{"as_of":"2026-08-07T12:36:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:212695c51aa407d515c8a4d172d72700c37d7c284e6c7e7934d4c3b26c6ae9a5","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":"2026-08-05T14:03:21.327224Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-04T21:25:27.812803Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2108.00443","last_updated":"2021-08-01T12:35:16Z","snapshot_observed_at":"2026-07-06T11:34:31.916599Z","submitted_at":"2021-08-01T12:35:16Z","title":"A Survey on Audio Synthesis and Audio-Visual Multimodal Processing","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2108.00443","snapshot_observed_at":"2026-08-05T14:03:21.327224Z","title":"A survey on audio synthesis and audio-visual multimodal processing","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.21761","last_updated":"2025-08-29T16:36:16Z","snapshot_observed_at":"2026-08-06T20:49:22.250981Z","submitted_at":"2025-08-29T16:36:16Z","title":"Learning from Silence and Noise for Visual Sound Source Localization","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-05T14:03:21.327224Z"},"links":{"cited_paper":"/paper/2108.00443","citing_paper":"/paper/2508.21761"},"observation_digest":"sha256:07863fc1a24fa66f7fbe3ebd80b390ef19789136d675e8f9d5a3e334e0ee8e85","observation_id":"3c7d422b-5187-4053-8ea8-18ee6b274945","resolution":{"observed_at":"2026-08-05T14:03:21.327224Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2108.00443","last_updated":"2021-08-01T12:35:16Z","snapshot_observed_at":"2026-07-06T11:34:31.916599Z","submitted_at":"2021-08-01T12:35:16Z","title":"A Survey on Audio Synthesis and Audio-Visual Multimodal Processing","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2108.00443","snapshot_observed_at":"2026-08-05T05:01:36.985927Z","title":"A Survey on Audio Synthesis and Audio-Visual Multimodal Processing","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.05786","last_updated":"2025-09-06T17:42:22Z","snapshot_observed_at":"2026-08-06T08:41:25.841683Z","submitted_at":"2025-09-06T17:42:22Z","title":"Effectively obtaining acoustic, visual and textual data from videos","version":1},"reference_index":100,"source":"pdf_text","source_observed_at":"2026-08-05T05:01:36.985927Z"},"links":{"cited_paper":"/paper/2108.00443","citing_paper":"/paper/2509.05786"},"observation_digest":"sha256:d9dd6652c9021260b89613f5f78bd02f19398ddfa9074b77a6cdfc42e68267a6","observation_id":"b956306a-aaff-4ab1-bd9c-34721c77bd74","resolution":{"observed_at":"2026-08-05T05:01:36.985927Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2108.00443","last_updated":"2021-08-01T12:35:16Z","snapshot_observed_at":"2026-07-06T11:34:31.916599Z","submitted_at":"2021-08-01T12:35:16Z","title":"A Survey on Audio Synthesis and Audio-Visual Multimodal Processing","version":1},"cited_work":{"arxiv_id":"2108.00443","doi":null,"metadata_source":"pith","pith_arxiv_id":"2108.00443","snapshot_observed_at":"2026-08-04T21:25:27.812803Z","title":"A Survey on Audio Synthesis and Audio-Visual Multimodal Processing","venue":"eess.AS","work_id":"84a5a7c1-e0d4-4430-922b-4f5e1bfc624c","year":2021},"citing_paper":{"arxiv_id":"2509.09717","last_updated":"2025-09-09T18:57:10Z","snapshot_observed_at":"2026-08-06T19:09:07.884728Z","submitted_at":"2025-09-09T18:57:10Z","title":"Testing chatbots on the creation of encoders for audio conditioned image generation","version":1},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-08-04T21:25:27.206894Z"},"links":{"cited_paper":"/paper/2108.00443","citing_paper":"/paper/2509.09717"},"observation_digest":"sha256:a3bb59200bb99e994322f8d8d74f013a0ef2441285d89e4561a01d44e3486e86","observation_id":"a0fc0fbc-155f-4321-8f35-c0266598a0db","resolution":{"observed_at":"2026-08-04T21:25:27.823348Z","resolver_source":"local_arxiv","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/2108.00443/citation-record","integrity":"/paper/2108.00443/integrity","json":"/paper/2108.00443/citation-record.json","paper":"/paper/2108.00443"},"outbound":[],"paper":{"arxiv_id":"2108.00443","last_updated":"2021-08-01T12:35:16Z","latest_version":1,"primary_category":"eess.AS","snapshot_observed_at":"2026-07-06T11:34:31.916599Z","submitted_at":"2021-08-01T12:35:16Z","title":"A Survey on Audio Synthesis and Audio-Visual Multimodal Processing"},"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:2108.00443."}