{"as_of":"2026-08-08T11:05:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:9cdb3cee6d9342cecc27b2d5e55692d16474dd3823781c38e0bdaf4da31a2a97","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":"2026-08-02T19:39:50.132135Z","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":"2412.08247","last_updated":"2025-03-31T13:31:19Z","snapshot_observed_at":"2026-07-06T20:05:10.188170Z","submitted_at":"2024-12-11T09:55:09Z","title":"MoMuSE: Momentum Multi-modal Target Speaker Extraction for Real-time Scenarios with Impaired Visual Cues","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.08247","snapshot_observed_at":"2026-08-02T19:39:50.132135Z","title":"Momuse: Momentum multi-modal target speaker extraction for real-time scenarios with impaired visual cues,","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":30,"source":"pdf_text","source_observed_at":"2026-08-02T19:39:50.132135Z"},"links":{"cited_paper":"/paper/2412.08247","citing_paper":"/paper/2603.01530"},"observation_digest":"sha256:7088a17ce3caf816a6545e6628b05fee4d3a04a2fd3755fae24cc5dce446dbe8","observation_id":"7e7e147e-96ba-4759-a544-6ae1f7d213e7","resolution":{"observed_at":"2026-08-02T19:39:50.132135Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2412.08247/citation-record","integrity":"/paper/2412.08247/integrity","json":"/paper/2412.08247/citation-record.json","paper":"/paper/2412.08247"},"outbound":[],"paper":{"arxiv_id":"2412.08247","last_updated":"2025-03-31T13:31:19Z","latest_version":2,"primary_category":"cs.SD","snapshot_observed_at":"2026-07-06T20:05:10.188170Z","submitted_at":"2024-12-11T09:55:09Z","title":"MoMuSE: Momentum Multi-modal Target Speaker Extraction for Real-time Scenarios with Impaired Visual Cues"},"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:2412.08247."}