{"as_of":"2026-08-09T20:25:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:6cba7d6ee8db0b2162d06b1a62ec6270a6da499581145db0ba54b3b381768540","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":"2026-08-06T12:50:00.887904Z","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":"2026-07-09T15:16:18.182832Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2107.06592","last_updated":"2021-07-25T15:00:51Z","snapshot_observed_at":"2026-08-05T01:33:12.418999Z","submitted_at":"2021-07-14T10:30:34Z","title":"Is Someone Speaking? Exploring Long-term Temporal Features for Audio-visual Active Speaker Detection","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2107.06592","snapshot_observed_at":"2026-08-06T12:50:00.887904Z","title":"Is Someone Speaking? Exploring Long-term Temporal Features for Audio-visual Active Speaker Detection,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.21448","last_updated":"2025-08-04T16:20:43Z","snapshot_observed_at":"2026-08-06T12:50:00.349677Z","submitted_at":"2025-07-29T02:38:56Z","title":"Real-Time Audio-Visual Speech Enhancement Using Pre-trained Visual Representations","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T12:50:00.887904Z"},"links":{"cited_paper":"/paper/2107.06592","citing_paper":"/paper/2507.21448"},"observation_digest":"sha256:251cb0338257fe3bfd54cadc998a6388754351f3a76a9106ed1d3d9a94e66608","observation_id":"a4299ee8-9644-4ef2-b76c-783a57c86573","resolution":{"observed_at":"2026-08-06T12:50:00.887904Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2107.06592","last_updated":"2021-07-25T15:00:51Z","snapshot_observed_at":"2026-08-05T01:33:12.418999Z","submitted_at":"2021-07-14T10:30:34Z","title":"Is Someone Speaking? Exploring Long-term Temporal Features for Audio-visual Active Speaker Detection","version":2},"cited_work":{"arxiv_id":"2107.06592","doi":null,"metadata_source":"pith","pith_arxiv_id":"2107.06592","snapshot_observed_at":"2026-07-09T15:16:18.182832Z","title":"Is Someone Speaking? Exploring Long-term Temporal Features for Audio-visual Active Speaker Detection","venue":"eess.AS","work_id":"70d87ecf-ea91-43f5-a9a8-0fb9dc3cbd49","year":2021},"citing_paper":{"arxiv_id":"2607.07294","last_updated":"2026-07-08T11:34:00Z","snapshot_observed_at":"2026-08-08T06:24:18.456938Z","submitted_at":"2026-07-08T11:34:00Z","title":"Multimodal Voice Activity Projection for Turn-Taking in Social Robots with Voice-Activity-Related Pretrained Encoders","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-07-09T15:07:52.715880Z"},"links":{"cited_paper":"/paper/2107.06592","citing_paper":"/paper/2607.07294"},"observation_digest":"sha256:bc5892b33d16dcd1163fa81e1629a83735a64c736325fea171b966326ff4ac42","observation_id":"8823cca0-f77c-4553-b411-afb1410635fd","resolution":{"observed_at":"2026-07-09T15:16:18.184153Z","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/2107.06592/citation-record","integrity":"/paper/2107.06592/integrity","json":"/paper/2107.06592/citation-record.json","paper":"/paper/2107.06592"},"outbound":[],"paper":{"arxiv_id":"2107.06592","last_updated":"2021-07-25T15:00:51Z","latest_version":2,"primary_category":"eess.AS","snapshot_observed_at":"2026-08-05T01:33:12.418999Z","submitted_at":"2021-07-14T10:30:34Z","title":"Is Someone Speaking? Exploring Long-term Temporal Features for Audio-visual Active Speaker Detection"},"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:2107.06592."}