{"as_of":"2026-08-09T18:12:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:5d5be172f3381bccd1904ce21955569d4e9f10d842f0b253ec3b7d9a050c08d0","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":"2026-08-09T06:31:02.800959+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":"2026-05-17T22:41:43.411128Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":1,"source":"arxiv_reference","source_observed_at":"2026-08-05T02:28:24.338817Z","state":"measured"}],"external_citation_measurements":[{"count":2,"observed_at":"2026-08-05T02:28:24.338817Z","source":"arxiv_reference"}],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2211.09383","last_updated":"2023-03-14T02:42:07Z","snapshot_observed_at":"2026-07-06T14:19:39.156008Z","submitted_at":"2022-11-17T07:17:24Z","title":"Grad-StyleSpeech: Any-speaker Adaptive Text-to-Speech Synthesis with Diffusion Models","version":2},"cited_work":{"arxiv_id":"2211.09383","doi":"10.48550/arxiv.2211.09383","metadata_source":"arxiv_reference","pith_arxiv_id":"2211.09383","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Any-speaker adaptive text-to-speech synthesis with diffusion models","venue":"arXiv (Cornell University)","work_id":"c4ded83c-cf06-4fd1-82be-d0f76c6b4ec0","year":2022},"citing_paper":{"arxiv_id":"2301.02111","last_updated":"2023-01-05T15:37:15Z","snapshot_observed_at":"2026-08-07T10:11:17.796562Z","submitted_at":"2023-01-05T15:37:15Z","title":"Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-13T01:31:06.635613Z"},"links":{"cited_paper":"/paper/2211.09383","citing_paper":"/paper/2301.02111"},"observation_digest":"sha256:3b227ba48aff39907739cf3fa460846afa8258157d2c23f7126c4269238467e1","observation_id":"d4789d3f-ed65-4a47-a9ea-7b36800571cb","resolution":{"observed_at":"2026-05-13T01:31:07.090934Z","resolver_source":"arxiv_id","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"}},{"citation":{"cited_paper":{"arxiv_id":"2211.09383","last_updated":"2023-03-14T02:42:07Z","snapshot_observed_at":"2026-07-06T14:19:39.156008Z","submitted_at":"2022-11-17T07:17:24Z","title":"Grad-StyleSpeech: Any-speaker Adaptive Text-to-Speech Synthesis with Diffusion Models","version":2},"cited_work":{"arxiv_id":"2211.09383","doi":"10.48550/arxiv.2211.09383","metadata_source":"arxiv_reference","pith_arxiv_id":"2211.09383","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Any-speaker adaptive text-to-speech synthesis with diffusion models","venue":"arXiv (Cornell University)","work_id":"c4ded83c-cf06-4fd1-82be-d0f76c6b4ec0","year":2022},"citing_paper":{"arxiv_id":"2301.02111","last_updated":"2023-01-05T15:37:15Z","snapshot_observed_at":"2026-08-07T10:11:17.796562Z","submitted_at":"2023-01-05T15:37:15Z","title":"Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-13T01:31:06.635613Z"},"links":{"cited_paper":"/paper/2211.09383","citing_paper":"/paper/2301.02111"},"observation_digest":"sha256:c563c6269dc3b46ef302107557dac5bf40f324e6e61131123181391b6701dc7a","observation_id":"8854bd9f-f7e2-4f53-b779-cd40cc3f72a9","resolution":{"observed_at":"2026-05-13T01:31:07.069766Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"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"}},{"citation":{"cited_paper":{"arxiv_id":"2211.09383","last_updated":"2023-03-14T02:42:07Z","snapshot_observed_at":"2026-07-06T14:19:39.156008Z","submitted_at":"2022-11-17T07:17:24Z","title":"Grad-StyleSpeech: Any-speaker Adaptive Text-to-Speech Synthesis with Diffusion Models","version":2},"cited_work":{"arxiv_id":"2211.09383","doi":"10.48550/arxiv.2211.09383","metadata_source":"arxiv_reference","pith_arxiv_id":"2211.09383","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Any-speaker adaptive text-to-speech synthesis with diffusion models","venue":"arXiv (Cornell University)","work_id":"c4ded83c-cf06-4fd1-82be-d0f76c6b4ec0","year":2022},"citing_paper":{"arxiv_id":"2306.14289","last_updated":"2023-07-01T07:26:22Z","snapshot_observed_at":"2026-08-08T16:17:33.420400Z","submitted_at":"2023-06-25T16:37:25Z","title":"Faster Segment Anything: Towards Lightweight SAM for Mobile Applications","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-05-17T22:41:43.411128Z"},"links":{"cited_paper":"/paper/2211.09383","citing_paper":"/paper/2306.14289"},"observation_digest":"sha256:0545e577bd10ece1b61fcf91d2378a0acb5a32e367ef78e4b40c8a367f6f0558","observation_id":"9f0158a4-7282-4feb-b3db-870572029ac9","resolution":{"observed_at":"2026-05-17T22:41:43.503409Z","resolver_source":"arxiv_id","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/2211.09383/citation-record","integrity":"/paper/2211.09383/integrity","json":"/paper/2211.09383/citation-record.json","paper":"/paper/2211.09383"},"outbound":[],"paper":{"arxiv_id":"2211.09383","last_updated":"2023-03-14T02:42:07Z","latest_version":2,"primary_category":"eess.AS","snapshot_observed_at":"2026-07-06T14:19:39.156008Z","submitted_at":"2022-11-17T07:17:24Z","title":"Grad-StyleSpeech: Any-speaker Adaptive Text-to-Speech Synthesis with Diffusion Models"},"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 3 inbound Pith citation observations for arXiv:2211.09383."}