{"as_of":"2026-08-22T08:47:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e0f6030e28a3d521c412ac21d47b7886f902c3a5b0d75d21c67ba0b3a5c26a5a","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":"2026-08-22T06:32:14.747728+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":"2026-08-05T05:01:37.171723Z","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":"2026-08-04T21:25:27.501540Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2109.13354","last_updated":"2021-09-27T21:25:31Z","snapshot_observed_at":"2026-08-20T02:26:54.242698Z","submitted_at":"2021-09-27T21:25:31Z","title":"Audio-to-Image Cross-Modal Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.13354","snapshot_observed_at":"2026-08-05T05:01:37.171723Z","title":"Audio-to-Image Cross-Modal Generation","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.05786","last_updated":"2025-09-06T17:42:22Z","snapshot_observed_at":"2026-08-15T05:55:38.630847Z","submitted_at":"2025-09-06T17:42:22Z","title":"Effectively obtaining acoustic, visual and textual data from videos","version":1},"reference_index":139,"source":"pdf_text","source_observed_at":"2026-08-05T05:01:37.171723Z"},"links":{"cited_paper":"/paper/2109.13354","citing_paper":"/paper/2509.05786"},"observation_digest":"sha256:19f0aad24d346a1d3a026379cd2a0d7d519b98cfadfc3e34b5bb1a9a2c7db00c","observation_id":"754d6a5e-8c41-42ec-8c79-0990eeba4d14","resolution":{"observed_at":"2026-08-05T05:01:37.171723Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.13354","last_updated":"2021-09-27T21:25:31Z","snapshot_observed_at":"2026-08-20T02:26:54.242698Z","submitted_at":"2021-09-27T21:25:31Z","title":"Audio-to-Image Cross-Modal Generation","version":1},"cited_work":{"arxiv_id":"2109.13354","doi":null,"metadata_source":"pith","pith_arxiv_id":"2109.13354","snapshot_observed_at":"2026-08-04T21:25:27.501540Z","title":"Audio-to-Image Cross-Modal Generation","venue":"cs.MM","work_id":"8bf3bbb2-bad1-48ba-8a5e-acc86e62c0af","year":2021},"citing_paper":{"arxiv_id":"2509.09717","last_updated":"2025-09-09T18:57:10Z","snapshot_observed_at":"2026-08-15T13:12:57.491333Z","submitted_at":"2025-09-09T18:57:10Z","title":"Testing chatbots on the creation of encoders for audio conditioned image generation","version":1},"reference_index":124,"source":"pdf_text","source_observed_at":"2026-08-04T21:25:27.449496Z"},"links":{"cited_paper":"/paper/2109.13354","citing_paper":"/paper/2509.09717"},"observation_digest":"sha256:82326a3894f0d526c937e76f42fe944e8102e4edd6f27251dd1f87efeca24349","observation_id":"488399ec-f8c8-459a-b03c-2ca468e0d04c","resolution":{"observed_at":"2026-08-04T21:25:27.509053Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2109.13354/citation-record","integrity":"/paper/2109.13354/integrity","json":"/paper/2109.13354/citation-record.json","paper":"/paper/2109.13354"},"outbound":[],"paper":{"arxiv_id":"2109.13354","last_updated":"2021-09-27T21:25:31Z","latest_version":1,"primary_category":"cs.MM","snapshot_observed_at":"2026-08-20T02:26:54.242698Z","submitted_at":"2021-09-27T21:25:31Z","title":"Audio-to-Image Cross-Modal Generation"},"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":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"thesis":"As of 22 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2109.13354."}