{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SDGL4WXXDMZKFOQ6HJQKGGQGZG","short_pith_number":"pith:SDGL4WXX","schema_version":"1.0","canonical_sha256":"90ccbe5af71b32a2ba1e3a60a31a06c99f23d6e9ae88e9780de8c20e31f571c8","source":{"kind":"arxiv","id":"2311.01149","version":2},"attestation_state":"computed","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2311.01149","created_at":"2026-07-05T07:11:19.566525+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.01149v2","created_at":"2026-07-05T07:11:19.566525+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.01149","created_at":"2026-07-05T07:11:19.566525+00:00"},{"alias_kind":"pith_short_12","alias_value":"SDGL4WXXDMZK","created_at":"2026-07-05T07:11:19.566525+00:00"},{"alias_kind":"pith_short_16","alias_value":"SDGL4WXXDMZKFOQ6","created_at":"2026-07-05T07:11:19.566525+00:00"},{"alias_kind":"pith_short_8","alias_value":"SDGL4WXX","created_at":"2026-07-05T07:11:19.566525+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30175","citing_title":"CORTEX: High-Quality Cross-Domain Organization of Web-Scale Corpora through Ontological Corpus Graph","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00955","citing_title":"E-MIA: Exam-Style Black-Box Membership Inference Attacks against RAG Systems","ref_index":44,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SDGL4WXXDMZKFOQ6HJQKGGQGZG","json":"https://pith.science/pith/SDGL4WXXDMZKFOQ6HJQKGGQGZG.json","graph_json":"https://pith.science/api/pith-number/SDGL4WXXDMZKFOQ6HJQKGGQGZG/graph.json","events_json":"https://pith.science/api/pith-number/SDGL4WXXDMZKFOQ6HJQKGGQGZG/events.json","paper":"https://pith.science/paper/SDGL4WXX"},"agent_actions":{"view_html":"https://pith.science/pith/SDGL4WXXDMZKFOQ6HJQKGGQGZG","download_json":"https://pith.science/pith/SDGL4WXXDMZKFOQ6HJQKGGQGZG.json","view_paper":"https://pith.science/paper/SDGL4WXX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.01149&json=true","fetch_graph":"https://pith.science/api/pith-number/SDGL4WXXDMZKFOQ6HJQKGGQGZG/graph.json","fetch_events":"https://pith.science/api/pith-number/SDGL4WXXDMZKFOQ6HJQKGGQGZG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SDGL4WXXDMZKFOQ6HJQKGGQGZG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SDGL4WXXDMZKFOQ6HJQKGGQGZG/action/storage_attestation","attest_author":"https://pith.science/pith/SDGL4WXXDMZKFOQ6HJQKGGQGZG/action/author_attestation","sign_citation":"https://pith.science/pith/SDGL4WXXDMZKFOQ6HJQKGGQGZG/action/citation_signature","submit_replication":"https://pith.science/pith/SDGL4WXXDMZKFOQ6HJQKGGQGZG/action/replication_record"}},"created_at":"2026-07-05T07:11:19.566525+00:00","updated_at":"2026-07-05T07:11:19.566525+00:00"}