{"as_of":"2026-08-09T05:43:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a2f65ff1e8e0ec8609643d666b37e39f9782f4a05edd0ba3b72296073113a4e9","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":"2026-08-08T12:44:39.547898Z","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":"2026-08-06T20:18:54.481173Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2407.10920","last_updated":"2024-10-14T13:08:01Z","snapshot_observed_at":"2026-07-06T18:46:35.304901Z","submitted_at":"2024-07-15T17:21:41Z","title":"Benchmarking Vision Language Models for Cultural Understanding","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.10920","snapshot_observed_at":"2026-08-08T12:44:39.547898Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.07455","last_updated":"2025-02-11T10:57:12Z","snapshot_observed_at":"2026-08-08T12:39:01.074888Z","submitted_at":"2025-02-11T10:57:12Z","title":"RusCode: Russian Cultural Code Benchmark for Text-to-Image Generation","version":1},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-08T12:44:39.547898Z"},"links":{"cited_paper":"/paper/2407.10920","citing_paper":"/paper/2502.07455"},"observation_digest":"sha256:1455c5c2cba0e281e73fa41461d3c3e620da1f84eec3dc289e7eed7fdf8ebbd4","observation_id":"01237b83-405b-4235-8225-524e8909871a","resolution":{"observed_at":"2026-08-08T12:44:39.547898Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.10920","last_updated":"2024-10-14T13:08:01Z","snapshot_observed_at":"2026-07-06T18:46:35.304901Z","submitted_at":"2024-07-15T17:21:41Z","title":"Benchmarking Vision Language Models for Cultural Understanding","version":3},"cited_work":{"arxiv_id":"2407.10920","doi":null,"metadata_source":"pith","pith_arxiv_id":"2407.10920","snapshot_observed_at":"2026-08-06T20:18:54.481173Z","title":"Benchmarking Vision Language Models for Cultural Understanding","venue":"cs.CV","work_id":"1882dcdc-b4ad-4f94-92fa-de1b68b32239","year":2024},"citing_paper":{"arxiv_id":"2507.03330","last_updated":"2025-07-04T06:30:50Z","snapshot_observed_at":"2026-08-06T20:10:47.330075Z","submitted_at":"2025-07-04T06:30:50Z","title":"Exploring Object Status Recognition for Recipe Progress Tracking in Non-Visual Cooking","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-06T20:18:52.500914Z"},"links":{"cited_paper":"/paper/2407.10920","citing_paper":"/paper/2507.03330"},"observation_digest":"sha256:dc14a1557b2949c14b49a27fe298028e1e09bef9ffb1214f899ef9c7ab62fca0","observation_id":"2d457f4e-0ef9-46d6-a444-3c51da2ee204","resolution":{"observed_at":"2026-08-06T20:18:54.523035Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"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/2407.10920/citation-record","integrity":"/paper/2407.10920/integrity","json":"/paper/2407.10920/citation-record.json","paper":"/paper/2407.10920"},"outbound":[],"paper":{"arxiv_id":"2407.10920","last_updated":"2024-10-14T13:08:01Z","latest_version":3,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T18:46:35.304901Z","submitted_at":"2024-07-15T17:21:41Z","title":"Benchmarking Vision Language Models for Cultural Understanding"},"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 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2407.10920."}