{"as_of":"2026-08-12T03:21:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:9110c94b87dbf9876256857274a5cb84d7686a455062ba560db6e099c9c70845","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":"2026-08-11T06:34:44.6726+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":"2026-08-11T19:10:14.057549Z","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":"2026-08-11T04:34:08.061442Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2104.03521","last_updated":"2021-04-08T05:50:09Z","snapshot_observed_at":"2026-08-11T16:14:09.597441Z","submitted_at":"2021-04-08T05:50:09Z","title":"Towards Multi-Scale Style Control for Expressive Speech Synthesis","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.03521","snapshot_observed_at":"2026-08-11T19:10:14.057549Z","title":"Towards multi- scale style control for expressive speech synthesis,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.07116","last_updated":"2024-12-10T02:06:10Z","snapshot_observed_at":"2026-08-11T19:03:45.798171Z","submitted_at":"2024-12-10T02:06:10Z","title":"A Review of Human Emotion Synthesis Based on Generative Technology","version":1},"reference_index":165,"source":"pdf_text","source_observed_at":"2026-08-11T19:10:14.057549Z"},"links":{"cited_paper":"/paper/2104.03521","citing_paper":"/paper/2412.07116"},"observation_digest":"sha256:53f45346598e2d22e8e81772293ea729dc84fd6bdbc29307f1fbb7cddb6f2e5d","observation_id":"de5af162-8655-4896-bbc7-0b5b9c6afcff","resolution":{"observed_at":"2026-08-11T19:10:14.057549Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.03521","last_updated":"2021-04-08T05:50:09Z","snapshot_observed_at":"2026-08-11T16:14:09.597441Z","submitted_at":"2021-04-08T05:50:09Z","title":"Towards Multi-Scale Style Control for Expressive Speech Synthesis","version":1},"cited_work":{"arxiv_id":"2104.03521","doi":null,"metadata_source":"pith","pith_arxiv_id":"2104.03521","snapshot_observed_at":"2026-08-11T04:34:08.061442Z","title":"Towards Multi-Scale Style Control for Expressive Speech Synthesis","venue":"cs.SD","work_id":"d4bb2001-f1b3-449c-88d1-bd83584466f5","year":2021},"citing_paper":{"arxiv_id":"2412.18748","last_updated":"2024-12-31T07:27:26Z","snapshot_observed_at":"2026-08-11T04:28:26.087195Z","submitted_at":"2024-12-25T02:41:13Z","title":"Towards Expressive Video Dubbing with Multiscale Multimodal Context Interaction","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-11T04:34:07.838476Z"},"links":{"cited_paper":"/paper/2104.03521","citing_paper":"/paper/2412.18748"},"observation_digest":"sha256:fae780c0ca5226d632b51e50fceadf026095b62834e3bc22aba11993f03e1fc4","observation_id":"ce456576-3b5c-4c7f-83c9-3b088757a057","resolution":{"observed_at":"2026-08-11T04:34:08.066385Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2104.03521/citation-record","integrity":"/paper/2104.03521/integrity","json":"/paper/2104.03521/citation-record.json","paper":"/paper/2104.03521"},"outbound":[],"paper":{"arxiv_id":"2104.03521","last_updated":"2021-04-08T05:50:09Z","latest_version":1,"primary_category":"cs.SD","snapshot_observed_at":"2026-08-11T16:14:09.597441Z","submitted_at":"2021-04-08T05:50:09Z","title":"Towards Multi-Scale Style Control for Expressive 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":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"thesis":"As of 12 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2104.03521."}