{"as_of":"2026-08-21T01:41:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:84c1c685010134bd213e0c37f73a0a922b5b7d64661a77e01412103b52e055f8","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":"2026-08-12T14:40:23.689402Z","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":"2026-05-23T08:12:43.930786Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2310.04991","last_updated":"2023-10-11T07:20:32Z","snapshot_observed_at":"2026-08-18T10:31:55.477975Z","submitted_at":"2023-10-08T03:35:27Z","title":"Video-Teller: Enhancing Cross-Modal Generation with Fusion and Decoupling","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.04991","snapshot_observed_at":"2026-08-12T14:40:23.689402Z","title":"Video- teller: Enhancing cross-modal generation with fusion and decoupling","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.15024","last_updated":"2025-03-28T14:11:37Z","snapshot_observed_at":"2026-08-19T01:50:35.848234Z","submitted_at":"2024-11-22T15:55:19Z","title":"DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models","version":3},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-12T14:40:23.689402Z"},"links":{"cited_paper":"/paper/2310.04991","citing_paper":"/paper/2411.15024"},"observation_digest":"sha256:4fc50b44d38e0077ef57c56f3cc016635d311d54e282fe8eb5bdd55263e4dbbe","observation_id":"a101bd37-0ac1-417c-baa6-8b59d8bce438","resolution":{"observed_at":"2026-08-12T14:40:23.689402Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.04991","last_updated":"2023-10-11T07:20:32Z","snapshot_observed_at":"2026-08-18T10:31:55.477975Z","submitted_at":"2023-10-08T03:35:27Z","title":"Video-Teller: Enhancing Cross-Modal Generation with Fusion and Decoupling","version":3},"cited_work":{"arxiv_id":"2310.04991","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2310.04991","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Video- teller: Enhancing cross-modal generation with fusion and decoupling","venue":null,"work_id":"980d6b44-87fb-4deb-839b-55b5f9d3c1fc","year":2023},"citing_paper":{"arxiv_id":"2412.02930","last_updated":"2026-04-19T04:24:58Z","snapshot_observed_at":"2026-08-15T03:52:27.783345Z","submitted_at":"2024-12-04T00:50:33Z","title":"TemporalVLM: Video LLMs for Temporal Reasoning in Long Videos","version":6},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-05-23T08:08:01.889675Z"},"links":{"cited_paper":"/paper/2310.04991","citing_paper":"/paper/2412.02930"},"observation_digest":"sha256:c4f0987c0656d980471e47d37cf53bff0df80998c6b6935465f8ba6e6c677232","observation_id":"46226cf0-a31d-4ab5-b743-d3dd520afca2","resolution":{"observed_at":"2026-05-23T08:12:43.933455Z","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/2310.04991/citation-record","integrity":"/paper/2310.04991/integrity","json":"/paper/2310.04991/citation-record.json","paper":"/paper/2310.04991"},"outbound":[],"paper":{"arxiv_id":"2310.04991","last_updated":"2023-10-11T07:20:32Z","latest_version":3,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-18T10:31:55.477975Z","submitted_at":"2023-10-08T03:35:27Z","title":"Video-Teller: Enhancing Cross-Modal Generation with Fusion and Decoupling"},"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 21 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2310.04991."}