{"as_of":"2026-08-18T08:20:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:6c940711688e71105575dae6bd3a974589835a281de0732dbf1d5e5439955420","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":"2026-08-18T06:34:40.430872+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":"2026-08-15T18:47:36.900503Z","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":"2026-05-11T14:16:24.061825Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2311.00968","last_updated":"2024-03-04T07:54:31Z","snapshot_observed_at":"2026-08-17T08:07:39.014645Z","submitted_at":"2023-11-02T03:33:00Z","title":"Video2Music: Suitable Music Generation from Videos using an Affective Multimodal Transformer model","version":2},"cited_work":{"arxiv_id":"2311.00968","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2311.00968","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Ideogram v2, 2024.https://ideogram.ai/","venue":null,"work_id":"df660e85-88ef-4513-abe1-f041374cf106","year":2024},"citing_paper":{"arxiv_id":"2410.13720","last_updated":"2025-02-26T16:05:55Z","snapshot_observed_at":"2026-08-17T10:09:03.767186Z","submitted_at":"2024-10-17T16:22:46Z","title":"Movie Gen: A Cast of Media Foundation Models","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-05-11T14:16:18.521699Z"},"links":{"cited_paper":"/paper/2311.00968","citing_paper":"/paper/2410.13720"},"observation_digest":"sha256:796cdf4cdf481ec8e68a53d3adf5c69179e989e728454ef84e71449b4b4ff28e","observation_id":"e940fd72-b93e-406a-867d-451dbb5e3c57","resolution":{"observed_at":"2026-05-11T14:16:24.096063Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2311.00968","last_updated":"2024-03-04T07:54:31Z","snapshot_observed_at":"2026-08-17T08:07:39.014645Z","submitted_at":"2023-11-02T03:33:00Z","title":"Video2Music: Suitable Music Generation from Videos using an Affective Multimodal Transformer model","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.00968","snapshot_observed_at":"2026-08-15T18:47:36.900503Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.18881","last_updated":"2025-06-23T17:52:16Z","snapshot_observed_at":"2026-08-17T09:39:27.667198Z","submitted_at":"2025-06-23T17:52:16Z","title":"Let Your Video Listen to Your Music!","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-15T18:47:36.900503Z"},"links":{"cited_paper":"/paper/2311.00968","citing_paper":"/paper/2506.18881"},"observation_digest":"sha256:780bb4ac336ed0d25a861a74f0697ac664ed1bc900932074ba20750f80872996","observation_id":"f552493c-5635-4ad2-97af-1a1d58a0e6a1","resolution":{"observed_at":"2026-08-15T18:47:36.900503Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2311.00968/citation-record","integrity":"/paper/2311.00968/integrity","json":"/paper/2311.00968/citation-record.json","paper":"/paper/2311.00968"},"outbound":[],"paper":{"arxiv_id":"2311.00968","last_updated":"2024-03-04T07:54:31Z","latest_version":2,"primary_category":"cs.SD","snapshot_observed_at":"2026-08-17T08:07:39.014645Z","submitted_at":"2023-11-02T03:33:00Z","title":"Video2Music: Suitable Music Generation from Videos using an Affective Multimodal Transformer model"},"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":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2311.00968."}