{"as_of":"2026-08-16T08:39:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:3dde6fd5e661743dc218d7441d3de8372914c5d650bb4a9a315bd16a687a1212","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":2,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":2,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-16T06:30:59.297886+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T21:02:45.723124Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-06T15:48:26.139431Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2409.10058","last_updated":"2024-09-16T07:39:58Z","snapshot_observed_at":"2026-08-12T22:44:18.582093Z","submitted_at":"2024-09-16T07:39:58Z","title":"StyleTTS-ZS: Efficient High-Quality Zero-Shot Text-to-Speech Synthesis with Distilled Time-Varying Style Diffusion","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.10058","snapshot_observed_at":"2026-08-15T21:02:45.723124Z","title":"Styletts-zs: Efficient high- quality zero-shot text-to-speech synthesis with distilled time-varying style diffusion","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.11200","last_updated":"2025-05-16T12:57:23Z","snapshot_observed_at":"2026-08-15T20:53:37.329930Z","submitted_at":"2025-05-16T12:57:23Z","title":"Audio Turing Test: Benchmarking the Human-likeness of Large Language Model-based Text-to-Speech Systems in Chinese","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-15T21:02:45.723124Z"},"links":{"cited_paper":"/paper/2409.10058","citing_paper":"/paper/2505.11200"},"observation_digest":"sha256:d2f8187d409ebb5c80de6a8d6b1ec9c42197d1e74a544a5587d347f6621b3b20","observation_id":"25e06993-00be-4795-9ff1-7e7478a64e9e","resolution":{"observed_at":"2026-08-15T21:02:45.723124Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.10058","last_updated":"2024-09-16T07:39:58Z","snapshot_observed_at":"2026-08-12T22:44:18.582093Z","submitted_at":"2024-09-16T07:39:58Z","title":"StyleTTS-ZS: Efficient High-Quality Zero-Shot Text-to-Speech Synthesis with Distilled Time-Varying Style Diffusion","version":1},"cited_work":{"arxiv_id":"2409.10058","doi":null,"metadata_source":"pith","pith_arxiv_id":"2409.10058","snapshot_observed_at":"2026-08-06T15:48:26.139431Z","title":"StyleTTS-ZS: Efficient High-Quality Zero-Shot Text-to-Speech Synthesis with Distilled Time-Varying Style Diffusion","venue":"eess.AS","work_id":"d907e384-c31d-4af8-933c-19b1a0e037cf","year":2024},"citing_paper":{"arxiv_id":"2507.14988","last_updated":"2025-07-20T14:48:48Z","snapshot_observed_at":"2026-08-11T00:57:14.977496Z","submitted_at":"2025-07-20T14:48:48Z","title":"DMOSpeech 2: Reinforcement Learning for Duration Prediction in Metric-Optimized Speech Synthesis","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T15:48:21.255061Z"},"links":{"cited_paper":"/paper/2409.10058","citing_paper":"/paper/2507.14988"},"observation_digest":"sha256:6de91eed5e1d7dbfb7806e9b85eee7423295ad82f51cda30c70885dc6f7e3d69","observation_id":"658aac14-d570-47f6-b978-9161804f311e","resolution":{"observed_at":"2026-08-06T15:48:26.218116Z","resolver_source":"local_arxiv","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"}}],"links":{"evidence":"/evidence","html":"/paper/2409.10058/citation-record","integrity":"/paper/2409.10058/integrity","json":"/paper/2409.10058/citation-record.json","paper":"/paper/2409.10058"},"outbound":[],"paper":{"arxiv_id":"2409.10058","last_updated":"2024-09-16T07:39:58Z","latest_version":1,"primary_category":"eess.AS","snapshot_observed_at":"2026-08-12T22:44:18.582093Z","submitted_at":"2024-09-16T07:39:58Z","title":"StyleTTS-ZS: Efficient High-Quality Zero-Shot Text-to-Speech Synthesis with Distilled Time-Varying Style Diffusion"},"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 16 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2409.10058."}