{"as_of":"2026-08-22T04:52:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:369bba93b7093a2bd8a49762baf379a17dabf1ffedc36bcd71ce2e66543d7f80","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":"2026-08-21T06:32:19.484+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":"2026-08-05T23:32:17.911414Z","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":"2026-08-05T23:32:18.875089Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2405.12540","last_updated":"2024-05-21T07:12:27Z","snapshot_observed_at":"2026-08-19T01:09:02.535941Z","submitted_at":"2024-05-21T07:12:27Z","title":"Context-Enhanced Video Moment Retrieval with Large Language Models","version":1},"cited_work":{"arxiv_id":"2405.12540","doi":null,"metadata_source":"pith","pith_arxiv_id":"2405.12540","snapshot_observed_at":"2026-08-05T23:32:18.875089Z","title":"Context-Enhanced Video Moment Retrieval with Large Language Models","venue":"cs.CV","work_id":"0cf89c0e-a92a-411c-b63a-c3a06f6ea730","year":2024},"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":100,"source":"arxiv_source","source_observed_at":"2026-08-05T23:32:17.911414Z"},"links":{"cited_paper":"/paper/2405.12540","citing_paper":"/paper/2508.10922"},"observation_digest":"sha256:2ac593ec805ed96774c45085e17fa9cf649fa4c07a765bcf9eb5a0215ca8752c","observation_id":"a55f8afc-6794-49d6-b2e8-f7c444f1765a","resolution":{"observed_at":"2026-08-05T23:32:18.882066Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2405.12540","last_updated":"2024-05-21T07:12:27Z","snapshot_observed_at":"2026-08-19T01:09:02.535941Z","submitted_at":"2024-05-21T07:12:27Z","title":"Context-Enhanced Video Moment Retrieval with Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.12540","snapshot_observed_at":"2026-08-03T21:42:48.592779Z","title":"Context-enhanced video moment retrieval with large language models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2511.14143","last_updated":"2026-06-08T00:19:12Z","snapshot_observed_at":"2026-08-17T20:53:08.632103Z","submitted_at":"2025-11-18T05:03:17Z","title":"SMART: Shot-Aware Multimodal Video Moment Retrieval with Audio-Enhanced MLLM","version":2},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-03T21:42:48.592779Z"},"links":{"cited_paper":"/paper/2405.12540","citing_paper":"/paper/2511.14143"},"observation_digest":"sha256:f5b140e05c995549116d20c470ce2fea4ffd4ae796a10d94961192df71d2b6eb","observation_id":"61f663c5-8429-4518-86b7-a902f7a1d71e","resolution":{"observed_at":"2026-08-03T21:42:48.592779Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2405.12540/citation-record","integrity":"/paper/2405.12540/integrity","json":"/paper/2405.12540/citation-record.json","paper":"/paper/2405.12540"},"outbound":[],"paper":{"arxiv_id":"2405.12540","last_updated":"2024-05-21T07:12:27Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-19T01:09:02.535941Z","submitted_at":"2024-05-21T07:12:27Z","title":"Context-Enhanced Video Moment Retrieval with Large Language Models"},"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":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"thesis":"As of 22 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2405.12540."}