{"as_of":"2026-08-21T17:56:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:495d77c94b5cd2a03213d63416270c7f8447896fff46ae53ee2c137ce8799500","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":"2026-08-16T12:00:14.442092Z","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":"2026-08-15T22:59:49.205221Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2503.10745","last_updated":"2025-06-08T23:43:21Z","snapshot_observed_at":"2026-08-18T06:11:33.475579Z","submitted_at":"2025-03-13T17:56:22Z","title":"Unifying 2D and 3D Vision-Language Understanding","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.10745","snapshot_observed_at":"2026-08-16T12:00:14.442092Z","title":"Unifying 2d and 3d vision-language understanding, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2504.14151","last_updated":"2025-04-19T02:51:24Z","snapshot_observed_at":"2026-08-21T05:39:01.894944Z","submitted_at":"2025-04-19T02:51:24Z","title":"Locate 3D: Real-World Object Localization via Self-Supervised Learning in 3D","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-16T12:00:14.442092Z"},"links":{"cited_paper":"/paper/2503.10745","citing_paper":"/paper/2504.14151"},"observation_digest":"sha256:3a95f6ce8dd47f81e10239a41ee2ea194c402533af7933d4db04a92383f4ce79","observation_id":"4e4318b8-c513-4c4e-9aeb-59c37691f3b4","resolution":{"observed_at":"2026-08-16T12:00:14.442092Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.10745","last_updated":"2025-06-08T23:43:21Z","snapshot_observed_at":"2026-08-18T06:11:33.475579Z","submitted_at":"2025-03-13T17:56:22Z","title":"Unifying 2D and 3D Vision-Language Understanding","version":3},"cited_work":{"arxiv_id":"2503.10745","doi":null,"metadata_source":"pith","pith_arxiv_id":"2503.10745","snapshot_observed_at":"2026-08-15T22:59:49.205221Z","title":"Unifying 2D and 3D Vision-Language Understanding","venue":"cs.CV","work_id":"118260f1-6423-4e2d-93fb-41f6e72926c2","year":2025},"citing_paper":{"arxiv_id":"2505.05804","last_updated":"2025-05-25T20:00:44Z","snapshot_observed_at":"2026-08-17T16:49:42.533533Z","submitted_at":"2025-05-09T05:45:31Z","title":"Describe Anything in Medical Images","version":2},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-15T22:59:48.652371Z"},"links":{"cited_paper":"/paper/2503.10745","citing_paper":"/paper/2505.05804"},"observation_digest":"sha256:e9cf2717108697494975f5cd85052fc5803502d2d93cd089f9a88663012ecf47","observation_id":"9e016d87-bfef-49e9-92fd-31a9646e3dd4","resolution":{"observed_at":"2026-08-15T22:59:49.209687Z","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"}}],"links":{"evidence":"/evidence","html":"/paper/2503.10745/citation-record","integrity":"/paper/2503.10745/integrity","json":"/paper/2503.10745/citation-record.json","paper":"/paper/2503.10745"},"outbound":[],"paper":{"arxiv_id":"2503.10745","last_updated":"2025-06-08T23:43:21Z","latest_version":3,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-18T06:11:33.475579Z","submitted_at":"2025-03-13T17:56:22Z","title":"Unifying 2D and 3D Vision-Language 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":"2026-08-21T06:32:19.484+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:2503.10745."}