{"as_of":"2026-08-14T14:04:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:cca161248abd513ec1847a835db9485ce1a11b17d9f97c6ad2dbf0222de87ebe","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":"2026-08-14T06:32:32.682623+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":"2026-08-11T11:47:55.951519Z","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":"2026-08-10T00:02:26.365346Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2409.09823","last_updated":"2024-09-15T18:51:18Z","snapshot_observed_at":"2026-08-12T22:44:32.885142Z","submitted_at":"2024-09-15T18:51:18Z","title":"Efficient Video to Audio Mapper with Visual Scene Detection","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.09823","snapshot_observed_at":"2026-08-11T11:47:55.951519Z","title":"Efficient video to audio mapper with visual scene detection,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.15023","last_updated":"2025-05-05T16:55:53Z","snapshot_observed_at":"2026-08-12T01:15:28.643181Z","submitted_at":"2024-12-19T16:37:19Z","title":"FolAI: Synchronized Foley Sound Generation with Semantic and Temporal Alignment","version":3},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-11T11:47:55.951519Z"},"links":{"cited_paper":"/paper/2409.09823","citing_paper":"/paper/2412.15023"},"observation_digest":"sha256:77a379fbaa8f3aa80b0b3b5f7249fbd17e19a85c3d9b5b8b416fe343a0f9dc9f","observation_id":"3c706d48-760b-4ec9-a4d5-9226bf83234e","resolution":{"observed_at":"2026-08-11T11:47:55.951519Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.09823","last_updated":"2024-09-15T18:51:18Z","snapshot_observed_at":"2026-08-12T22:44:32.885142Z","submitted_at":"2024-09-15T18:51:18Z","title":"Efficient Video to Audio Mapper with Visual Scene Detection","version":1},"cited_work":{"arxiv_id":"2409.09823","doi":null,"metadata_source":"pith","pith_arxiv_id":"2409.09823","snapshot_observed_at":"2026-08-10T00:02:26.365346Z","title":"Efficient Video to Audio Mapper with Visual Scene Detection","venue":"cs.SD","work_id":"3632ef4d-5881-49eb-a119-4d46871a03ef","year":2024},"citing_paper":{"arxiv_id":"2501.18314","last_updated":"2025-07-14T07:08:07Z","snapshot_observed_at":"2026-08-14T07:26:04.635905Z","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":63,"source":"arxiv_source","source_observed_at":"2026-08-10T00:02:26.303436Z"},"links":{"cited_paper":"/paper/2409.09823","citing_paper":"/paper/2501.18314"},"observation_digest":"sha256:d72a029992a561b973cdf93d212c86ba1e1a2d86a9c39378a2c4358057efe2a4","observation_id":"910fe5ed-f1b0-48c2-8584-ca20a38da188","resolution":{"observed_at":"2026-08-10T00:02:26.371834Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2409.09823/citation-record","integrity":"/paper/2409.09823/integrity","json":"/paper/2409.09823/citation-record.json","paper":"/paper/2409.09823"},"outbound":[],"paper":{"arxiv_id":"2409.09823","last_updated":"2024-09-15T18:51:18Z","latest_version":1,"primary_category":"cs.SD","snapshot_observed_at":"2026-08-12T22:44:32.885142Z","submitted_at":"2024-09-15T18:51:18Z","title":"Efficient Video to Audio Mapper with Visual Scene Detection"},"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":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"thesis":"As of 14 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2409.09823."}