{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:EASXLVJVWDBV65WQHQLR4DQ2EC","short_pith_number":"pith:EASXLVJV","canonical_record":{"source":{"id":"2405.20175","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-30T15:45:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"41281743dcbad31acfae08a6176d3955983584c86775a5b47d240996084aba1b","abstract_canon_sha256":"2124a716939f6e84426e3f6ab341a86404614f8ed70fa15c86c4a16470b0a8b9"},"schema_version":"1.0"},"canonical_sha256":"202575d535b0c35f76d03c171e0e1a20892ba06cf28d4ff269079c555d2ee3bd","source":{"kind":"arxiv","id":"2405.20175","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.20175","created_at":"2026-07-05T08:25:17Z"},{"alias_kind":"arxiv_version","alias_value":"2405.20175v1","created_at":"2026-07-05T08:25:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.20175","created_at":"2026-07-05T08:25:17Z"},{"alias_kind":"pith_short_12","alias_value":"EASXLVJVWDBV","created_at":"2026-07-05T08:25:17Z"},{"alias_kind":"pith_short_16","alias_value":"EASXLVJVWDBV65WQ","created_at":"2026-07-05T08:25:17Z"},{"alias_kind":"pith_short_8","alias_value":"EASXLVJV","created_at":"2026-07-05T08:25:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:EASXLVJVWDBV65WQHQLR4DQ2EC","target":"record","payload":{"canonical_record":{"source":{"id":"2405.20175","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-30T15:45:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"41281743dcbad31acfae08a6176d3955983584c86775a5b47d240996084aba1b","abstract_canon_sha256":"2124a716939f6e84426e3f6ab341a86404614f8ed70fa15c86c4a16470b0a8b9"},"schema_version":"1.0"},"canonical_sha256":"202575d535b0c35f76d03c171e0e1a20892ba06cf28d4ff269079c555d2ee3bd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:25:17.033778Z","signature_b64":"+sCV3Wmwa1kf1UfmV5oaIMiF6KRnSKIVodF90KqPyF1X58W7aA/KwGbOhgbV32APxjF8VlzRxW+oALsj3JuVBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"202575d535b0c35f76d03c171e0e1a20892ba06cf28d4ff269079c555d2ee3bd","last_reissued_at":"2026-07-05T08:25:17.033255Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:25:17.033255Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.20175","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:25:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DK3D/SLOsKzimzwJJyWQWGqf8eLBR3x/+fSGJhkzauskcJa3UvcddvIqbDjZH9ts4fUHOaKcVy/BOS6/iwCBDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T05:59:02.843765Z"},"content_sha256":"1cd6e41c2ed338d17b3008dbd1c990685ab9278c4ca72c3e87d83e998b302856","schema_version":"1.0","event_id":"sha256:1cd6e41c2ed338d17b3008dbd1c990685ab9278c4ca72c3e87d83e998b302856"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:EASXLVJVWDBV65WQHQLR4DQ2EC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"InstructionCP: A fast approach to transfer Large Language Models into target language","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hung-yi Lee, Kuang-Ming Chen","submitted_at":"2024-05-30T15:45:13Z","abstract_excerpt":"The rapid development of large language models (LLMs) in recent years has largely focused on English, resulting in models that respond exclusively in English. To adapt these models to other languages, continual pre-training (CP) is often employed, followed by supervised fine-tuning (SFT) to maintain conversational abilities. However, CP and SFT can reduce a model's ability to filter harmful content. We propose Instruction Continual Pre-training (InsCP), which integrates instruction tags into the CP process to prevent loss of conversational proficiency while acquiring new languages. Our experim"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.20175","kind":"arxiv","version":1},"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/2405.20175/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":"2026-07-05T08:25:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aqWWPn5kIVEVtJHY0JQe9X5fAGKyLvpe2gILmmLgTnOTQYR4TNk3qBRsFL7/VYMJ66jvUJN0vs6jkrTfL+hIAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T05:59:02.844257Z"},"content_sha256":"6b8a71ed3ddb6df9c95769fd0c5c9aa75b744538f2c0dfcb247edc0c7925dd21","schema_version":"1.0","event_id":"sha256:6b8a71ed3ddb6df9c95769fd0c5c9aa75b744538f2c0dfcb247edc0c7925dd21"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EASXLVJVWDBV65WQHQLR4DQ2EC/bundle.json","state_url":"https://pith.science/pith/EASXLVJVWDBV65WQHQLR4DQ2EC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EASXLVJVWDBV65WQHQLR4DQ2EC/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":"2026-08-08T05:59:02Z","links":{"resolver":"https://pith.science/pith/EASXLVJVWDBV65WQHQLR4DQ2EC","bundle":"https://pith.science/pith/EASXLVJVWDBV65WQHQLR4DQ2EC/bundle.json","state":"https://pith.science/pith/EASXLVJVWDBV65WQHQLR4DQ2EC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EASXLVJVWDBV65WQHQLR4DQ2EC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EASXLVJVWDBV65WQHQLR4DQ2EC","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":"2124a716939f6e84426e3f6ab341a86404614f8ed70fa15c86c4a16470b0a8b9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-30T15:45:13Z","title_canon_sha256":"41281743dcbad31acfae08a6176d3955983584c86775a5b47d240996084aba1b"},"schema_version":"1.0","source":{"id":"2405.20175","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.20175","created_at":"2026-07-05T08:25:17Z"},{"alias_kind":"arxiv_version","alias_value":"2405.20175v1","created_at":"2026-07-05T08:25:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.20175","created_at":"2026-07-05T08:25:17Z"},{"alias_kind":"pith_short_12","alias_value":"EASXLVJVWDBV","created_at":"2026-07-05T08:25:17Z"},{"alias_kind":"pith_short_16","alias_value":"EASXLVJVWDBV65WQ","created_at":"2026-07-05T08:25:17Z"},{"alias_kind":"pith_short_8","alias_value":"EASXLVJV","created_at":"2026-07-05T08:25:17Z"}],"graph_snapshots":[{"event_id":"sha256:6b8a71ed3ddb6df9c95769fd0c5c9aa75b744538f2c0dfcb247edc0c7925dd21","target":"graph","created_at":"2026-07-05T08:25:17Z","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/2405.20175/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The rapid development of large language models (LLMs) in recent years has largely focused on English, resulting in models that respond exclusively in English. To adapt these models to other languages, continual pre-training (CP) is often employed, followed by supervised fine-tuning (SFT) to maintain conversational abilities. However, CP and SFT can reduce a model's ability to filter harmful content. We propose Instruction Continual Pre-training (InsCP), which integrates instruction tags into the CP process to prevent loss of conversational proficiency while acquiring new languages. Our experim","authors_text":"Hung-yi Lee, Kuang-Ming Chen","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-30T15:45:13Z","title":"InstructionCP: A fast approach to transfer Large Language Models into target language"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.20175","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":"sha256:1cd6e41c2ed338d17b3008dbd1c990685ab9278c4ca72c3e87d83e998b302856","target":"record","created_at":"2026-07-05T08:25:17Z","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":"2124a716939f6e84426e3f6ab341a86404614f8ed70fa15c86c4a16470b0a8b9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-30T15:45:13Z","title_canon_sha256":"41281743dcbad31acfae08a6176d3955983584c86775a5b47d240996084aba1b"},"schema_version":"1.0","source":{"id":"2405.20175","kind":"arxiv","version":1}},"canonical_sha256":"202575d535b0c35f76d03c171e0e1a20892ba06cf28d4ff269079c555d2ee3bd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"202575d535b0c35f76d03c171e0e1a20892ba06cf28d4ff269079c555d2ee3bd","first_computed_at":"2026-07-05T08:25:17.033255Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:25:17.033255Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+sCV3Wmwa1kf1UfmV5oaIMiF6KRnSKIVodF90KqPyF1X58W7aA/KwGbOhgbV32APxjF8VlzRxW+oALsj3JuVBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:25:17.033778Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.20175","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1cd6e41c2ed338d17b3008dbd1c990685ab9278c4ca72c3e87d83e998b302856","sha256:6b8a71ed3ddb6df9c95769fd0c5c9aa75b744538f2c0dfcb247edc0c7925dd21"],"state_sha256":"0f0b354c8ac52740aec9d0f167eaf603ed7514a181f576c8b70144c449e3fd3f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gz+w5hXymuP2TJcYnoPwQ1mtuTEYRlm6tmt7IGxiitlUfCFSOQ94/jkjFhfX5WxaA6WKn5dA9wsDsUI1HfWuAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T05:59:02.848308Z","bundle_sha256":"2f1211769eed54327bbb60e7e54f92029f7cf0c472441eb73cb219a43742bc60"}}