{"as_of":"2026-08-17T06:07:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:9eeba406c653a1916c256d88be329579beb74eaf3b922b0b00c0f40e50177ece","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":"2026-08-16T06:30:59.297886+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":"2026-08-15T19:25:16.156489Z","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":"2026-05-11T08:30:57.138779Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2406.19135","last_updated":"2024-06-27T12:39:55Z","snapshot_observed_at":"2026-08-16T17:30:00.258731Z","submitted_at":"2024-06-27T12:39:55Z","title":"DEX-TTS: Diffusion-based EXpressive Text-to-Speech with Style Modeling on Time Variability","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.19135","snapshot_observed_at":"2026-08-15T19:25:16.156489Z","title":"DEX-TTS: Diffusion-based EXpressive Text-to-Speech with style modeling on time variability,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.16741","last_updated":"2025-06-20T04:19:29Z","snapshot_observed_at":"2026-08-15T19:17:23.654198Z","submitted_at":"2025-06-20T04:19:29Z","title":"RapFlow-TTS: Rapid and High-Fidelity Text-to-Speech with Improved Consistency Flow Matching","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T19:25:16.156489Z"},"links":{"cited_paper":"/paper/2406.19135","citing_paper":"/paper/2506.16741"},"observation_digest":"sha256:33ff26ab897cfca24bca9157e8b03f43a3717bf7ddec952a5023830a0dc68d13","observation_id":"722e685c-fa66-4cb8-ad44-b8e8ee5cb6ef","resolution":{"observed_at":"2026-08-15T19:25:16.156489Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.19135","last_updated":"2024-06-27T12:39:55Z","snapshot_observed_at":"2026-08-16T17:30:00.258731Z","submitted_at":"2024-06-27T12:39:55Z","title":"DEX-TTS: Diffusion-based EXpressive Text-to-Speech with Style Modeling on Time Variability","version":1},"cited_work":{"arxiv_id":"2406.19135","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2406.19135","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Dex-tts: Diffusion-based expressive text-to-speech with style modeling on time variability","venue":null,"work_id":"c8c4df71-8467-47fb-8442-1ef874a7d8cd","year":2024},"citing_paper":{"arxiv_id":"2604.11283","last_updated":"2026-06-01T08:50:38Z","snapshot_observed_at":"2026-08-02T05:26:21.584719Z","submitted_at":"2026-04-13T10:42:31Z","title":"Multimodal Large Language Model-Enabled Video Translation: A Role-Oriented Survey","version":1},"reference_index":106,"source":"pdf_text","source_observed_at":"2026-05-10T16:36:33.264166Z"},"links":{"cited_paper":"/paper/2406.19135","citing_paper":"/paper/2604.11283"},"observation_digest":"sha256:ad1535635be95e0955d19e96702f0f99b55f15ea67bda4ce946173c89a43febb","observation_id":"3908a9ca-06ea-4cef-b380-c03b9cd63dae","resolution":{"observed_at":"2026-05-11T08:30:57.140754Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.19135","last_updated":"2024-06-27T12:39:55Z","snapshot_observed_at":"2026-08-16T17:30:00.258731Z","submitted_at":"2024-06-27T12:39:55Z","title":"DEX-TTS: Diffusion-based EXpressive Text-to-Speech with Style Modeling on Time Variability","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.19135","snapshot_observed_at":"2026-07-12T22:04:31.302192Z","title":"Dex-tts: Diffusion-based expressive text-to-speech with style modeling on time variability,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2604.11283","last_updated":"2026-06-01T08:50:38Z","snapshot_observed_at":"2026-08-02T05:26:21.584719Z","submitted_at":"2026-04-13T10:42:31Z","title":"Multimodal Large Language Model-Enabled Video Translation: A Role-Oriented Survey","version":2},"reference_index":104,"source":"pdf_text","source_observed_at":"2026-07-12T22:04:31.302192Z"},"links":{"cited_paper":"/paper/2406.19135","citing_paper":"/paper/2604.11283"},"observation_digest":"sha256:f743f602525500cc730dc66c256c59c2e8bfd8feca5c1354bffb91084bd4dbb4","observation_id":"930fa64c-b0f4-47cf-82f2-3cd3b617dfa0","resolution":{"observed_at":"2026-07-12T22:04:31.302192Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2406.19135/citation-record","integrity":"/paper/2406.19135/integrity","json":"/paper/2406.19135/citation-record.json","paper":"/paper/2406.19135"},"outbound":[],"paper":{"arxiv_id":"2406.19135","last_updated":"2024-06-27T12:39:55Z","latest_version":1,"primary_category":"eess.AS","snapshot_observed_at":"2026-08-16T17:30:00.258731Z","submitted_at":"2024-06-27T12:39:55Z","title":"DEX-TTS: Diffusion-based EXpressive Text-to-Speech with Style Modeling on Time Variability"},"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":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 17 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2406.19135."}