{"as_of":"2026-08-07T06:32:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:da2e132e789b5577c40d9062e29a19622000a20e97168794e0de3de9c439b0aa","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":"2026-08-06T06:34:29.942622+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":"2026-08-06T14:42:59.996885Z","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":"2026-08-06T10:59:54.749546Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2403.00522","last_updated":"2024-07-08T02:48:27Z","snapshot_observed_at":"2026-08-06T16:05:38.919884Z","submitted_at":"2024-03-01T13:30:51Z","title":"VisionLLaMA: A Unified LLaMA Backbone for Vision Tasks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.00522","snapshot_observed_at":"2026-08-06T14:42:59.996885Z","title":"Visionllama: A unified LLaMA interface for vision tasks","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.18009","last_updated":"2025-07-24T00:54:31Z","snapshot_observed_at":"2026-08-06T14:36:28.119010Z","submitted_at":"2025-07-24T00:54:31Z","title":"GRR-CoCa: Leveraging LLM Mechanisms in Multimodal Model Architectures","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-06T14:42:59.996885Z"},"links":{"cited_paper":"/paper/2403.00522","citing_paper":"/paper/2507.18009"},"observation_digest":"sha256:6d338e79c750325e6dc8abf0c20e41e0dec82b4a5abec338fc5fa67681093c79","observation_id":"7439bea8-daca-4d88-8499-61210ebfd298","resolution":{"observed_at":"2026-08-06T14:42:59.996885Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.00522","last_updated":"2024-07-08T02:48:27Z","snapshot_observed_at":"2026-08-06T16:05:38.919884Z","submitted_at":"2024-03-01T13:30:51Z","title":"VisionLLaMA: A Unified LLaMA Backbone for Vision Tasks","version":2},"cited_work":{"arxiv_id":"2403.00522","doi":null,"metadata_source":"pith","pith_arxiv_id":"2403.00522","snapshot_observed_at":"2026-08-06T10:59:54.749546Z","title":"VisionLLaMA: A Unified LLaMA Backbone for Vision Tasks","venue":"cs.CV","work_id":"d48deb2f-40b9-4a7e-ad94-d3cf2cf2b4c8","year":2024},"citing_paper":{"arxiv_id":"2507.23268","last_updated":"2025-08-04T02:46:11Z","snapshot_observed_at":"2026-08-06T10:59:51.682500Z","submitted_at":"2025-07-31T06:07:20Z","title":"PixNerd: Pixel Neural Field Diffusion","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T10:59:53.695426Z"},"links":{"cited_paper":"/paper/2403.00522","citing_paper":"/paper/2507.23268"},"observation_digest":"sha256:7b82335b9b4d84d36fff197373a755d552bd6f8305e7931be89655f5eab78562","observation_id":"1b636a14-23e1-4dd3-965e-2092e5b3d788","resolution":{"observed_at":"2026-08-06T10:59:54.761049Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2403.00522/citation-record","integrity":"/paper/2403.00522/integrity","json":"/paper/2403.00522/citation-record.json","paper":"/paper/2403.00522"},"outbound":[],"paper":{"arxiv_id":"2403.00522","last_updated":"2024-07-08T02:48:27Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-06T16:05:38.919884Z","submitted_at":"2024-03-01T13:30:51Z","title":"VisionLLaMA: A Unified LLaMA Backbone for Vision Tasks"},"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":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2403.00522."}