{"as_of":"2026-08-10T12:30:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:613fccaaddd0b863cb159f72416228fb0cf334b86e4fd81879e4ca7caefea5bb","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":"2026-08-10T06:31:04.303077+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":"2026-08-07T10:53:17.755251Z","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":"2026-08-07T10:53:17.755251Z","title":"D., et al","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.04214","last_updated":"2025-06-04T17:57:26Z","snapshot_observed_at":"2026-08-08T10:09:33.418979Z","submitted_at":"2025-06-04T17:57:26Z","title":"Sounding that Object: Interactive Object-Aware Image to Audio Generation","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T10:53:17.755251Z"},"links":{"cited_paper":"/paper/2407.04416","citing_paper":"/paper/2506.04214"},"observation_digest":"sha256:568740c22f469eca5df641acdd46f937572778b7bdc076f4a7750879aacb9a4e","observation_id":"f491f5a3-11f0-4614-94de-1a71b8fca4f4","resolution":{"observed_at":"2026-08-07T10:53:17.755251Z","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":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":"2026-08-10T02:00:05.966441Z","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":"sha256:6726875bbe4dae4bb9a39ea45be7af56f1e66966966a20419ae847d3e3b28e00","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":"2026-08-09T15:40:13.197295Z","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":"sha256:589a577838b246e15a9868b77c031320d32656fbed780a073a9edc8cf16117cd","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 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-09T15:40:13.197295Z","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:f747a00f3683e05d8e3b599c059cdf940b702d4f8435a0c086cbeaf82fd238fb","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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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:2407.04416."}