{"as_of":"2026-08-08T08:49:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:f78745c951a4e157df834e4aac307dac43e226023984aee9d3ab417f8ece9e4b","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":"2026-08-07T13:21:57.116700Z","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":"2026-05-11T14:16:26.039153Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2406.04321","last_updated":"2025-05-07T15:59:51Z","snapshot_observed_at":"2026-08-06T11:22:41.689160Z","submitted_at":"2024-06-06T17:58:11Z","title":"VidMuse: A Simple Video-to-Music Generation Framework with Long-Short-Term Modeling","version":3},"cited_work":{"arxiv_id":"2406.04321","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2406.04321","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"VidMuse: A simple video-to-music generation framework with long-short-term modeling.arXiv preprint arXiv:2406.04321","venue":null,"work_id":"9df700a8-b245-4f1a-8137-940b50505154","year":null},"citing_paper":{"arxiv_id":"2410.13720","last_updated":"2025-02-26T16:05:55Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-10-17T16:22:46Z","title":"Movie Gen: A Cast of Media Foundation Models","version":2},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-05-11T14:16:18.521699Z"},"links":{"cited_paper":"/paper/2406.04321","citing_paper":"/paper/2410.13720"},"observation_digest":"sha256:5df669d522e1a110913401b52980655f58ee9cb7b0c864679e202383381c60f9","observation_id":"9f54eb01-8fd8-4a42-9a8b-610b770f4a19","resolution":{"observed_at":"2026-05-11T14:16:26.050224Z","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"}},{"citation":{"cited_paper":{"arxiv_id":"2406.04321","last_updated":"2025-05-07T15:59:51Z","snapshot_observed_at":"2026-08-06T11:22:41.689160Z","submitted_at":"2024-06-06T17:58:11Z","title":"VidMuse: A Simple Video-to-Music Generation Framework with Long-Short-Term Modeling","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.04321","snapshot_observed_at":"2026-08-07T13:21:57.116700Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.22053","last_updated":"2025-08-05T07:47:10Z","snapshot_observed_at":"2026-08-07T13:13:55.055771Z","submitted_at":"2025-05-28T07:23:53Z","title":"AudioGenie: A Training-Free Multi-Agent Framework for Diverse Multimodality-to-Multiaudio Generation","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-07T13:21:57.116700Z"},"links":{"cited_paper":"/paper/2406.04321","citing_paper":"/paper/2505.22053"},"observation_digest":"sha256:76012577c2a40a54dd1547fd02f6678b2af616d7d17bbf66ef96502f6f0120d3","observation_id":"3e247ced-3b1e-4915-8d1c-826888a83921","resolution":{"observed_at":"2026-08-07T13:21:57.116700Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.04321","last_updated":"2025-05-07T15:59:51Z","snapshot_observed_at":"2026-08-06T11:22:41.689160Z","submitted_at":"2024-06-06T17:58:11Z","title":"VidMuse: A Simple Video-to-Music Generation Framework with Long-Short-Term Modeling","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.04321","snapshot_observed_at":"2026-08-07T00:49:42.900461Z","title":"Vidmuse: A simple video-to- music generation framework with long-short-term mod- eling,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.12573","last_updated":"2025-06-27T22:16:16Z","snapshot_observed_at":"2026-08-07T00:43:22.099305Z","submitted_at":"2025-06-14T16:58:42Z","title":"Video-Guided Text-to-Music Generation Using Public Domain Movie Collections","version":3},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T00:49:42.900461Z"},"links":{"cited_paper":"/paper/2406.04321","citing_paper":"/paper/2506.12573"},"observation_digest":"sha256:84d6f92e80560167e8a9cdbb89d05a6ebd8a403a170d7868a3f4d5fd49bf4473","observation_id":"1450699d-fda3-4db1-be6d-12e8ad47a34d","resolution":{"observed_at":"2026-08-07T00:49:42.900461Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.04321","last_updated":"2025-05-07T15:59:51Z","snapshot_observed_at":"2026-08-06T11:22:41.689160Z","submitted_at":"2024-06-06T17:58:11Z","title":"VidMuse: A Simple Video-to-Music Generation Framework with Long-Short-Term Modeling","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.04321","snapshot_observed_at":"2026-08-06T13:31:13.546156Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.20627","last_updated":"2025-07-28T08:41:20Z","snapshot_observed_at":"2026-08-07T13:56:06.044916Z","submitted_at":"2025-07-28T08:41:20Z","title":"Controllable Video-to-Music Generation with Multiple Time-Varying Conditions","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-06T13:31:13.546156Z"},"links":{"cited_paper":"/paper/2406.04321","citing_paper":"/paper/2507.20627"},"observation_digest":"sha256:d16bcd7168a4b20d279427fe9e14bb3c40986c98dc4ace08f03b52c5a60d64a7","observation_id":"7ddbb19c-5d4a-4b51-af85-9cd9dbd4a62e","resolution":{"observed_at":"2026-08-06T13:31:13.546156Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2406.04321/citation-record","integrity":"/paper/2406.04321/integrity","json":"/paper/2406.04321/citation-record.json","paper":"/paper/2406.04321"},"outbound":[],"paper":{"arxiv_id":"2406.04321","last_updated":"2025-05-07T15:59:51Z","latest_version":3,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-06T11:22:41.689160Z","submitted_at":"2024-06-06T17:58:11Z","title":"VidMuse: A Simple Video-to-Music Generation Framework with Long-Short-Term Modeling"},"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:2406.04321."}