{"as_of":"2026-08-07T22:29:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:6fd5b49bdbd4d32464be8bcfd049b3ff52e0037aa3e1e10f18b7e1266ed52a7e","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":3,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":3,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T23:21:55.224747Z","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":"2026-05-11T08:30:57.049427Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2307.10550","last_updated":"2023-07-20T03:28:06Z","snapshot_observed_at":"2026-08-06T07:47:26.343695Z","submitted_at":"2023-07-20T03:28:06Z","title":"SC VALL-E: Style-Controllable Zero-Shot Text to Speech Synthesizer","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.10550","snapshot_observed_at":"2026-08-06T23:21:55.224747Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.21619","last_updated":"2025-09-03T10:46:35Z","snapshot_observed_at":"2026-08-07T04:02:25.950869Z","submitted_at":"2025-06-23T08:33:40Z","title":"IndexTTS2: A Breakthrough in Emotionally Expressive and Duration-Controlled Auto-Regressive Zero-Shot Text-to-Speech","version":2},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-06T23:21:55.224747Z"},"links":{"cited_paper":"/paper/2307.10550","citing_paper":"/paper/2506.21619"},"observation_digest":"sha256:601a2444a1d6ef6a4f65629ecb9582e725c03a494231c4db80de7a78be41fe8b","observation_id":"a2e58924-eafc-479b-b71f-e7919cd052b9","resolution":{"observed_at":"2026-08-06T23:21:55.224747Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.10550","last_updated":"2023-07-20T03:28:06Z","snapshot_observed_at":"2026-08-06T07:47:26.343695Z","submitted_at":"2023-07-20T03:28:06Z","title":"SC VALL-E: Style-Controllable Zero-Shot Text to Speech Synthesizer","version":1},"cited_work":{"arxiv_id":"2307.10550","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2307.10550","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Sc vall-e: Style-controllable zero- shot text to speech synthesizer","venue":null,"work_id":"cee130ab-6fb7-4d75-a8d1-b45aff0fc316","year":2023},"citing_paper":{"arxiv_id":"2604.11283","last_updated":"2026-06-01T08:50:38Z","snapshot_observed_at":"2026-08-02T05:26:21.584719Z","submitted_at":"2026-04-13T10:42:31Z","title":"Multimodal Large Language Model-Enabled Video Translation: A Role-Oriented Survey","version":1},"reference_index":97,"source":"pdf_text","source_observed_at":"2026-05-10T16:36:33.264166Z"},"links":{"cited_paper":"/paper/2307.10550","citing_paper":"/paper/2604.11283"},"observation_digest":"sha256:3b937f6034b1ed4ed0019af31b2e830c5f69c38187a9ba9fc34e69acaac00ce6","observation_id":"bf04d5ca-b047-4895-ad47-1389903a95c5","resolution":{"observed_at":"2026-05-11T08:30:57.052426Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.10550","last_updated":"2023-07-20T03:28:06Z","snapshot_observed_at":"2026-08-06T07:47:26.343695Z","submitted_at":"2023-07-20T03:28:06Z","title":"SC VALL-E: Style-Controllable Zero-Shot Text to Speech Synthesizer","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.10550","snapshot_observed_at":"2026-07-12T22:04:31.302192Z","title":"Sc vall-e: Style-controllable zero- shot text to speech synthesizer,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2604.11283","last_updated":"2026-06-01T08:50:38Z","snapshot_observed_at":"2026-08-02T05:26:21.584719Z","submitted_at":"2026-04-13T10:42:31Z","title":"Multimodal Large Language Model-Enabled Video Translation: A Role-Oriented Survey","version":2},"reference_index":95,"source":"pdf_text","source_observed_at":"2026-07-12T22:04:31.302192Z"},"links":{"cited_paper":"/paper/2307.10550","citing_paper":"/paper/2604.11283"},"observation_digest":"sha256:023d98ca5afe000e4eb8ff87c60ad121e0006e79d8b21a397a6fab7ec769a208","observation_id":"de70324d-a926-4f93-ab8b-cc9bd948aa7b","resolution":{"observed_at":"2026-07-12T22:04:31.302192Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2307.10550/citation-record","integrity":"/paper/2307.10550/integrity","json":"/paper/2307.10550/citation-record.json","paper":"/paper/2307.10550"},"outbound":[],"paper":{"arxiv_id":"2307.10550","last_updated":"2023-07-20T03:28:06Z","latest_version":1,"primary_category":"cs.SD","snapshot_observed_at":"2026-08-06T07:47:26.343695Z","submitted_at":"2023-07-20T03:28:06Z","title":"SC VALL-E: Style-Controllable Zero-Shot Text to Speech Synthesizer"},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2307.10550."}