{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:M7NKI6LEJ5E2NYLRF2RPHNWRHF","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":"ae33d6498ec043a36ded154761ff8ecb08ed578ce7d237ea1215a459585620f7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-13T21:09:38Z","title_canon_sha256":"5004e04562b885a0300451445eeaa1c6d67147dca6b5fcbfd3ba537ae669c257"},"schema_version":"1.0","source":{"id":"2407.12869","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.12869","created_at":"2026-07-05T08:48:45Z"},{"alias_kind":"arxiv_version","alias_value":"2407.12869v2","created_at":"2026-07-05T08:48:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12869","created_at":"2026-07-05T08:48:45Z"},{"alias_kind":"pith_short_12","alias_value":"M7NKI6LEJ5E2","created_at":"2026-07-05T08:48:45Z"},{"alias_kind":"pith_short_16","alias_value":"M7NKI6LEJ5E2NYLR","created_at":"2026-07-05T08:48:45Z"},{"alias_kind":"pith_short_8","alias_value":"M7NKI6LE","created_at":"2026-07-05T08:48:45Z"}],"graph_snapshots":[{"event_id":"sha256:16e70b4e6865cce52211a6bacc65f28a64e36439c7c6fefefdb3bb9274c057c4","target":"graph","created_at":"2026-07-05T08:48:45Z","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/2407.12869/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present an efficient method for adapting a monolingual Large Language Model (LLM) to another language, addressing challenges of catastrophic forgetting and tokenizer limitations. We focus this study on adapting Llama 2 to Arabic. Our two-stage approach begins with expanding the vocabulary and training only the embeddings matrix, followed by full model continual pre-training on a bilingual corpus. By continually pre-training on a mix of Arabic and English corpora, the model retains its proficiency in English while acquiring capabilities in Arabic. Our approach results in significant improvem","authors_text":"Avraham Sheinin, Biswajit Mishra, Bokang Jia, Gokul Ramakrishnan, Gurpreet Gosal, Joel Hestness, Mohamed El Karim Chami, Natalia Vassilieva, Neha Sengupta, Onkar Pandit, Parvez Mullah, Preslav Nakov, Rahul Pal, Rituraj Joshi, Samta Kamboj, Samujjwal Ghosh, Satheesh Katipomu, Soundar Doraiswamy, Sunil Kumar Sahu, Yishi Xu, Zhiming (Charles) Chen","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-13T21:09:38Z","title":"Bilingual Adaptation of Monolingual Foundation Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.12869","kind":"arxiv","version":2},"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":"sha256:7078e0db823b07b972c478d7a0462ec62b611e06d202bb0478948f8dbf62e58f","target":"record","created_at":"2026-07-05T08:48:45Z","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":"ae33d6498ec043a36ded154761ff8ecb08ed578ce7d237ea1215a459585620f7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-13T21:09:38Z","title_canon_sha256":"5004e04562b885a0300451445eeaa1c6d67147dca6b5fcbfd3ba537ae669c257"},"schema_version":"1.0","source":{"id":"2407.12869","kind":"arxiv","version":2}},"canonical_sha256":"67daa479644f49a6e1712ea2f3b6d1397735a010d8ab12b1fd22353cf24af2c5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"67daa479644f49a6e1712ea2f3b6d1397735a010d8ab12b1fd22353cf24af2c5","first_computed_at":"2026-07-05T08:48:45.684803Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:48:45.684803Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ARXNhdjXM6evHRomff34NhBi8sDpbhMxJJ7TGxhdua7jGlDCd95zExgkKMIEVEUkL2f/rIIg4TWNQKUKeAxYCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:48:45.685241Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.12869","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7078e0db823b07b972c478d7a0462ec62b611e06d202bb0478948f8dbf62e58f","sha256:16e70b4e6865cce52211a6bacc65f28a64e36439c7c6fefefdb3bb9274c057c4"],"state_sha256":"fd2ed2de060f13833a68f9917eec1c171761e10a6d40a88186ad08f6e47e4556"}