{"as_of":"2026-08-23T23:38:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:1d6e6a9ce8201d1944d0c4870eb1885fad66a3811cad228ba0945079cb4e4c7b","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":"2026-08-23T06:30:58.430688+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":"2026-08-12T05:12:20.134645Z","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":"2026-05-11T07:16:10.026674Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2503.06287","last_updated":"2025-03-08T17:24:42Z","snapshot_observed_at":"2026-08-16T12:51:54.923785Z","submitted_at":"2025-03-08T17:24:42Z","title":"Your Large Vision-Language Model Only Needs A Few Attention Heads For Visual Grounding","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.06287","snapshot_observed_at":"2026-08-12T05:12:20.134645Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2412.00684","last_updated":"2025-04-20T10:32:37Z","snapshot_observed_at":"2026-08-13T05:15:28.741838Z","submitted_at":"2024-12-01T05:47:59Z","title":"Paint Outside the Box: Synthesizing and Selecting Training Data for Visual Grounding","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-12T05:12:20.134645Z"},"links":{"cited_paper":"/paper/2503.06287","citing_paper":"/paper/2412.00684"},"observation_digest":"sha256:9bcf71a87253b10b16b27a99b68e1b815a8bccb9cbb0e5e34487ec788b62f85d","observation_id":"d0aa87e5-b1d2-4437-9442-8f2185c8cb80","resolution":{"observed_at":"2026-08-12T05:12:20.134645Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.06287","last_updated":"2025-03-08T17:24:42Z","snapshot_observed_at":"2026-08-16T12:51:54.923785Z","submitted_at":"2025-03-08T17:24:42Z","title":"Your Large Vision-Language Model Only Needs A Few Attention Heads For Visual Grounding","version":1},"cited_work":{"arxiv_id":"2503.06287","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2503.06287","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"bcd2406a-a70d-481e-9003-464a343b1344","year":2025},"citing_paper":{"arxiv_id":"2604.08456","last_updated":"2026-04-09T16:51:42Z","snapshot_observed_at":"2026-08-11T03:43:39.621933Z","submitted_at":"2026-04-09T16:51:42Z","title":"Entropy-Gradient Grounding: Training-Free Evidence Retrieval in Vision-Language Models","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-10T17:14:11.941977Z"},"links":{"cited_paper":"/paper/2503.06287","citing_paper":"/paper/2604.08456"},"observation_digest":"sha256:7b1bdaa471718eb328e3d32eb13f0eedce7fd8f5d5c614cc4562bd669aa42d1d","observation_id":"36568896-89af-4186-ae3c-c50ac2862f1a","resolution":{"observed_at":"2026-05-11T07:16:10.105891Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2503.06287/citation-record","integrity":"/paper/2503.06287/integrity","json":"/paper/2503.06287/citation-record.json","paper":"/paper/2503.06287"},"outbound":[],"paper":{"arxiv_id":"2503.06287","last_updated":"2025-03-08T17:24:42Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-16T12:51:54.923785Z","submitted_at":"2025-03-08T17:24:42Z","title":"Your Large Vision-Language Model Only Needs A Few Attention Heads For Visual Grounding"},"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":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"thesis":"As of 23 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2503.06287."}