{"as_of":"2026-08-12T17:45:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c59d977ac55234c89f020a9fe541a4dd3e8ef4d7c8dd6db5eebd894207271430","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":"2026-08-12T06:34:41.77262+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":"2026-08-11T19:32:24.115348Z","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":"2026-08-06T15:48:25.826113Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2408.13893","last_updated":"2024-08-28T07:16:37Z","snapshot_observed_at":"2026-08-12T13:03:16.172277Z","submitted_at":"2024-08-25T17:07:39Z","title":"SimpleSpeech 2: Towards Simple and Efficient Text-to-Speech with Flow-based Scalar Latent Transformer Diffusion Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.13893","snapshot_observed_at":"2026-08-11T19:32:24.115348Z","title":"In IEEE Interna- tional Conference on Acoustics, Speech and Signal Processing, pages 6199–6203","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.06602","last_updated":"2025-08-25T07:30:54Z","snapshot_observed_at":"2026-08-11T19:26:50.636660Z","submitted_at":"2024-12-09T15:50:25Z","title":"Towards Controllable Speech Synthesis in the Era of Large Language Models: A Systematic Survey","version":3},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-11T19:32:24.115348Z"},"links":{"cited_paper":"/paper/2408.13893","citing_paper":"/paper/2412.06602"},"observation_digest":"sha256:6c7b00fdb296a91ebac30c5755b9ebdde1c2e41e7fa341070588ba9a888686aa","observation_id":"8d23af91-f43b-42e5-8a7c-f30840e33a93","resolution":{"observed_at":"2026-08-11T19:32:24.115348Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.13893","last_updated":"2024-08-28T07:16:37Z","snapshot_observed_at":"2026-08-12T13:03:16.172277Z","submitted_at":"2024-08-25T17:07:39Z","title":"SimpleSpeech 2: Towards Simple and Efficient Text-to-Speech with Flow-based Scalar Latent Transformer Diffusion Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.13893","snapshot_observed_at":"2026-08-10T20:34:37.671286Z","title":"Simplespeech 2: Towards simple and efficient text-to-speech with flow-based scalar latent transformer diffusion models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.08238","last_updated":"2026-06-05T17:32:46Z","snapshot_observed_at":"2026-08-10T20:27:08.151956Z","submitted_at":"2025-01-14T16:26:14Z","title":"CodecFake+: Codec-Based Resynthesized Data as a Proxy for Detecting CodecFake Speech","version":3},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-10T20:34:37.671286Z"},"links":{"cited_paper":"/paper/2408.13893","citing_paper":"/paper/2501.08238"},"observation_digest":"sha256:43ad383b4682f6233374075fb3c81c26683ecc44ca6c127229d22df9de167d32","observation_id":"5ae7b87e-a029-49ba-8ef0-20ddb5d6da4b","resolution":{"observed_at":"2026-08-10T20:34:37.671286Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.13893","last_updated":"2024-08-28T07:16:37Z","snapshot_observed_at":"2026-08-12T13:03:16.172277Z","submitted_at":"2024-08-25T17:07:39Z","title":"SimpleSpeech 2: Towards Simple and Efficient Text-to-Speech with Flow-based Scalar Latent Transformer Diffusion Models","version":2},"cited_work":{"arxiv_id":"2408.13893","doi":null,"metadata_source":"pith","pith_arxiv_id":"2408.13893","snapshot_observed_at":"2026-08-06T15:48:25.826113Z","title":"SimpleSpeech 2: Towards Simple and Efficient Text-to-Speech with Flow-based Scalar Latent Transformer Diffusion Models","venue":"cs.SD","work_id":"0ae7d75b-1d08-42c2-bde8-893fc4002ad0","year":2024},"citing_paper":{"arxiv_id":"2507.14988","last_updated":"2025-07-20T14:48:48Z","snapshot_observed_at":"2026-08-11T00:57:14.977496Z","submitted_at":"2025-07-20T14:48:48Z","title":"DMOSpeech 2: Reinforcement Learning for Duration Prediction in Metric-Optimized Speech Synthesis","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T15:48:21.342231Z"},"links":{"cited_paper":"/paper/2408.13893","citing_paper":"/paper/2507.14988"},"observation_digest":"sha256:d21802b9b4f030f6e16e6508b9c64663ba0e850ce5fe076cfd9a753cb283f588","observation_id":"622d2823-e56a-4b2f-b553-fbff7e28ba02","resolution":{"observed_at":"2026-08-06T15:48:25.980592Z","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/2408.13893/citation-record","integrity":"/paper/2408.13893/integrity","json":"/paper/2408.13893/citation-record.json","paper":"/paper/2408.13893"},"outbound":[],"paper":{"arxiv_id":"2408.13893","last_updated":"2024-08-28T07:16:37Z","latest_version":2,"primary_category":"cs.SD","snapshot_observed_at":"2026-08-12T13:03:16.172277Z","submitted_at":"2024-08-25T17:07:39Z","title":"SimpleSpeech 2: Towards Simple and Efficient Text-to-Speech with Flow-based Scalar Latent Transformer 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 3 inbound Pith citation observations for arXiv:2408.13893."}