{"as_of":"2026-08-10T04:35:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ea481aeff4292f8b6c8efdd179866d20e985cc43017d021245fa0e1c0f2ea2ec","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":1,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":1,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T00:51:29.579149Z","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":"2026-08-06T00:51:33.198619Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2404.01339","last_updated":"2024-03-31T00:38:02Z","snapshot_observed_at":"2026-08-06T17:35:41.454428Z","submitted_at":"2024-03-31T00:38:02Z","title":"Humane Speech Synthesis through Zero-Shot Emotion and Disfluency Generation","version":1},"cited_work":{"arxiv_id":"2404.01339","doi":null,"metadata_source":"pith","pith_arxiv_id":"2404.01339","snapshot_observed_at":"2026-08-06T00:51:33.198619Z","title":"Humane Speech Synthesis through Zero-Shot Emotion and Disfluency Generation","venue":"cs.CL","work_id":"042e3538-2208-493e-a807-a1c56bc387b2","year":2024},"citing_paper":{"arxiv_id":"2508.04195","last_updated":"2025-08-06T08:25:26Z","snapshot_observed_at":"2026-08-06T17:34:54.346667Z","submitted_at":"2025-08-06T08:25:26Z","title":"NVSpeech: An Integrated and Scalable Pipeline for Human-Like Speech Modeling with Paralinguistic Vocalizations","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-06T00:51:29.579149Z"},"links":{"cited_paper":"/paper/2404.01339","citing_paper":"/paper/2508.04195"},"observation_digest":"sha256:f8c89b2752afc471987a2eedee357013badd0a10df3ed8e8b19c834a5d3c2307","observation_id":"bc2d1ba8-8745-4564-bf8f-7f57b24c0aa9","resolution":{"observed_at":"2026-08-06T00:51:33.246231Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2404.01339/citation-record","integrity":"/paper/2404.01339/integrity","json":"/paper/2404.01339/citation-record.json","paper":"/paper/2404.01339"},"outbound":[],"paper":{"arxiv_id":"2404.01339","last_updated":"2024-03-31T00:38:02Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-06T17:35:41.454428Z","submitted_at":"2024-03-31T00:38:02Z","title":"Humane Speech Synthesis through Zero-Shot Emotion and Disfluency Generation"},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 1 inbound Pith citation observation for arXiv:2404.01339."}