{"as_of":"2026-08-09T20:09:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:4c5b22bbf82c58cdfc34f47aa96fbb5ffdfa9e91d18c0d157146465f06abac14","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":"2026-08-09T06:31:02.800959+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":"2026-08-07T11:57:58.145318Z","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":"2026-05-11T15:41:35.189000Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2407.14006","last_updated":"2024-07-19T03:36:48Z","snapshot_observed_at":"2026-08-04T23:04:33.326889Z","submitted_at":"2024-07-19T03:36:48Z","title":"MSceneSpeech: A Multi-Scene Speech Dataset For Expressive Speech Synthesis","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.14006","snapshot_observed_at":"2026-08-07T11:57:58.145318Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.01014","last_updated":"2025-06-01T13:53:28Z","snapshot_observed_at":"2026-08-07T23:06:59.165463Z","submitted_at":"2025-06-01T13:53:28Z","title":"Rhythm Controllable and Efficient Zero-Shot Voice Conversion via Shortcut Flow Matching","version":1},"reference_index":61,"source":"arxiv_source","source_observed_at":"2026-08-07T11:57:58.145318Z"},"links":{"cited_paper":"/paper/2407.14006","citing_paper":"/paper/2506.01014"},"observation_digest":"sha256:8e350331746755fb470735c9883f97821d7c0df75c7b9b74ee492933aa4c6ee2","observation_id":"cb33f6ef-e28f-49ba-a466-cfa9380b5009","resolution":{"observed_at":"2026-08-07T11:57:58.145318Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.14006","last_updated":"2024-07-19T03:36:48Z","snapshot_observed_at":"2026-08-04T23:04:33.326889Z","submitted_at":"2024-07-19T03:36:48Z","title":"MSceneSpeech: A Multi-Scene Speech Dataset For Expressive Speech Synthesis","version":1},"cited_work":{"arxiv_id":"2407.14006","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2407.14006","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Mscenespeech: A multi-scene speech dataset for expressive speech synthesis.arXiv preprint arXiv:2407.14006","venue":null,"work_id":"a17daa92-ccaf-4eb6-9045-b4b718462ebf","year":null},"citing_paper":{"arxiv_id":"2605.00251","last_updated":"2026-04-30T21:32:40Z","snapshot_observed_at":"2026-08-06T03:10:18.640256Z","submitted_at":"2026-04-30T21:32:40Z","title":"Alethia: A Foundational Encoder for Voice Deepfakes","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-05-09T19:27:59.124425Z"},"links":{"cited_paper":"/paper/2407.14006","citing_paper":"/paper/2605.00251"},"observation_digest":"sha256:077e5474f3341faae415f7f5cdb22e32804474b5a2d347c911634f733f5a8952","observation_id":"de63e1e9-9ecb-4c86-80fa-fdce143c610e","resolution":{"observed_at":"2026-05-11T15:41:35.279155Z","resolver_source":"arxiv_id","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/2407.14006/citation-record","integrity":"/paper/2407.14006/integrity","json":"/paper/2407.14006/citation-record.json","paper":"/paper/2407.14006"},"outbound":[],"paper":{"arxiv_id":"2407.14006","last_updated":"2024-07-19T03:36:48Z","latest_version":1,"primary_category":"eess.AS","snapshot_observed_at":"2026-08-04T23:04:33.326889Z","submitted_at":"2024-07-19T03:36:48Z","title":"MSceneSpeech: A Multi-Scene Speech Dataset For Expressive Speech Synthesis"},"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 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2407.14006."}