{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KS6C2BNLTGRVCA6YHKDVXGSZMY","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"2fb3bee1e8d6183fbd4acca54c8bded5e33afb9d9ed99c0de7ac35fedd08b1aa","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-08-25T17:07:39Z","title_canon_sha256":"9186253f34d90ba3983561da2aec74dfa2541cefc83ce894c375b33ffb65d4a7"},"schema_version":"1.0","source":{"id":"2408.13893","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.13893","created_at":"2026-07-05T09:00:07Z"},{"alias_kind":"arxiv_version","alias_value":"2408.13893v2","created_at":"2026-07-05T09:00:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.13893","created_at":"2026-07-05T09:00:07Z"},{"alias_kind":"pith_short_12","alias_value":"KS6C2BNLTGRV","created_at":"2026-07-05T09:00:07Z"},{"alias_kind":"pith_short_16","alias_value":"KS6C2BNLTGRVCA6Y","created_at":"2026-07-05T09:00:07Z"},{"alias_kind":"pith_short_8","alias_value":"KS6C2BNL","created_at":"2026-07-05T09:00:07Z"}],"graph_snapshots":[{"event_id":"sha256:889f42624e86dcbb1dacedaf762565b95fa5a9f061f404804d1ac4d960991620","target":"graph","created_at":"2026-07-05T09:00:07Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2408.13893/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Scaling Text-to-speech (TTS) to large-scale datasets has been demonstrated as an effective method for improving the diversity and naturalness of synthesized speech. At the high level, previous large-scale TTS models can be categorized into either Auto-regressive (AR) based (\\textit{e.g.}, VALL-E) or Non-auto-regressive (NAR) based models (\\textit{e.g.}, NaturalSpeech 2/3). Although these works demonstrate good performance, they still have potential weaknesses. For instance, AR-based models are plagued by unstable generation quality and slow generation speed; meanwhile, some NAR-based models ne","authors_text":"Dading Chong, Dongchao Yang, Haohan Guo, Helen Meng, Rongjie Huang, Songxiang Liu, Xixin Wu, Yuanyuan Wang","cross_cats":["cs.CL","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","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"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.13893","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:145bae0ed411644ec40192af6399e64553c7b1ad657e908c617cc2fb52fdad39","target":"record","created_at":"2026-07-05T09:00:07Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"2fb3bee1e8d6183fbd4acca54c8bded5e33afb9d9ed99c0de7ac35fedd08b1aa","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-08-25T17:07:39Z","title_canon_sha256":"9186253f34d90ba3983561da2aec74dfa2541cefc83ce894c375b33ffb65d4a7"},"schema_version":"1.0","source":{"id":"2408.13893","kind":"arxiv","version":2}},"canonical_sha256":"54bc2d05ab99a35103d83a875b9a596606bc0541443e76ba1f0bf42da805167b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"54bc2d05ab99a35103d83a875b9a596606bc0541443e76ba1f0bf42da805167b","first_computed_at":"2026-07-05T09:00:07.964771Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:00:07.964771Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"R+oyZVOTt0iJzUjoLpcekNiVV/v00Kb0KJNrH+niS/Juur7o7gAEohdwTgrcW1Jyw6ZdHaRHw74UE+09xH/ODA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:00:07.965278Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.13893","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:145bae0ed411644ec40192af6399e64553c7b1ad657e908c617cc2fb52fdad39","sha256:889f42624e86dcbb1dacedaf762565b95fa5a9f061f404804d1ac4d960991620"],"state_sha256":"eaca29a1f0ea588d2cd326d40c7463a0759a3f7586c87b0a978dad8a747acb5b"}