{"as_of":"2026-08-20T15:59:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:dddf0de2d44fc0f66fe6d52250b56556127b87748f01f3615626c3d3657d022e","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":"2026-08-20T06:33:59.587034+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":"2026-08-15T20:13:46.821102Z","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":"2026-08-05T23:41:51.151962Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2410.01350","last_updated":"2025-01-10T05:35:32Z","snapshot_observed_at":"2026-08-19T18:51:48.567853Z","submitted_at":"2024-10-02T09:07:33Z","title":"Takin-VC: Expressive Zero-Shot Voice Conversion via Adaptive Hybrid Content Encoding and Enhanced Timbre Modeling","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.01350","snapshot_observed_at":"2026-08-15T20:13:46.821102Z","title":"Takin-vc: Zero-shot voice conversion via jointly hy- brid content and memory-augmented context-aware timbre mod- eling,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.13805","last_updated":"2025-05-20T01:34:29Z","snapshot_observed_at":"2026-08-18T15:58:14.553558Z","submitted_at":"2025-05-20T01:34:29Z","title":"ClapFM-EVC: High-Fidelity and Flexible Emotional Voice Conversion with Dual Control from Natural Language and Speech","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-15T20:13:46.821102Z"},"links":{"cited_paper":"/paper/2410.01350","citing_paper":"/paper/2505.13805"},"observation_digest":"sha256:ab036392b47958b604c7de628e51be6a05a4b6603f286aa327cb3245e402f915","observation_id":"895f996a-c5b1-4561-95c8-0133e93f0769","resolution":{"observed_at":"2026-08-15T20:13:46.821102Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.01350","last_updated":"2025-01-10T05:35:32Z","snapshot_observed_at":"2026-08-19T18:51:48.567853Z","submitted_at":"2024-10-02T09:07:33Z","title":"Takin-VC: Expressive Zero-Shot Voice Conversion via Adaptive Hybrid Content Encoding and Enhanced Timbre Modeling","version":2},"cited_work":{"arxiv_id":"2410.01350","doi":null,"metadata_source":"pith","pith_arxiv_id":"2410.01350","snapshot_observed_at":"2026-08-05T23:41:51.151962Z","title":"Takin-VC: Expressive Zero-Shot Voice Conversion via Adaptive Hybrid Content Encoding and Enhanced Timbre Modeling","venue":"cs.SD","work_id":"6d754432-7820-42a5-882f-17e69699940a","year":2024},"citing_paper":{"arxiv_id":"2508.04996","last_updated":"2025-08-08T01:59:26Z","snapshot_observed_at":"2026-08-10T13:44:35.896964Z","submitted_at":"2025-08-07T03:08:49Z","title":"REF-VC: Robust, Expressive and Fast Zero-Shot Voice Conversion with Diffusion Transformers","version":2},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-05T23:41:51.059823Z"},"links":{"cited_paper":"/paper/2410.01350","citing_paper":"/paper/2508.04996"},"observation_digest":"sha256:24efaeab1d59eb9e320264d6b6eee8924d0c322b046abf0e1c8e70d17e590d63","observation_id":"c2fda04f-302d-4776-940c-016614f39ffd","resolution":{"observed_at":"2026-08-05T23:41:51.156909Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2410.01350/citation-record","integrity":"/paper/2410.01350/integrity","json":"/paper/2410.01350/citation-record.json","paper":"/paper/2410.01350"},"outbound":[],"paper":{"arxiv_id":"2410.01350","last_updated":"2025-01-10T05:35:32Z","latest_version":2,"primary_category":"cs.SD","snapshot_observed_at":"2026-08-19T18:51:48.567853Z","submitted_at":"2024-10-02T09:07:33Z","title":"Takin-VC: Expressive Zero-Shot Voice Conversion via Adaptive Hybrid Content Encoding and Enhanced Timbre Modeling"},"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":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"thesis":"As of 20 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2410.01350."}