{"as_of":"2026-08-08T13:47:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:455b883112ffd1e01a8727c0bc1a848b1c11d6d60b0beb2ffafa28caf8023c60","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":4,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":4,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T14:58:58.358652Z","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":"2026-05-11T09:51:00.731265Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2412.04724","last_updated":"2024-12-10T05:52:28Z","snapshot_observed_at":"2026-08-07T11:14:08.982821Z","submitted_at":"2024-12-06T02:31:23Z","title":"StableVC: Style Controllable Zero-Shot Voice Conversion with Conditional Flow Matching","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.04724","snapshot_observed_at":"2026-08-07T14:58:58.358652Z","title":"Preprint, arXiv:2412.04724","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.16691","last_updated":"2025-05-23T05:07:17Z","snapshot_observed_at":"2026-08-07T15:22:39.973665Z","submitted_at":"2025-05-22T13:57:02Z","title":"EZ-VC: Easy Zero-shot Any-to-Any Voice Conversion","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T14:58:58.358652Z"},"links":{"cited_paper":"/paper/2412.04724","citing_paper":"/paper/2505.16691"},"observation_digest":"sha256:01ccf2d57197dd8b738b39ed647aed761d6fe8bf490d62ab116bf7876b0ba9d3","observation_id":"493a615c-a7b9-4057-bea5-f2569222ea15","resolution":{"observed_at":"2026-08-07T14:58:58.358652Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.04724","last_updated":"2024-12-10T05:52:28Z","snapshot_observed_at":"2026-08-07T11:14:08.982821Z","submitted_at":"2024-12-06T02:31:23Z","title":"StableVC: Style Controllable Zero-Shot Voice Conversion with Conditional Flow Matching","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.04724","snapshot_observed_at":"2026-08-07T11:28:39.448947Z","title":"Sta- blevc: Style controllable zero-shot voice conversion with condi- tional flow matching,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.02414","last_updated":"2025-06-03T04:00:53Z","snapshot_observed_at":"2026-08-07T21:53:15.843632Z","submitted_at":"2025-06-03T04:00:53Z","title":"StarVC: A Unified Auto-Regressive Framework for Joint Text and Speech Generation in Voice Conversion","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T11:28:39.448947Z"},"links":{"cited_paper":"/paper/2412.04724","citing_paper":"/paper/2506.02414"},"observation_digest":"sha256:17f3d34e7847496f7a9b5e7d266b82c3a0ae2929c72174ce61a5c19686443662","observation_id":"3b16057f-5c85-4021-8d28-792b3fb0e1d0","resolution":{"observed_at":"2026-08-07T11:28:39.448947Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.04724","last_updated":"2024-12-10T05:52:28Z","snapshot_observed_at":"2026-08-07T11:14:08.982821Z","submitted_at":"2024-12-06T02:31:23Z","title":"StableVC: Style Controllable Zero-Shot Voice Conversion with Conditional Flow Matching","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.04724","snapshot_observed_at":"2026-08-05T23:41:51.092586Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.04996","last_updated":"2025-08-08T01:59:26Z","snapshot_observed_at":"2026-08-05T23:41:48.793102Z","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":32,"source":"arxiv_source","source_observed_at":"2026-08-05T23:41:51.092586Z"},"links":{"cited_paper":"/paper/2412.04724","citing_paper":"/paper/2508.04996"},"observation_digest":"sha256:69345348185c3b30f8c29d67d6094a6b38544f67ba88dc9cb81dc38cbb7ecfc7","observation_id":"c2682900-ab98-4dc0-b954-d0f4287430d1","resolution":{"observed_at":"2026-08-05T23:41:51.092586Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.04724","last_updated":"2024-12-10T05:52:28Z","snapshot_observed_at":"2026-08-07T11:14:08.982821Z","submitted_at":"2024-12-06T02:31:23Z","title":"StableVC: Style Controllable Zero-Shot Voice Conversion with Conditional Flow Matching","version":2},"cited_work":{"arxiv_id":"2412.04724","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2412.04724","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2412.04724 (2024)","venue":null,"work_id":"2fbb43d5-af47-4513-9f4c-3b6bf5105101","year":2024},"citing_paper":{"arxiv_id":"2604.12292","last_updated":"2026-04-14T05:03:57Z","snapshot_observed_at":"2026-08-06T05:09:28.270784Z","submitted_at":"2026-04-14T05:03:57Z","title":"CoSyncDiT: Cognitive Synchronous Diffusion Transformer for Movie Dubbing","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-05-10T15:46:58.010112Z"},"links":{"cited_paper":"/paper/2412.04724","citing_paper":"/paper/2604.12292"},"observation_digest":"sha256:854797dc29f93327ba78cfadd4d273625da62149c4d3d0afd1e0476907f8cedd","observation_id":"baadc65e-1c9e-4c55-a478-bbbffe36b1de","resolution":{"observed_at":"2026-05-11T09:51:00.733701Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2412.04724/citation-record","integrity":"/paper/2412.04724/integrity","json":"/paper/2412.04724/citation-record.json","paper":"/paper/2412.04724"},"outbound":[],"paper":{"arxiv_id":"2412.04724","last_updated":"2024-12-10T05:52:28Z","latest_version":2,"primary_category":"eess.AS","snapshot_observed_at":"2026-08-07T11:14:08.982821Z","submitted_at":"2024-12-06T02:31:23Z","title":"StableVC: Style Controllable Zero-Shot Voice Conversion with Conditional Flow Matching"},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2412.04724."}