{"as_of":"2026-08-12T18:33:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:8b821ec9a5e010bfa8e3ef6d74e13eb0bb21f06a91def01526fa2b8d0477596c","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":"2026-08-12T06:34:41.77262+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":"2026-08-11T15:03:10.608963Z","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":"2026-08-10T19:05:48.353679Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2201.08071","last_updated":"2023-03-13T13:55:30Z","snapshot_observed_at":"2026-08-12T12:22:39.224616Z","submitted_at":"2022-01-20T09:10:20Z","title":"Temporal Sentence Grounding in Videos: A Survey and Future Directions","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.08071","snapshot_observed_at":"2026-08-11T15:03:10.608963Z","title":"The elements of temporal sentence grounding in videos: A survey and futur e directions,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.11391","last_updated":"2024-12-16T02:37:58Z","snapshot_observed_at":"2026-08-11T14:56:51.979372Z","submitted_at":"2024-12-16T02:37:58Z","title":"Temporal Contrastive Learning for Video Temporal Reasoning in Large Vision-Language Models","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-11T15:03:10.608963Z"},"links":{"cited_paper":"/paper/2201.08071","citing_paper":"/paper/2412.11391"},"observation_digest":"sha256:36337b605856c4cc1e5ffdb24a3a3232b595f5c86e6b01e9b5d98ca46afaaf46","observation_id":"6649c21a-592f-445a-b08e-a77b3f96058c","resolution":{"observed_at":"2026-08-11T15:03:10.608963Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.08071","last_updated":"2023-03-13T13:55:30Z","snapshot_observed_at":"2026-08-12T12:22:39.224616Z","submitted_at":"2022-01-20T09:10:20Z","title":"Temporal Sentence Grounding in Videos: A Survey and Future Directions","version":3},"cited_work":{"arxiv_id":"2201.08071","doi":null,"metadata_source":"pith","pith_arxiv_id":"2201.08071","snapshot_observed_at":"2026-08-10T19:05:48.353679Z","title":"Temporal Sentence Grounding in Videos: A Survey and Future Directions","venue":"cs.CV","work_id":"2ee6f3f9-78cd-4af0-971c-4959c0b64ffb","year":2022},"citing_paper":{"arxiv_id":"2501.10692","last_updated":"2025-01-18T08:09:44Z","snapshot_observed_at":"2026-08-12T03:12:41.859367Z","submitted_at":"2025-01-18T08:09:44Z","title":"Multi-modal Fusion and Query Refinement Network for Video Moment Retrieval and Highlight Detection","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-10T19:05:48.169189Z"},"links":{"cited_paper":"/paper/2201.08071","citing_paper":"/paper/2501.10692"},"observation_digest":"sha256:1c5708cc23d63a00ff22631165ae9f0df991cf7a5f0c2e6c410793b386dfba3d","observation_id":"978ceb9b-bade-4c84-8886-774fdcd1944e","resolution":{"observed_at":"2026-08-10T19:05:48.364200Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2201.08071/citation-record","integrity":"/paper/2201.08071/integrity","json":"/paper/2201.08071/citation-record.json","paper":"/paper/2201.08071"},"outbound":[],"paper":{"arxiv_id":"2201.08071","last_updated":"2023-03-13T13:55:30Z","latest_version":3,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-12T12:22:39.224616Z","submitted_at":"2022-01-20T09:10:20Z","title":"Temporal Sentence Grounding in Videos: A Survey and Future Directions"},"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":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"thesis":"As of 12 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2201.08071."}