{"as_of":"2026-08-17T09:21:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e7a737f1d52b6be88228bd83c5f5b28b578f7942aacc9a7af0a577844c9ef928","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":"2026-08-17T06:30:58.91139+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":"2026-08-12T14:53:11.674068Z","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":"2026-08-12T11:30:20.687073Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2407.21757","last_updated":"2024-09-12T14:01:56Z","snapshot_observed_at":"2026-08-16T13:29:28.012956Z","submitted_at":"2024-07-31T17:23:57Z","title":"Learning Video Context as Interleaved Multimodal Sequences","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.21757","snapshot_observed_at":"2026-08-12T14:53:11.674068Z","title":"Learning video context as interleaved multimodal sequences","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2411.15262","last_updated":"2025-03-31T02:52:56Z","snapshot_observed_at":"2026-08-17T06:16:48.528716Z","submitted_at":"2024-11-22T10:25:08Z","title":"MovieBench: A Hierarchical Movie Level Dataset for Long Video Generation","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-12T14:53:11.674068Z"},"links":{"cited_paper":"/paper/2407.21757","citing_paper":"/paper/2411.15262"},"observation_digest":"sha256:fe585a4c42e3885e3565e5bd11c60e729e4ad48b364c3f0a1a0aef646fa93dba","observation_id":"e711e1a0-fcd2-498f-a614-d7d707dd5288","resolution":{"observed_at":"2026-08-12T14:53:11.674068Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.21757","last_updated":"2024-09-12T14:01:56Z","snapshot_observed_at":"2026-08-16T13:29:28.012956Z","submitted_at":"2024-07-31T17:23:57Z","title":"Learning Video Context as Interleaved Multimodal Sequences","version":2},"cited_work":{"arxiv_id":"2407.21757","doi":null,"metadata_source":"pith","pith_arxiv_id":"2407.21757","snapshot_observed_at":"2026-08-12T11:30:20.687073Z","title":"Learning Video Context as Interleaved Multimodal Sequences","venue":"cs.CV","work_id":"6491bf8c-0e6b-41e3-8313-77b02581c136","year":2024},"citing_paper":{"arxiv_id":"2411.18180","last_updated":"2024-11-27T09:54:59Z","snapshot_observed_at":"2026-08-12T23:07:07.521493Z","submitted_at":"2024-11-27T09:54:59Z","title":"DistinctAD: Distinctive Audio Description Generation in Contexts","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-12T11:30:20.233251Z"},"links":{"cited_paper":"/paper/2407.21757","citing_paper":"/paper/2411.18180"},"observation_digest":"sha256:b7406bb4de825399f497904e9d2749790501585c3ab309a6920f65b30e47a542","observation_id":"22704919-9201-4f2c-85f9-42851797e616","resolution":{"observed_at":"2026-08-12T11:30:20.692183Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2407.21757/citation-record","integrity":"/paper/2407.21757/integrity","json":"/paper/2407.21757/citation-record.json","paper":"/paper/2407.21757"},"outbound":[],"paper":{"arxiv_id":"2407.21757","last_updated":"2024-09-12T14:01:56Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-16T13:29:28.012956Z","submitted_at":"2024-07-31T17:23:57Z","title":"Learning Video Context as Interleaved Multimodal Sequences"},"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":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 17 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2407.21757."}