{"as_of":"2026-08-10T12:28:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:762b5facdaf3edf479102c709da534ce9a09c0b0def48f29f084ac42a2ace9ce","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":"2026-08-10T06:31:04.303077+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":"2026-08-07T15:41:07.984130Z","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":"2026-08-07T15:41:09.929010Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2406.08024","last_updated":"2024-06-12T09:22:45Z","snapshot_observed_at":"2026-08-10T12:00:28.972867Z","submitted_at":"2024-06-12T09:22:45Z","title":"Fewer Tokens and Fewer Videos: Extending Video Understanding Abilities in Large Vision-Language Models","version":1},"cited_work":{"arxiv_id":"2406.08024","doi":null,"metadata_source":"pith","pith_arxiv_id":"2406.08024","snapshot_observed_at":"2026-08-07T15:41:09.929010Z","title":"Fewer Tokens and Fewer Videos: Extending Video Understanding Abilities in Large Vision-Language Models","venue":"cs.CV","work_id":"0a6d8c66-db97-435f-b4bf-a5e5f1a5ca8d","year":2024},"citing_paper":{"arxiv_id":"2505.14321","last_updated":"2025-05-20T13:07:55Z","snapshot_observed_at":"2026-08-07T23:44:06.171904Z","submitted_at":"2025-05-20T13:07:55Z","title":"Breaking Down Video LLM Benchmarks: Knowledge, Spatial Perception, or True Temporal Understanding?","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T15:41:07.984130Z"},"links":{"cited_paper":"/paper/2406.08024","citing_paper":"/paper/2505.14321"},"observation_digest":"sha256:81b57b73b2db1504307407b5362df5449d73575200064a8bcb014405c226111b","observation_id":"1db472a9-81e2-4a50-8841-9cefcd3006ee","resolution":{"observed_at":"2026-08-07T15:41:09.987240Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.08024","last_updated":"2024-06-12T09:22:45Z","snapshot_observed_at":"2026-08-10T12:00:28.972867Z","submitted_at":"2024-06-12T09:22:45Z","title":"Fewer Tokens and Fewer Videos: Extending Video Understanding Abilities in Large Vision-Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.08024","snapshot_observed_at":"2026-08-04T19:28:32.618929Z","title":"Fewer tokens and fewer videos: Extending video under- standing abilities in large vision-language models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.09263","last_updated":"2025-09-11T08:49:22Z","snapshot_observed_at":"2026-08-09T11:40:10.651044Z","submitted_at":"2025-09-11T08:49:22Z","title":"DATE: Dynamic Absolute Time Enhancement for Long Video Understanding","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-04T19:28:32.618929Z"},"links":{"cited_paper":"/paper/2406.08024","citing_paper":"/paper/2509.09263"},"observation_digest":"sha256:28233ac6c7997f40cbe4368cef1b80e3b8e8dbf70dcc9dafe0368e2489f1d877","observation_id":"857f07fd-9954-45a6-ad11-5ab223d512e0","resolution":{"observed_at":"2026-08-04T19:28:32.618929Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2406.08024/citation-record","integrity":"/paper/2406.08024/integrity","json":"/paper/2406.08024/citation-record.json","paper":"/paper/2406.08024"},"outbound":[],"paper":{"arxiv_id":"2406.08024","last_updated":"2024-06-12T09:22:45Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-10T12:00:28.972867Z","submitted_at":"2024-06-12T09:22:45Z","title":"Fewer Tokens and Fewer Videos: Extending Video Understanding Abilities in Large Vision-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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2406.08024."}