{"as_of":"2026-08-04T11:47:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:02794d1c6d6d7764abca591302e1e74b6e4e8f90d7b15b4b400f8ffca01eaffb","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":"2026-08-04T06:34:03.388597+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":"2026-08-01T20:28:47.778868Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-10T22:46:40.632054Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2309.02033","last_updated":"2023-12-20T08:27:40Z","snapshot_observed_at":"2026-07-31T00:13:11.084124Z","submitted_at":"2023-09-05T08:22:07Z","title":"Data-Juicer: A One-Stop Data Processing System for Large Language Models","version":3},"cited_work":{"arxiv_id":"2309.02033","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2309.02033","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Data-juicer: A one-stop data processing system for large language models","venue":null,"work_id":"0cfa214c-40cb-4c98-88b1-e3109d3f0bdf","year":2023},"citing_paper":{"arxiv_id":"2303.18223","last_updated":"2026-03-18T05:34:39Z","snapshot_observed_at":"2026-08-04T11:07:48.536954Z","submitted_at":"2023-03-31T17:28:46Z","title":"A Survey of Large Language Models","version":19},"reference_index":266,"source":"pdf_text","source_observed_at":"2026-05-10T22:46:39.268353Z"},"links":{"cited_paper":"/paper/2309.02033","citing_paper":"/paper/2303.18223"},"observation_digest":"sha256:3663049befcaf3aaf9b4412091240272819c9a54f1be2786f358834988808988","observation_id":"839122d6-0cc2-4fbb-84f3-2f2bd7de2ffa","resolution":{"observed_at":"2026-05-10T22:46:40.635714Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2309.02033","last_updated":"2023-12-20T08:27:40Z","snapshot_observed_at":"2026-07-31T00:13:11.084124Z","submitted_at":"2023-09-05T08:22:07Z","title":"Data-Juicer: A One-Stop Data Processing System for Large Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.02033","snapshot_observed_at":"2026-08-01T20:28:47.778868Z","title":"Data-juicer: A one-stop data processing system for large language models, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.16617","last_updated":"2026-07-24T08:50:49Z","snapshot_observed_at":"2026-08-01T20:28:46.647386Z","submitted_at":"2026-07-18T03:30:19Z","title":"DataFlow-Harness: A Grounded Code-Agent Platform for Constructing Editable LLM Data Pipelines","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-01T20:28:47.778868Z"},"links":{"cited_paper":"/paper/2309.02033","citing_paper":"/paper/2607.16617"},"observation_digest":"sha256:a7104d97a1f2b39d4abec4e0c3a77896d589d9942dddf129504838d5ec0c851f","observation_id":"d27164ad-2ca9-4275-9afb-18bd426474d9","resolution":{"observed_at":"2026-08-01T20:28:47.778868Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2309.02033/citation-record","integrity":"/paper/2309.02033/integrity","json":"/paper/2309.02033/citation-record.json","paper":"/paper/2309.02033"},"outbound":[],"paper":{"arxiv_id":"2309.02033","last_updated":"2023-12-20T08:27:40Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-31T00:13:11.084124Z","submitted_at":"2023-09-05T08:22:07Z","title":"Data-Juicer: A One-Stop Data Processing System for Large Language 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":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"thesis":"As of 4 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2309.02033."}