{"as_of":"2026-08-07T06:31:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c31ff965ec05f2d6920f72d77f4c3a6b93b160cdd77a8f02afcf4bf72dcc3fa7","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":3,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":3,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-06T06:34:29.942622+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T17:02:46.490467Z","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":"2026-07-08T00:04:22.536675Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2407.04416","last_updated":"2025-01-01T13:46:37Z","snapshot_observed_at":"2026-07-06T18:41:53.152987Z","submitted_at":"2024-07-05T11:07:13Z","title":"Sound-VECaps: Improving Audio Generation with Visual Enhanced Captions","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.04416","snapshot_observed_at":"2026-08-06T17:02:46.490467Z","title":"Sound-vecaps: Improving audio generation with visual enhanced captions,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.11967","last_updated":"2025-07-16T06:58:14Z","snapshot_observed_at":"2026-08-06T16:54:50.538184Z","submitted_at":"2025-07-16T06:58:14Z","title":"Language-Guided Contrastive Audio-Visual Masked Autoencoder with Automatically Generated Audio-Visual-Text Triplets from Videos","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T17:02:46.490467Z"},"links":{"cited_paper":"/paper/2407.04416","citing_paper":"/paper/2507.11967"},"observation_digest":"sha256:79ec077414f2d2b133e9bdd00bc620da5005253e68491cccec22ce14d6b466e8","observation_id":"400238fd-6039-465d-a1a4-3597ab50cd9d","resolution":{"observed_at":"2026-08-06T17:02:46.490467Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.04416","last_updated":"2025-01-01T13:46:37Z","snapshot_observed_at":"2026-07-06T18:41:53.152987Z","submitted_at":"2024-07-05T11:07:13Z","title":"Sound-VECaps: Improving Audio Generation with Visual Enhanced Captions","version":4},"cited_work":{"arxiv_id":"2407.04416","doi":null,"metadata_source":"pith","pith_arxiv_id":"2407.04416","snapshot_observed_at":"2026-07-08T00:04:22.536675Z","title":"Sound-VECaps: Improving Audio Generation with Visual Enhanced Captions","venue":"cs.SD","work_id":"30a64d36-a955-4081-8f4b-7fffb471d130","year":2024},"citing_paper":{"arxiv_id":"2607.05196","last_updated":"2026-07-07T15:36:48Z","snapshot_observed_at":"2026-07-11T07:46:45.098798Z","submitted_at":"2026-07-06T15:11:57Z","title":"Unified Audio Intelligence Without Regressing on Text Intelligence","version":1},"reference_index":67,"source":"arxiv_source","source_observed_at":"2026-07-07T23:59:38.702609Z"},"links":{"cited_paper":"/paper/2407.04416","citing_paper":"/paper/2607.05196"},"observation_digest":"sha256:55710ae5c830b68f8c63c54a31cd314a239374c5c842577454b9c71b6787cb98","observation_id":"42eee5fb-72fb-4fed-b827-dc747763a45f","resolution":{"observed_at":"2026-07-08T00:04:22.538025Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.04416","last_updated":"2025-01-01T13:46:37Z","snapshot_observed_at":"2026-07-06T18:41:53.152987Z","submitted_at":"2024-07-05T11:07:13Z","title":"Sound-VECaps: Improving Audio Generation with Visual Enhanced Captions","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.04416","snapshot_observed_at":"2026-07-11T07:46:49.059192Z","title":"arXiv preprint arXiv:2407.04416 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.05196","last_updated":"2026-07-07T15:36:48Z","snapshot_observed_at":"2026-07-11T07:46:45.098798Z","submitted_at":"2026-07-06T15:11:57Z","title":"Unified Audio Intelligence Without Regressing on Text Intelligence","version":2},"reference_index":67,"source":"arxiv_source","source_observed_at":"2026-07-11T07:46:49.059192Z"},"links":{"cited_paper":"/paper/2407.04416","citing_paper":"/paper/2607.05196"},"observation_digest":"sha256:438aca709d81631ef87cd793e53c3028e29c9fdca448c4d69a19845f127ce328","observation_id":"9b7c5262-0aff-4d9f-bd34-95b37b4fdf84","resolution":{"observed_at":"2026-07-11T07:46:49.059192Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2407.04416/citation-record","integrity":"/paper/2407.04416/integrity","json":"/paper/2407.04416/citation-record.json","paper":"/paper/2407.04416"},"outbound":[],"paper":{"arxiv_id":"2407.04416","last_updated":"2025-01-01T13:46:37Z","latest_version":4,"primary_category":"cs.SD","snapshot_observed_at":"2026-07-06T18:41:53.152987Z","submitted_at":"2024-07-05T11:07:13Z","title":"Sound-VECaps: Improving Audio Generation with Visual Enhanced Captions"},"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":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2407.04416."}