{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:C5QSEJMJ2NVI2LOW6HD55ZNLDB","short_pith_number":"pith:C5QSEJMJ","canonical_record":{"source":{"id":"2407.18743","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-26T13:55:21Z","cross_cats_sorted":[],"title_canon_sha256":"a80de6b1a0d0453365993a8d564585825d02ec1f498601f86b183cb2c1514fe3","abstract_canon_sha256":"a92e63c92c4c75e5307de800b1789f36d3d6042d58d974846ba318a70d405fdc"},"schema_version":"1.0"},"canonical_sha256":"1761222589d36a8d2dd6f1c7dee5ab18791c07fd31cacfd41c13a5be06c91a68","source":{"kind":"arxiv","id":"2407.18743","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.18743","created_at":"2026-07-05T08:48:54Z"},{"alias_kind":"arxiv_version","alias_value":"2407.18743v1","created_at":"2026-07-05T08:48:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.18743","created_at":"2026-07-05T08:48:54Z"},{"alias_kind":"pith_short_12","alias_value":"C5QSEJMJ2NVI","created_at":"2026-07-05T08:48:54Z"},{"alias_kind":"pith_short_16","alias_value":"C5QSEJMJ2NVI2LOW","created_at":"2026-07-05T08:48:54Z"},{"alias_kind":"pith_short_8","alias_value":"C5QSEJMJ","created_at":"2026-07-05T08:48:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:C5QSEJMJ2NVI2LOW6HD55ZNLDB","target":"record","payload":{"canonical_record":{"source":{"id":"2407.18743","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-26T13:55:21Z","cross_cats_sorted":[],"title_canon_sha256":"a80de6b1a0d0453365993a8d564585825d02ec1f498601f86b183cb2c1514fe3","abstract_canon_sha256":"a92e63c92c4c75e5307de800b1789f36d3d6042d58d974846ba318a70d405fdc"},"schema_version":"1.0"},"canonical_sha256":"1761222589d36a8d2dd6f1c7dee5ab18791c07fd31cacfd41c13a5be06c91a68","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:48:54.399092Z","signature_b64":"ytV42SWolQNRlEKI57os6fY7hTO9zHa+7JUTqwWG/jGI11/yVVbhp2i6LM+IMGdGfkjISfWI2UoMY5EBTz37AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1761222589d36a8d2dd6f1c7dee5ab18791c07fd31cacfd41c13a5be06c91a68","last_reissued_at":"2026-07-05T08:48:54.398716Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:48:54.398716Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.18743","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":"2026-07-05T08:48:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/d5T/mfknBAmPwVZRFfqIaIkpi5fsG9plZuYE41HEOHscjfSEl/2UlHaZzKuRdbU6KsR0fD9Emsog7S7zMuOBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T15:49:06.646423Z"},"content_sha256":"987dd217fe9a795a9995ddfde52fb6637024b58f0973e0c6e3b36ada1e518bba","schema_version":"1.0","event_id":"sha256:987dd217fe9a795a9995ddfde52fb6637024b58f0973e0c6e3b36ada1e518bba"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:C5QSEJMJ2NVI2LOW6HD55ZNLDB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Effective and Efficient Continual Pre-training of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Di Hu, Jiapeng Wang, Jiaxin Mao, Jie Chen, Jinhao Jiang, Ji-Rong Wen, Jun Xu, Kun Zhou, Ruihua Song, Rui Yan, Wayne Xin Zhao, Wenbing Huang, Xu Chen, Yankai Lin, Yingqian Min, Yutao Zhu, Zhewei Wei, Zhicheng Dou, Zhipeng Chen","submitted_at":"2024-07-26T13:55:21Z","abstract_excerpt":"Continual pre-training (CPT) has been an important approach for adapting language models to specific domains or tasks. To make the CPT approach more traceable, this paper presents a technical report for continually pre-training Llama-3 (8B), which significantly enhances the Chinese language ability and scientific reasoning ability of the backbone model. To enhance the new abilities while retaining the original abilities, we design specific data mixture and curriculum strategies by utilizing existing datasets and synthesizing high-quality datasets. Specifically, we synthesize multidisciplinary "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.18743","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/2407.18743/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":"2026-07-05T08:48:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EYT1npd9FpfJVrQjiRdSXiBnKknDxHeGED4aTCDfRd9Y4jvW+OClLNuKXc4IsGPNYaQ3YgUNf638o8GzXt5yBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T15:49:06.646938Z"},"content_sha256":"19d93032018165d62fa04a374d9a70cc83b67bc97c2d7fd4da98fd8f5b6b4294","schema_version":"1.0","event_id":"sha256:19d93032018165d62fa04a374d9a70cc83b67bc97c2d7fd4da98fd8f5b6b4294"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/C5QSEJMJ2NVI2LOW6HD55ZNLDB/bundle.json","state_url":"https://pith.science/pith/C5QSEJMJ2NVI2LOW6HD55ZNLDB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/C5QSEJMJ2NVI2LOW6HD55ZNLDB/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":"2026-08-07T15:49:06Z","links":{"resolver":"https://pith.science/pith/C5QSEJMJ2NVI2LOW6HD55ZNLDB","bundle":"https://pith.science/pith/C5QSEJMJ2NVI2LOW6HD55ZNLDB/bundle.json","state":"https://pith.science/pith/C5QSEJMJ2NVI2LOW6HD55ZNLDB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/C5QSEJMJ2NVI2LOW6HD55ZNLDB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:C5QSEJMJ2NVI2LOW6HD55ZNLDB","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":"a92e63c92c4c75e5307de800b1789f36d3d6042d58d974846ba318a70d405fdc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-26T13:55:21Z","title_canon_sha256":"a80de6b1a0d0453365993a8d564585825d02ec1f498601f86b183cb2c1514fe3"},"schema_version":"1.0","source":{"id":"2407.18743","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.18743","created_at":"2026-07-05T08:48:54Z"},{"alias_kind":"arxiv_version","alias_value":"2407.18743v1","created_at":"2026-07-05T08:48:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.18743","created_at":"2026-07-05T08:48:54Z"},{"alias_kind":"pith_short_12","alias_value":"C5QSEJMJ2NVI","created_at":"2026-07-05T08:48:54Z"},{"alias_kind":"pith_short_16","alias_value":"C5QSEJMJ2NVI2LOW","created_at":"2026-07-05T08:48:54Z"},{"alias_kind":"pith_short_8","alias_value":"C5QSEJMJ","created_at":"2026-07-05T08:48:54Z"}],"graph_snapshots":[{"event_id":"sha256:19d93032018165d62fa04a374d9a70cc83b67bc97c2d7fd4da98fd8f5b6b4294","target":"graph","created_at":"2026-07-05T08:48:54Z","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/2407.18743/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Continual pre-training (CPT) has been an important approach for adapting language models to specific domains or tasks. To make the CPT approach more traceable, this paper presents a technical report for continually pre-training Llama-3 (8B), which significantly enhances the Chinese language ability and scientific reasoning ability of the backbone model. To enhance the new abilities while retaining the original abilities, we design specific data mixture and curriculum strategies by utilizing existing datasets and synthesizing high-quality datasets. Specifically, we synthesize multidisciplinary ","authors_text":"Di Hu, Jiapeng Wang, Jiaxin Mao, Jie Chen, Jinhao Jiang, Ji-Rong Wen, Jun Xu, Kun Zhou, Ruihua Song, Rui Yan, Wayne Xin Zhao, Wenbing Huang, Xu Chen, Yankai Lin, Yingqian Min, Yutao Zhu, Zhewei Wei, Zhicheng Dou, Zhipeng Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-26T13:55:21Z","title":"Towards Effective and Efficient Continual Pre-training of Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.18743","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":"sha256:987dd217fe9a795a9995ddfde52fb6637024b58f0973e0c6e3b36ada1e518bba","target":"record","created_at":"2026-07-05T08:48:54Z","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":"a92e63c92c4c75e5307de800b1789f36d3d6042d58d974846ba318a70d405fdc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-26T13:55:21Z","title_canon_sha256":"a80de6b1a0d0453365993a8d564585825d02ec1f498601f86b183cb2c1514fe3"},"schema_version":"1.0","source":{"id":"2407.18743","kind":"arxiv","version":1}},"canonical_sha256":"1761222589d36a8d2dd6f1c7dee5ab18791c07fd31cacfd41c13a5be06c91a68","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1761222589d36a8d2dd6f1c7dee5ab18791c07fd31cacfd41c13a5be06c91a68","first_computed_at":"2026-07-05T08:48:54.398716Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:48:54.398716Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ytV42SWolQNRlEKI57os6fY7hTO9zHa+7JUTqwWG/jGI11/yVVbhp2i6LM+IMGdGfkjISfWI2UoMY5EBTz37AA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:48:54.399092Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.18743","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:987dd217fe9a795a9995ddfde52fb6637024b58f0973e0c6e3b36ada1e518bba","sha256:19d93032018165d62fa04a374d9a70cc83b67bc97c2d7fd4da98fd8f5b6b4294"],"state_sha256":"7aa8fcabd9cffd5962b4658ee276f18fbc13dcd589e93ca64016d717d571f21c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AyKOVvKMZwFdaqYCE4JU27dXQIU/oT+8T5S9k45ZMWlguIOlyNVLYAydzoju8+JmmwbH2ev9mvny9jKVZBPxCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T15:49:06.681303Z","bundle_sha256":"1a411fe07f4f705865e47bc1d31338f0b45f723626835e8f1d46ab2855468de4"}}