{"as_of":"2026-08-09T20:34:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:6377e8373758baf7f13a6ccd99b72b109ef99f6f65d5327a5a918fbaa51ca588","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":"2026-08-09T06:31:02.800959+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":"2026-08-09T19:24:20.398584Z","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":"2026-08-07T23:04:01.974209Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2409.00486","last_updated":"2024-08-31T15:43:22Z","snapshot_observed_at":"2026-07-06T19:08:44.269514Z","submitted_at":"2024-08-31T15:43:22Z","title":"Multi-scale Multi-instance Visual Sound Localization and Segmentation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.00486","snapshot_observed_at":"2026-08-09T19:24:20.398584Z","title":"Multi-scale multi-instance visual sound localization and segmentation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.00358","last_updated":"2025-02-20T22:37:12Z","snapshot_observed_at":"2026-08-09T19:15:33.974314Z","submitted_at":"2025-02-01T07:40:29Z","title":"Do Audio-Visual Segmentation Models Truly Segment Sounding Objects?","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-09T19:24:20.398584Z"},"links":{"cited_paper":"/paper/2409.00486","citing_paper":"/paper/2502.00358"},"observation_digest":"sha256:024deacacc772e6f3ae6e2644a1b25ba6a404b7e56c01b40577e5ca45ae647ff","observation_id":"70a85fd3-07f4-43e8-8e23-f392a5eeadad","resolution":{"observed_at":"2026-08-09T19:24:20.398584Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.00486","last_updated":"2024-08-31T15:43:22Z","snapshot_observed_at":"2026-07-06T19:08:44.269514Z","submitted_at":"2024-08-31T15:43:22Z","title":"Multi-scale Multi-instance Visual Sound Localization and Segmentation","version":1},"cited_work":{"arxiv_id":"2409.00486","doi":null,"metadata_source":"pith","pith_arxiv_id":"2409.00486","snapshot_observed_at":"2026-08-07T23:04:01.974209Z","title":"Multi-scale Multi-instance Visual Sound Localization and Segmentation","venue":"cs.CV","work_id":"9aab51dd-5305-41f8-b3ff-0c3301c006a5","year":2024},"citing_paper":{"arxiv_id":"2608.05816","last_updated":"2026-08-06T09:47:34Z","snapshot_observed_at":"2026-08-09T20:11:50.278003Z","submitted_at":"2026-08-06T09:47:34Z","title":"Whence the Voice? Self-supervised Dual-source Audio-Visual Localisation via Selective Convergence","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T23:04:01.791902Z"},"links":{"cited_paper":"/paper/2409.00486","citing_paper":"/paper/2608.05816"},"observation_digest":"sha256:d1946df819bda66c237364556ad5ee9f6b438ca5ada5b34e1bca42cd5580e827","observation_id":"7d9570fc-408d-4b6a-b6aa-a5a106d818b8","resolution":{"observed_at":"2026-08-07T23:04:01.982686Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2409.00486/citation-record","integrity":"/paper/2409.00486/integrity","json":"/paper/2409.00486/citation-record.json","paper":"/paper/2409.00486"},"outbound":[],"paper":{"arxiv_id":"2409.00486","last_updated":"2024-08-31T15:43:22Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T19:08:44.269514Z","submitted_at":"2024-08-31T15:43:22Z","title":"Multi-scale Multi-instance Visual Sound Localization and Segmentation"},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2409.00486."}