{"as_of":"2026-08-12T18:59:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:04973ec7f9dd70b11b5f8c87f7e37468bfad227c7df67450601d5eb92c4c8821","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":"2026-08-12T06:34:41.77262+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":"2026-08-11T20:29:54.356313Z","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":"2026-05-13T02:06:23.538743Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2305.04001","last_updated":"2023-05-23T06:59:30Z","snapshot_observed_at":"2026-08-12T01:15:58.956782Z","submitted_at":"2023-05-06T10:26:56Z","title":"AADiff: Audio-Aligned Video Synthesis with Text-to-Image Diffusion","version":2},"cited_work":{"arxiv_id":"2305.04001","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2305.04001","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2305.04001 , year=","venue":null,"work_id":"1f8f925b-cba2-4bef-a6c3-da1e31a29fca","year":null},"citing_paper":{"arxiv_id":"2404.02101","last_updated":"2025-03-13T18:35:06Z","snapshot_observed_at":"2026-08-12T01:27:32.593496Z","submitted_at":"2024-04-02T16:52:41Z","title":"CameraCtrl: Enabling Camera Control for Text-to-Video Generation","version":2},"reference_index":61,"source":"arxiv_source","source_observed_at":"2026-05-13T02:06:23.410241Z"},"links":{"cited_paper":"/paper/2305.04001","citing_paper":"/paper/2404.02101"},"observation_digest":"sha256:46bb241b5d0b6149ab1a1685a5b934c6326a331b50ecce8bd50d57e7211e882e","observation_id":"a5dd61d1-6528-4824-9437-0971e1749d39","resolution":{"observed_at":"2026-05-13T02:06:23.542147Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.04001","last_updated":"2023-05-23T06:59:30Z","snapshot_observed_at":"2026-08-12T01:15:58.956782Z","submitted_at":"2023-05-06T10:26:56Z","title":"AADiff: Audio-Aligned Video Synthesis with Text-to-Image Diffusion","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.04001","snapshot_observed_at":"2026-08-11T20:29:54.356313Z","title":"arXiv preprint arXiv:2305.04001 (2023)","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.05694","last_updated":"2024-12-07T16:43:02Z","snapshot_observed_at":"2026-08-12T01:16:32.318451Z","submitted_at":"2024-12-07T16:43:02Z","title":"Combining Genre Classification and Harmonic-Percussive Features with Diffusion Models for Music-Video Generation","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-11T20:29:54.356313Z"},"links":{"cited_paper":"/paper/2305.04001","citing_paper":"/paper/2412.05694"},"observation_digest":"sha256:13755f0367499ada13cb75aed34c75849b49b06c99d41905f5e05445015188ad","observation_id":"2fa31471-94e2-4c59-8004-4f6e7a7fa5b9","resolution":{"observed_at":"2026-08-11T20:29:54.356313Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.04001","last_updated":"2023-05-23T06:59:30Z","snapshot_observed_at":"2026-08-12T01:15:58.956782Z","submitted_at":"2023-05-06T10:26:56Z","title":"AADiff: Audio-Aligned Video Synthesis with Text-to-Image Diffusion","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.04001","snapshot_observed_at":"2026-08-11T11:38:08.356490Z","title":"Aadiff: Audio-aligned video synthesis with text-to- image diffusion","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.15191","last_updated":"2025-03-10T18:30:39Z","snapshot_observed_at":"2026-08-12T01:16:41.969157Z","submitted_at":"2024-12-19T18:57:21Z","title":"AV-Link: Temporally-Aligned Diffusion Features for Cross-Modal Audio-Video Generation","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-11T11:38:08.356490Z"},"links":{"cited_paper":"/paper/2305.04001","citing_paper":"/paper/2412.15191"},"observation_digest":"sha256:4e759bb438bd76ca902cf3ffe6a5087d8026942ba2bbb9651878b2fe5fb04c6c","observation_id":"08fb4f88-1400-45e6-9001-162a68cd3ee4","resolution":{"observed_at":"2026-08-11T11:38:08.356490Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.04001","last_updated":"2023-05-23T06:59:30Z","snapshot_observed_at":"2026-08-12T01:15:58.956782Z","submitted_at":"2023-05-06T10:26:56Z","title":"AADiff: Audio-Aligned Video Synthesis with Text-to-Image Diffusion","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.04001","snapshot_observed_at":"2026-08-11T11:36:18.059869Z","title":"Aadiff: Audio-aligned video synthesis with text-to- image diffusion","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.15214","last_updated":"2025-03-28T07:08:24Z","snapshot_observed_at":"2026-08-11T11:30:01.293314Z","submitted_at":"2024-12-19T18:59:56Z","title":"LeviTor: 3D Trajectory Oriented Image-to-Video Synthesis","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-11T11:36:18.059869Z"},"links":{"cited_paper":"/paper/2305.04001","citing_paper":"/paper/2412.15214"},"observation_digest":"sha256:0a3506d66883c3cce468e3a091e5bdd40d4f7a4deffa08edca3283542ea0f7dd","observation_id":"929fdb38-3a13-401a-8446-f59e14f70089","resolution":{"observed_at":"2026-08-11T11:36:18.059869Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2305.04001/citation-record","integrity":"/paper/2305.04001/integrity","json":"/paper/2305.04001/citation-record.json","paper":"/paper/2305.04001"},"outbound":[],"paper":{"arxiv_id":"2305.04001","last_updated":"2023-05-23T06:59:30Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-12T01:15:58.956782Z","submitted_at":"2023-05-06T10:26:56Z","title":"AADiff: Audio-Aligned Video Synthesis with Text-to-Image Diffusion"},"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":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"thesis":"As of 12 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2305.04001."}