{"as_of":"2026-08-08T13:32:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:459f354386ce5b17133f399701730d335808e1e08035b0fd6c29c7501899918e","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":4,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":4,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T17:46:17.295613Z","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":"2026-08-05T11:41:42.733852Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2502.11128","last_updated":"2025-09-03T01:59:58Z","snapshot_observed_at":"2026-08-07T18:14:46.399260Z","submitted_at":"2025-02-16T13:54:32Z","title":"FELLE: Autoregressive Speech Synthesis with Token-Wise Coarse-to-Fine Flow Matching","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.11128","snapshot_observed_at":"2026-08-06T17:46:17.295613Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.10109","last_updated":"2025-07-14T09:50:53Z","snapshot_observed_at":"2026-08-08T02:46:03.641224Z","submitted_at":"2025-07-14T09:50:53Z","title":"DualDub: Video-to-Soundtrack Generation via Joint Speech and Background Audio Synthesis","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-06T17:46:17.295613Z"},"links":{"cited_paper":"/paper/2502.11128","citing_paper":"/paper/2507.10109"},"observation_digest":"sha256:3a2c82db318dd98803f560504d63a871751c0336416335a59455d133409fbe82","observation_id":"c778f8fa-b4e8-4720-a550-e1c19f05d7d0","resolution":{"observed_at":"2026-08-06T17:46:17.295613Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.11128","last_updated":"2025-09-03T01:59:58Z","snapshot_observed_at":"2026-08-07T18:14:46.399260Z","submitted_at":"2025-02-16T13:54:32Z","title":"FELLE: Autoregressive Speech Synthesis with Token-Wise Coarse-to-Fine Flow Matching","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.11128","snapshot_observed_at":"2026-08-06T11:22:27.493156Z","title":"Felle: Autoregressive speech synthesis with token-wise coarse-to-fine flow matching","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.22746","last_updated":"2025-08-01T03:37:42Z","snapshot_observed_at":"2026-08-06T13:36:59.117683Z","submitted_at":"2025-07-30T15:03:36Z","title":"Next Tokens Denoising for Speech Synthesis","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T11:22:27.493156Z"},"links":{"cited_paper":"/paper/2502.11128","citing_paper":"/paper/2507.22746"},"observation_digest":"sha256:60a7cc893788c99b5a7645756041094e99d6ca9de521540155b88d1e93255f41","observation_id":"efbba303-682e-4bdb-9678-fe4e6a456f05","resolution":{"observed_at":"2026-08-06T11:22:27.493156Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.11128","last_updated":"2025-09-03T01:59:58Z","snapshot_observed_at":"2026-08-07T18:14:46.399260Z","submitted_at":"2025-02-16T13:54:32Z","title":"FELLE: Autoregressive Speech Synthesis with Token-Wise Coarse-to-Fine Flow Matching","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.11128","snapshot_observed_at":"2026-08-05T16:01:52.818331Z","title":"Felle: Autoregressive speech synthesis with token-wise coarse-to-fine flow matching, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2508.19098","last_updated":"2025-08-26T14:59:30Z","snapshot_observed_at":"2026-08-06T21:25:08.912503Z","submitted_at":"2025-08-26T14:59:30Z","title":"CLEAR: Continuous Latent Autoregressive Modeling for High-quality and Low-latency Speech Synthesis","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-05T16:01:52.818331Z"},"links":{"cited_paper":"/paper/2502.11128","citing_paper":"/paper/2508.19098"},"observation_digest":"sha256:eb4a344531f47bbe2fd96524e1e23cbd8eccd646dbb6e14e9bd1d870726bddfa","observation_id":"c5b0d8c7-9cc3-4359-8b41-ce886d522b74","resolution":{"observed_at":"2026-08-05T16:01:52.818331Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.11128","last_updated":"2025-09-03T01:59:58Z","snapshot_observed_at":"2026-08-07T18:14:46.399260Z","submitted_at":"2025-02-16T13:54:32Z","title":"FELLE: Autoregressive Speech Synthesis with Token-Wise Coarse-to-Fine Flow Matching","version":2},"cited_work":{"arxiv_id":"2502.11128","doi":null,"metadata_source":"pith","pith_arxiv_id":"2502.11128","snapshot_observed_at":"2026-08-05T11:41:42.733852Z","title":"FELLE: Autoregressive Speech Synthesis with Token-Wise Coarse-to-Fine Flow Matching","venue":"cs.CL","work_id":"9e0d9a01-b398-47a5-a8fe-71f51be57ef6","year":2025},"citing_paper":{"arxiv_id":"2509.02398","last_updated":"2025-09-02T15:10:09Z","snapshot_observed_at":"2026-08-07T14:04:39.516006Z","submitted_at":"2025-09-02T15:10:09Z","title":"TTA-Bench: A Comprehensive Benchmark for Evaluating Text-to-Audio Models","version":1},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-05T11:41:41.566443Z"},"links":{"cited_paper":"/paper/2502.11128","citing_paper":"/paper/2509.02398"},"observation_digest":"sha256:cc618340b5ae247dbaed6c97315a7098ec4c976ae2024c542dc9c29a77d44362","observation_id":"3882d03c-8f3b-4384-b0b7-7ac957202b0f","resolution":{"observed_at":"2026-08-05T11:41:42.890538Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2502.11128/citation-record","integrity":"/paper/2502.11128/integrity","json":"/paper/2502.11128/citation-record.json","paper":"/paper/2502.11128"},"outbound":[],"paper":{"arxiv_id":"2502.11128","last_updated":"2025-09-03T01:59:58Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-07T18:14:46.399260Z","submitted_at":"2025-02-16T13:54:32Z","title":"FELLE: Autoregressive Speech Synthesis with Token-Wise Coarse-to-Fine Flow Matching"},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2502.11128."}