{"as_of":"2026-08-07T07:34:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:fd1d6acd4f98db746f760456505cc479af1ded7440b54833e9424257596343cc","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":"2026-08-05T14:03:19.216337Z","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":"2026-07-01T23:06:21.321184Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2502.00358","last_updated":"2025-02-20T22:37:12Z","snapshot_observed_at":"2026-07-06T20:29:26.524162Z","submitted_at":"2025-02-01T07:40:29Z","title":"Do Audio-Visual Segmentation Models Truly Segment Sounding Objects?","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.00358","snapshot_observed_at":"2026-08-05T14:03:19.216337Z","title":"Do audio-visual segmentation models truly segment sounding objects? arXiv preprint arXiv:2502.00358, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2508.21761","last_updated":"2025-08-29T16:36:16Z","snapshot_observed_at":"2026-08-06T20:49:22.250981Z","submitted_at":"2025-08-29T16:36:16Z","title":"Learning from Silence and Noise for Visual Sound Source Localization","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-05T14:03:19.216337Z"},"links":{"cited_paper":"/paper/2502.00358","citing_paper":"/paper/2508.21761"},"observation_digest":"sha256:89a5f4be0159cb32d486a82351427b43cc2ddb9d315c9bdc0c008f470ae28e6c","observation_id":"5ac2cb49-56c7-419a-97c4-702c5577b400","resolution":{"observed_at":"2026-08-05T14:03:19.216337Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.00358","last_updated":"2025-02-20T22:37:12Z","snapshot_observed_at":"2026-07-06T20:29:26.524162Z","submitted_at":"2025-02-01T07:40:29Z","title":"Do Audio-Visual Segmentation Models Truly Segment Sounding Objects?","version":2},"cited_work":{"arxiv_id":"2502.00358","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.00358","snapshot_observed_at":"2026-07-01T23:06:21.321184Z","title":"arXiv preprint arXiv:2502.00358 , year=","venue":null,"work_id":"352abb85-4dcc-4824-bbd4-9a00add0b52e","year":null},"citing_paper":{"arxiv_id":"2606.07643","last_updated":"2026-06-01T19:12:09Z","snapshot_observed_at":"2026-08-04T07:32:54.888878Z","submitted_at":"2026-06-01T19:12:09Z","title":"AVI-Bench: Toward Human-like Audio-Visual Intelligence of Omni-MLLMs","version":1},"reference_index":79,"source":"arxiv_source","source_observed_at":"2026-06-28T14:36:53.295540Z"},"links":{"cited_paper":"/paper/2502.00358","citing_paper":"/paper/2606.07643"},"observation_digest":"sha256:763063d3938003e88003929dcd77df4fc8506ed596a9e3a963d5b56e2141e314","observation_id":"a7d7f17a-5f35-478f-9cd9-388ff19e134c","resolution":{"observed_at":"2026-07-01T23:06:21.323631Z","resolver_source":"arxiv_id","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/2502.00358/citation-record","integrity":"/paper/2502.00358/integrity","json":"/paper/2502.00358/citation-record.json","paper":"/paper/2502.00358"},"outbound":[],"paper":{"arxiv_id":"2502.00358","last_updated":"2025-02-20T22:37:12Z","latest_version":2,"primary_category":"cs.SD","snapshot_observed_at":"2026-07-06T20:29:26.524162Z","submitted_at":"2025-02-01T07:40:29Z","title":"Do Audio-Visual Segmentation Models Truly Segment Sounding Objects?"},"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:2502.00358."}