{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BCWLLW7TFK4AJS5XXM5OE2LXQR","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":"e3dc41edaa013c99e82fcf04d6f63fa3d71127954164f6cf7cce348d148472c3","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-27T06:07:55Z","title_canon_sha256":"600e1964d629da32441c1a2aa631ab3a49dc6dc3eac92044d81adf610ffb1dac"},"schema_version":"1.0","source":{"id":"2404.17790","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.17790","created_at":"2026-07-05T08:12:54Z"},{"alias_kind":"arxiv_version","alias_value":"2404.17790v1","created_at":"2026-07-05T08:12:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.17790","created_at":"2026-07-05T08:12:54Z"},{"alias_kind":"pith_short_12","alias_value":"BCWLLW7TFK4A","created_at":"2026-07-05T08:12:54Z"},{"alias_kind":"pith_short_16","alias_value":"BCWLLW7TFK4AJS5X","created_at":"2026-07-05T08:12:54Z"},{"alias_kind":"pith_short_8","alias_value":"BCWLLW7T","created_at":"2026-07-05T08:12:54Z"}],"graph_snapshots":[{"event_id":"sha256:c3436fc34fe191dbff9aa7027801ac72d5e5291b8963f8044ea063f261af7283","target":"graph","created_at":"2026-07-05T08:12:54Z","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/2404.17790/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Cross-lingual continual pre-training of large language models (LLMs) initially trained on English corpus allows us to leverage the vast amount of English language resources and reduce the pre-training cost. In this study, we constructed Swallow, an LLM with enhanced Japanese capability, by extending the vocabulary of Llama 2 to include Japanese characters and conducting continual pre-training on a large Japanese web corpus. Experimental results confirmed that the performance on Japanese tasks drastically improved through continual pre-training, and the performance monotonically increased with ","authors_text":"Hirai Shota, Hiroki Iida, Kakeru Hattori, Kazuki Fujii, Masanari Ohi, Mengsay Loem, Naoaki Okazaki, Rio Yokota, Sakae Mizuki, Taishi Nakamura","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-27T06:07:55Z","title":"Continual Pre-Training for Cross-Lingual LLM Adaptation: Enhancing Japanese Language Capabilities"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.17790","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":"sha256:522f7d347f12608d706c10a66d87033cdc885a4ff95d647ca81209bf7f23143e","target":"record","created_at":"2026-07-05T08:12:54Z","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":"e3dc41edaa013c99e82fcf04d6f63fa3d71127954164f6cf7cce348d148472c3","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-27T06:07:55Z","title_canon_sha256":"600e1964d629da32441c1a2aa631ab3a49dc6dc3eac92044d81adf610ffb1dac"},"schema_version":"1.0","source":{"id":"2404.17790","kind":"arxiv","version":1}},"canonical_sha256":"08acb5dbf32ab804cbb7bb3ae269778452d04cd8aeabc340845403bfaf2d41ca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"08acb5dbf32ab804cbb7bb3ae269778452d04cd8aeabc340845403bfaf2d41ca","first_computed_at":"2026-07-05T08:12:54.219866Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:12:54.219866Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"u394pHorc/rgPEHZcQNK54/p50rwMePlhwn3eRnWxo1ZqIhzd/SdRd0HZExYA4aw4Ql2zTulpjwXcgokXCVoDA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:12:54.220356Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.17790","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:522f7d347f12608d706c10a66d87033cdc885a4ff95d647ca81209bf7f23143e","sha256:c3436fc34fe191dbff9aa7027801ac72d5e5291b8963f8044ea063f261af7283"],"state_sha256":"53ed2e8879453361ecc4f804b9f9a2831c527507e9d8ad2619b74e06852e169f"}