{"as_of":"2026-07-31T18:48:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:5bcdf28efc1553e767b5307adabc9fed503c2918e916789b9ecf074352205f7c","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":"2026-07-31T06:34:12.847434+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":"2026-06-30T21:18:08.991522Z","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":"2026-07-01T14:25:47.176963Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2507.21448","last_updated":"2025-08-04T16:20:43Z","snapshot_observed_at":"2026-07-06T22:04:20.800847Z","submitted_at":"2025-07-29T02:38:56Z","title":"Real-Time Audio-Visual Speech Enhancement Using Pre-trained Visual Representations","version":2},"cited_work":{"arxiv_id":"2507.21448","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2507.21448","snapshot_observed_at":"2026-07-01T14:25:47.176963Z","title":"Real-time audio-visual speech enhancement using pre-trained visual representations,","venue":null,"work_id":"a3c4da02-b29a-4f9d-9797-1c8071b097e8","year":2025},"citing_paper":{"arxiv_id":"2605.13931","last_updated":"2026-05-27T00:11:29Z","snapshot_observed_at":"2026-07-06T23:25:25.361350Z","submitted_at":"2026-05-13T16:04:12Z","title":"FSD50K-Solo: Automated Curation of Single-Source Sound Events","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-06-30T21:18:08.991522Z"},"links":{"cited_paper":"/paper/2507.21448","citing_paper":"/paper/2605.13931"},"observation_digest":"sha256:4608ab226163814d80f16345751ad4cbbc22bb53710359ab2d8dde94b4e11d66","observation_id":"b7317e6e-dbb0-42c4-8761-97e6f89fb4d3","resolution":{"observed_at":"2026-07-01T14:25:47.179446Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-31T06:34:12.847434+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-31T06:34:12.847434+00:00","source":"crossref"},{"observed_at":"2026-07-31T06:34:08.642788+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2507.21448/citation-record","integrity":"/paper/2507.21448/integrity","json":"/paper/2507.21448/citation-record.json","paper":"/paper/2507.21448"},"outbound":[],"paper":{"arxiv_id":"2507.21448","last_updated":"2025-08-04T16:20:43Z","latest_version":2,"primary_category":"eess.AS","snapshot_observed_at":"2026-07-06T22:04:20.800847Z","submitted_at":"2025-07-29T02:38:56Z","title":"Real-Time Audio-Visual Speech Enhancement Using Pre-trained Visual Representations"},"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":"2026-07-31T06:34:12.847434+00:00","source":"crossref"},{"observed_at":"2026-07-31T06:34:08.642788+00:00","source":"retraction_watch"}],"thesis":"As of 31 July 2026, this Paper Citation Record lists 0 of 0 outbound references and 1 inbound Pith citation observation for arXiv:2507.21448."}