{"as_of":"2026-08-08T22:37:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:8fa1fb128297c5dc4e9e17296aecb0238a31db5ebc7fc3273aee7eb386b66910","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":4,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":4,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-08T14:26:46.637418Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-07-03T13:28:18.784433Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2411.17698","last_updated":"2025-03-17T17:44:37Z","snapshot_observed_at":"2026-07-31T09:11:09.636803Z","submitted_at":"2024-11-26T18:59:58Z","title":"Video-Guided Foley Sound Generation with Multimodal Controls","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.17698","snapshot_observed_at":"2026-08-08T14:26:46.637418Z","title":"Video-guided foley sound generation with multimodal controls","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.06782","last_updated":"2025-02-12T10:07:07Z","snapshot_observed_at":"2026-08-08T14:18:27.556352Z","submitted_at":"2025-02-10T18:58:11Z","title":"Lumina-Video: Efficient and Flexible Video Generation with Multi-scale Next-DiT","version":2},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-08T14:26:46.637418Z"},"links":{"cited_paper":"/paper/2411.17698","citing_paper":"/paper/2502.06782"},"observation_digest":"sha256:aa5b9a0885e376651f5f49d6e1a2fe880cff03db5e8aec192659a90a68109def","observation_id":"ebef3684-b017-4923-be0b-8838c65c39b1","resolution":{"observed_at":"2026-08-08T14:26:46.637418Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.17698","last_updated":"2025-03-17T17:44:37Z","snapshot_observed_at":"2026-07-31T09:11:09.636803Z","submitted_at":"2024-11-26T18:59:58Z","title":"Video-Guided Foley Sound Generation with Multimodal Controls","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.17698","snapshot_observed_at":"2026-08-07T14:05:09.819840Z","title":"Video-guided foley sound generation with multimodal con- trols","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.20038","last_updated":"2025-05-26T14:24:19Z","snapshot_observed_at":"2026-08-07T13:58:26.646650Z","submitted_at":"2025-05-26T14:24:19Z","title":"Towards Video to Piano Music Generation with Chain-of-Perform Support Benchmarks","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T14:05:09.819840Z"},"links":{"cited_paper":"/paper/2411.17698","citing_paper":"/paper/2505.20038"},"observation_digest":"sha256:2573980e06c205973546914d00f8642406aac7381fc9aa01f93527251512e46b","observation_id":"5001ff69-54ec-4cfe-8d99-1f5e3c17a8b5","resolution":{"observed_at":"2026-08-07T14:05:09.819840Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.17698","last_updated":"2025-03-17T17:44:37Z","snapshot_observed_at":"2026-07-31T09:11:09.636803Z","submitted_at":"2024-11-26T18:59:58Z","title":"Video-Guided Foley Sound Generation with Multimodal Controls","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.17698","snapshot_observed_at":"2026-08-06T22:45:05.422297Z","title":"Video-guided foley sound generation with multimodal controls","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.20995","last_updated":"2026-06-30T12:17:01Z","snapshot_observed_at":"2026-08-07T10:47:31.323670Z","submitted_at":"2025-06-26T04:20:08Z","title":"Step-by-Step Video-to-Audio Synthesis via Negative Audio Guidance","version":4},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-06T22:45:05.422297Z"},"links":{"cited_paper":"/paper/2411.17698","citing_paper":"/paper/2506.20995"},"observation_digest":"sha256:8f3f0ee42b29d1a657db6d1da6d33d933b2a14705b6cacd80b86dae32c63e363","observation_id":"83671cc3-1f8c-46ab-adbb-f180111af7f3","resolution":{"observed_at":"2026-08-06T22:45:05.422297Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.17698","last_updated":"2025-03-17T17:44:37Z","snapshot_observed_at":"2026-07-31T09:11:09.636803Z","submitted_at":"2024-11-26T18:59:58Z","title":"Video-Guided Foley Sound Generation with Multimodal Controls","version":4},"cited_work":{"arxiv_id":"2411.17698","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2411.17698","snapshot_observed_at":"2026-07-03T13:28:18.784433Z","title":"Video-guided fo- ley sound generation with multimodal controls,","venue":null,"work_id":"1b76b314-ed36-4453-8d79-20866c1c534e","year":2024},"citing_paper":{"arxiv_id":"2606.12555","last_updated":"2026-07-02T19:10:03Z","snapshot_observed_at":"2026-07-12T14:16:32.755376Z","submitted_at":"2026-06-10T18:06:27Z","title":"AudioX-Turbo: A Unified Framework for Efficient Anything-to-Audio Generation","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-06-27T08:04:48.283908Z"},"links":{"cited_paper":"/paper/2411.17698","citing_paper":"/paper/2606.12555"},"observation_digest":"sha256:16b0dfa691d0f0c95876e5f109c12b9b632c059dc03167178a15775ea993b8c5","observation_id":"cecbaf3d-0d77-4f51-9c13-55545ca37267","resolution":{"observed_at":"2026-07-03T13:28:18.786232Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2411.17698/citation-record","integrity":"/paper/2411.17698/integrity","json":"/paper/2411.17698/citation-record.json","paper":"/paper/2411.17698"},"outbound":[],"paper":{"arxiv_id":"2411.17698","last_updated":"2025-03-17T17:44:37Z","latest_version":4,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-31T09:11:09.636803Z","submitted_at":"2024-11-26T18:59:58Z","title":"Video-Guided Foley Sound Generation with Multimodal Controls"},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2411.17698."}