{"as_of":"2026-08-19T21:10:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:1c9f75240f24de13d756679f82aac2c59fcd97d3e2ca66bcbbb5d1520d27ae4f","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":2,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":2,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-19T06:32:44.657259+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-05T23:58:33.194516Z","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":"2026-05-12T03:06:19.420840Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2409.07967","last_updated":"2025-05-09T12:14:15Z","snapshot_observed_at":"2026-08-18T20:09:51.524572Z","submitted_at":"2024-09-12T11:54:25Z","title":"Locality-aware Cross-modal Correspondence Learning for Dense Audio-Visual Events Localization","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.07967","snapshot_observed_at":"2026-08-05T23:58:33.194516Z","title":"In AAAI, 5075–5083","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2508.04566","last_updated":"2025-08-06T15:49:53Z","snapshot_observed_at":"2026-08-17T03:39:28.605998Z","submitted_at":"2025-08-06T15:49:53Z","title":"CLASP: Cross-modal Salient Anchor-based Semantic Propagation for Weakly-supervised Dense Audio-Visual Event Localization","version":1},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-05T23:58:33.194516Z"},"links":{"cited_paper":"/paper/2409.07967","citing_paper":"/paper/2508.04566"},"observation_digest":"sha256:0e4e12689f320fabe5ea5945835690d9a96b03cfec13a79846c4460eabbc3241","observation_id":"7a9d3f3f-4eda-48a6-b719-1ca4aa02ec36","resolution":{"observed_at":"2026-08-05T23:58:33.194516Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.07967","last_updated":"2025-05-09T12:14:15Z","snapshot_observed_at":"2026-08-18T20:09:51.524572Z","submitted_at":"2024-09-12T11:54:25Z","title":"Locality-aware Cross-modal Correspondence Learning for Dense Audio-Visual Events Localization","version":4},"cited_work":{"arxiv_id":"2409.07967","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2409.07967","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Locality-aware cross- modal correspondence learning for dense audio-visual events localization","venue":null,"work_id":"325fa6c2-ebcd-4a70-afb6-ae151675a7e3","year":2024},"citing_paper":{"arxiv_id":"2605.08723","last_updated":"2026-05-09T06:13:27Z","snapshot_observed_at":"2026-08-13T08:44:32.434014Z","submitted_at":"2026-05-09T06:13:27Z","title":"EAR: Enhancing Uni-Modal Representations for Weakly Supervised Audio-Visual Video Parsing","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-05-12T03:03:13.496634Z"},"links":{"cited_paper":"/paper/2409.07967","citing_paper":"/paper/2605.08723"},"observation_digest":"sha256:bca89461f7eb2a1e2f5bbf0369422ee53fac9a545872196481fb7c68bdbf2fef","observation_id":"43eab3bd-c4e1-43ea-abe8-7c7c777d8553","resolution":{"observed_at":"2026-05-12T03:06:19.422788Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2409.07967/citation-record","integrity":"/paper/2409.07967/integrity","json":"/paper/2409.07967/citation-record.json","paper":"/paper/2409.07967"},"outbound":[],"paper":{"arxiv_id":"2409.07967","last_updated":"2025-05-09T12:14:15Z","latest_version":4,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-18T20:09:51.524572Z","submitted_at":"2024-09-12T11:54:25Z","title":"Locality-aware Cross-modal Correspondence Learning for Dense Audio-Visual Events Localization"},"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":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"thesis":"As of 19 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2409.07967."}