{"as_of":"2026-08-20T05:55:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:9554252faa17b5a87e5564bbf104fa963756f371357ff9dc61b63b2e33731412","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":"2026-08-19T06:32:44.657259+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":"2026-08-11T17:48:52.683627Z","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":"2026-08-11T17:48:53.042625Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2305.12903","last_updated":"2023-05-22T10:37:27Z","snapshot_observed_at":"2026-08-19T14:07:43.471187Z","submitted_at":"2023-05-22T10:37:27Z","title":"DiffAVA: Personalized Text-to-Audio Generation with Visual Alignment","version":1},"cited_work":{"arxiv_id":"2305.12903","doi":null,"metadata_source":"pith","pith_arxiv_id":"2305.12903","snapshot_observed_at":"2026-08-11T17:48:53.042625Z","title":"DiffAVA: Personalized Text-to-Audio Generation with Visual Alignment","venue":"cs.CV","work_id":"df9de825-6003-4e33-a6bc-12cb3fc9c890","year":2023},"citing_paper":{"arxiv_id":"2412.08577","last_updated":"2024-12-11T17:51:44Z","snapshot_observed_at":"2026-08-17T22:03:12.805680Z","submitted_at":"2024-12-11T17:51:44Z","title":"Mel-Refine: A Plug-and-Play Approach to Refine Mel-Spectrogram in Audio Generation","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-11T17:48:52.683627Z"},"links":{"cited_paper":"/paper/2305.12903","citing_paper":"/paper/2412.08577"},"observation_digest":"sha256:000e273060079eb52267bacd4c3859d614148ab4925f3f0b716aef214c697428","observation_id":"2cb2e1c0-2998-462c-9931-137bb4148e51","resolution":{"observed_at":"2026-08-11T17:48:53.049824Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2305.12903/citation-record","integrity":"/paper/2305.12903/integrity","json":"/paper/2305.12903/citation-record.json","paper":"/paper/2305.12903"},"outbound":[],"paper":{"arxiv_id":"2305.12903","last_updated":"2023-05-22T10:37:27Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-19T14:07:43.471187Z","submitted_at":"2023-05-22T10:37:27Z","title":"DiffAVA: Personalized Text-to-Audio Generation with Visual 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":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"thesis":"As of 20 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 1 inbound Pith citation observation for arXiv:2305.12903."}