{"as_of":"2026-08-14T15:50:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d965a35dcc0b4cabd95f590c23777d88a5c99ac15b25e8751769a53399c4400c","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":"2026-08-14T06:32:32.682623+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":"2026-07-12T22:04:31.302192Z","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":"2026-05-11T08:30:57.190417Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2309.12792","last_updated":"2023-09-22T11:06:04Z","snapshot_observed_at":"2026-08-13T10:07:39.254560Z","submitted_at":"2023-09-22T11:06:04Z","title":"DurIAN-E: Duration Informed Attention Network For Expressive Text-to-Speech Synthesis","version":1},"cited_work":{"arxiv_id":"2309.12792","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2309.12792","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Durian-e: Duration informed attention network for expressive text-to-speech synthesis","venue":null,"work_id":"0dc680a1-3d3d-4e3b-afdd-7ff9de3aaf1c","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":86,"source":"pdf_text","source_observed_at":"2026-05-10T16:36:33.264166Z"},"links":{"cited_paper":"/paper/2309.12792","citing_paper":"/paper/2604.11283"},"observation_digest":"sha256:edbf2e191bae83d0265052efda07b5cdf09f433dbe10c070ed75a2986b02e1b7","observation_id":"d49bc0f6-a10b-4e09-8e5d-4c17c576fad4","resolution":{"observed_at":"2026-05-11T08:30:57.191984Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2309.12792","last_updated":"2023-09-22T11:06:04Z","snapshot_observed_at":"2026-08-13T10:07:39.254560Z","submitted_at":"2023-09-22T11:06:04Z","title":"DurIAN-E: Duration Informed Attention Network For Expressive Text-to-Speech Synthesis","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.12792","snapshot_observed_at":"2026-07-12T22:04:31.302192Z","title":"Durian-e: Duration informed attention network for expressive text-to-speech synthesis,","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":134,"source":"pdf_text","source_observed_at":"2026-07-12T22:04:31.302192Z"},"links":{"cited_paper":"/paper/2309.12792","citing_paper":"/paper/2604.11283"},"observation_digest":"sha256:f10064e4eb84a25e508323e363837851b12fe6c0df32e1dc94abd00796b88686","observation_id":"c9137fd7-37cf-41a1-be14-f8dea6754bf5","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/2309.12792/citation-record","integrity":"/paper/2309.12792/integrity","json":"/paper/2309.12792/citation-record.json","paper":"/paper/2309.12792"},"outbound":[],"paper":{"arxiv_id":"2309.12792","last_updated":"2023-09-22T11:06:04Z","latest_version":1,"primary_category":"eess.AS","snapshot_observed_at":"2026-08-13T10:07:39.254560Z","submitted_at":"2023-09-22T11:06:04Z","title":"DurIAN-E: Duration Informed Attention Network For Expressive Text-to-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":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"thesis":"As of 14 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2309.12792."}