{"as_of":"2026-08-21T08:54:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:cc87a7955b950f2416b936566a178c12fa87f047403b0c45029a1e7a9a48bf46","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":2,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":2,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-21T06:32:19.484+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T23:10:21.873194Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-10T20:33:20.897741Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2309.13079","last_updated":"2023-09-26T10:38:19Z","snapshot_observed_at":"2026-08-18T00:31:00.021500Z","submitted_at":"2023-09-21T09:02:28Z","title":"MiChao-HuaFen 1.0: A Specialized Pre-trained Corpus Dataset for Domain-specific Large Models","version":2},"cited_work":{"arxiv_id":"2309.13079","doi":null,"metadata_source":"pith","pith_arxiv_id":"2309.13079","snapshot_observed_at":"2026-08-10T20:33:20.897741Z","title":"MiChao-HuaFen 1.0: A Specialized Pre-trained Corpus Dataset for Domain-specific Large Models","venue":"cs.CL","work_id":"bc2bbae7-a041-4892-a9b8-2761ccfa0eaf","year":2023},"citing_paper":{"arxiv_id":"2501.08197","last_updated":"2025-01-14T15:22:47Z","snapshot_observed_at":"2026-08-13T06:16:32.798188Z","submitted_at":"2025-01-14T15:22:47Z","title":"OpenCSG Chinese Corpus: A Series of High-quality Chinese Datasets for LLM Training","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-10T20:33:20.604501Z"},"links":{"cited_paper":"/paper/2309.13079","citing_paper":"/paper/2501.08197"},"observation_digest":"sha256:c258ba25f02f7a95bcf9bf8e79fc823c7fbd60f100a02c4140059dc2eb353812","observation_id":"c3485399-cb3c-4c62-8265-829878092397","resolution":{"observed_at":"2026-08-10T20:33:20.904151Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2309.13079","last_updated":"2023-09-26T10:38:19Z","snapshot_observed_at":"2026-08-18T00:31:00.021500Z","submitted_at":"2023-09-21T09:02:28Z","title":"MiChao-HuaFen 1.0: A Specialized Pre-trained Corpus Dataset for Domain-specific Large Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.13079","snapshot_observed_at":"2026-08-15T23:10:21.873194Z","title":"Michao- huafen 1.0: A specialized pre-trained corpus dataset for domain-specific large models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.05427","last_updated":"2025-05-08T17:15:20Z","snapshot_observed_at":"2026-08-20T10:32:21.926447Z","submitted_at":"2025-05-08T17:15:20Z","title":"Ultra-FineWeb: Efficient Data Filtering and Verification for High-Quality LLM Training Data","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-15T23:10:21.873194Z"},"links":{"cited_paper":"/paper/2309.13079","citing_paper":"/paper/2505.05427"},"observation_digest":"sha256:f5785b6668f32c99ddc3ae74920199a5459083a81668ebe60a5359f8b3c980b5","observation_id":"35fdbb6c-4c20-46e3-a3c2-4edb453c42fc","resolution":{"observed_at":"2026-08-15T23:10:21.873194Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2309.13079/citation-record","integrity":"/paper/2309.13079/integrity","json":"/paper/2309.13079/citation-record.json","paper":"/paper/2309.13079"},"outbound":[],"paper":{"arxiv_id":"2309.13079","last_updated":"2023-09-26T10:38:19Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-18T00:31:00.021500Z","submitted_at":"2023-09-21T09:02:28Z","title":"MiChao-HuaFen 1.0: A Specialized Pre-trained Corpus Dataset for Domain-specific Large Models"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"thesis":"As of 21 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2309.13079."}