{"as_of":"2026-08-10T08:25:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ec3ca8f204278056e55017a97ede867382befd1021d560a5b2f7a119b697edb6","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":"2026-08-10T06:31:04.303077+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":"2026-08-08T11:50:21.003985Z","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":"2026-05-13T21:49:52.234477Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2111.07402","last_updated":"2022-12-13T14:12:02Z","snapshot_observed_at":"2026-08-05T21:50:11.152608Z","submitted_at":"2021-11-14T18:16:42Z","title":"Textless Speech Emotion Conversion using Discrete and Decomposed Representations","version":3},"cited_work":{"arxiv_id":"2111.07402","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2111.07402","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Textless speech emotion conversion using decomposed and discrete representations.arXiv preprint arXiv:2111.07402","venue":null,"work_id":"d179a7c4-d6eb-42d4-b787-68215d5cb5fb","year":null},"citing_paper":{"arxiv_id":"2210.13438","last_updated":"2022-10-24T17:52:02Z","snapshot_observed_at":"2026-08-09T07:12:13.721596Z","submitted_at":"2022-10-24T17:52:02Z","title":"High Fidelity Neural Audio Compression","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-05-13T21:49:52.184932Z"},"links":{"cited_paper":"/paper/2111.07402","citing_paper":"/paper/2210.13438"},"observation_digest":"sha256:98b88c399d07c28334d2489818d98e31c23fbe348907902114d4468b920ea525","observation_id":"448398a6-b82c-448b-9e25-4d4f409d59ad","resolution":{"observed_at":"2026-05-13T21:49:52.236134Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2111.07402","last_updated":"2022-12-13T14:12:02Z","snapshot_observed_at":"2026-08-05T21:50:11.152608Z","submitted_at":"2021-11-14T18:16:42Z","title":"Textless Speech Emotion Conversion using Discrete and Decomposed Representations","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2111.07402","snapshot_observed_at":"2026-08-05T22:34:42.520181Z","title":"Textless speech emotion conversion using discrete and decomposed representations,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.06890","last_updated":"2025-08-09T08:46:32Z","snapshot_observed_at":"2026-08-09T15:28:21.576303Z","submitted_at":"2025-08-09T08:46:32Z","title":"Maestro-EVC: Controllable Emotional Voice Conversion Guided by References and Explicit Prosody","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-05T22:34:42.520181Z"},"links":{"cited_paper":"/paper/2111.07402","citing_paper":"/paper/2508.06890"},"observation_digest":"sha256:995c9d9236ac9ded435aa27dfaca96d4d5f3f524c34d14e492960bc6aa96e20f","observation_id":"be03c332-48be-41df-aaaf-f72c62f3b4fe","resolution":{"observed_at":"2026-08-05T22:34:42.520181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2111.07402","last_updated":"2022-12-13T14:12:02Z","snapshot_observed_at":"2026-08-05T21:50:11.152608Z","submitted_at":"2021-11-14T18:16:42Z","title":"Textless Speech Emotion Conversion using Discrete and Decomposed Representations","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2111.07402","snapshot_observed_at":"2026-08-08T11:50:21.003985Z","title":"arXiv preprint arXiv:2111.07402 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.05507","last_updated":"2026-08-06T01:19:35Z","snapshot_observed_at":"2026-08-09T23:10:58.519642Z","submitted_at":"2026-08-06T01:19:35Z","title":"AffectDF: The Most Comprehensive Benchmark for Speech Deepfake Detection against Emotionally Expressive Attacks","version":1},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-08T11:50:21.003985Z"},"links":{"cited_paper":"/paper/2111.07402","citing_paper":"/paper/2608.05507"},"observation_digest":"sha256:70130972fc942dc2c690ae187205ef9ddec86b7067c88abcf834fbd8cd52d97e","observation_id":"20f2c225-b11c-43a8-babd-4ee563595883","resolution":{"observed_at":"2026-08-08T11:50:21.003985Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2111.07402/citation-record","integrity":"/paper/2111.07402/integrity","json":"/paper/2111.07402/citation-record.json","paper":"/paper/2111.07402"},"outbound":[],"paper":{"arxiv_id":"2111.07402","last_updated":"2022-12-13T14:12:02Z","latest_version":3,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-05T21:50:11.152608Z","submitted_at":"2021-11-14T18:16:42Z","title":"Textless Speech Emotion Conversion using Discrete and Decomposed Representations"},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2111.07402."}