{"as_of":"2026-08-09T12:25:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a5b2173bbe46c6f352f98ab969a429bcea084a0610b74ca8ef853b53a290a3b6","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":"2026-08-09T06:31:02.800959+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":"2026-08-07T15:04:51.000297Z","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":"2026-08-07T00:21:59.600878Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2401.08052","last_updated":"2025-07-31T10:50:49Z","snapshot_observed_at":"2026-08-09T02:11:53.896653Z","submitted_at":"2024-01-16T02:06:28Z","title":"Multi-Input Multi-Output Target-Speaker Voice Activity Detection For Unified, Flexible, and Robust Audio-Visual Speaker Diarization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.08052","snapshot_observed_at":"2026-08-07T15:04:51.000297Z","title":"Multi-input multi-output target-speaker voice activity detection for unified, flexible, and robust audio- visual speaker diarization,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.16387","last_updated":"2025-05-22T08:39:48Z","snapshot_observed_at":"2026-08-07T14:59:45.104814Z","submitted_at":"2025-05-22T08:39:48Z","title":"Multi-Channel Sequence-to-Sequence Neural Diarization: Experimental Results for The MISP 2025 Challenge","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T15:04:51.000297Z"},"links":{"cited_paper":"/paper/2401.08052","citing_paper":"/paper/2505.16387"},"observation_digest":"sha256:7567c55b1cf329d70522ad97932fc7c5ea9de4b108471d982f4a37f0b375bf33","observation_id":"8c45c1e7-7a83-4781-afae-c1fc57acfaf0","resolution":{"observed_at":"2026-08-07T15:04:51.000297Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.08052","last_updated":"2025-07-31T10:50:49Z","snapshot_observed_at":"2026-08-09T02:11:53.896653Z","submitted_at":"2024-01-16T02:06:28Z","title":"Multi-Input Multi-Output Target-Speaker Voice Activity Detection For Unified, Flexible, and Robust Audio-Visual Speaker Diarization","version":3},"cited_work":{"arxiv_id":"2401.08052","doi":null,"metadata_source":"pith","pith_arxiv_id":"2401.08052","snapshot_observed_at":"2026-08-07T00:21:59.600878Z","title":"Multi-Input Multi-Output Target-Speaker Voice Activity Detection For Unified, Flexible, and Robust Audio-Visual Speaker Diarization","venue":"eess.AS","work_id":"ecab30e6-7498-4cb6-a64a-6b8655278b5f","year":2024},"citing_paper":{"arxiv_id":"2506.14427","last_updated":"2025-06-28T05:50:08Z","snapshot_observed_at":"2026-08-08T08:23:57.394977Z","submitted_at":"2025-06-17T11:44:20Z","title":"M3SD: Multi-modal, Multi-scenario and Multi-language Speaker Diarization Dataset","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T00:21:54.869454Z"},"links":{"cited_paper":"/paper/2401.08052","citing_paper":"/paper/2506.14427"},"observation_digest":"sha256:7167b9a500eaf722359f6a6ddb7bbbfac72c4b670773d4cb0f07615d58601bb6","observation_id":"c140ea81-7ae9-40be-b600-f63c29793861","resolution":{"observed_at":"2026-08-07T00:21:59.726773Z","resolver_source":"local_arxiv","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"}}],"links":{"evidence":"/evidence","html":"/paper/2401.08052/citation-record","integrity":"/paper/2401.08052/integrity","json":"/paper/2401.08052/citation-record.json","paper":"/paper/2401.08052"},"outbound":[],"paper":{"arxiv_id":"2401.08052","last_updated":"2025-07-31T10:50:49Z","latest_version":3,"primary_category":"eess.AS","snapshot_observed_at":"2026-08-09T02:11:53.896653Z","submitted_at":"2024-01-16T02:06:28Z","title":"Multi-Input Multi-Output Target-Speaker Voice Activity Detection For Unified, Flexible, and Robust Audio-Visual Speaker Diarization"},"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 2 inbound Pith citation observations for arXiv:2401.08052."}