{"as_of":"2026-08-13T23:51:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d225269480e1a2bd826ece2d8877b637f888e76028e4158442bc59b1c68ea58c","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":"2026-08-13T06:32:02.005865+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":"2026-08-12T15:06:04.866401Z","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":"2026-08-11T23:05:27.703270Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2305.03204","last_updated":"2023-05-04T23:27:21Z","snapshot_observed_at":"2026-08-13T11:48:58.488724Z","submitted_at":"2023-05-04T23:27:21Z","title":"VideoOFA: Two-Stage Pre-Training for Video-to-Text Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.03204","snapshot_observed_at":"2026-08-12T15:06:04.866401Z","title":"Videoofa: Two- stage pre-training for video-to-text generation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.14688","last_updated":"2024-11-22T02:46:44Z","snapshot_observed_at":"2026-08-12T14:58:42.271167Z","submitted_at":"2024-11-22T02:46:44Z","title":"Whats in a Video: Factorized Autoregressive Decoding for Online Dense Video Captioning","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-12T15:06:04.866401Z"},"links":{"cited_paper":"/paper/2305.03204","citing_paper":"/paper/2411.14688"},"observation_digest":"sha256:001698d8bbb7d25d8fe5b44fc74f6ca762bcb64f112ba7af6b26ec6c39ee76b0","observation_id":"322233ca-9b62-4e1c-8271-0d32a8f6c89e","resolution":{"observed_at":"2026-08-12T15:06:04.866401Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.03204","last_updated":"2023-05-04T23:27:21Z","snapshot_observed_at":"2026-08-13T11:48:58.488724Z","submitted_at":"2023-05-04T23:27:21Z","title":"VideoOFA: Two-Stage Pre-Training for Video-to-Text Generation","version":1},"cited_work":{"arxiv_id":"2305.03204","doi":null,"metadata_source":"pith","pith_arxiv_id":"2305.03204","snapshot_observed_at":"2026-08-11T23:05:27.703270Z","title":"VideoOFA: Two-Stage Pre-Training for Video-to-Text Generation","venue":"cs.CV","work_id":"7c91a56b-404e-4ddb-875f-d88c89203c2a","year":2023},"citing_paper":{"arxiv_id":"2412.15220","last_updated":"2024-12-03T21:48:08Z","snapshot_observed_at":"2026-08-13T15:30:52.325262Z","submitted_at":"2024-12-03T21:48:08Z","title":"SyncFlow: Toward Temporally Aligned Joint Audio-Video Generation from Text","version":1},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-11T23:05:27.379194Z"},"links":{"cited_paper":"/paper/2305.03204","citing_paper":"/paper/2412.15220"},"observation_digest":"sha256:f8063a7e204c73ec116f6a193cff1cc48b0412d4145bae675d596f6dd383450c","observation_id":"0f8d7c8f-0779-4c12-b2e9-e5a4d6623cd4","resolution":{"observed_at":"2026-08-11T23:05:27.710092Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2305.03204/citation-record","integrity":"/paper/2305.03204/integrity","json":"/paper/2305.03204/citation-record.json","paper":"/paper/2305.03204"},"outbound":[],"paper":{"arxiv_id":"2305.03204","last_updated":"2023-05-04T23:27:21Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-13T11:48:58.488724Z","submitted_at":"2023-05-04T23:27:21Z","title":"VideoOFA: Two-Stage Pre-Training for Video-to-Text Generation"},"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":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2305.03204."}