{"as_of":"2026-08-06T06:12:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:49dbc945effb70c11f929ac91e62bf89d9240d98482fd8120976426206b3f366","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":"2026-08-05T06:32:48.257954+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":"2026-07-10T10:31:23.170749Z","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":"2026-07-10T10:37:01.579016Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2404.05600","last_updated":"2024-04-08T15:21:17Z","snapshot_observed_at":"2026-08-05T11:57:00.393189Z","submitted_at":"2024-04-08T15:21:17Z","title":"SpeechAlign: Aligning Speech Generation to Human Preferences","version":1},"cited_work":{"arxiv_id":"2404.05600","doi":null,"metadata_source":"pith","pith_arxiv_id":"2404.05600","snapshot_observed_at":"2026-07-10T10:37:01.579016Z","title":"SpeechAlign: Aligning speech generation to human preferences","venue":"cs.CL","work_id":"374bf864-7e85-42ed-acac-9de2a595aba1","year":2024},"citing_paper":{"arxiv_id":"2406.02430","last_updated":"2024-06-04T15:48:29Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-06-04T15:48:29Z","title":"Seed-TTS: A Family of High-Quality Versatile Speech Generation Models","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-05-15T12:26:37.300599Z"},"links":{"cited_paper":"/paper/2404.05600","citing_paper":"/paper/2406.02430"},"observation_digest":"sha256:cea8bb5b01c8d2a46ebb7c09ef1cdbc4e5379a18f80f9605dbc189ecedc87d63","observation_id":"2b1927a3-db00-49e5-9f38-c32ea6a04dea","resolution":{"observed_at":"2026-05-15T12:26:37.389182Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.05600","last_updated":"2024-04-08T15:21:17Z","snapshot_observed_at":"2026-08-05T11:57:00.393189Z","submitted_at":"2024-04-08T15:21:17Z","title":"SpeechAlign: Aligning Speech Generation to Human Preferences","version":1},"cited_work":{"arxiv_id":"2404.05600","doi":null,"metadata_source":"pith","pith_arxiv_id":"2404.05600","snapshot_observed_at":"2026-07-10T10:37:01.579016Z","title":"SpeechAlign: Aligning speech generation to human preferences","venue":"cs.CL","work_id":"374bf864-7e85-42ed-acac-9de2a595aba1","year":2024},"citing_paper":{"arxiv_id":"2607.08256","last_updated":"2026-08-05T11:29:52Z","snapshot_observed_at":"2026-08-06T05:52:03.061167Z","submitted_at":"2026-07-09T09:01:03Z","title":"Best-of-$N$ TTS Evaluation is Confounded by ASR Family Alignment","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-07-10T10:31:23.170749Z"},"links":{"cited_paper":"/paper/2404.05600","citing_paper":"/paper/2607.08256"},"observation_digest":"sha256:f6ac6ec2ed853f74072a92fadf586fb3ae551cea090907581d9ee805c29a3e63","observation_id":"f3471bd0-7b7c-41d8-b70b-0a1b1b96ebb1","resolution":{"observed_at":"2026-07-10T10:37:01.580228Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2404.05600/citation-record","integrity":"/paper/2404.05600/integrity","json":"/paper/2404.05600/citation-record.json","paper":"/paper/2404.05600"},"outbound":[],"paper":{"arxiv_id":"2404.05600","last_updated":"2024-04-08T15:21:17Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-05T11:57:00.393189Z","submitted_at":"2024-04-08T15:21:17Z","title":"SpeechAlign: Aligning Speech Generation to Human Preferences"},"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":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"thesis":"As of 6 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2404.05600."}