{"as_of":"2026-08-11T05:41:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:63b72f2998c95b5ac38c3cc5216a84da72b1fae5e6aacf7ff7aac4c50a200669","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":"2026-08-10T06:31:04.303077+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":"2026-08-06T19:55:03.233086Z","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":"2026-08-05T17:34:03.528650Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2401.08166","last_updated":"2024-01-16T07:13:16Z","snapshot_observed_at":"2026-08-06T00:01:14.217961Z","submitted_at":"2024-01-16T07:13:16Z","title":"ED-TTS: Multi-Scale Emotion Modeling using Cross-Domain Emotion Diarization for Emotional Speech Synthesis","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.08166","snapshot_observed_at":"2026-08-06T19:55:03.233086Z","title":"ED-TTS: Multi-scale emo- tion modeling using cross-domain emotion diarization for emotional speech synthesis","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.04349","last_updated":"2025-07-06T11:22:08Z","snapshot_observed_at":"2026-08-08T12:03:57.857500Z","submitted_at":"2025-07-06T11:22:08Z","title":"TTS-CtrlNet: Time varying emotion aligned text-to-speech generation with ControlNet","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T19:55:03.233086Z"},"links":{"cited_paper":"/paper/2401.08166","citing_paper":"/paper/2507.04349"},"observation_digest":"sha256:cee0e1886eca1339e28daa14561e988b9c0dfe1b38621b61f39b753cb57c5fe8","observation_id":"300d42a3-b2bf-4d08-a03f-d3579d2f27cf","resolution":{"observed_at":"2026-08-06T19:55:03.233086Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.08166","last_updated":"2024-01-16T07:13:16Z","snapshot_observed_at":"2026-08-06T00:01:14.217961Z","submitted_at":"2024-01-16T07:13:16Z","title":"ED-TTS: Multi-Scale Emotion Modeling using Cross-Domain Emotion Diarization for Emotional Speech Synthesis","version":1},"cited_work":{"arxiv_id":"2401.08166","doi":null,"metadata_source":"pith","pith_arxiv_id":"2401.08166","snapshot_observed_at":"2026-08-05T17:34:03.528650Z","title":"ED-TTS: Multi-Scale Emotion Modeling using Cross-Domain Emotion Diarization for Emotional Speech Synthesis","venue":"eess.AS","work_id":"49307d2c-7d5a-4010-bd72-699877e08918","year":2024},"citing_paper":{"arxiv_id":"2508.16188","last_updated":"2025-08-27T19:49:56Z","snapshot_observed_at":"2026-08-11T04:53:14.351865Z","submitted_at":"2025-08-22T08:08:45Z","title":"Seeing is Believing: Emotion-Aware Audio-Visual Language Modeling for Expressive Speech Generation","version":2},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-05T17:34:01.108489Z"},"links":{"cited_paper":"/paper/2401.08166","citing_paper":"/paper/2508.16188"},"observation_digest":"sha256:bce7b85d91dbb961af5c5ca22ca61925ac714c7acb295942682430c6c7d90ba8","observation_id":"e6e0c795-db41-4b7d-b1a3-b682878165fa","resolution":{"observed_at":"2026-08-05T17:34:03.655927Z","resolver_source":"local_arxiv","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"}}],"links":{"evidence":"/evidence","html":"/paper/2401.08166/citation-record","integrity":"/paper/2401.08166/integrity","json":"/paper/2401.08166/citation-record.json","paper":"/paper/2401.08166"},"outbound":[],"paper":{"arxiv_id":"2401.08166","last_updated":"2024-01-16T07:13:16Z","latest_version":1,"primary_category":"eess.AS","snapshot_observed_at":"2026-08-06T00:01:14.217961Z","submitted_at":"2024-01-16T07:13:16Z","title":"ED-TTS: Multi-Scale Emotion Modeling using Cross-Domain Emotion Diarization for Emotional Speech Synthesis"},"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 11 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2401.08166."}