{"as_of":"2026-08-07T22:34:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:6cd40cebc0183ddeb09525532489b95ce5b76ad7d4671ea849d607a9593fb357","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":"2026-08-07T06:34:17.273281+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":"2026-08-07T11:44:11.892307Z","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":"2026-08-06T13:24:31.297834Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2309.07929","last_updated":"2024-02-02T08:02:35Z","snapshot_observed_at":"2026-07-06T16:18:37.399390Z","submitted_at":"2023-09-13T05:43:35Z","title":"Prompting Segmentation with Sound Is Generalizable Audio-Visual Source Localizer","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.07929","snapshot_observed_at":"2026-08-07T11:44:11.892307Z","title":"Prompting segmentation with sound is generalizable audio-visual source localizer","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.01558","last_updated":"2025-06-02T11:36:25Z","snapshot_observed_at":"2026-08-07T11:36:04.057631Z","submitted_at":"2025-06-02T11:36:25Z","title":"SAM2-LOVE: Segment Anything Model 2 in Language-aided Audio-Visual Scenes","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T11:44:11.892307Z"},"links":{"cited_paper":"/paper/2309.07929","citing_paper":"/paper/2506.01558"},"observation_digest":"sha256:b5cdb0ba3bcf88e58f6d89497047ba02dbffe0cd88b1bd2d19942f6afcc1a681","observation_id":"f31b91df-7213-47e0-aca7-bd32ddac1e79","resolution":{"observed_at":"2026-08-07T11:44:11.892307Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.07929","last_updated":"2024-02-02T08:02:35Z","snapshot_observed_at":"2026-07-06T16:18:37.399390Z","submitted_at":"2023-09-13T05:43:35Z","title":"Prompting Segmentation with Sound Is Generalizable Audio-Visual Source Localizer","version":3},"cited_work":{"arxiv_id":"2309.07929","doi":null,"metadata_source":"pith","pith_arxiv_id":"2309.07929","snapshot_observed_at":"2026-08-06T13:24:31.297834Z","title":"Prompting Segmentation with Sound Is Generalizable Audio-Visual Source Localizer","venue":"cs.CV","work_id":"4edfe677-ba82-47dd-ba87-f3a17568e05c","year":2023},"citing_paper":{"arxiv_id":"2507.20740","last_updated":"2025-07-28T11:46:35Z","snapshot_observed_at":"2026-08-07T21:15:45.770589Z","submitted_at":"2025-07-28T11:46:35Z","title":"Implicit Counterfactual Learning for Audio-Visual Segmentation","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-06T13:24:29.839727Z"},"links":{"cited_paper":"/paper/2309.07929","citing_paper":"/paper/2507.20740"},"observation_digest":"sha256:c2ba511a2f9cf9d1cf1e329f6ce65609120fc08681d2494b8cbcab9fb46df82e","observation_id":"b00d8a91-7e04-44c4-be8e-414d4a62e7f1","resolution":{"observed_at":"2026-08-06T13:24:31.372411Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2309.07929/citation-record","integrity":"/paper/2309.07929/integrity","json":"/paper/2309.07929/citation-record.json","paper":"/paper/2309.07929"},"outbound":[],"paper":{"arxiv_id":"2309.07929","last_updated":"2024-02-02T08:02:35Z","latest_version":3,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T16:18:37.399390Z","submitted_at":"2023-09-13T05:43:35Z","title":"Prompting Segmentation with Sound Is Generalizable Audio-Visual Source Localizer"},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2309.07929."}