{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HU6ZW33XXUJX4BPCF44FMWSSWY","short_pith_number":"pith:HU6ZW33X","schema_version":"1.0","canonical_sha256":"3d3d9b6f77bd137e05e22f38565a52b6274f13aa75dd8f358a5114ba245cf0c6","source":{"kind":"arxiv","id":"2501.08197","version":1},"attestation_state":"computed","paper":{"title":"OpenCSG Chinese Corpus: A Series of High-quality Chinese Datasets for LLM Training","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ji Pei, Ran Chen, Wei Wang, Yijiong Yu, Zekun Wang, Ziyun Dai","submitted_at":"2025-01-14T15:22:47Z","abstract_excerpt":"Large language models (LLMs) have demonstrated remarkable capabilities, but their success heavily relies on the quality of pretraining corpora. For Chinese LLMs, the scarcity of high-quality Chinese datasets presents a significant challenge, often limiting their performance. To address this issue, we propose the OpenCSG Chinese Corpus, a series of high-quality datasets specifically designed for LLM pretraining, post-training, and fine-tuning. This corpus includes Fineweb-edu-chinese, Fineweb-edu-chinese-v2, Cosmopedia-chinese, and Smoltalk-chinese, each with distinct characteristics: Fineweb-e"},"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":"2501.08197","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-14T15:22:47Z","cross_cats_sorted":[],"title_canon_sha256":"d5fe8ed3b9f5bc39cbfafe74aea81a0a447da9748ed47dbd1699b0612bc3d385","abstract_canon_sha256":"0150ed19c6ebde0b8e97a567244c2fd46e653712dbc3e11ae0647937c47ac935"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:00:57.403468Z","signature_b64":"5eXkP2+5d82ripDtmpr8iXCOP7MvZJW3Wabfe8lxtsSL2UWGS80bWtv/O4SEvrxft3n+vL2hT9yRzbLrrVH9Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d3d9b6f77bd137e05e22f38565a52b6274f13aa75dd8f358a5114ba245cf0c6","last_reissued_at":"2026-07-05T10:00:57.402994Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:00:57.402994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OpenCSG Chinese Corpus: A Series of High-quality Chinese Datasets for LLM Training","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ji Pei, Ran Chen, Wei Wang, Yijiong Yu, Zekun Wang, Ziyun Dai","submitted_at":"2025-01-14T15:22:47Z","abstract_excerpt":"Large language models (LLMs) have demonstrated remarkable capabilities, but their success heavily relies on the quality of pretraining corpora. For Chinese LLMs, the scarcity of high-quality Chinese datasets presents a significant challenge, often limiting their performance. To address this issue, we propose the OpenCSG Chinese Corpus, a series of high-quality datasets specifically designed for LLM pretraining, post-training, and fine-tuning. This corpus includes Fineweb-edu-chinese, Fineweb-edu-chinese-v2, Cosmopedia-chinese, and Smoltalk-chinese, each with distinct characteristics: Fineweb-e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.08197","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/2501.08197/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":"2501.08197","created_at":"2026-07-05T10:00:57.403050+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.08197v1","created_at":"2026-07-05T10:00:57.403050+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.08197","created_at":"2026-07-05T10:00:57.403050+00:00"},{"alias_kind":"pith_short_12","alias_value":"HU6ZW33XXUJX","created_at":"2026-07-05T10:00:57.403050+00:00"},{"alias_kind":"pith_short_16","alias_value":"HU6ZW33XXUJX4BPC","created_at":"2026-07-05T10:00:57.403050+00:00"},{"alias_kind":"pith_short_8","alias_value":"HU6ZW33X","created_at":"2026-07-05T10:00:57.403050+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12950","citing_title":"Maestro: Workload-Aware Cross-Cluster Scheduling for LLM-Based Multi-Agent Systems","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30580","citing_title":"Speculative Decoding and the Curse of Multilinguality","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18056","citing_title":"ConSA: Controllable Sparsity in Hybrid Attention via Learnable Allocation","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HU6ZW33XXUJX4BPCF44FMWSSWY","json":"https://pith.science/pith/HU6ZW33XXUJX4BPCF44FMWSSWY.json","graph_json":"https://pith.science/api/pith-number/HU6ZW33XXUJX4BPCF44FMWSSWY/graph.json","events_json":"https://pith.science/api/pith-number/HU6ZW33XXUJX4BPCF44FMWSSWY/events.json","paper":"https://pith.science/paper/HU6ZW33X"},"agent_actions":{"view_html":"https://pith.science/pith/HU6ZW33XXUJX4BPCF44FMWSSWY","download_json":"https://pith.science/pith/HU6ZW33XXUJX4BPCF44FMWSSWY.json","view_paper":"https://pith.science/paper/HU6ZW33X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.08197&json=true","fetch_graph":"https://pith.science/api/pith-number/HU6ZW33XXUJX4BPCF44FMWSSWY/graph.json","fetch_events":"https://pith.science/api/pith-number/HU6ZW33XXUJX4BPCF44FMWSSWY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HU6ZW33XXUJX4BPCF44FMWSSWY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HU6ZW33XXUJX4BPCF44FMWSSWY/action/storage_attestation","attest_author":"https://pith.science/pith/HU6ZW33XXUJX4BPCF44FMWSSWY/action/author_attestation","sign_citation":"https://pith.science/pith/HU6ZW33XXUJX4BPCF44FMWSSWY/action/citation_signature","submit_replication":"https://pith.science/pith/HU6ZW33XXUJX4BPCF44FMWSSWY/action/replication_record"}},"created_at":"2026-07-05T10:00:57.403050+00:00","updated_at":"2026-07-05T10:00:57.403050+00:00"}