{"as_of":"2026-08-10T04:45:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d6712218324bf9dede0ee279d4d7896a25cae17c5cca32e7d813ea4b03f46af3","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":4,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":4,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T00:02:26.229598Z","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":"2026-06-29T22:54:00.771281Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2409.08601","last_updated":"2025-03-24T04:00:01Z","snapshot_observed_at":"2026-08-09T12:58:51.986437Z","submitted_at":"2024-09-13T07:31:44Z","title":"STA-V2A: Video-to-Audio Generation with Semantic and Temporal Alignment","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.08601","snapshot_observed_at":"2026-08-10T00:02:26.229598Z","title":"STA-V2A : Video-to-audio generation with semantic and temporal alignment","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.18314","last_updated":"2025-07-14T07:08:07Z","snapshot_observed_at":"2026-08-09T23:52:58.437414Z","submitted_at":"2025-01-30T12:43:47Z","title":"AGAV-Rater: Adapting Large Multimodal Model for AI-Generated Audio-Visual Quality Assessment","version":2},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-10T00:02:26.229598Z"},"links":{"cited_paper":"/paper/2409.08601","citing_paper":"/paper/2501.18314"},"observation_digest":"sha256:ee3e5e9d08cfdd32075be4e0ce2cd648b3c47d11f5e05c3aee4f9e94436571af","observation_id":"0173fc3d-43ff-461d-8c7a-f56bc89cdaf7","resolution":{"observed_at":"2026-08-10T00:02:26.229598Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.08601","last_updated":"2025-03-24T04:00:01Z","snapshot_observed_at":"2026-08-09T12:58:51.986437Z","submitted_at":"2024-09-13T07:31:44Z","title":"STA-V2A: Video-to-Audio Generation with Semantic and Temporal Alignment","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.08601","snapshot_observed_at":"2026-08-06T20:37:18.302787Z","title":"Sta-v2a: Video- to-audio generation with semantic and temporal align- ment","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.02271","last_updated":"2025-07-03T03:23:11Z","snapshot_observed_at":"2026-08-08T12:03:28.548055Z","submitted_at":"2025-07-03T03:23:11Z","title":"Spotlighting Partially Visible Cinematic Language for Video-to-Audio Generation via Self-distillation","version":1},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-06T20:37:18.302787Z"},"links":{"cited_paper":"/paper/2409.08601","citing_paper":"/paper/2507.02271"},"observation_digest":"sha256:0d3db00c0665b9995397f63d1d0c2ef005ee2007ea91faf17c80861a6f499ef8","observation_id":"bcfd0b05-4dc7-41cc-801b-84536be8fcc6","resolution":{"observed_at":"2026-08-06T20:37:18.302787Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.08601","last_updated":"2025-03-24T04:00:01Z","snapshot_observed_at":"2026-08-09T12:58:51.986437Z","submitted_at":"2024-09-13T07:31:44Z","title":"STA-V2A: Video-to-Audio Generation with Semantic and Temporal Alignment","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.08601","snapshot_observed_at":"2026-08-05T05:50:17.678651Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.04957","last_updated":"2025-09-05T09:24:08Z","snapshot_observed_at":"2026-08-07T23:46:34.892649Z","submitted_at":"2025-09-05T09:24:08Z","title":"Efficient Video-to-Audio Generation via Multiple Foundation Models Mapper","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-05T05:50:17.678651Z"},"links":{"cited_paper":"/paper/2409.08601","citing_paper":"/paper/2509.04957"},"observation_digest":"sha256:450c173737a86779684b8d177197e9ac35e3d0a7332ce9449d5a0c26b4c0a1ac","observation_id":"18a912f6-1e23-49fe-8f26-677563723251","resolution":{"observed_at":"2026-08-05T05:50:17.678651Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.08601","last_updated":"2025-03-24T04:00:01Z","snapshot_observed_at":"2026-08-09T12:58:51.986437Z","submitted_at":"2024-09-13T07:31:44Z","title":"STA-V2A: Video-to-Audio Generation with Semantic and Temporal Alignment","version":2},"cited_work":{"arxiv_id":"2409.08601","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2409.08601","snapshot_observed_at":"2026-06-29T22:54:00.771281Z","title":"Sta-v2a: Video-to-audio gen- eration with semantic and temporal alignment.arXiv preprint arXiv:2409.08601, 2024","venue":null,"work_id":"4ea441ba-30d1-4516-bb13-a916b1af2e2c","year":2024},"citing_paper":{"arxiv_id":"2605.26244","last_updated":"2026-05-25T18:12:09Z","snapshot_observed_at":"2026-08-06T05:46:08.521756Z","submitted_at":"2026-05-25T18:12:09Z","title":"LongAV-Compass: Towards Unified Evaluation of Minute-Scale Audio-Visual Generation Across T2AV, I2AV, and V2AV","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-06-29T22:52:38.330851Z"},"links":{"cited_paper":"/paper/2409.08601","citing_paper":"/paper/2605.26244"},"observation_digest":"sha256:fa3f72f6350c970f40128746d0d8addad83fb8cec807667ea0668a57d245fd53","observation_id":"a6bfaaf5-79d6-459f-a589-8f22094298a1","resolution":{"observed_at":"2026-06-29T22:54:00.772785Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2409.08601/citation-record","integrity":"/paper/2409.08601/integrity","json":"/paper/2409.08601/citation-record.json","paper":"/paper/2409.08601"},"outbound":[],"paper":{"arxiv_id":"2409.08601","last_updated":"2025-03-24T04:00:01Z","latest_version":2,"primary_category":"cs.SD","snapshot_observed_at":"2026-08-09T12:58:51.986437Z","submitted_at":"2024-09-13T07:31:44Z","title":"STA-V2A: Video-to-Audio Generation with Semantic and Temporal Alignment"},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2409.08601."}