{"as_of":"2026-08-08T09:56:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a1418ee8211ac6409c0472f9c4288bcdd93d727f45596dce1f0b60624ca0448d","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":"2026-08-08T06:32:00.761636+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":"2026-08-06T21:52:05.884792Z","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":"2026-08-06T21:52:09.528067Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2407.07801","last_updated":"2024-07-11T02:38:14Z","snapshot_observed_at":"2026-07-06T18:44:20.262496Z","submitted_at":"2024-07-10T16:17:49Z","title":"AVCap: Leveraging Audio-Visual Features as Text Tokens for Captioning","version":2},"cited_work":{"arxiv_id":"2407.07801","doi":null,"metadata_source":"pith","pith_arxiv_id":"2407.07801","snapshot_observed_at":"2026-08-06T21:52:09.528067Z","title":"AVCap: Leveraging Audio-Visual Features as Text Tokens for Captioning","venue":"eess.AS","work_id":"3398b6b0-57a4-4bb4-a6ce-9db9e6dc62c8","year":2024},"citing_paper":{"arxiv_id":"2506.23271","last_updated":"2025-06-29T14:52:01Z","snapshot_observed_at":"2026-08-06T21:45:05.156058Z","submitted_at":"2025-06-29T14:52:01Z","title":"Mettle: Meta-Token Learning for Memory-Efficient Audio-Visual Adaptation","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-06T21:52:05.884792Z"},"links":{"cited_paper":"/paper/2407.07801","citing_paper":"/paper/2506.23271"},"observation_digest":"sha256:13d4ec07f6a3ad8419d45be3dc35bd512fa87c22e9e1d4be5c4e95eeffc55024","observation_id":"e045ada3-9866-492a-9455-47c4ad783cc4","resolution":{"observed_at":"2026-08-06T21:52:09.610064Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2407.07801/citation-record","integrity":"/paper/2407.07801/integrity","json":"/paper/2407.07801/citation-record.json","paper":"/paper/2407.07801"},"outbound":[],"paper":{"arxiv_id":"2407.07801","last_updated":"2024-07-11T02:38:14Z","latest_version":2,"primary_category":"eess.AS","snapshot_observed_at":"2026-07-06T18:44:20.262496Z","submitted_at":"2024-07-10T16:17:49Z","title":"AVCap: Leveraging Audio-Visual Features as Text Tokens for Captioning"},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 1 inbound Pith citation observation for arXiv:2407.07801."}