{"as_of":"2026-08-06T21:32:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:cf8dbf30286255a81ddb035159a0d20639f9ee66cffe00b2593aa50dfc2af052","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":"2026-08-03T13:26:06.713886Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2505.19015","last_updated":"2025-08-08T09:55:18Z","snapshot_observed_at":"2026-07-06T21:30:00.261435Z","submitted_at":"2025-05-25T07:37:34Z","title":"Can Multimodal Large Language Models Understand Spatial Relations?","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.19015","snapshot_observed_at":"2026-08-03T13:26:06.713886Z","title":"Can multi- modal large language models understand spatial relations? arXiv preprint arXiv:2505.19015, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2512.24331","last_updated":"2026-05-25T12:17:46Z","snapshot_observed_at":"2026-08-03T13:26:03.435180Z","submitted_at":"2025-12-30T16:35:00Z","title":"Spatial-aware Vision Language Model for Autonomous Driving","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-03T13:26:06.713886Z"},"links":{"cited_paper":"/paper/2505.19015","citing_paper":"/paper/2512.24331"},"observation_digest":"sha256:c0579ed1bf1111177b6993ee346b1efb2f294c185fcb79d9f6487d1917ba031c","observation_id":"09564187-549e-4c2d-84e4-0eef8ac830b1","resolution":{"observed_at":"2026-08-03T13:26:06.713886Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.19015","last_updated":"2025-08-08T09:55:18Z","snapshot_observed_at":"2026-07-06T21:30:00.261435Z","submitted_at":"2025-05-25T07:37:34Z","title":"Can Multimodal Large Language Models Understand Spatial Relations?","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.19015","snapshot_observed_at":"2026-08-03T12:25:50.226593Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2601.03191","last_updated":"2026-05-23T10:05:21Z","snapshot_observed_at":"2026-08-03T12:25:46.099231Z","submitted_at":"2026-01-06T17:13:23Z","title":"AnatomiX, an Anatomy-Aware Grounded Multimodal Large Language Model for Chest X-Ray Interpretation","version":3},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-03T12:25:50.226593Z"},"links":{"cited_paper":"/paper/2505.19015","citing_paper":"/paper/2601.03191"},"observation_digest":"sha256:667a5999ac736640ea09946931e271fde6bf7e1785b99f949806590e9846c0bd","observation_id":"e795f2a0-0f3f-4d36-9c85-8229c6859310","resolution":{"observed_at":"2026-08-03T12:25:50.226593Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2505.19015/citation-record","integrity":"/paper/2505.19015/integrity","json":"/paper/2505.19015/citation-record.json","paper":"/paper/2505.19015"},"outbound":[],"paper":{"arxiv_id":"2505.19015","last_updated":"2025-08-08T09:55:18Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T21:30:00.261435Z","submitted_at":"2025-05-25T07:37:34Z","title":"Can Multimodal Large Language Models Understand Spatial Relations?"},"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 6 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2505.19015."}