{"as_of":"2026-08-11T20:09:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:adfcb1ccc690e072382b4ebe86c49adf63bb4fe8d0894a93bbbe63f101591550","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":"2026-08-11T06:34:44.6726+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":"2026-08-10T22:06:47.521592Z","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":"2026-08-10T20:58:24.210371Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2406.18591","last_updated":"2024-06-07T16:28:06Z","snapshot_observed_at":"2026-07-06T18:37:30.752868Z","submitted_at":"2024-06-07T16:28:06Z","title":"Composition Vision-Language Understanding via Segment and Depth Anything Model","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.18591","snapshot_observed_at":"2026-08-10T22:06:47.521592Z","title":"Composition vision-language understanding via segment and depth anything model","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.02811","last_updated":"2025-04-22T06:27:44Z","snapshot_observed_at":"2026-08-11T16:53:38.990258Z","submitted_at":"2025-01-06T07:20:36Z","title":"First-place Solution for Streetscape Shop Sign Recognition Competition","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-10T22:06:47.521592Z"},"links":{"cited_paper":"/paper/2406.18591","citing_paper":"/paper/2501.02811"},"observation_digest":"sha256:a35de416173ea48bd1fce3858d7f2a2302de180b01386992500a4bab0813ce3e","observation_id":"78987285-6ead-49e2-8da2-2ca6ed107c8b","resolution":{"observed_at":"2026-08-10T22:06:47.521592Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.18591","last_updated":"2024-06-07T16:28:06Z","snapshot_observed_at":"2026-07-06T18:37:30.752868Z","submitted_at":"2024-06-07T16:28:06Z","title":"Composition Vision-Language Understanding via Segment and Depth Anything Model","version":1},"cited_work":{"arxiv_id":"2406.18591","doi":null,"metadata_source":"pith","pith_arxiv_id":"2406.18591","snapshot_observed_at":"2026-08-10T20:58:24.210371Z","title":"Composition Vision-Language Understanding via Segment and Depth Anything Model","venue":"cs.CV","work_id":"77d04cf7-6f30-4d19-a14b-0f6e1eb3f874","year":2024},"citing_paper":{"arxiv_id":"2501.06680","last_updated":"2025-07-30T17:16:46Z","snapshot_observed_at":"2026-08-11T18:19:31.331205Z","submitted_at":"2025-01-12T01:31:07Z","title":"Application of Vision-Language Model to Pedestrians Behavior and Scene Understanding in Autonomous Driving","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-10T20:58:22.283808Z"},"links":{"cited_paper":"/paper/2406.18591","citing_paper":"/paper/2501.06680"},"observation_digest":"sha256:ea575c2155a8c25bc321cb4b0556cca5ab9d54cc2d312f9426aa772567fd1558","observation_id":"5f87289d-1f85-4537-b73d-e6d7b4feac02","resolution":{"observed_at":"2026-08-10T20:58:24.279948Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2406.18591/citation-record","integrity":"/paper/2406.18591/integrity","json":"/paper/2406.18591/citation-record.json","paper":"/paper/2406.18591"},"outbound":[],"paper":{"arxiv_id":"2406.18591","last_updated":"2024-06-07T16:28:06Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T18:37:30.752868Z","submitted_at":"2024-06-07T16:28:06Z","title":"Composition Vision-Language Understanding via Segment and Depth Anything Model"},"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":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"thesis":"As of 11 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2406.18591."}