{"as_of":"2026-08-09T15:43:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:2cb5c4029af0742c9edf0bb95f2980e2c69ad3709351d97b76f1179715ee2a05","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":"2026-08-04T18:59:47.452738Z","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":"2026-07-01T22:46:20.145372Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2310.14778","last_updated":"2025-04-13T08:28:06Z","snapshot_observed_at":"2026-08-01T21:27:02.095539Z","submitted_at":"2023-10-23T10:29:33Z","title":"Audio-Visual Speaker Tracking: Progress, Challenges, and Future Directions","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.14778","snapshot_observed_at":"2026-08-04T18:59:47.452738Z","title":"Audio-visual speaker tracking: Progress, challenges, and future directions,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.09526","last_updated":"2025-09-11T15:08:09Z","snapshot_observed_at":"2026-08-09T14:38:23.869513Z","submitted_at":"2025-09-11T15:08:09Z","title":"Region-Specific Audio Tagging for Spatial Sound","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-04T18:59:47.452738Z"},"links":{"cited_paper":"/paper/2310.14778","citing_paper":"/paper/2509.09526"},"observation_digest":"sha256:e3fea5d3dc2a8fd7d564f683c209119ab312880ec99d19f1152c3741109d2131","observation_id":"df0f26ab-47a0-4a07-a444-b77d99b1b78a","resolution":{"observed_at":"2026-08-04T18:59:47.452738Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.14778","last_updated":"2025-04-13T08:28:06Z","snapshot_observed_at":"2026-08-01T21:27:02.095539Z","submitted_at":"2023-10-23T10:29:33Z","title":"Audio-Visual Speaker Tracking: Progress, Challenges, and Future Directions","version":5},"cited_work":{"arxiv_id":"2310.14778","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2310.14778","snapshot_observed_at":"2026-07-01T22:46:20.145372Z","title":"arXiv preprint arXiv:2310.14778 , year=","venue":null,"work_id":"6fd36f21-549e-4761-8bb4-cc02d52ddcaa","year":null},"citing_paper":{"arxiv_id":"2606.02724","last_updated":"2026-06-01T18:00:08Z","snapshot_observed_at":"2026-08-02T20:01:29.972723Z","submitted_at":"2026-06-01T18:00:08Z","title":"AVTrack: Audio-Visual Tracking in Human-centric Complex Scenes","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-06-28T15:00:41.632699Z"},"links":{"cited_paper":"/paper/2310.14778","citing_paper":"/paper/2606.02724"},"observation_digest":"sha256:73474af6a53885074d7e5f4d51d619dcba71a8852b0fe51914fce1aeec92386e","observation_id":"c628d0db-83fa-4d2b-a41a-5e64556af70c","resolution":{"observed_at":"2026-07-01T22:46:20.147281Z","resolver_source":"arxiv_id","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/2310.14778/citation-record","integrity":"/paper/2310.14778/integrity","json":"/paper/2310.14778/citation-record.json","paper":"/paper/2310.14778"},"outbound":[],"paper":{"arxiv_id":"2310.14778","last_updated":"2025-04-13T08:28:06Z","latest_version":5,"primary_category":"cs.MM","snapshot_observed_at":"2026-08-01T21:27:02.095539Z","submitted_at":"2023-10-23T10:29:33Z","title":"Audio-Visual Speaker Tracking: Progress, Challenges, and Future Directions"},"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:2310.14778."}