{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HU6ZW33XXUJX4BPCF44FMWSSWY","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":"0150ed19c6ebde0b8e97a567244c2fd46e653712dbc3e11ae0647937c47ac935","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-14T15:22:47Z","title_canon_sha256":"d5fe8ed3b9f5bc39cbfafe74aea81a0a447da9748ed47dbd1699b0612bc3d385"},"schema_version":"1.0","source":{"id":"2501.08197","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.08197","created_at":"2026-07-05T10:00:57Z"},{"alias_kind":"arxiv_version","alias_value":"2501.08197v1","created_at":"2026-07-05T10:00:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.08197","created_at":"2026-07-05T10:00:57Z"},{"alias_kind":"pith_short_12","alias_value":"HU6ZW33XXUJX","created_at":"2026-07-05T10:00:57Z"},{"alias_kind":"pith_short_16","alias_value":"HU6ZW33XXUJX4BPC","created_at":"2026-07-05T10:00:57Z"},{"alias_kind":"pith_short_8","alias_value":"HU6ZW33X","created_at":"2026-07-05T10:00:57Z"}],"graph_snapshots":[{"event_id":"sha256:986dd336547195b2d1b5990b0e4c73e3c43b949b99cf654975793bfb90b585aa","target":"graph","created_at":"2026-07-05T10:00:57Z","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/2501.08197/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Ji Pei, Ran Chen, Wei Wang, Yijiong Yu, Zekun Wang, Ziyun Dai","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-14T15:22:47Z","title":"OpenCSG Chinese Corpus: A Series of High-quality Chinese Datasets for LLM Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.08197","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:a41a0d3ac8cd097c7a4f481d80167b49b660784000c648487604af65f2ffb2e1","target":"record","created_at":"2026-07-05T10:00:57Z","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":"0150ed19c6ebde0b8e97a567244c2fd46e653712dbc3e11ae0647937c47ac935","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-14T15:22:47Z","title_canon_sha256":"d5fe8ed3b9f5bc39cbfafe74aea81a0a447da9748ed47dbd1699b0612bc3d385"},"schema_version":"1.0","source":{"id":"2501.08197","kind":"arxiv","version":1}},"canonical_sha256":"3d3d9b6f77bd137e05e22f38565a52b6274f13aa75dd8f358a5114ba245cf0c6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3d3d9b6f77bd137e05e22f38565a52b6274f13aa75dd8f358a5114ba245cf0c6","first_computed_at":"2026-07-05T10:00:57.402994Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:00:57.402994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5eXkP2+5d82ripDtmpr8iXCOP7MvZJW3Wabfe8lxtsSL2UWGS80bWtv/O4SEvrxft3n+vL2hT9yRzbLrrVH9Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:00:57.403468Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.08197","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a41a0d3ac8cd097c7a4f481d80167b49b660784000c648487604af65f2ffb2e1","sha256:986dd336547195b2d1b5990b0e4c73e3c43b949b99cf654975793bfb90b585aa"],"state_sha256":"47445f1d31af4dfe4ed0175b0bb6505e14ffd44a2fe5ed2487f873fcb5e85abb"}