{"as_of":"2026-08-20T22:56:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:668f09bf0d5e6b766a83384a560807653ffa25a2e76e6878ff5f6fa972393710","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":"2026-08-20T06:33:59.587034+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":"2026-08-05T23:32:17.640437Z","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":"2026-07-04T06:39:37.665560Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2104.00234","last_updated":"2021-04-01T03:30:45Z","snapshot_observed_at":"2026-08-16T18:34:36.308315Z","submitted_at":"2021-04-01T03:30:45Z","title":"A Survey on Natural Language Video Localization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.00234","snapshot_observed_at":"2026-08-05T23:32:17.640437Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.10922","last_updated":"2025-08-07T08:52:11Z","snapshot_observed_at":"2026-08-15T18:49:45.191733Z","submitted_at":"2025-08-07T08:52:11Z","title":"A Survey on Video Temporal Grounding with Multimodal Large Language Model","version":1},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-05T23:32:17.640437Z"},"links":{"cited_paper":"/paper/2104.00234","citing_paper":"/paper/2508.10922"},"observation_digest":"sha256:088f36c0f1bd35a1d76b90d1bb3c436b1d5f694c39f960d40f7f0a7029767303","observation_id":"014b09cb-8115-4e53-a693-aabaadb268e0","resolution":{"observed_at":"2026-08-05T23:32:17.640437Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.00234","last_updated":"2021-04-01T03:30:45Z","snapshot_observed_at":"2026-08-16T18:34:36.308315Z","submitted_at":"2021-04-01T03:30:45Z","title":"A Survey on Natural Language Video Localization","version":1},"cited_work":{"arxiv_id":"2104.00234","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2104.00234","snapshot_observed_at":"2026-07-04T06:39:37.665560Z","title":null,"venue":null,"work_id":"0891a53a-44cc-44a7-a706-86cfd6b495a3","year":2021},"citing_paper":{"arxiv_id":"2606.21734","last_updated":"2026-06-19T20:43:49Z","snapshot_observed_at":"2026-08-05T18:05:51.515234Z","submitted_at":"2026-06-19T20:43:49Z","title":"HPP: Hierarchical Programmatic Probing for Long Video Understanding by Decoupling Perception and Reasoning","version":1},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-06-26T14:19:53.450263Z"},"links":{"cited_paper":"/paper/2104.00234","citing_paper":"/paper/2606.21734"},"observation_digest":"sha256:26b99fe72776f836837d791c03d70f3b2c8db4ebcf03b114e6d36fa8cba10893","observation_id":"5ab20302-ea66-4856-ae14-1bcf89fdb913","resolution":{"observed_at":"2026-07-04T06:39:37.666898Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2104.00234/citation-record","integrity":"/paper/2104.00234/integrity","json":"/paper/2104.00234/citation-record.json","paper":"/paper/2104.00234"},"outbound":[],"paper":{"arxiv_id":"2104.00234","last_updated":"2021-04-01T03:30:45Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-16T18:34:36.308315Z","submitted_at":"2021-04-01T03:30:45Z","title":"A Survey on Natural Language Video Localization"},"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":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"thesis":"As of 20 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2104.00234."}