{"as_of":"2026-08-07T11:40:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:09af803bee3576427ea0b06653913686a494eeb8302ba359c39c41b07b3fcd94","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":3,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":3,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-02T14:55:35.240823Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":1,"source":"arxiv_reference","source_observed_at":"2026-08-05T02:28:24.338817Z","state":"measured"}],"external_citation_measurements":[{"count":0,"observed_at":"2026-08-05T02:28:24.338817Z","source":"arxiv_reference"}],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2405.21013","last_updated":"2024-06-04T09:14:39Z","snapshot_observed_at":"2026-07-06T18:23:23.565502Z","submitted_at":"2024-05-31T16:55:04Z","title":"StrucTexTv3: An Efficient Vision-Language Model for Text-rich Image Perception, Comprehension, and Beyond","version":3},"cited_work":{"arxiv_id":"2405.21013","doi":"10.48550/arxiv.2405.21013","metadata_source":"arxiv_reference","pith_arxiv_id":"2405.21013","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":null,"venue":"arXiv (Cornell University)","work_id":"439df7fe-4bba-47ce-ac9f-b476defa0264","year":2024},"citing_paper":{"arxiv_id":"2507.09861","last_updated":"2026-04-21T13:31:05Z","snapshot_observed_at":"2026-07-06T21:56:35.665677Z","submitted_at":"2025-07-14T02:10:31Z","title":"A Survey on MLLM-based Visually Rich Document Understanding: Methods, Challenges, and Emerging Trends","version":2},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-05-19T04:38:49.512293Z"},"links":{"cited_paper":"/paper/2405.21013","citing_paper":"/paper/2507.09861"},"observation_digest":"sha256:c71a1498a2ec93b55bf63a451aaaf17fcc08f1d4753d8b703b02a78c1a747ef1","observation_id":"19958aae-0780-4d69-8f90-f945a8f9217b","resolution":{"observed_at":"2026-05-19T04:42:04.054783Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2405.21013","last_updated":"2024-06-04T09:14:39Z","snapshot_observed_at":"2026-07-06T18:23:23.565502Z","submitted_at":"2024-05-31T16:55:04Z","title":"StrucTexTv3: An Efficient Vision-Language Model for Text-rich Image Perception, Comprehension, and Beyond","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.21013","snapshot_observed_at":"2026-08-02T14:55:35.240823Z","title":"arXiv preprint arXiv:2405.21013 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.16203","last_updated":"2026-05-05T10:59:34Z","snapshot_observed_at":"2026-08-04T21:09:24.743822Z","submitted_at":"2026-05-05T10:59:34Z","title":"DocOCR-Eval: A Correction-Based Framework for OCR Tool Selection Without Ground Truth","version":1},"reference_index":131,"source":"arxiv_source","source_observed_at":"2026-08-02T14:55:35.240823Z"},"links":{"cited_paper":"/paper/2405.21013","citing_paper":"/paper/2607.16203"},"observation_digest":"sha256:39fac643f93929389813f24e789cf4f532df91b9f5d53cfa04de033c6c870f7e","observation_id":"19cc131f-6418-4917-afa5-73c8063ed159","resolution":{"observed_at":"2026-08-02T14:55:35.240823Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.21013","last_updated":"2024-06-04T09:14:39Z","snapshot_observed_at":"2026-07-06T18:23:23.565502Z","submitted_at":"2024-05-31T16:55:04Z","title":"StrucTexTv3: An Efficient Vision-Language Model for Text-rich Image Perception, Comprehension, and Beyond","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.21013","snapshot_observed_at":"2026-08-01T14:16:08.174815Z","title":"Structextv3: An efficient vision-language model for text-rich image perception, comprehension, and beyond","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.18839","last_updated":"2026-07-21T08:25:32Z","snapshot_observed_at":"2026-08-06T00:56:05.972442Z","submitted_at":"2026-07-21T08:25:32Z","title":"HPD-Parsing: Hierarchical Parallel Document Parsing","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-01T14:16:08.174815Z"},"links":{"cited_paper":"/paper/2405.21013","citing_paper":"/paper/2607.18839"},"observation_digest":"sha256:8ec5d0d336ea6417e3c09c3f8a53b05edc87dde1a88f12e7d26edeb6a5273d16","observation_id":"7df8770a-6f1c-46f8-b24a-712a61df026d","resolution":{"observed_at":"2026-08-01T14:16:08.174815Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2405.21013/citation-record","integrity":"/paper/2405.21013/integrity","json":"/paper/2405.21013/citation-record.json","paper":"/paper/2405.21013"},"outbound":[],"paper":{"arxiv_id":"2405.21013","last_updated":"2024-06-04T09:14:39Z","latest_version":3,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T18:23:23.565502Z","submitted_at":"2024-05-31T16:55:04Z","title":"StrucTexTv3: An Efficient Vision-Language Model for Text-rich Image Perception, Comprehension, and Beyond"},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2405.21013."}