{"as_of":"2026-08-08T21:27:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:704b2f0075470b7306d6348916f89497145202357e951716704adc00cac06191","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":"2026-08-08T06:32:00.761636+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":"2026-08-07T00:29:38.989560Z","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":"2026-05-11T07:16:00.232541Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2211.12171","last_updated":"2022-11-22T10:58:38Z","snapshot_observed_at":"2026-07-06T14:21:38.060588Z","submitted_at":"2022-11-22T10:58:38Z","title":"PromptTTS: Controllable Text-to-Speech with Text Descriptions","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2211.12171","snapshot_observed_at":"2026-08-07T00:29:38.989560Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.13894","last_updated":"2025-06-16T18:16:04Z","snapshot_observed_at":"2026-08-07T00:24:13.202195Z","submitted_at":"2025-06-16T18:16:04Z","title":"EmoNews: A Spoken Dialogue System for Expressive News Conversations","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-07T00:29:38.989560Z"},"links":{"cited_paper":"/paper/2211.12171","citing_paper":"/paper/2506.13894"},"observation_digest":"sha256:a2587050fa8f97f783652e38821438354220355b503dc9a8a21ee2e90a87ad96","observation_id":"bcce6e5c-37ba-4793-86ef-c6943ecc5d8c","resolution":{"observed_at":"2026-08-07T00:29:38.989560Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2211.12171","last_updated":"2022-11-22T10:58:38Z","snapshot_observed_at":"2026-07-06T14:21:38.060588Z","submitted_at":"2022-11-22T10:58:38Z","title":"PromptTTS: Controllable Text-to-Speech with Text Descriptions","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2211.12171","snapshot_observed_at":"2026-08-06T20:01:35.458407Z","title":"Prompttts: Con- trollable text-to-speech with text descriptions,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.08012","last_updated":"2025-07-05T10:59:00Z","snapshot_observed_at":"2026-08-08T05:05:40.148191Z","submitted_at":"2025-07-05T10:59:00Z","title":"RepeaTTS: Towards Feature Discovery through Repeated Fine-Tuning","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T20:01:35.458407Z"},"links":{"cited_paper":"/paper/2211.12171","citing_paper":"/paper/2507.08012"},"observation_digest":"sha256:ca9efa534c8d30f80b8350d3566c64174bc00fd940ea11acc8ac7a9760d66312","observation_id":"8940ffb5-6e18-4948-ab54-0e82cd0d3441","resolution":{"observed_at":"2026-08-06T20:01:35.458407Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2211.12171","last_updated":"2022-11-22T10:58:38Z","snapshot_observed_at":"2026-07-06T14:21:38.060588Z","submitted_at":"2022-11-22T10:58:38Z","title":"PromptTTS: Controllable Text-to-Speech with Text Descriptions","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2211.12171","snapshot_observed_at":"2026-07-13T16:09:50.207908Z","title":"Prompttts: Con- trollable text-to-speech with text descriptions,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.28737","last_updated":"2026-06-20T22:01:30Z","snapshot_observed_at":"2026-08-07T03:32:35.423463Z","submitted_at":"2026-03-30T17:50:07Z","title":"ParaSpeechCLAP: A Dual-Encoder Speech-Text Model for Rich Stylistic Language-Audio Pretraining","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-07-13T16:09:50.207908Z"},"links":{"cited_paper":"/paper/2211.12171","citing_paper":"/paper/2603.28737"},"observation_digest":"sha256:b4e0a00c6fdeb5a844d2e614bafd6fb810eb0cd3ddab982d84291af63aa8385b","observation_id":"de3fa17f-ac2d-4128-b463-a383bb27fae9","resolution":{"observed_at":"2026-07-13T16:09:50.207908Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2211.12171","last_updated":"2022-11-22T10:58:38Z","snapshot_observed_at":"2026-07-06T14:21:38.060588Z","submitted_at":"2022-11-22T10:58:38Z","title":"PromptTTS: Controllable Text-to-Speech with Text Descriptions","version":1},"cited_work":{"arxiv_id":"2211.12171","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2211.12171","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"ae4824cf-6a0c-472e-a624-83aff04f8b3a","year":2022},"citing_paper":{"arxiv_id":"2604.08363","last_updated":"2026-04-09T15:27:22Z","snapshot_observed_at":"2026-07-06T22:57:26.678728Z","submitted_at":"2026-04-09T15:27:22Z","title":"CapTalk: Unified Voice Design for Single-Utterance and Dialogue Speech Generation","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-05-10T17:15:28.918204Z"},"links":{"cited_paper":"/paper/2211.12171","citing_paper":"/paper/2604.08363"},"observation_digest":"sha256:a1628207d81d4d89967e234517266f4a1ffa870284d1330b827c7a7394002ea6","observation_id":"fce47ef0-b991-4a77-9796-dc8a700ef704","resolution":{"observed_at":"2026-05-11T07:16:00.242490Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2211.12171/citation-record","integrity":"/paper/2211.12171/integrity","json":"/paper/2211.12171/citation-record.json","paper":"/paper/2211.12171"},"outbound":[],"paper":{"arxiv_id":"2211.12171","last_updated":"2022-11-22T10:58:38Z","latest_version":1,"primary_category":"eess.AS","snapshot_observed_at":"2026-07-06T14:21:38.060588Z","submitted_at":"2022-11-22T10:58:38Z","title":"PromptTTS: Controllable Text-to-Speech with Text Descriptions"},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2211.12171."}