{"as_of":"2026-08-08T17:16:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:228a9162148ce8ccc67e73e1b835463dcb63ae5c7c9cecea7ebcaad5a9d8ff10","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":"2026-08-07T10:27:05.643589Z","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":"2026-08-07T10:27:05.822980Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2104.04598","last_updated":"2021-06-21T10:56:29Z","snapshot_observed_at":"2026-07-06T10:58:11.204048Z","submitted_at":"2021-04-03T07:07:21Z","title":"Cross-Modal learning for Audio-Visual Video Parsing","version":2},"cited_work":{"arxiv_id":"2104.04598","doi":null,"metadata_source":"pith","pith_arxiv_id":"2104.04598","snapshot_observed_at":"2026-08-07T10:27:05.822980Z","title":"Cross-Modal learning for Audio-Visual Video Parsing","venue":"cs.SD","work_id":"2593efd4-564f-4bb6-a287-9add728d504e","year":2021},"citing_paper":{"arxiv_id":"2506.05328","last_updated":"2025-07-22T07:00:35Z","snapshot_observed_at":"2026-08-07T11:49:44.536475Z","submitted_at":"2025-06-05T17:58:33Z","title":"AV-Reasoner: Improving and Benchmarking Clue-Grounded Audio-Visual Counting for MLLMs","version":2},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-07T10:27:05.643589Z"},"links":{"cited_paper":"/paper/2104.04598","citing_paper":"/paper/2506.05328"},"observation_digest":"sha256:1029bc2b3d6f3bccf3dfdd649a5e802bd919931f16bdcd9486c428f94855efe4","observation_id":"3ad08ab3-41c1-486e-8ab4-6402bbae9db1","resolution":{"observed_at":"2026-08-07T10:27:05.828372Z","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/2104.04598/citation-record","integrity":"/paper/2104.04598/integrity","json":"/paper/2104.04598/citation-record.json","paper":"/paper/2104.04598"},"outbound":[],"paper":{"arxiv_id":"2104.04598","last_updated":"2021-06-21T10:56:29Z","latest_version":2,"primary_category":"cs.SD","snapshot_observed_at":"2026-07-06T10:58:11.204048Z","submitted_at":"2021-04-03T07:07:21Z","title":"Cross-Modal learning for Audio-Visual Video Parsing"},"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:2104.04598."}