{"as_of":"2026-08-15T09:36:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:f62db1f742f84accb44bc8f8684cf49813691ecebac93c13aac03828475af0fe","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":"2026-08-15T06:32:42.880941+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":"2026-08-12T18:47:51.357279Z","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":"2026-05-22T13:44:52.866183Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2204.00768","last_updated":"2024-10-24T04:54:27Z","snapshot_observed_at":"2026-08-15T04:22:23.476279Z","submitted_at":"2022-04-02T05:28:48Z","title":"VQTTS: High-Fidelity Text-to-Speech Synthesis with Self-Supervised VQ Acoustic Feature","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.00768","snapshot_observed_at":"2026-08-12T18:47:51.357279Z","title":"Vqtts: High-fidelity text- to-speech synthesis with self-supervised vq acoustic feature","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.11258","last_updated":"2024-11-18T03:22:34Z","snapshot_observed_at":"2026-08-15T01:57:56.506162Z","submitted_at":"2024-11-18T03:22:34Z","title":"ESTVocoder: An Excitation-Spectral-Transformed Neural Vocoder Conditioned on Mel Spectrogram","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-12T18:47:51.357279Z"},"links":{"cited_paper":"/paper/2204.00768","citing_paper":"/paper/2411.11258"},"observation_digest":"sha256:4bb94dda42668986740d0227f3bab0f50aa81b310113147484e90abd332ccffa","observation_id":"3a511ba9-fbc4-4dca-870e-1e75faf706da","resolution":{"observed_at":"2026-08-12T18:47:51.357279Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2204.00768","last_updated":"2024-10-24T04:54:27Z","snapshot_observed_at":"2026-08-15T04:22:23.476279Z","submitted_at":"2022-04-02T05:28:48Z","title":"VQTTS: High-Fidelity Text-to-Speech Synthesis with Self-Supervised VQ Acoustic Feature","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.00768","snapshot_observed_at":"2026-08-11T14:59:01.566307Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.18619","last_updated":"2024-12-30T03:00:30Z","snapshot_observed_at":"2026-08-13T14:56:43.704817Z","submitted_at":"2024-12-16T05:02:25Z","title":"Next Token Prediction Towards Multimodal Intelligence: A Comprehensive Survey","version":2},"reference_index":103,"source":"pdf_text","source_observed_at":"2026-08-11T14:59:01.566307Z"},"links":{"cited_paper":"/paper/2204.00768","citing_paper":"/paper/2412.18619"},"observation_digest":"sha256:52022e92f1c74672d67af9de8df6d3cd4f3f36c027aeefe6c5fd8708b698d039","observation_id":"ff2989f7-042b-4f65-82e9-d8e8e599ae32","resolution":{"observed_at":"2026-08-11T14:59:01.566307Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2204.00768","last_updated":"2024-10-24T04:54:27Z","snapshot_observed_at":"2026-08-15T04:22:23.476279Z","submitted_at":"2022-04-02T05:28:48Z","title":"VQTTS: High-Fidelity Text-to-Speech Synthesis with Self-Supervised VQ Acoustic Feature","version":4},"cited_work":{"arxiv_id":"2204.00768","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2204.00768","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Vqtts: High-fidelity text-to- speech synthesis with self-supervised vq acoustic feature","venue":null,"work_id":"9f880dee-e0c2-481f-85fe-172f7d1768d4","year":2022},"citing_paper":{"arxiv_id":"2505.14202","last_updated":"2026-04-06T02:54:59Z","snapshot_observed_at":"2026-08-12T16:44:00.851327Z","submitted_at":"2025-05-20T11:01:36Z","title":"MSDformer: Multi-scale Discrete Transformer For Time Series Generation","version":3},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-05-22T13:44:08.891339Z"},"links":{"cited_paper":"/paper/2204.00768","citing_paper":"/paper/2505.14202"},"observation_digest":"sha256:1acab8b4a2d33c1c111d20264292ddb608146e41fa660e6cd5485e7adfd0d486","observation_id":"2e1c1b96-84b4-486b-b68e-c73f1f38b6a3","resolution":{"observed_at":"2026-05-22T13:44:52.868270Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2204.00768/citation-record","integrity":"/paper/2204.00768/integrity","json":"/paper/2204.00768/citation-record.json","paper":"/paper/2204.00768"},"outbound":[],"paper":{"arxiv_id":"2204.00768","last_updated":"2024-10-24T04:54:27Z","latest_version":4,"primary_category":"eess.AS","snapshot_observed_at":"2026-08-15T04:22:23.476279Z","submitted_at":"2022-04-02T05:28:48Z","title":"VQTTS: High-Fidelity Text-to-Speech Synthesis with Self-Supervised VQ Acoustic Feature"},"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":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"thesis":"As of 15 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2204.00768."}