{"as_of":"2026-08-09T13:22:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c3937667f0e4dc95690063a8401459db9f5bd06a4a777c39713ab27798ede6f9","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":"2026-08-09T06:31:02.800959+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":"2026-08-05T19:01:53.037954Z","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":"2026-08-05T19:01:53.161374Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2501.14607","last_updated":"2025-06-30T16:09:19Z","snapshot_observed_at":"2026-07-06T20:25:40.715105Z","submitted_at":"2025-01-24T16:24:15Z","title":"ReferDINO: Referring Video Object Segmentation with Visual Grounding Foundations","version":2},"cited_work":{"arxiv_id":"2501.14607","doi":null,"metadata_source":"pith","pith_arxiv_id":"2501.14607","snapshot_observed_at":"2026-08-05T19:01:53.161374Z","title":"ReferDINO: Referring Video Object Segmentation with Visual Grounding Foundations","venue":"cs.CV","work_id":"34987a8e-b2cc-406a-a771-1c0e665a2b6d","year":2025},"citing_paper":{"arxiv_id":"2508.13584","last_updated":"2025-08-19T07:36:04Z","snapshot_observed_at":"2026-08-05T19:01:41.734511Z","submitted_at":"2025-08-19T07:36:04Z","title":"Temporal-Conditional Referring Video Object Segmentation with Noise-Free Text-to-Video Diffusion Model","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-05T19:01:53.037954Z"},"links":{"cited_paper":"/paper/2501.14607","citing_paper":"/paper/2508.13584"},"observation_digest":"sha256:088f22f1749e6be8eb3b83f711c9384940849f5a31cf67c24c42e46635818fe3","observation_id":"ac71e21a-a829-46aa-ba28-b147d0845531","resolution":{"observed_at":"2026-08-05T19:01:53.166093Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2501.14607","last_updated":"2025-06-30T16:09:19Z","snapshot_observed_at":"2026-07-06T20:25:40.715105Z","submitted_at":"2025-01-24T16:24:15Z","title":"ReferDINO: Referring Video Object Segmentation with Visual Grounding Foundations","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.14607","snapshot_observed_at":"2026-07-11T23:56:52.009530Z","title":"Referdino: Referring video object segmenta- tion with visual grounding foundations.arXiv preprint arXiv:2501.14607,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.03789","last_updated":"2026-07-04T09:32:13Z","snapshot_observed_at":"2026-08-08T01:59:20.644759Z","submitted_at":"2026-07-04T09:32:13Z","title":"G$^2$TAM: Geometry Grounded Track Anything Model","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-07-11T23:56:52.009530Z"},"links":{"cited_paper":"/paper/2501.14607","citing_paper":"/paper/2607.03789"},"observation_digest":"sha256:ea003169ff235f1c523d47ecba165437c792050c7b2c9399cd16a7f2334087b3","observation_id":"1ad0b777-8d58-4ecf-9391-9c849c917c3d","resolution":{"observed_at":"2026-07-11T23:56:52.009530Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2501.14607/citation-record","integrity":"/paper/2501.14607/integrity","json":"/paper/2501.14607/citation-record.json","paper":"/paper/2501.14607"},"outbound":[],"paper":{"arxiv_id":"2501.14607","last_updated":"2025-06-30T16:09:19Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T20:25:40.715105Z","submitted_at":"2025-01-24T16:24:15Z","title":"ReferDINO: Referring Video Object Segmentation with Visual Grounding Foundations"},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2501.14607."}