{"as_of":"2026-08-12T22:54:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:7b439f86e4c9681e9511087ce86786821b53539396ff9e6b24219d3f3f752f58","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":"2026-08-12T06:34:41.77262+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":"2026-08-11T19:10:14.119369Z","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":"2026-08-07T12:45:11.349273Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2409.06451","last_updated":"2024-09-10T12:13:24Z","snapshot_observed_at":"2026-08-12T22:47:48.086088Z","submitted_at":"2024-09-10T12:13:24Z","title":"Enhancing Emotional Text-to-Speech Controllability with Natural Language Guidance through Contrastive Learning and Diffusion Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.06451","snapshot_observed_at":"2026-08-11T19:10:14.119369Z","title":"Enhancing emo- tional text-to-speech controllability with natural language guid- ance through contrastive learning and diffusion models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.07116","last_updated":"2024-12-10T02:06:10Z","snapshot_observed_at":"2026-08-12T11:05:41.848957Z","submitted_at":"2024-12-10T02:06:10Z","title":"A Review of Human Emotion Synthesis Based on Generative Technology","version":1},"reference_index":181,"source":"pdf_text","source_observed_at":"2026-08-11T19:10:14.119369Z"},"links":{"cited_paper":"/paper/2409.06451","citing_paper":"/paper/2412.07116"},"observation_digest":"sha256:f2a4ce2c5b860ffbc9b524de575ecd585c49de6af61c676b6140f5d683411684","observation_id":"3fc63555-d69f-4323-8580-e06859e06dfa","resolution":{"observed_at":"2026-08-11T19:10:14.119369Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.06451","last_updated":"2024-09-10T12:13:24Z","snapshot_observed_at":"2026-08-12T22:47:48.086088Z","submitted_at":"2024-09-10T12:13:24Z","title":"Enhancing Emotional Text-to-Speech Controllability with Natural Language Guidance through Contrastive Learning and Diffusion Models","version":1},"cited_work":{"arxiv_id":"2409.06451","doi":null,"metadata_source":"pith","pith_arxiv_id":"2409.06451","snapshot_observed_at":"2026-08-07T12:45:11.349273Z","title":"Enhancing Emotional Text-to-Speech Controllability with Natural Language Guidance through Contrastive Learning and Diffusion Models","venue":"cs.SD","work_id":"413389f6-160f-4bd6-85b1-a7406911170e","year":2024},"citing_paper":{"arxiv_id":"2505.23732","last_updated":"2025-05-29T17:56:55Z","snapshot_observed_at":"2026-08-10T23:24:30.514690Z","submitted_at":"2025-05-29T17:56:55Z","title":"EmotionRankCLAP: Bridging Natural Language Speaking Styles and Ordinal Speech Emotion via Rank-N-Contrast","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T12:45:08.523771Z"},"links":{"cited_paper":"/paper/2409.06451","citing_paper":"/paper/2505.23732"},"observation_digest":"sha256:1e42feab5649465cdee055463f836c40778972babe5bbd84de9d53d92c6bc77a","observation_id":"6844ad37-59b2-4f93-a12b-17fcb56aaa86","resolution":{"observed_at":"2026-08-07T12:45:11.427331Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2409.06451/citation-record","integrity":"/paper/2409.06451/integrity","json":"/paper/2409.06451/citation-record.json","paper":"/paper/2409.06451"},"outbound":[],"paper":{"arxiv_id":"2409.06451","last_updated":"2024-09-10T12:13:24Z","latest_version":1,"primary_category":"cs.SD","snapshot_observed_at":"2026-08-12T22:47:48.086088Z","submitted_at":"2024-09-10T12:13:24Z","title":"Enhancing Emotional Text-to-Speech Controllability with Natural Language Guidance through Contrastive Learning and Diffusion Models"},"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":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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:2409.06451."}