{"as_of":"2026-08-22T03:00:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:0073e35b7c62df3838803ac2c2a8f0decd1908105730c916c3f6434401142a0a","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":"2026-08-21T06:32:19.484+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":"2026-08-11T20:31:07.690883Z","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":"2026-05-18T08:12:30.298940Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2104.01408","last_updated":"2021-06-14T02:14:11Z","snapshot_observed_at":"2026-08-21T04:08:49.403772Z","submitted_at":"2021-04-03T13:52:47Z","title":"Reinforcement Learning for Emotional Text-to-Speech Synthesis with Improved Emotion Discriminability","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.01408","snapshot_observed_at":"2026-08-11T20:31:07.690883Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.05738","last_updated":"2024-12-07T20:18:46Z","snapshot_observed_at":"2026-08-16T23:06:26.627663Z","submitted_at":"2024-12-07T20:18:46Z","title":"Exploring the Impact of Emotional Voice Integration in Sign-to-Speech Translators for Deaf-to-Hearing Communication","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-11T20:31:07.690883Z"},"links":{"cited_paper":"/paper/2104.01408","citing_paper":"/paper/2412.05738"},"observation_digest":"sha256:a5ca039ba0f1de6436d66b2f30f0c8a3b2267a7a10cf7a15c24886637ebbb0e7","observation_id":"4287f8a8-9395-4b29-bfec-cf16682ac836","resolution":{"observed_at":"2026-08-11T20:31:07.690883Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.01408","last_updated":"2021-06-14T02:14:11Z","snapshot_observed_at":"2026-08-21T04:08:49.403772Z","submitted_at":"2021-04-03T13:52:47Z","title":"Reinforcement Learning for Emotional Text-to-Speech Synthesis with Improved Emotion Discriminability","version":2},"cited_work":{"arxiv_id":"2104.01408","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2104.01408","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"b750946c-66dd-4710-a508-82b7d92e412a","year":2021},"citing_paper":{"arxiv_id":"2511.20657","last_updated":"2026-05-02T12:09:38Z","snapshot_observed_at":"2026-08-13T15:15:19.905394Z","submitted_at":"2025-10-11T07:40:36Z","title":"Intelligent Agents with Emotional Intelligence: Current Trends, Challenges, and Future Prospects","version":2},"reference_index":94,"source":"pdf_text","source_observed_at":"2026-05-18T08:11:31.181704Z"},"links":{"cited_paper":"/paper/2104.01408","citing_paper":"/paper/2511.20657"},"observation_digest":"sha256:a6c5d2cf6655771b67aac98883e34fcd33d5ff21b0555c48cafb50ecfc23fa74","observation_id":"fc601b39-816b-403a-af2f-93880e6d5b7e","resolution":{"observed_at":"2026-05-18T08:12:30.302007Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2104.01408","last_updated":"2021-06-14T02:14:11Z","snapshot_observed_at":"2026-08-21T04:08:49.403772Z","submitted_at":"2021-04-03T13:52:47Z","title":"Reinforcement Learning for Emotional Text-to-Speech Synthesis with Improved Emotion Discriminability","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.01408","snapshot_observed_at":"2026-08-03T06:36:32.668134Z","title":"Reinforcement learning for emotional text-to-speech synthesis with improved emo- tion discriminability.arXiv preprint arXiv:2104.01408,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2601.22661","last_updated":"2026-05-27T18:10:43Z","snapshot_observed_at":"2026-08-13T04:26:16.591748Z","submitted_at":"2026-01-30T07:27:48Z","title":"Evaluating and Rewarding LALMs for Expressive Role-Play TTS via Mean Continuation Log-Probability","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-03T06:36:32.668134Z"},"links":{"cited_paper":"/paper/2104.01408","citing_paper":"/paper/2601.22661"},"observation_digest":"sha256:9b38b0394dc02309a1e92757f24a1d0a741d9a7814d7868e26f62be9afdffbbd","observation_id":"8c2c6535-9aa0-4a03-8ede-cde0e03d33f1","resolution":{"observed_at":"2026-08-03T06:36:32.668134Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2104.01408/citation-record","integrity":"/paper/2104.01408/integrity","json":"/paper/2104.01408/citation-record.json","paper":"/paper/2104.01408"},"outbound":[],"paper":{"arxiv_id":"2104.01408","last_updated":"2021-06-14T02:14:11Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-21T04:08:49.403772Z","submitted_at":"2021-04-03T13:52:47Z","title":"Reinforcement Learning for Emotional Text-to-Speech Synthesis with Improved Emotion Discriminability"},"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":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"thesis":"As of 22 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2104.01408."}