{"as_of":"2026-08-10T05:29:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:b6d31df6c3cd6f5bf439de5d729a04a8c9b368a0ea79b9101cb8da5c48ddc558","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":1,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":1,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-16T17:25:38.591071Z","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":"2026-05-16T17:28:10.057432Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2508.08237","last_updated":"2026-06-30T17:19:50Z","snapshot_observed_at":"2026-08-05T21:29:14.404752Z","submitted_at":"2025-08-11T17:53:23Z","title":"VGGSounder: Audio-Visual Evaluations for Foundation Models","version":5},"cited_work":{"arxiv_id":"2508.08237","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2508.08237","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Vggsounder: Audio-visual evaluations for foundation models.ArXiv, abs/2508.08237","venue":null,"work_id":"8c5ede27-1b27-4759-a895-0a55ee68a56f","year":2025},"citing_paper":{"arxiv_id":"2601.02731","last_updated":"2026-04-29T02:44:11Z","snapshot_observed_at":"2026-07-06T22:40:46.465095Z","submitted_at":"2026-01-06T05:49:41Z","title":"Omni2Sound: Towards Unified Video-Text-to-Audio Generation","version":3},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-05-16T17:25:38.591071Z"},"links":{"cited_paper":"/paper/2508.08237","citing_paper":"/paper/2601.02731"},"observation_digest":"sha256:717bedba5f074ac2f49cad2ae3db82a9b8370e397a5382e3ea1af5cc97635097","observation_id":"7f1875e6-12f4-43f5-92ce-4a35e1679747","resolution":{"observed_at":"2026-06-04T02:07:39.404044Z","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/2508.08237/citation-record","integrity":"/paper/2508.08237/integrity","json":"/paper/2508.08237/citation-record.json","paper":"/paper/2508.08237"},"outbound":[],"paper":{"arxiv_id":"2508.08237","last_updated":"2026-06-30T17:19:50Z","latest_version":5,"primary_category":"cs.MM","snapshot_observed_at":"2026-08-05T21:29:14.404752Z","submitted_at":"2025-08-11T17:53:23Z","title":"VGGSounder: Audio-Visual Evaluations for Foundation Models"},"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 1 inbound Pith citation observation for arXiv:2508.08237."}