{"as_of":"2026-08-07T23:27:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:55ca72a22959199fba9bfc00e5c2c60d46e96c16f63577d249936d26e227f9d4","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":3,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":3,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T19:39:52.764864Z","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":"2026-05-17T01:03:15.203891Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2404.16305","last_updated":"2024-04-26T02:23:24Z","snapshot_observed_at":"2026-07-06T18:05:16.683850Z","submitted_at":"2024-04-25T03:14:49Z","title":"Semantically consistent Video-to-Audio Generation using Multimodal Language Large Model","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.16305","snapshot_observed_at":"2026-08-06T19:39:52.764864Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.04959","last_updated":"2025-07-13T09:31:19Z","snapshot_observed_at":"2026-08-07T10:47:44.341783Z","submitted_at":"2025-07-07T13:01:50Z","title":"Hear-Your-Click: Interactive Object-Specific Video-to-Audio Generation","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T19:39:52.764864Z"},"links":{"cited_paper":"/paper/2404.16305","citing_paper":"/paper/2507.04959"},"observation_digest":"sha256:abd4186c76fb5debc6488dfd2b791dc4cc141949ee96ad833b5f4509355a86aa","observation_id":"7a208eb1-b5ab-4f60-b6cb-f59eda251448","resolution":{"observed_at":"2026-08-06T19:39:52.764864Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.16305","last_updated":"2024-04-26T02:23:24Z","snapshot_observed_at":"2026-07-06T18:05:16.683850Z","submitted_at":"2024-04-25T03:14:49Z","title":"Semantically consistent Video-to-Audio Generation using Multimodal Language Large Model","version":2},"cited_work":{"arxiv_id":"2404.16305","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2404.16305","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"com/research/video-generation-models-as-world-simulators","venue":null,"work_id":"e01a4ca3-169f-41c9-adf9-19a9dd64a994","year":2025},"citing_paper":{"arxiv_id":"2510.01284","last_updated":"2025-09-30T21:03:50Z","snapshot_observed_at":"2026-08-06T11:49:53.749464Z","submitted_at":"2025-09-30T21:03:50Z","title":"Ovi: Twin Backbone Cross-Modal Fusion for Audio-Video Generation","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-17T01:03:15.183360Z"},"links":{"cited_paper":"/paper/2404.16305","citing_paper":"/paper/2510.01284"},"observation_digest":"sha256:d0b8575eb8cff7ecf09e73d11feb4602cad3401038f4302d937c11952972dc1b","observation_id":"c340d833-540e-49a6-ac7c-09537bd9008c","resolution":{"observed_at":"2026-05-17T01:03:15.206803Z","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"}},{"citation":{"cited_paper":{"arxiv_id":"2404.16305","last_updated":"2024-04-26T02:23:24Z","snapshot_observed_at":"2026-07-06T18:05:16.683850Z","submitted_at":"2024-04-25T03:14:49Z","title":"Semantically consistent Video-to-Audio Generation using Multimodal Language Large Model","version":2},"cited_work":{"arxiv_id":"2404.16305","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2404.16305","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"com/research/video-generation-models-as-world-simulators","venue":null,"work_id":"e01a4ca3-169f-41c9-adf9-19a9dd64a994","year":2025},"citing_paper":{"arxiv_id":"2604.23909","last_updated":"2026-04-26T23:03:15Z","snapshot_observed_at":"2026-07-06T23:10:02.659384Z","submitted_at":"2026-04-26T23:03:15Z","title":"AMAVA: Adaptive Motion-Aware Video-to-Audio Framework for Visually-Impaired Assistance","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-08T06:24:21.611234Z"},"links":{"cited_paper":"/paper/2404.16305","citing_paper":"/paper/2604.23909"},"observation_digest":"sha256:5614a32536c2440a1b32a137d8ac1b2d5d1cb13ed80161c8f2c90c48e44c247d","observation_id":"f646db97-c6ea-43c5-877a-b25cd2f2f765","resolution":{"observed_at":"2026-05-11T21:11:20.091923Z","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/2404.16305/citation-record","integrity":"/paper/2404.16305/integrity","json":"/paper/2404.16305/citation-record.json","paper":"/paper/2404.16305"},"outbound":[],"paper":{"arxiv_id":"2404.16305","last_updated":"2024-04-26T02:23:24Z","latest_version":2,"primary_category":"cs.MM","snapshot_observed_at":"2026-07-06T18:05:16.683850Z","submitted_at":"2024-04-25T03:14:49Z","title":"Semantically consistent Video-to-Audio Generation using Multimodal Language Large 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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2404.16305."}