{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:G4XLV4EIAZSCTIOWHZCPGLVPCM","short_pith_number":"pith:G4XLV4EI","schema_version":"1.0","canonical_sha256":"372ebaf088066429a1d63e44f32eaf133ddf9583371fecd51fcf258560eb07d6","source":{"kind":"arxiv","id":"2204.06487","version":3},"attestation_state":"computed","paper":{"title":"Adapting Pre-trained Language Models to African Languages via Multilingual Adaptive Fine-Tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"David Ifeoluwa Adelani, Dietrich Klakow, Jesujoba O. Alabi, Marius Mosbach","submitted_at":"2022-04-13T16:13:49Z","abstract_excerpt":"Multilingual pre-trained language models (PLMs) have demonstrated impressive performance on several downstream tasks for both high-resourced and low-resourced languages. However, there is still a large performance drop for languages unseen during pre-training, especially African languages. One of the most effective approaches to adapt to a new language is \\textit{language adaptive fine-tuning} (LAFT) -- fine-tuning a multilingual PLM on monolingual texts of a language using the pre-training objective. However, adapting to a target language individually takes a large disk space and limits the c"},"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":"2204.06487","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-04-13T16:13:49Z","cross_cats_sorted":[],"title_canon_sha256":"00e3f4bdf55f22d0bb695a4e18222fdcedca2ad51ca1b2d28875bc65da66e46d","abstract_canon_sha256":"7a6458c7b118ee1507a6c4462f0db3e835398f0a72174c81966ccd0d8a7e4c40"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:07:41.645779Z","signature_b64":"yQaeP7tME3iiGVqdLf4D3J3wnpuYBhMTAQaTYQHz4wezdb7KxX/DHXKRTplMcIbIe5I+5bS2tPZSdGUfc1ZMAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"372ebaf088066429a1d63e44f32eaf133ddf9583371fecd51fcf258560eb07d6","last_reissued_at":"2026-07-05T05:07:41.645328Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:07:41.645328Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adapting Pre-trained Language Models to African Languages via Multilingual Adaptive Fine-Tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"David Ifeoluwa Adelani, Dietrich Klakow, Jesujoba O. Alabi, Marius Mosbach","submitted_at":"2022-04-13T16:13:49Z","abstract_excerpt":"Multilingual pre-trained language models (PLMs) have demonstrated impressive performance on several downstream tasks for both high-resourced and low-resourced languages. However, there is still a large performance drop for languages unseen during pre-training, especially African languages. One of the most effective approaches to adapt to a new language is \\textit{language adaptive fine-tuning} (LAFT) -- fine-tuning a multilingual PLM on monolingual texts of a language using the pre-training objective. However, adapting to a target language individually takes a large disk space and limits the c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.06487","kind":"arxiv","version":3},"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/2204.06487/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":"2204.06487","created_at":"2026-07-05T05:07:41.645385+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.06487v3","created_at":"2026-07-05T05:07:41.645385+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.06487","created_at":"2026-07-05T05:07:41.645385+00:00"},{"alias_kind":"pith_short_12","alias_value":"G4XLV4EIAZSC","created_at":"2026-07-05T05:07:41.645385+00:00"},{"alias_kind":"pith_short_16","alias_value":"G4XLV4EIAZSCTIOW","created_at":"2026-07-05T05:07:41.645385+00:00"},{"alias_kind":"pith_short_8","alias_value":"G4XLV4EI","created_at":"2026-07-05T05:07:41.645385+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.03241","citing_title":"KinyaColBERT: A Lexically Grounded Retrieval Model for Low-Resource Retrieval-Augmented Generation","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G4XLV4EIAZSCTIOWHZCPGLVPCM","json":"https://pith.science/pith/G4XLV4EIAZSCTIOWHZCPGLVPCM.json","graph_json":"https://pith.science/api/pith-number/G4XLV4EIAZSCTIOWHZCPGLVPCM/graph.json","events_json":"https://pith.science/api/pith-number/G4XLV4EIAZSCTIOWHZCPGLVPCM/events.json","paper":"https://pith.science/paper/G4XLV4EI"},"agent_actions":{"view_html":"https://pith.science/pith/G4XLV4EIAZSCTIOWHZCPGLVPCM","download_json":"https://pith.science/pith/G4XLV4EIAZSCTIOWHZCPGLVPCM.json","view_paper":"https://pith.science/paper/G4XLV4EI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.06487&json=true","fetch_graph":"https://pith.science/api/pith-number/G4XLV4EIAZSCTIOWHZCPGLVPCM/graph.json","fetch_events":"https://pith.science/api/pith-number/G4XLV4EIAZSCTIOWHZCPGLVPCM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G4XLV4EIAZSCTIOWHZCPGLVPCM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G4XLV4EIAZSCTIOWHZCPGLVPCM/action/storage_attestation","attest_author":"https://pith.science/pith/G4XLV4EIAZSCTIOWHZCPGLVPCM/action/author_attestation","sign_citation":"https://pith.science/pith/G4XLV4EIAZSCTIOWHZCPGLVPCM/action/citation_signature","submit_replication":"https://pith.science/pith/G4XLV4EIAZSCTIOWHZCPGLVPCM/action/replication_record"}},"created_at":"2026-07-05T05:07:41.645385+00:00","updated_at":"2026-07-05T05:07:41.645385+00:00"}