{"as_of":"2026-08-13T12:30:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a1351686c1fcacd6d235f25159acae00f33b80449c2b35a74078896626748fb4","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":"2026-08-13T06:32:02.005865+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":"2026-08-12T14:04:00.566673Z","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":"2026-08-12T14:04:03.502799Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2106.06939","last_updated":"2021-06-13T07:41:15Z","snapshot_observed_at":"2026-08-11T15:36:31.702820Z","submitted_at":"2021-06-13T07:41:15Z","title":"Cross-Modal Attention Consistency for Video-Audio Unsupervised Learning","version":1},"cited_work":{"arxiv_id":"2106.06939","doi":null,"metadata_source":"pith","pith_arxiv_id":"2106.06939","snapshot_observed_at":"2026-08-12T14:04:03.502799Z","title":"Cross-Modal Attention Consistency for Video-Audio Unsupervised Learning","venue":"cs.CV","work_id":"1d3e61c1-27d4-485a-ab05-11f5afc62aec","year":2021},"citing_paper":{"arxiv_id":"2412.00049","last_updated":"2024-11-24T03:26:34Z","snapshot_observed_at":"2026-08-13T08:29:44.393581Z","submitted_at":"2024-11-24T03:26:34Z","title":"A Survey of Recent Advances and Challenges in Deep Audio-Visual Correlation Learning","version":1},"reference_index":91,"source":"pdf_text","source_observed_at":"2026-08-12T14:04:00.566673Z"},"links":{"cited_paper":"/paper/2106.06939","citing_paper":"/paper/2412.00049"},"observation_digest":"sha256:57c6fc5d9f8efc76c4f353353c98bc1c87c84bab7dde4d65235beb233f3db21c","observation_id":"9f6bb235-fea6-4038-b03a-9446ab66c110","resolution":{"observed_at":"2026-08-12T14:04:03.507418Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2106.06939/citation-record","integrity":"/paper/2106.06939/integrity","json":"/paper/2106.06939/citation-record.json","paper":"/paper/2106.06939"},"outbound":[],"paper":{"arxiv_id":"2106.06939","last_updated":"2021-06-13T07:41:15Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-11T15:36:31.702820Z","submitted_at":"2021-06-13T07:41:15Z","title":"Cross-Modal Attention Consistency for Video-Audio Unsupervised Learning"},"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":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 1 inbound Pith citation observation for arXiv:2106.06939."}