{"as_of":"2026-08-08T09:53:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:b261fdabb74b8c7cfbc92d96f8e64405b69579fac5492102d4fe5579687fbe8c","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":"2026-08-08T06:32:00.761636+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":"2026-08-05T23:35:24.850312Z","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":"2026-05-11T21:11:15.380295Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2403.00816","last_updated":"2024-08-14T07:26:08Z","snapshot_observed_at":"2026-07-06T17:38:17.853302Z","submitted_at":"2024-02-26T01:17:50Z","title":"Read and Think: An Efficient Step-wise Multimodal Language Model for Document Understanding and Reasoning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.00816","snapshot_observed_at":"2026-08-05T23:35:24.850312Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.05053","last_updated":"2025-08-07T06:10:15Z","snapshot_observed_at":"2026-08-08T05:00:22.796967Z","submitted_at":"2025-08-07T06:10:15Z","title":"Finding Needles in Images: Can Multimodal LLMs Locate Fine Details?","version":1},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-05T23:35:24.850312Z"},"links":{"cited_paper":"/paper/2403.00816","citing_paper":"/paper/2508.05053"},"observation_digest":"sha256:106e3a34c0e0b482a30ac4720b92219df40b635caffc9a8b1d11bd57c5136553","observation_id":"62327dcb-40d3-49b5-9c7d-b367369e0bd4","resolution":{"observed_at":"2026-08-05T23:35:24.850312Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.00816","last_updated":"2024-08-14T07:26:08Z","snapshot_observed_at":"2026-07-06T17:38:17.853302Z","submitted_at":"2024-02-26T01:17:50Z","title":"Read and Think: An Efficient Step-wise Multimodal Language Model for Document Understanding and Reasoning","version":3},"cited_work":{"arxiv_id":"2403.00816","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2403.00816","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Tianshu Zhang, Xiang Yue, Yifei Li, Hunar Batra, Shangmin Guo, Shiyu Chen, Linbin Wang, Semih Yavuz, Richard Yan, Xinyu Zhang, and Tao Yu","venue":null,"work_id":"d5653c2e-7451-45d9-bf7d-12957cd62869","year":null},"citing_paper":{"arxiv_id":"2604.23813","last_updated":"2026-04-26T17:26:06Z","snapshot_observed_at":"2026-07-06T23:09:58.193241Z","submitted_at":"2026-04-26T17:26:06Z","title":"ShredBench: Evaluating the Semantic Reasoning Capabilities of Multimodal LLMs in Document Reconstruction","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-05-08T06:34:56.032634Z"},"links":{"cited_paper":"/paper/2403.00816","citing_paper":"/paper/2604.23813"},"observation_digest":"sha256:f883f42e92fa321a25d216ab0aabcfe073722858001061fd602459b3208c46c3","observation_id":"e68c01ca-211e-42cd-8849-d243b58424b9","resolution":{"observed_at":"2026-05-11T21:11:15.394692Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2403.00816/citation-record","integrity":"/paper/2403.00816/integrity","json":"/paper/2403.00816/citation-record.json","paper":"/paper/2403.00816"},"outbound":[],"paper":{"arxiv_id":"2403.00816","last_updated":"2024-08-14T07:26:08Z","latest_version":3,"primary_category":"cs.IR","snapshot_observed_at":"2026-07-06T17:38:17.853302Z","submitted_at":"2024-02-26T01:17:50Z","title":"Read and Think: An Efficient Step-wise Multimodal Language Model for Document Understanding and Reasoning"},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2403.00816."}