{"as_of":"2026-08-08T09:13:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:b263cefa84441ffc5404d542374d4767f032a5a337ce0e1828abfdf10491250c","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":1,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":1,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-02T19:39:50.510822Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2404.12725","last_updated":"2024-05-05T08:00:17Z","snapshot_observed_at":"2026-07-06T18:02:36.759308Z","submitted_at":"2024-04-19T09:08:44Z","title":"Separate in the Speech Chain: Cross-Modal Conditional Audio-Visual Target Speech Extraction","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.12725","snapshot_observed_at":"2026-08-02T19:39:50.510822Z","title":"Separate in the speech chain: Cross-modal conditional audio-visual target speech extraction,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.01530","last_updated":"2026-06-29T12:25:41Z","snapshot_observed_at":"2026-08-08T04:36:38.509410Z","submitted_at":"2026-03-02T07:00:48Z","title":"CueNet: Robust Audio-Visual Speaker Extraction through Cross-Modal Cue Mining and Interaction","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-02T19:39:50.510822Z"},"links":{"cited_paper":"/paper/2404.12725","citing_paper":"/paper/2603.01530"},"observation_digest":"sha256:15bf3714103c80469eff49b5b7aaf5c85cdb3f062824b76679e9fa77ce9fc5e0","observation_id":"7691e0c9-511a-47ff-8a85-d36e2f90fdbc","resolution":{"observed_at":"2026-08-02T19:39:50.510822Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2404.12725/citation-record","integrity":"/paper/2404.12725/integrity","json":"/paper/2404.12725/citation-record.json","paper":"/paper/2404.12725"},"outbound":[],"paper":{"arxiv_id":"2404.12725","last_updated":"2024-05-05T08:00:17Z","latest_version":2,"primary_category":"cs.SD","snapshot_observed_at":"2026-07-06T18:02:36.759308Z","submitted_at":"2024-04-19T09:08:44Z","title":"Separate in the Speech Chain: Cross-Modal Conditional Audio-Visual Target Speech Extraction"},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 1 inbound Pith citation observation for arXiv:2404.12725."}