{"as_of":"2026-08-07T21:22:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:3b82d3c469dbfaddff5fe8b0e39bbf1f47d78a8a8fa713c01b84b998cc8dfbbc","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":"2026-08-05T14:03:21.674724Z","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":"2026-08-05T14:03:22.989858Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2412.06209","last_updated":"2024-12-09T05:04:50Z","snapshot_observed_at":"2026-08-03T03:28:55.901215Z","submitted_at":"2024-12-09T05:04:50Z","title":"Sound2Vision: Generating Diverse Visuals from Audio through Cross-Modal Latent Alignment","version":1},"cited_work":{"arxiv_id":"2412.06209","doi":null,"metadata_source":"pith","pith_arxiv_id":"2412.06209","snapshot_observed_at":"2026-08-05T14:03:22.989858Z","title":"Sound2Vision: Generating Diverse Visuals from Audio through Cross-Modal Latent Alignment","venue":"cs.CV","work_id":"5274d8eb-932a-4e9c-b11b-45b44d751fde","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":63,"source":"pdf_text","source_observed_at":"2026-08-05T14:03:21.674724Z"},"links":{"cited_paper":"/paper/2412.06209","citing_paper":"/paper/2508.21761"},"observation_digest":"sha256:6e3d665ada4ce9e32761b5ce9c13a5180e4ce859d541a8d76a36d3207a9676d1","observation_id":"fd6bf942-0d75-4daa-8780-f3e02d52b7b9","resolution":{"observed_at":"2026-08-05T14:03:23.027866Z","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/2412.06209/citation-record","integrity":"/paper/2412.06209/integrity","json":"/paper/2412.06209/citation-record.json","paper":"/paper/2412.06209"},"outbound":[],"paper":{"arxiv_id":"2412.06209","last_updated":"2024-12-09T05:04:50Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-03T03:28:55.901215Z","submitted_at":"2024-12-09T05:04:50Z","title":"Sound2Vision: Generating Diverse Visuals from Audio through Cross-Modal Latent Alignment"},"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:2412.06209."}