{"as_of":"2026-08-09T17:18:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:34c38f6fc92194d3000b32917c6f8c7f095cd181e513a0e9845937837290770d","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":"2026-08-09T06:31:02.800959+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":"2026-08-05T05:01:36.709931Z","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":"2026-08-04T21:25:28.334295Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2211.11225","last_updated":"2022-11-21T07:40:01Z","snapshot_observed_at":"2026-08-05T21:35:06.193836Z","submitted_at":"2022-11-21T07:40:01Z","title":"TimbreCLIP: Connecting Timbre to Text and Images","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2211.11225","snapshot_observed_at":"2026-08-05T05:01:36.709931Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.05786","last_updated":"2025-09-06T17:42:22Z","snapshot_observed_at":"2026-08-08T09:14:25.199933Z","submitted_at":"2025-09-06T17:42:22Z","title":"Effectively obtaining acoustic, visual and textual data from videos","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-05T05:01:36.709931Z"},"links":{"cited_paper":"/paper/2211.11225","citing_paper":"/paper/2509.05786"},"observation_digest":"sha256:108a0d8ed79d829b95ac8366f5f0da0128f9dc28186836216e0c25082b1ec77a","observation_id":"93caa914-ba11-49d9-8659-e4964ef9e460","resolution":{"observed_at":"2026-08-05T05:01:36.709931Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2211.11225","last_updated":"2022-11-21T07:40:01Z","snapshot_observed_at":"2026-08-05T21:35:06.193836Z","submitted_at":"2022-11-21T07:40:01Z","title":"TimbreCLIP: Connecting Timbre to Text and Images","version":1},"cited_work":{"arxiv_id":"2211.11225","doi":null,"metadata_source":"pith","pith_arxiv_id":"2211.11225","snapshot_observed_at":"2026-08-04T21:25:28.334295Z","title":"TimbreCLIP: Connecting Timbre to Text and Images","venue":"cs.SD","work_id":"78c19035-64b7-48a0-927a-64b20e37dcd8","year":2022},"citing_paper":{"arxiv_id":"2509.09717","last_updated":"2025-09-09T18:57:10Z","snapshot_observed_at":"2026-08-08T11:56:25.298917Z","submitted_at":"2025-09-09T18:57:10Z","title":"Testing chatbots on the creation of encoders for audio conditioned image generation","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-04T21:25:26.858805Z"},"links":{"cited_paper":"/paper/2211.11225","citing_paper":"/paper/2509.09717"},"observation_digest":"sha256:a7f826e191f24810ad8aab32d60fde837917091012ea43a1a6841803ffe1f5b0","observation_id":"e2250698-490c-43ca-9507-c52ddad3006b","resolution":{"observed_at":"2026-08-04T21:25:28.343551Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2211.11225/citation-record","integrity":"/paper/2211.11225/integrity","json":"/paper/2211.11225/citation-record.json","paper":"/paper/2211.11225"},"outbound":[],"paper":{"arxiv_id":"2211.11225","last_updated":"2022-11-21T07:40:01Z","latest_version":1,"primary_category":"cs.SD","snapshot_observed_at":"2026-08-05T21:35:06.193836Z","submitted_at":"2022-11-21T07:40:01Z","title":"TimbreCLIP: Connecting Timbre to Text and Images"},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2211.11225."}