{"as_of":"2026-08-07T21:26:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:3747738c527505f85631980bc693009e2485982d452c065ea8b0abd346fc36f4","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":"2026-08-06T06:04:28.939172Z","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":"2026-08-06T06:04:30.278075Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2407.18505","last_updated":"2024-07-26T04:27:13Z","snapshot_observed_at":"2026-08-06T20:35:28.187816Z","submitted_at":"2024-07-26T04:27:13Z","title":"VoxSim: A perceptual voice similarity dataset","version":1},"cited_work":{"arxiv_id":"2407.18505","doi":null,"metadata_source":"pith","pith_arxiv_id":"2407.18505","snapshot_observed_at":"2026-08-06T06:04:30.278075Z","title":"VoxSim: A perceptual voice similarity dataset","venue":"eess.AS","work_id":"e4e7d89b-e381-420a-9e87-3e68217b629f","year":2024},"citing_paper":{"arxiv_id":"2508.00733","last_updated":"2025-08-07T04:31:04Z","snapshot_observed_at":"2026-08-06T20:34:36.422314Z","submitted_at":"2025-08-01T16:03:57Z","title":"AudioGen-Omni: A Unified Multimodal Diffusion Transformer for Video-Synchronized Audio, Speech, and Song Generation","version":4},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T06:04:28.939172Z"},"links":{"cited_paper":"/paper/2407.18505","citing_paper":"/paper/2508.00733"},"observation_digest":"sha256:4f861aa1b5754d09da0302e4405a2744de2bb94c7e353d214648c06a58bf6237","observation_id":"2b310c81-4c27-40cb-8c4f-8af5af29d927","resolution":{"observed_at":"2026-08-06T06:04:30.281776Z","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/2407.18505/citation-record","integrity":"/paper/2407.18505/integrity","json":"/paper/2407.18505/citation-record.json","paper":"/paper/2407.18505"},"outbound":[],"paper":{"arxiv_id":"2407.18505","last_updated":"2024-07-26T04:27:13Z","latest_version":1,"primary_category":"eess.AS","snapshot_observed_at":"2026-08-06T20:35:28.187816Z","submitted_at":"2024-07-26T04:27:13Z","title":"VoxSim: A perceptual voice similarity dataset"},"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:2407.18505."}