{"as_of":"2026-08-10T13:26:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:7cb3a03c8a994cda44182cf5e450894caab28ade1fad0341881675f7264007d2","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":"2026-08-10T06:31:04.303077+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":"2026-08-06T20:01:29.086266Z","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":"2026-08-06T20:01:29.482055Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2203.15796","last_updated":"2022-08-15T20:39:28Z","snapshot_observed_at":"2026-08-10T12:18:19.154755Z","submitted_at":"2022-03-29T17:57:53Z","title":"Unsupervised Text-to-Speech Synthesis by Unsupervised Automatic Speech Recognition","version":2},"cited_work":{"arxiv_id":"2203.15796","doi":null,"metadata_source":"pith","pith_arxiv_id":"2203.15796","snapshot_observed_at":"2026-08-06T20:01:29.482055Z","title":"Unsupervised Text-to-Speech Synthesis by Unsupervised Automatic Speech Recognition","venue":"eess.AS","work_id":"746a8103-9e46-4082-a5e7-3597235417b6","year":2022},"citing_paper":{"arxiv_id":"2507.04036","last_updated":"2025-07-05T13:24:15Z","snapshot_observed_at":"2026-08-07T22:33:32.445282Z","submitted_at":"2025-07-05T13:24:15Z","title":"PresentAgent: Multimodal Agent for Presentation Video Generation","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-06T20:01:29.086266Z"},"links":{"cited_paper":"/paper/2203.15796","citing_paper":"/paper/2507.04036"},"observation_digest":"sha256:2d953b9475c757b9deaf8a6059bf85db6860d668b9a124e207aea803bc6c8207","observation_id":"376c5d22-5ea4-4e77-836e-2d90a3d977d4","resolution":{"observed_at":"2026-08-06T20:01:29.486456Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2203.15796/citation-record","integrity":"/paper/2203.15796/integrity","json":"/paper/2203.15796/citation-record.json","paper":"/paper/2203.15796"},"outbound":[],"paper":{"arxiv_id":"2203.15796","last_updated":"2022-08-15T20:39:28Z","latest_version":2,"primary_category":"eess.AS","snapshot_observed_at":"2026-08-10T12:18:19.154755Z","submitted_at":"2022-03-29T17:57:53Z","title":"Unsupervised Text-to-Speech Synthesis by Unsupervised Automatic Speech Recognition"},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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:2203.15796."}