{"as_of":"2026-08-09T13:27:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d0b31927b0a6ae40be589f52308f1fd8f6445bc18c8503d6480db1808a21811f","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":4,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":4,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T23:04:01.879461Z","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":"2026-05-19T11:17:15.488882Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2301.13190","last_updated":"2023-01-30T18:53:32Z","snapshot_observed_at":"2026-08-05T20:42:38.247638Z","submitted_at":"2023-01-30T18:53:32Z","title":"Audio-Visual Segmentation with Semantics","version":1},"cited_work":{"arxiv_id":"2301.13190","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2301.13190","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Audio-visual segmentation with semantics","venue":null,"work_id":"f67ca607-e400-4396-8d2b-8ddfd46fabcd","year":2023},"citing_paper":{"arxiv_id":"2506.01015","last_updated":"2026-05-14T17:12:31Z","snapshot_observed_at":"2026-07-06T21:34:34.091508Z","submitted_at":"2025-06-01T13:57:42Z","title":"AuralSAM2: Enabling SAM2 Hear Through Pyramid Audio-Visual Feature Prompting","version":2},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-05-19T11:14:29.394752Z"},"links":{"cited_paper":"/paper/2301.13190","citing_paper":"/paper/2506.01015"},"observation_digest":"sha256:fe90fae7d1253acad3a00d670baad3e17b2c54f63717ccfa6c0f02aaa1f22fdb","observation_id":"f750eccb-292c-46f7-ad45-2ff3fc4e98bc","resolution":{"observed_at":"2026-05-19T11:17:15.490626Z","resolver_source":"arxiv_id","status":"verified_exact"},"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"}},{"citation":{"cited_paper":{"arxiv_id":"2301.13190","last_updated":"2023-01-30T18:53:32Z","snapshot_observed_at":"2026-08-05T20:42:38.247638Z","submitted_at":"2023-01-30T18:53:32Z","title":"Audio-Visual Segmentation with Semantics","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2301.13190","snapshot_observed_at":"2026-08-07T11:44:12.186738Z","title":"Audio- visual segmentation with semantics","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.01558","last_updated":"2025-06-02T11:36:25Z","snapshot_observed_at":"2026-08-09T06:07:41.748272Z","submitted_at":"2025-06-02T11:36:25Z","title":"SAM2-LOVE: Segment Anything Model 2 in Language-aided Audio-Visual Scenes","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-07T11:44:12.186738Z"},"links":{"cited_paper":"/paper/2301.13190","citing_paper":"/paper/2506.01558"},"observation_digest":"sha256:28702f3f627ba45bdaa7a3e19141dbe38bf7c2a21faca9e9d166c5dea12ef78d","observation_id":"3321ace5-26c3-49e0-8a45-7ab64cb4f444","resolution":{"observed_at":"2026-08-07T11:44:12.186738Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2301.13190","last_updated":"2023-01-30T18:53:32Z","snapshot_observed_at":"2026-08-05T20:42:38.247638Z","submitted_at":"2023-01-30T18:53:32Z","title":"Audio-Visual Segmentation with Semantics","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2301.13190","snapshot_observed_at":"2026-08-06T19:47:28.634151Z","title":"Audio- visual segmentation with semantics","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.04667","last_updated":"2025-07-08T14:46:46Z","snapshot_observed_at":"2026-08-08T17:03:18.891133Z","submitted_at":"2025-07-07T05:12:34Z","title":"What's Making That Sound Right Now? Video-centric Audio-Visual Localization","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-06T19:47:28.634151Z"},"links":{"cited_paper":"/paper/2301.13190","citing_paper":"/paper/2507.04667"},"observation_digest":"sha256:22abd1e590ba00f67d7fea70254e889ec8ec69558893fffdce220f914950ac36","observation_id":"4f421f1c-d8a9-4b1f-b122-40798004a8a2","resolution":{"observed_at":"2026-08-06T19:47:28.634151Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2301.13190","last_updated":"2023-01-30T18:53:32Z","snapshot_observed_at":"2026-08-05T20:42:38.247638Z","submitted_at":"2023-01-30T18:53:32Z","title":"Audio-Visual Segmentation with Semantics","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2301.13190","snapshot_observed_at":"2026-08-07T23:04:01.879461Z","title":"arXiv preprint arXiv:2301.13190 (2023)","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.05816","last_updated":"2026-08-06T09:47:34Z","snapshot_observed_at":"2026-08-09T13:10:48.345070Z","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":40,"source":"pdf_text","source_observed_at":"2026-08-07T23:04:01.879461Z"},"links":{"cited_paper":"/paper/2301.13190","citing_paper":"/paper/2608.05816"},"observation_digest":"sha256:fb0e29dbc3dbafca7e4f12796cee069487ae4a9468e469df1610e7c5d67a7713","observation_id":"027d935b-c4ad-4bfa-976f-f0b81b9b0548","resolution":{"observed_at":"2026-08-07T23:04:01.879461Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2301.13190/citation-record","integrity":"/paper/2301.13190/integrity","json":"/paper/2301.13190/citation-record.json","paper":"/paper/2301.13190"},"outbound":[],"paper":{"arxiv_id":"2301.13190","last_updated":"2023-01-30T18:53:32Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-05T20:42:38.247638Z","submitted_at":"2023-01-30T18:53:32Z","title":"Audio-Visual Segmentation with Semantics"},"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 4 inbound Pith citation observations for arXiv:2301.13190."}