{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4U72QVPQ3LXRNVFHFKQA4HXKKZ","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":"8ab34fdf85020432ac99c2c9bd85c6a4f403601538626506339be0a64aad4343","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-08T17:15:20Z","title_canon_sha256":"315fdfcbd506e9c5a7619a484c4acdaed297cf678ad09b9f52494a8e45420325"},"schema_version":"1.0","source":{"id":"2505.05427","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.05427","created_at":"2026-07-05T11:00:24Z"},{"alias_kind":"arxiv_version","alias_value":"2505.05427v1","created_at":"2026-07-05T11:00:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.05427","created_at":"2026-07-05T11:00:24Z"},{"alias_kind":"pith_short_12","alias_value":"4U72QVPQ3LXR","created_at":"2026-07-05T11:00:24Z"},{"alias_kind":"pith_short_16","alias_value":"4U72QVPQ3LXRNVFH","created_at":"2026-07-05T11:00:24Z"},{"alias_kind":"pith_short_8","alias_value":"4U72QVPQ","created_at":"2026-07-05T11:00:24Z"}],"graph_snapshots":[{"event_id":"sha256:c2f2e40a1a9ec3e63824f3c093bd47d03bc6e8c0e05d0cd0169e327233ef7153","target":"graph","created_at":"2026-07-05T11:00:24Z","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/2505.05427/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data quality has become a key factor in enhancing model performance with the rapid development of large language models (LLMs). Model-driven data filtering has increasingly become a primary approach for acquiring high-quality data. However, it still faces two main challenges: (1) the lack of an efficient data verification strategy makes it difficult to provide timely feedback on data quality; and (2) the selection of seed data for training classifiers lacks clear criteria and relies heavily on human expertise, introducing a degree of subjectivity. To address the first challenge, we introduce a","authors_text":"Chaojun Xiao, Guoyang Zeng, Hongya Lyu, Jie Cai, Jie Zhou, Peijun Tang, Xu Han, Yewei Fang, Yudong Wang, Zhiyuan Liu, Zhi Zheng, Zixuan Fu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-08T17:15:20Z","title":"Ultra-FineWeb: Efficient Data Filtering and Verification for High-Quality LLM Training Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.05427","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:afb6856d9d72e52fe4ada4e495f4d6e235b3068a6193ca862c97ecae33d2112c","target":"record","created_at":"2026-07-05T11:00:24Z","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":"8ab34fdf85020432ac99c2c9bd85c6a4f403601538626506339be0a64aad4343","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-08T17:15:20Z","title_canon_sha256":"315fdfcbd506e9c5a7619a484c4acdaed297cf678ad09b9f52494a8e45420325"},"schema_version":"1.0","source":{"id":"2505.05427","kind":"arxiv","version":1}},"canonical_sha256":"e53fa855f0daef16d4a72aa00e1eea566debc71ff3c6ed1cdec52d9a337355a4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e53fa855f0daef16d4a72aa00e1eea566debc71ff3c6ed1cdec52d9a337355a4","first_computed_at":"2026-07-05T11:00:24.315881Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:00:24.315881Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yl1oDYCpkPcnFrOOM8xd2Pcet+rSaBpg/11G3F+SmE4aF8G0pG7fjIP7dafkwcpNC5rMaXF7ltOmt36We0WcAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:00:24.316459Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.05427","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:afb6856d9d72e52fe4ada4e495f4d6e235b3068a6193ca862c97ecae33d2112c","sha256:c2f2e40a1a9ec3e63824f3c093bd47d03bc6e8c0e05d0cd0169e327233ef7153"],"state_sha256":"3f0a0b9c26a104bfd52056ce076e7b5660aa0c3b806ce66a9f65df09456b0f09"}