{"as_of":"2026-08-08T03:34:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:75553351464589a09eee01e41466f70e5ec4c1b5023e57aa2f33eb0146ee9021","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":"2026-08-07T06:34:17.273281+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":"2026-08-06T17:46:18.671928Z","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":"2026-05-11T16:36:06.125427Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2309.16429","last_updated":"2023-09-28T13:26:26Z","snapshot_observed_at":"2026-08-06T23:39:18.970710Z","submitted_at":"2023-09-28T13:26:26Z","title":"Diverse and Aligned Audio-to-Video Generation via Text-to-Video Model Adaptation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.16429","snapshot_observed_at":"2026-08-06T17:46:18.671928Z","title":"arXiv:2309.16429 [cs.LG]","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.10109","last_updated":"2025-07-14T09:50:53Z","snapshot_observed_at":"2026-08-08T02:46:03.641224Z","submitted_at":"2025-07-14T09:50:53Z","title":"DualDub: Video-to-Soundtrack Generation via Joint Speech and Background Audio Synthesis","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-06T17:46:18.671928Z"},"links":{"cited_paper":"/paper/2309.16429","citing_paper":"/paper/2507.10109"},"observation_digest":"sha256:36fcf61c06ba769868cc631a45db9ec5426f21e660363e01006dad961a142f25","observation_id":"7417fdab-75af-4ed8-918e-d769dee767a7","resolution":{"observed_at":"2026-08-06T17:46:18.671928Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.16429","last_updated":"2023-09-28T13:26:26Z","snapshot_observed_at":"2026-08-06T23:39:18.970710Z","submitted_at":"2023-09-28T13:26:26Z","title":"Diverse and Aligned Audio-to-Video Generation via Text-to-Video Model Adaptation","version":1},"cited_work":{"arxiv_id":"2309.16429","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2309.16429","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Cheng, H","venue":null,"work_id":"8e62251d-8fe4-494b-aa37-eb349317e3be","year":null},"citing_paper":{"arxiv_id":"2605.01809","last_updated":"2026-05-03T10:25:47Z","snapshot_observed_at":"2026-08-06T14:33:30.037257Z","submitted_at":"2026-05-03T10:25:47Z","title":"TMD-Bench: A Multi-Level Evaluation Paradigm for Music-Dance Co-Generation","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-09T16:11:16.551910Z"},"links":{"cited_paper":"/paper/2309.16429","citing_paper":"/paper/2605.01809"},"observation_digest":"sha256:f5c71c93a4ad2940a7c4c6675684ae14f98e57f69bed48469b082221849133a1","observation_id":"cf33e13c-4b42-426d-b960-2d197b1f75f0","resolution":{"observed_at":"2026-05-11T16:36:06.132105Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2309.16429/citation-record","integrity":"/paper/2309.16429/integrity","json":"/paper/2309.16429/citation-record.json","paper":"/paper/2309.16429"},"outbound":[],"paper":{"arxiv_id":"2309.16429","last_updated":"2023-09-28T13:26:26Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-06T23:39:18.970710Z","submitted_at":"2023-09-28T13:26:26Z","title":"Diverse and Aligned Audio-to-Video Generation via Text-to-Video Model Adaptation"},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2309.16429."}