LLM Performance on African Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"AbdelRahim Elmadany, Hawau Olamide Toyin, Ife Adebara, Muhammad Abdul-Mageed, Nahom Tesfu Ghebremichael","submitted_at":"2025-02-26T21:49:54Z","abstract_excerpt":"Africa's rich linguistic heritage remains underrepresented in NLP, largely due to historical policies that favor foreign languages and create significant data inequities. In this paper, we integrate theoretical insights on Africa's language landscape with an empirical evaluation using Sahara - a comprehensive benchmark curated from large-scale, publicly accessible datasets capturing the continent's linguistic diversity. By systematically assessing the performance of leading large language models (LLMs) on Sahara, we demonstrate how policy-induced data variations directly impact model effective"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.19582","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2502.19582/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2502.19582","created_at":"2026-07-05T11:15:19.796955+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.19582v2","created_at":"2026-07-05T11:15:19.796955+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.19582","created_at":"2026-07-05T11:15:19.796955+00:00"},{"alias_kind":"pith_short_12","alias_value":"2SFLDA2DZKJ2","created_at":"2026-07-05T11:15:19.796955+00:00"},{"alias_kind":"pith_short_16","alias_value":"2SFLDA2DZKJ2KOGZ","created_at":"2026-07-05T11:15:19.796955+00:00"},{"alias_kind":"pith_short_8","alias_value":"2SFLDA2D","created_at":"2026-07-05T11:15:19.796955+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2SFLDA2DZKJ2KOGZOXX7E4S2RT","json":"https://pith.science/pith/2SFLDA2DZKJ2KOGZOXX7E4S2RT.json","graph_json":"https://pith.science/api/pith-number/2SFLDA2DZKJ2KOGZOXX7E4S2RT/graph.json","events_json":"https://pith.science/api/pith-number/2SFLDA2DZKJ2KOGZOXX7E4S2RT/events.json","paper":"https://pith.science/paper/2SFLDA2D"},"agent_actions":{"view_html":"https://pith.science/pith/2SFLDA2DZKJ2KOGZOXX7E4S2RT","download_json":"https://pith.science/pith/2SFLDA2DZKJ2KOGZOXX7E4S2RT.json","view_paper":"https://pith.science/paper/2SFLDA2D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.19582&json=true","fetch_graph":"https://pith.science/api/pith-number/2SFLDA2DZKJ2KOGZOXX7E4S2RT/graph.json","fetch_events":"https://pith.science/api/pith-number/2SFLDA2DZKJ2KOGZOXX7E4S2RT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2SFLDA2DZKJ2KOGZOXX7E4S2RT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2SFLDA2DZKJ2KOGZOXX7E4S2RT/action/storage_attestation","attest_author":"https://pith.science/pith/2SFLDA2DZKJ2KOGZOXX7E4S2RT/action/author_attestation","sign_citation":"https://pith.science/pith/2SFLDA2DZKJ2KOGZOXX7E4S2RT/action/citation_signature","submit_replication":"https://pith.science/pith/2SFLDA2DZKJ2KOGZOXX7E4S2RT/action/replication_record"}},"created_at":"2026-07-05T11:15:19.796955+00:00","updated_at":"2026-07-05T11:15:19.796955+00:00"}