{"as_of":"2026-08-07T10:33:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d5949c4d89109f786ed4ba5b27955e2348e50562a8357f00fff46f242cbad215","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":"2026-08-07T06:34:17.273281+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":"2026-08-06T13:20:35.775390Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-16T23:53:42.844634Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2503.03854","last_updated":"2025-05-30T13:04:40Z","snapshot_observed_at":"2026-08-07T10:09:13.623264Z","submitted_at":"2025-03-05T19:36:43Z","title":"Vision-Language Models Struggle to Align Entities across Modalities","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.03854","snapshot_observed_at":"2026-08-06T13:20:35.775390Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.20804","last_updated":"2026-07-18T05:33:43Z","snapshot_observed_at":"2026-08-06T13:20:34.959928Z","submitted_at":"2025-07-28T13:16:23Z","title":"MMGraphRAG: Bridging Vision and Language with Interpretable Multimodal Knowledge Graphs","version":3},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T13:20:35.775390Z"},"links":{"cited_paper":"/paper/2503.03854","citing_paper":"/paper/2507.20804"},"observation_digest":"sha256:d943078e754fbd33ff1bc90e6c81f2c6c386c06f55c4178eef3139d7c9a0d790","observation_id":"fb8ac57e-8672-4ff0-ac36-224ebb32bca9","resolution":{"observed_at":"2026-08-06T13:20:35.775390Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.03854","last_updated":"2025-05-30T13:04:40Z","snapshot_observed_at":"2026-08-07T10:09:13.623264Z","submitted_at":"2025-03-05T19:36:43Z","title":"Vision-Language Models Struggle to Align Entities across Modalities","version":2},"cited_work":{"arxiv_id":"2503.03854","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2503.03854","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Vision-language models struggle to align entities across modalities","venue":null,"work_id":"5c9f55ac-83c2-4144-83b5-997c68f45013","year":2025},"citing_paper":{"arxiv_id":"2512.08923","last_updated":"2026-04-22T09:19:17Z","snapshot_observed_at":"2026-07-06T22:38:13.359449Z","submitted_at":"2025-12-09T18:57:07Z","title":"Same Content, Different Answers: Cross-Modal Inconsistency in MLLMs","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-16T23:52:13.813452Z"},"links":{"cited_paper":"/paper/2503.03854","citing_paper":"/paper/2512.08923"},"observation_digest":"sha256:62e17067bacc1869020556a3ad63b275c803a2c988a94a63f3dfeb2ef5d92e47","observation_id":"82fd1ed4-f002-4700-bb0b-9d9a2288c4ea","resolution":{"observed_at":"2026-05-16T23:53:42.846348Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2503.03854/citation-record","integrity":"/paper/2503.03854/integrity","json":"/paper/2503.03854/citation-record.json","paper":"/paper/2503.03854"},"outbound":[],"paper":{"arxiv_id":"2503.03854","last_updated":"2025-05-30T13:04:40Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-07T10:09:13.623264Z","submitted_at":"2025-03-05T19:36:43Z","title":"Vision-Language Models Struggle to Align Entities across Modalities"},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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:2503.03854."}