{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:W6K3X444YGGN5YKDX67FSTAYPI","short_pith_number":"pith:W6K3X444","schema_version":"1.0","canonical_sha256":"b795bbf39cc18cdee143bfbe594c187a32fd185af0230932ab594b5ccc2d5906","source":{"kind":"arxiv","id":"2212.10785","version":2},"attestation_state":"computed","paper":{"title":"SERENGETI: Massively Multilingual Language Models for Africa","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"AbdelRahim Elmadany, Alcides Alcoba Inciarte, Ife Adebara, Muhammad Abdul-Mageed","submitted_at":"2022-12-21T05:54:14Z","abstract_excerpt":"Multilingual pretrained language models (mPLMs) acquire valuable, generalizable linguistic information during pretraining and have advanced the state of the art on task-specific finetuning. To date, only ~31 out of ~2,000 African languages are covered in existing language models. We ameliorate this limitation by developing SERENGETI, a massively multilingual language model that covers 517 African languages and language varieties. We evaluate our novel models on eight natural language understanding tasks across 20 datasets, comparing to 4 mPLMs that cover 4-23 African languages. SERENGETI outpe"},"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":"2212.10785","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-21T05:54:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e549826aa96a4b79bc3e6a47602d6d2194fba75ecdc85f63f076593c27a4bb59","abstract_canon_sha256":"fd364e2480e35581c5bf16744eea9e6acafd133522481d6cfe911c5cc99daaa1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:14:23.477238Z","signature_b64":"uUgO7aVxNwDEOgDXWDuilT6HH3M6UEPp8Dqc8ygg1qrLy+AwVaFOLo+U8sOd0W09AuzNBbrMUiK/lnayBSElBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b795bbf39cc18cdee143bfbe594c187a32fd185af0230932ab594b5ccc2d5906","last_reissued_at":"2026-07-05T06:14:23.476667Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:14:23.476667Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SERENGETI: Massively Multilingual Language Models for Africa","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"AbdelRahim Elmadany, Alcides Alcoba Inciarte, Ife Adebara, Muhammad Abdul-Mageed","submitted_at":"2022-12-21T05:54:14Z","abstract_excerpt":"Multilingual pretrained language models (mPLMs) acquire valuable, generalizable linguistic information during pretraining and have advanced the state of the art on task-specific finetuning. To date, only ~31 out of ~2,000 African languages are covered in existing language models. We ameliorate this limitation by developing SERENGETI, a massively multilingual language model that covers 517 African languages and language varieties. We evaluate our novel models on eight natural language understanding tasks across 20 datasets, comparing to 4 mPLMs that cover 4-23 African languages. SERENGETI outpe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.10785","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/2212.10785/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":"2212.10785","created_at":"2026-07-05T06:14:23.476763+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.10785v2","created_at":"2026-07-05T06:14:23.476763+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.10785","created_at":"2026-07-05T06:14:23.476763+00:00"},{"alias_kind":"pith_short_12","alias_value":"W6K3X444YGGN","created_at":"2026-07-05T06:14:23.476763+00:00"},{"alias_kind":"pith_short_16","alias_value":"W6K3X444YGGN5YKD","created_at":"2026-07-05T06:14:23.476763+00:00"},{"alias_kind":"pith_short_8","alias_value":"W6K3X444","created_at":"2026-07-05T06:14:23.476763+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/W6K3X444YGGN5YKDX67FSTAYPI","json":"https://pith.science/pith/W6K3X444YGGN5YKDX67FSTAYPI.json","graph_json":"https://pith.science/api/pith-number/W6K3X444YGGN5YKDX67FSTAYPI/graph.json","events_json":"https://pith.science/api/pith-number/W6K3X444YGGN5YKDX67FSTAYPI/events.json","paper":"https://pith.science/paper/W6K3X444"},"agent_actions":{"view_html":"https://pith.science/pith/W6K3X444YGGN5YKDX67FSTAYPI","download_json":"https://pith.science/pith/W6K3X444YGGN5YKDX67FSTAYPI.json","view_paper":"https://pith.science/paper/W6K3X444","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.10785&json=true","fetch_graph":"https://pith.science/api/pith-number/W6K3X444YGGN5YKDX67FSTAYPI/graph.json","fetch_events":"https://pith.science/api/pith-number/W6K3X444YGGN5YKDX67FSTAYPI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W6K3X444YGGN5YKDX67FSTAYPI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W6K3X444YGGN5YKDX67FSTAYPI/action/storage_attestation","attest_author":"https://pith.science/pith/W6K3X444YGGN5YKDX67FSTAYPI/action/author_attestation","sign_citation":"https://pith.science/pith/W6K3X444YGGN5YKDX67FSTAYPI/action/citation_signature","submit_replication":"https://pith.science/pith/W6K3X444YGGN5YKDX67FSTAYPI/action/replication_record"}},"created_at":"2026-07-05T06:14:23.476763+00:00","updated_at":"2026-07-05T06:14:23.476763+00:00"}