{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CFTZHTAJLMO6BIF3DM5TKIPXRJ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"0c1fc10fd8cb87b28bba3e0adfaab6d330ad07d14a31820d9684b9ca303930f1","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-16T23:50:21Z","title_canon_sha256":"6cc26a9d9d2baa5277a30b758fcee99b9921b8916112211335f319dca997bc94"},"schema_version":"1.0","source":{"id":"2412.12417","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.12417","created_at":"2026-07-05T09:50:14Z"},{"alias_kind":"arxiv_version","alias_value":"2412.12417v1","created_at":"2026-07-05T09:50:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.12417","created_at":"2026-07-05T09:50:14Z"},{"alias_kind":"pith_short_12","alias_value":"CFTZHTAJLMO6","created_at":"2026-07-05T09:50:14Z"},{"alias_kind":"pith_short_16","alias_value":"CFTZHTAJLMO6BIF3","created_at":"2026-07-05T09:50:14Z"},{"alias_kind":"pith_short_8","alias_value":"CFTZHTAJ","created_at":"2026-07-05T09:50:14Z"}],"graph_snapshots":[{"event_id":"sha256:5ed285b27b12675d373b3f78a34476835bd9c97cd01487b49cd4210d9ad7aaee","target":"graph","created_at":"2026-07-05T09:50:14Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2412.12417/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have shown remarkable performance across various tasks, yet significant disparities remain for non-English languages, and especially native African languages. This paper addresses these disparities by creating approximately 1 million human-translated words of new benchmark data in 8 low-resource African languages, covering a population of over 160 million speakers of: Amharic, Bambara, Igbo, Sepedi (Northern Sotho), Shona, Sesotho (Southern Sotho), Setswana, and Tsonga. Our benchmarks are translations of Winogrande and three sections of MMLU: college medicine, clin","authors_text":"Adam Kasumovic, Aven Zitzelberger, Guillaume Chabot-Couture, Jessica Lundin, Mohammad Ghassemi, Tuka Alhanai","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-16T23:50:21Z","title":"Bridging the Gap: Enhancing LLM Performance for Low-Resource African Languages with New Benchmarks, Fine-Tuning, and Cultural Adjustments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.12417","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:9dc34bfcaef760705695aa79a67b56f69b875fab110bdb75fc4ef85b0b360319","target":"record","created_at":"2026-07-05T09:50:14Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"0c1fc10fd8cb87b28bba3e0adfaab6d330ad07d14a31820d9684b9ca303930f1","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-16T23:50:21Z","title_canon_sha256":"6cc26a9d9d2baa5277a30b758fcee99b9921b8916112211335f319dca997bc94"},"schema_version":"1.0","source":{"id":"2412.12417","kind":"arxiv","version":1}},"canonical_sha256":"116793cc095b1de0a0bb1b3b3521f78a5186beee131cafa71e0399995d71e337","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"116793cc095b1de0a0bb1b3b3521f78a5186beee131cafa71e0399995d71e337","first_computed_at":"2026-07-05T09:50:14.570715Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:50:14.570715Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5TQp8gr1KZl82IkaXzwLdezkwjsqwDZfiBfeDfCVqR9v3af0Lokex0I8/LXR6JN3n55yvMC4abOhSDV6gQaqAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:50:14.571200Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.12417","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9dc34bfcaef760705695aa79a67b56f69b875fab110bdb75fc4ef85b0b360319","sha256:5ed285b27b12675d373b3f78a34476835bd9c97cd01487b49cd4210d9ad7aaee"],"state_sha256":"07dbb7577e58d7494ae66f6e5570e870f87888b689aa1d1743e09fc211a9ea4d"}