{"as_of":"2026-08-07T02:28:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:f149905f243ec68854d57b83fee2efa1377cd9201fe877d62eed1c2367b2d0c2","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":"2026-08-06T06:34:29.942622+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":"2026-08-06T23:21:52.191734Z","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":"2026-05-20T19:28:55.035862Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2409.12139","last_updated":"2024-09-24T02:00:54Z","snapshot_observed_at":"2026-08-02T15:34:06.836535Z","submitted_at":"2024-09-18T17:03:12Z","title":"Takin: A Cohort of Superior Quality Zero-shot Speech Generation Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.12139","snapshot_observed_at":"2026-08-06T23:21:52.191734Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.21619","last_updated":"2025-09-03T10:46:35Z","snapshot_observed_at":"2026-08-06T23:14:05.470807Z","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":6,"source":"arxiv_source","source_observed_at":"2026-08-06T23:21:52.191734Z"},"links":{"cited_paper":"/paper/2409.12139","citing_paper":"/paper/2506.21619"},"observation_digest":"sha256:2f8535c7986e37cf2e311d8be92d94ff47d1fab3175e610ee3ae459965f3f030","observation_id":"7c44ba08-afc8-4dbf-94ea-b407c5446dd0","resolution":{"observed_at":"2026-08-06T23:21:52.191734Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.12139","last_updated":"2024-09-24T02:00:54Z","snapshot_observed_at":"2026-08-02T15:34:06.836535Z","submitted_at":"2024-09-18T17:03:12Z","title":"Takin: A Cohort of Superior Quality Zero-shot Speech Generation Models","version":3},"cited_work":{"arxiv_id":"2409.12139","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2409.12139","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Takin: A cohort of superior quality zero-shot speech generation models","venue":null,"work_id":"5aa3fad0-04e0-477f-b41a-8278782c1679","year":2024},"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":85,"source":"pdf_text","source_observed_at":"2026-05-10T16:36:33.264166Z"},"links":{"cited_paper":"/paper/2409.12139","citing_paper":"/paper/2604.11283"},"observation_digest":"sha256:506da5bc215d6e5f8ce3271b0995a58853b1e1bb2aacf39628ad47c83cbb6f69","observation_id":"9a105887-2276-43a4-b86d-3c400676f55f","resolution":{"observed_at":"2026-05-11T08:30:57.090210Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2409.12139","last_updated":"2024-09-24T02:00:54Z","snapshot_observed_at":"2026-08-02T15:34:06.836535Z","submitted_at":"2024-09-18T17:03:12Z","title":"Takin: A Cohort of Superior Quality Zero-shot Speech Generation Models","version":3},"cited_work":{"arxiv_id":"2409.12139","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2409.12139","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Takin: A cohort of superior quality zero-shot speech generation models","venue":null,"work_id":"5aa3fad0-04e0-477f-b41a-8278782c1679","year":2024},"citing_paper":{"arxiv_id":"2605.16026","last_updated":"2026-05-15T15:01:45Z","snapshot_observed_at":"2026-07-06T23:27:15.745896Z","submitted_at":"2026-05-15T15:01:45Z","title":"From Flat Language Labels to Typological Priors: Structured Language Conditioning for Multilingual Speech-to-Speech Translation","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-20T19:25:18.488377Z"},"links":{"cited_paper":"/paper/2409.12139","citing_paper":"/paper/2605.16026"},"observation_digest":"sha256:95f96516c870b53b8a00bb3f04973cdd40fbd3f19982060e891189198cb1dc8a","observation_id":"134cabfc-d7b1-40b0-af6e-aba3893b0e06","resolution":{"observed_at":"2026-05-20T19:28:55.037530Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2409.12139/citation-record","integrity":"/paper/2409.12139/integrity","json":"/paper/2409.12139/citation-record.json","paper":"/paper/2409.12139"},"outbound":[],"paper":{"arxiv_id":"2409.12139","last_updated":"2024-09-24T02:00:54Z","latest_version":3,"primary_category":"cs.SD","snapshot_observed_at":"2026-08-02T15:34:06.836535Z","submitted_at":"2024-09-18T17:03:12Z","title":"Takin: A Cohort of Superior Quality Zero-shot Speech Generation Models"},"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":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+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:2409.12139."}