{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:SDGL4WXXDMZKFOQ6HJQKGGQGZG","short_pith_number":"pith:SDGL4WXX","canonical_record":{"source":{"id":"2311.01149","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-02T11:13:51Z","cross_cats_sorted":[],"title_canon_sha256":"a38b4b6a613dc45cda0c3e062a9ddf122eadd8deda332d05bb8cb2737ffba756","abstract_canon_sha256":"1ec7a76b08bf39d8d76046d8bde5899612849955c90142c35ea74dbda86085fa"},"schema_version":"1.0"},"canonical_sha256":"90ccbe5af71b32a2ba1e3a60a31a06c99f23d6e9ae88e9780de8c20e31f571c8","source":{"kind":"arxiv","id":"2311.01149","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.01149","created_at":"2026-07-05T07:11:19Z"},{"alias_kind":"arxiv_version","alias_value":"2311.01149v2","created_at":"2026-07-05T07:11:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.01149","created_at":"2026-07-05T07:11:19Z"},{"alias_kind":"pith_short_12","alias_value":"SDGL4WXXDMZK","created_at":"2026-07-05T07:11:19Z"},{"alias_kind":"pith_short_16","alias_value":"SDGL4WXXDMZKFOQ6","created_at":"2026-07-05T07:11:19Z"},{"alias_kind":"pith_short_8","alias_value":"SDGL4WXX","created_at":"2026-07-05T07:11:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:SDGL4WXXDMZKFOQ6HJQKGGQGZG","target":"record","payload":{"canonical_record":{"source":{"id":"2311.01149","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-02T11:13:51Z","cross_cats_sorted":[],"title_canon_sha256":"a38b4b6a613dc45cda0c3e062a9ddf122eadd8deda332d05bb8cb2737ffba756","abstract_canon_sha256":"1ec7a76b08bf39d8d76046d8bde5899612849955c90142c35ea74dbda86085fa"},"schema_version":"1.0"},"canonical_sha256":"90ccbe5af71b32a2ba1e3a60a31a06c99f23d6e9ae88e9780de8c20e31f571c8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:11:19.566983Z","signature_b64":"GdiSWO0yyE947SKacKEOqoOd6sj0vpgOAg9eS4SvFjcUxOh2K+Z5dX9Y/VsnZ1cYPiRhI/+2BU1nKHTqY7XcBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"90ccbe5af71b32a2ba1e3a60a31a06c99f23d6e9ae88e9780de8c20e31f571c8","last_reissued_at":"2026-07-05T07:11:19.566467Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:11:19.566467Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.01149","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:11:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wYpZZBchoKqw5GLy65qlGXPbXzpW1d34T3wnB4XC7dhB61FByjW9WuuYQE44JevMyMSB7LbeajcbR/QpI/bPDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T23:57:46.073934Z"},"content_sha256":"b34bc740f41d0389d1cdfa18a8f3b01a8902b983be07ddd54705f0af02226380","schema_version":"1.0","event_id":"sha256:b34bc740f41d0389d1cdfa18a8f3b01a8902b983be07ddd54705f0af02226380"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:SDGL4WXXDMZKFOQ6HJQKGGQGZG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ChineseWebText: Large-scale High-quality Chinese Web Text Extracted with Effective Evaluation Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chenglin Ding, Chengqing Zong, Dongyi Yi, Guibo Zhu, Jiajun Zhang, Jianghao Chen, Jinqiao Wang, Pu Jian, Qianlong Du, Tengxiao Xi","submitted_at":"2023-11-02T11:13:51Z","abstract_excerpt":"During the development of large language models (LLMs), the scale and quality of the pre-training data play a crucial role in shaping LLMs' capabilities. To accelerate the research of LLMs, several large-scale datasets, such as C4 [1], Pile [2], RefinedWeb [3] and WanJuan [4], have been released to the public. However, most of the released corpus focus mainly on English, and there is still lack of complete tool-chain for extracting clean texts from web data. Furthermore, fine-grained information of the corpus, e.g. the quality of each text, is missing. To address these challenges, we propose i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.01149","kind":"arxiv","version":2},"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/2311.01149/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":"2026-07-05T07:11:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wOSa58Lkx1rAU0f0BrlICiJIQ9psiUgOOR36CTaG/Lg3TQJjPODNPFYm/HvPNc63LlR1epbEya0rL40oO3tsDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T23:57:46.074458Z"},"content_sha256":"ee0fa7fb2795c516bec80209a753490f356f9f0b895880d884f4600af64bf05a","schema_version":"1.0","event_id":"sha256:ee0fa7fb2795c516bec80209a753490f356f9f0b895880d884f4600af64bf05a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SDGL4WXXDMZKFOQ6HJQKGGQGZG/bundle.json","state_url":"https://pith.science/pith/SDGL4WXXDMZKFOQ6HJQKGGQGZG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SDGL4WXXDMZKFOQ6HJQKGGQGZG/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":"2026-08-09T23:57:46Z","links":{"resolver":"https://pith.science/pith/SDGL4WXXDMZKFOQ6HJQKGGQGZG","bundle":"https://pith.science/pith/SDGL4WXXDMZKFOQ6HJQKGGQGZG/bundle.json","state":"https://pith.science/pith/SDGL4WXXDMZKFOQ6HJQKGGQGZG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SDGL4WXXDMZKFOQ6HJQKGGQGZG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:SDGL4WXXDMZKFOQ6HJQKGGQGZG","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":"1ec7a76b08bf39d8d76046d8bde5899612849955c90142c35ea74dbda86085fa","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-02T11:13:51Z","title_canon_sha256":"a38b4b6a613dc45cda0c3e062a9ddf122eadd8deda332d05bb8cb2737ffba756"},"schema_version":"1.0","source":{"id":"2311.01149","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.01149","created_at":"2026-07-05T07:11:19Z"},{"alias_kind":"arxiv_version","alias_value":"2311.01149v2","created_at":"2026-07-05T07:11:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.01149","created_at":"2026-07-05T07:11:19Z"},{"alias_kind":"pith_short_12","alias_value":"SDGL4WXXDMZK","created_at":"2026-07-05T07:11:19Z"},{"alias_kind":"pith_short_16","alias_value":"SDGL4WXXDMZKFOQ6","created_at":"2026-07-05T07:11:19Z"},{"alias_kind":"pith_short_8","alias_value":"SDGL4WXX","created_at":"2026-07-05T07:11:19Z"}],"graph_snapshots":[{"event_id":"sha256:ee0fa7fb2795c516bec80209a753490f356f9f0b895880d884f4600af64bf05a","target":"graph","created_at":"2026-07-05T07:11:19Z","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/2311.01149/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"During the development of large language models (LLMs), the scale and quality of the pre-training data play a crucial role in shaping LLMs' capabilities. To accelerate the research of LLMs, several large-scale datasets, such as C4 [1], Pile [2], RefinedWeb [3] and WanJuan [4], have been released to the public. However, most of the released corpus focus mainly on English, and there is still lack of complete tool-chain for extracting clean texts from web data. Furthermore, fine-grained information of the corpus, e.g. the quality of each text, is missing. To address these challenges, we propose i","authors_text":"Chenglin Ding, Chengqing Zong, Dongyi Yi, Guibo Zhu, Jiajun Zhang, Jianghao Chen, Jinqiao Wang, Pu Jian, Qianlong Du, Tengxiao Xi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-02T11:13:51Z","title":"ChineseWebText: Large-scale High-quality Chinese Web Text Extracted with Effective Evaluation Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.01149","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:b34bc740f41d0389d1cdfa18a8f3b01a8902b983be07ddd54705f0af02226380","target":"record","created_at":"2026-07-05T07:11:19Z","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":"1ec7a76b08bf39d8d76046d8bde5899612849955c90142c35ea74dbda86085fa","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-02T11:13:51Z","title_canon_sha256":"a38b4b6a613dc45cda0c3e062a9ddf122eadd8deda332d05bb8cb2737ffba756"},"schema_version":"1.0","source":{"id":"2311.01149","kind":"arxiv","version":2}},"canonical_sha256":"90ccbe5af71b32a2ba1e3a60a31a06c99f23d6e9ae88e9780de8c20e31f571c8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"90ccbe5af71b32a2ba1e3a60a31a06c99f23d6e9ae88e9780de8c20e31f571c8","first_computed_at":"2026-07-05T07:11:19.566467Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:11:19.566467Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GdiSWO0yyE947SKacKEOqoOd6sj0vpgOAg9eS4SvFjcUxOh2K+Z5dX9Y/VsnZ1cYPiRhI/+2BU1nKHTqY7XcBg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:11:19.566983Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.01149","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b34bc740f41d0389d1cdfa18a8f3b01a8902b983be07ddd54705f0af02226380","sha256:ee0fa7fb2795c516bec80209a753490f356f9f0b895880d884f4600af64bf05a"],"state_sha256":"e4589a1a6f5d0386d64b150db3c9b36746ec86473177777c2d6b8a8a219043db"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q7GFn0rzWBWlHeo6CK8Kd7OeMgKeE+v0TxMhcBd5xJAm3d5ftSWdU/YKWo+ZLf0UbmuSmTWmCY7QGnX8DaWfBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T23:57:46.078933Z","bundle_sha256":"d2cd5f57064e55865e23b199694275014be1b63de48739cbf5e1b1fd2374a16b"}}