{"as_of":"2026-08-07T21:21:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:2960b4ba003a917cb15e74db3f59a9f4667f80b11f431a9c2de704e8de6cd092","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":"2026-08-07T06:34:17.273281+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":"2026-08-05T14:03:17.100791Z","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":"2026-08-05T14:03:23.702312Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2408.12102","last_updated":"2024-08-22T03:34:03Z","snapshot_observed_at":"2026-08-06T14:46:32.213787Z","submitted_at":"2024-08-22T03:34:03Z","title":"Integrating Audio, Visual, and Semantic Information for Enhanced Multimodal Speaker Diarization","version":1},"cited_work":{"arxiv_id":"2408.12102","doi":null,"metadata_source":"pith","pith_arxiv_id":"2408.12102","snapshot_observed_at":"2026-08-05T14:03:23.702312Z","title":"Integrating Audio, Visual, and Semantic Information for Enhanced Multimodal Speaker Diarization","venue":"cs.LG","work_id":"9e879b76-c8a9-4c23-9e47-2a5f64fb1e88","year":2024},"citing_paper":{"arxiv_id":"2508.21761","last_updated":"2025-08-29T16:36:16Z","snapshot_observed_at":"2026-08-06T20:49:22.250981Z","submitted_at":"2025-08-29T16:36:16Z","title":"Learning from Silence and Noise for Visual Sound Source Localization","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-05T14:03:17.100791Z"},"links":{"cited_paper":"/paper/2408.12102","citing_paper":"/paper/2508.21761"},"observation_digest":"sha256:f3e5091bcc4cb879b729ef8d48ee4302dbec8094b573b5e075cc67fb69e129a1","observation_id":"18f1a1bf-66a1-46a6-84d2-e8af7158bfb4","resolution":{"observed_at":"2026-08-05T14:03:23.762550Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2408.12102/citation-record","integrity":"/paper/2408.12102/integrity","json":"/paper/2408.12102/citation-record.json","paper":"/paper/2408.12102"},"outbound":[],"paper":{"arxiv_id":"2408.12102","last_updated":"2024-08-22T03:34:03Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-06T14:46:32.213787Z","submitted_at":"2024-08-22T03:34:03Z","title":"Integrating Audio, Visual, and Semantic Information for Enhanced Multimodal 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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 1 inbound Pith citation observation for arXiv:2408.12102."}