{"as_of":"2026-08-06T14:05:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:43735cf3fb58d8b10bc2955b1911edf2d1043086e38668e7cd96ddc25d67ce84","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":"2026-08-06T06:34:29.942622+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":"2026-05-16T06:06:41.348728Z","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":"2026-05-16T06:06:41.477473Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2401.14321","last_updated":"2025-03-14T00:10:58Z","snapshot_observed_at":"2026-07-06T17:20:33.356092Z","submitted_at":"2024-01-25T17:19:01Z","title":"VALL-T: Decoder-Only Generative Transducer for Robust and Decoding-Controllable Text-to-Speech","version":5},"cited_work":{"arxiv_id":"2401.14321","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2401.14321","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"V ALL-T: decoder-only generative transducer for robust and decoding- controllable text-to-speech","venue":null,"work_id":"b655aed2-a337-4456-9a6c-5b69e0555397","year":2024},"citing_paper":{"arxiv_id":"2410.06885","last_updated":"2025-05-20T15:53:10Z","snapshot_observed_at":"2026-08-01T23:52:25.071174Z","submitted_at":"2024-10-09T13:46:34Z","title":"F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching","version":3},"reference_index":90,"source":"arxiv_source","source_observed_at":"2026-05-16T06:06:41.348728Z"},"links":{"cited_paper":"/paper/2401.14321","citing_paper":"/paper/2410.06885"},"observation_digest":"sha256:ea46274d522fbec2875093c04ecb76c58973fc5721e4e0a908b49e90efd77fd7","observation_id":"0e2b1200-720a-4f80-9466-db9ffa8ffb45","resolution":{"observed_at":"2026-05-16T06:06:41.479977Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2401.14321","last_updated":"2025-03-14T00:10:58Z","snapshot_observed_at":"2026-07-06T17:20:33.356092Z","submitted_at":"2024-01-25T17:19:01Z","title":"VALL-T: Decoder-Only Generative Transducer for Robust and Decoding-Controllable Text-to-Speech","version":5},"cited_work":{"arxiv_id":"2401.14321","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2401.14321","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"V ALL-T: decoder-only generative transducer for robust and decoding- controllable text-to-speech","venue":null,"work_id":"b655aed2-a337-4456-9a6c-5b69e0555397","year":2024},"citing_paper":{"arxiv_id":"2412.10117","last_updated":"2024-12-25T11:54:03Z","snapshot_observed_at":"2026-07-06T20:06:30.732685Z","submitted_at":"2024-12-13T12:59:39Z","title":"CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models","version":3},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-05-13T06:19:09.507440Z"},"links":{"cited_paper":"/paper/2401.14321","citing_paper":"/paper/2412.10117"},"observation_digest":"sha256:748fafff7f90a213d8d4f9be996e6fceac450c09018dfcb6f952850cb592e497","observation_id":"3498705f-a958-4917-b168-e003ba4c70ef","resolution":{"observed_at":"2026-05-13T06:19:09.541520Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2401.14321","last_updated":"2025-03-14T00:10:58Z","snapshot_observed_at":"2026-07-06T17:20:33.356092Z","submitted_at":"2024-01-25T17:19:01Z","title":"VALL-T: Decoder-Only Generative Transducer for Robust and Decoding-Controllable Text-to-Speech","version":5},"cited_work":{"arxiv_id":"2401.14321","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2401.14321","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"V ALL-T: decoder-only generative transducer for robust and decoding- controllable text-to-speech","venue":null,"work_id":"b655aed2-a337-4456-9a6c-5b69e0555397","year":2024},"citing_paper":{"arxiv_id":"2505.17589","last_updated":"2025-05-27T07:48:34Z","snapshot_observed_at":"2026-07-06T21:29:06.781083Z","submitted_at":"2025-05-23T07:55:21Z","title":"CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-16T05:27:25.425188Z"},"links":{"cited_paper":"/paper/2401.14321","citing_paper":"/paper/2505.17589"},"observation_digest":"sha256:13ac364bc7d2878061a494c25c88311f2578651169fc947762f9272065ffeb2c","observation_id":"f3c4b565-7901-46b2-9a28-bc5704648bbd","resolution":{"observed_at":"2026-05-16T05:27:25.479961Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2401.14321/citation-record","integrity":"/paper/2401.14321/integrity","json":"/paper/2401.14321/citation-record.json","paper":"/paper/2401.14321"},"outbound":[],"paper":{"arxiv_id":"2401.14321","last_updated":"2025-03-14T00:10:58Z","latest_version":5,"primary_category":"eess.AS","snapshot_observed_at":"2026-07-06T17:20:33.356092Z","submitted_at":"2024-01-25T17:19:01Z","title":"VALL-T: Decoder-Only Generative Transducer for Robust and Decoding-Controllable Text-to-Speech"},"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":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"thesis":"As of 6 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2401.14321."}