{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:TUJEHDJFDV35NM3LUEH2SP3SLQ","short_pith_number":"pith:TUJEHDJF","canonical_record":{"source":{"id":"2405.13923","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-22T18:53:25Z","cross_cats_sorted":[],"title_canon_sha256":"850324bac97b73281b5bf37ae4899c4419fcf16fd3c67698a736584d97469311","abstract_canon_sha256":"2cd460344cf6a0b486434b6d877e57ce83ffe4c8339791408056b8903c017381"},"schema_version":"1.0"},"canonical_sha256":"9d12438d251d77d6b36ba10fa93f725c016ec9d170f9e4e7cd69982e0f86c3d7","source":{"kind":"arxiv","id":"2405.13923","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.13923","created_at":"2026-07-05T12:02:34Z"},{"alias_kind":"arxiv_version","alias_value":"2405.13923v3","created_at":"2026-07-05T12:02:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.13923","created_at":"2026-07-05T12:02:34Z"},{"alias_kind":"pith_short_12","alias_value":"TUJEHDJFDV35","created_at":"2026-07-05T12:02:34Z"},{"alias_kind":"pith_short_16","alias_value":"TUJEHDJFDV35NM3L","created_at":"2026-07-05T12:02:34Z"},{"alias_kind":"pith_short_8","alias_value":"TUJEHDJF","created_at":"2026-07-05T12:02:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:TUJEHDJFDV35NM3LUEH2SP3SLQ","target":"record","payload":{"canonical_record":{"source":{"id":"2405.13923","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-22T18:53:25Z","cross_cats_sorted":[],"title_canon_sha256":"850324bac97b73281b5bf37ae4899c4419fcf16fd3c67698a736584d97469311","abstract_canon_sha256":"2cd460344cf6a0b486434b6d877e57ce83ffe4c8339791408056b8903c017381"},"schema_version":"1.0"},"canonical_sha256":"9d12438d251d77d6b36ba10fa93f725c016ec9d170f9e4e7cd69982e0f86c3d7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:02:34.266556Z","signature_b64":"lZYHKviQ43FM/HQ+zAfWElB3AjMFiVKnFtMyRihK8cHjgAyGAuVq8tfCLeimfqKC8SLtJveP3xFmybyJb4P6Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d12438d251d77d6b36ba10fa93f725c016ec9d170f9e4e7cd69982e0f86c3d7","last_reissued_at":"2026-07-05T12:02:34.265961Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:02:34.265961Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.13923","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:02:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YdFGSuRsu1GVxnBoxwab6mGZn+QEdWONLn/nqaNyeXFwgEzGy1xzl3B9zo8lQPaZTw41qF1qytZXHtaBAPvwCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-16T11:31:58.233479Z"},"content_sha256":"df2b3b8e88ae051bbd5b5b3d067c92c1fc9b10661b7b7ac8ce980318af68392b","schema_version":"1.0","event_id":"sha256:df2b3b8e88ae051bbd5b5b3d067c92c1fc9b10661b7b7ac8ce980318af68392b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:TUJEHDJFDV35NM3LUEH2SP3SLQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Why Not Transform Chat Large Language Models to Non-English?","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chang Su, Hao Yang, Jiahuan Li, Jiajun Chen, Jiaxin Guo, Ming Zhu, Min Zhang, Shuaijie She, Shujian Huang, Wei Zou, Xiang Geng, Xiaofeng Zhao, Xinglin Lyu, Yanqing Zhao, Yinglu Li, Yuang Li, Zhejian Lai","submitted_at":"2024-05-22T18:53:25Z","abstract_excerpt":"The scarcity of non-English data limits the development of non-English large language models (LLMs). Transforming English-centric LLMs to non-English has been identified as an effective and resource-efficient method. Previous works start from base LLMs and perform knowledge distillation (KD) with data generated by stronger LLMs, e.g. GPT-4. Compared to base LLMs, chat LLMs are further optimized for advanced abilities, e.g. multi-turn conversation and human preference alignment, and thus more powerful in both helpfulness and safety. However, transforming a chat LLM involves two critical issues:"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.13923","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/2405.13923/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:02:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WRrsuAxa05YzIFttA35cnNPOgKF+nB7lKPc/P/AA/0B6FrK+4tCbuLz2xyyEvZmFq3eBKhBEbNYkEuiBQUmfCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-16T11:31:58.233855Z"},"content_sha256":"0fde41c514f50b2358c2afe2e53bf1f07c464309932261f5fe421a6d595be153","schema_version":"1.0","event_id":"sha256:0fde41c514f50b2358c2afe2e53bf1f07c464309932261f5fe421a6d595be153"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TUJEHDJFDV35NM3LUEH2SP3SLQ/bundle.json","state_url":"https://pith.science/pith/TUJEHDJFDV35NM3LUEH2SP3SLQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TUJEHDJFDV35NM3LUEH2SP3SLQ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-16T11:31:58Z","links":{"resolver":"https://pith.science/pith/TUJEHDJFDV35NM3LUEH2SP3SLQ","bundle":"https://pith.science/pith/TUJEHDJFDV35NM3LUEH2SP3SLQ/bundle.json","state":"https://pith.science/pith/TUJEHDJFDV35NM3LUEH2SP3SLQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TUJEHDJFDV35NM3LUEH2SP3SLQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TUJEHDJFDV35NM3LUEH2SP3SLQ","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":"2cd460344cf6a0b486434b6d877e57ce83ffe4c8339791408056b8903c017381","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-22T18:53:25Z","title_canon_sha256":"850324bac97b73281b5bf37ae4899c4419fcf16fd3c67698a736584d97469311"},"schema_version":"1.0","source":{"id":"2405.13923","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.13923","created_at":"2026-07-05T12:02:34Z"},{"alias_kind":"arxiv_version","alias_value":"2405.13923v3","created_at":"2026-07-05T12:02:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.13923","created_at":"2026-07-05T12:02:34Z"},{"alias_kind":"pith_short_12","alias_value":"TUJEHDJFDV35","created_at":"2026-07-05T12:02:34Z"},{"alias_kind":"pith_short_16","alias_value":"TUJEHDJFDV35NM3L","created_at":"2026-07-05T12:02:34Z"},{"alias_kind":"pith_short_8","alias_value":"TUJEHDJF","created_at":"2026-07-05T12:02:34Z"}],"graph_snapshots":[{"event_id":"sha256:0fde41c514f50b2358c2afe2e53bf1f07c464309932261f5fe421a6d595be153","target":"graph","created_at":"2026-07-05T12:02:34Z","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/2405.13923/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The scarcity of non-English data limits the development of non-English large language models (LLMs). Transforming English-centric LLMs to non-English has been identified as an effective and resource-efficient method. Previous works start from base LLMs and perform knowledge distillation (KD) with data generated by stronger LLMs, e.g. GPT-4. Compared to base LLMs, chat LLMs are further optimized for advanced abilities, e.g. multi-turn conversation and human preference alignment, and thus more powerful in both helpfulness and safety. However, transforming a chat LLM involves two critical issues:","authors_text":"Chang Su, Hao Yang, Jiahuan Li, Jiajun Chen, Jiaxin Guo, Ming Zhu, Min Zhang, Shuaijie She, Shujian Huang, Wei Zou, Xiang Geng, Xiaofeng Zhao, Xinglin Lyu, Yanqing Zhao, Yinglu Li, Yuang Li, Zhejian Lai","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-22T18:53:25Z","title":"Why Not Transform Chat Large Language Models to Non-English?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.13923","kind":"arxiv","version":3},"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:df2b3b8e88ae051bbd5b5b3d067c92c1fc9b10661b7b7ac8ce980318af68392b","target":"record","created_at":"2026-07-05T12:02:34Z","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":"2cd460344cf6a0b486434b6d877e57ce83ffe4c8339791408056b8903c017381","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-22T18:53:25Z","title_canon_sha256":"850324bac97b73281b5bf37ae4899c4419fcf16fd3c67698a736584d97469311"},"schema_version":"1.0","source":{"id":"2405.13923","kind":"arxiv","version":3}},"canonical_sha256":"9d12438d251d77d6b36ba10fa93f725c016ec9d170f9e4e7cd69982e0f86c3d7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9d12438d251d77d6b36ba10fa93f725c016ec9d170f9e4e7cd69982e0f86c3d7","first_computed_at":"2026-07-05T12:02:34.265961Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:02:34.265961Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lZYHKviQ43FM/HQ+zAfWElB3AjMFiVKnFtMyRihK8cHjgAyGAuVq8tfCLeimfqKC8SLtJveP3xFmybyJb4P6Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T12:02:34.266556Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.13923","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:df2b3b8e88ae051bbd5b5b3d067c92c1fc9b10661b7b7ac8ce980318af68392b","sha256:0fde41c514f50b2358c2afe2e53bf1f07c464309932261f5fe421a6d595be153"],"state_sha256":"7075593034cd4cb12ce43795b03ce4aca352a394576bdfac8475761a2b2d42b9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Jc4H9NwVbtGp6ZLxuZcwa2Y3Lmf0qrIaXU/4au70v+baGRmesJCTdF40egreQ+OhHYuVwUMCWp94i0zRrjnxCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-16T11:31:58.235994Z","bundle_sha256":"52b9e96d779e97b90c6d599c352081496e387058fd0168bfbe6fa6017cb9d06f"}}