{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BX5C343I7NURFJEIBXOKHCJSUG","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":"e0ceb8af76d98d8c1ec255ff4d8083cfa547d1a05ba44f34da097200438c6e12","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"eess.AS","submitted_at":"2025-02-26T08:22:00Z","title_canon_sha256":"3192267fa0c074cfe9aaff91425920956a4f95fb7665a314c14ab0122bba0f8d"},"schema_version":"1.0","source":{"id":"2502.18924","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.18924","created_at":"2026-07-05T10:40:38Z"},{"alias_kind":"arxiv_version","alias_value":"2502.18924v4","created_at":"2026-07-05T10:40:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.18924","created_at":"2026-07-05T10:40:38Z"},{"alias_kind":"pith_short_12","alias_value":"BX5C343I7NUR","created_at":"2026-07-05T10:40:38Z"},{"alias_kind":"pith_short_16","alias_value":"BX5C343I7NURFJEI","created_at":"2026-07-05T10:40:38Z"},{"alias_kind":"pith_short_8","alias_value":"BX5C343I","created_at":"2026-07-05T10:40:38Z"}],"graph_snapshots":[{"event_id":"sha256:055046bb9f79b805764fa33befd18c226aa97a07799fc739160185d0e78db5c1","target":"graph","created_at":"2026-07-05T10:40:38Z","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/2502.18924/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While recent zero-shot text-to-speech (TTS) models have significantly improved speech quality and expressiveness, mainstream systems still suffer from issues related to speech-text alignment modeling: 1) models without explicit speech-text alignment modeling exhibit less robustness, especially for hard sentences in practical applications; 2) predefined alignment-based models suffer from naturalness constraints of forced alignments. This paper introduces \\textit{MegaTTS 3}, a TTS system featuring an innovative sparse alignment algorithm that guides the latent diffusion transformer (DiT). Specif","authors_text":"Bai Jionghao, Boyang Zhang, Chen Zhang, Jialong Zuo, Rui Liu, Ruiqi Li, Shengpeng Ji, Xiang Yin, Xiaoda Yang, Yi Ren, Yu Zhang, Zhenhui Ye, Zhou Zhao, Ziyue Jiang","cross_cats":["cs.LG","cs.SD"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"eess.AS","submitted_at":"2025-02-26T08:22:00Z","title":"MegaTTS 3: Sparse Alignment Enhanced Latent Diffusion Transformer for Zero-Shot Speech Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.18924","kind":"arxiv","version":4},"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:c38dd414af6817eaa42e3e03f00267d00b87a3c82208a859062b115c31fd80ba","target":"record","created_at":"2026-07-05T10:40:38Z","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":"e0ceb8af76d98d8c1ec255ff4d8083cfa547d1a05ba44f34da097200438c6e12","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"eess.AS","submitted_at":"2025-02-26T08:22:00Z","title_canon_sha256":"3192267fa0c074cfe9aaff91425920956a4f95fb7665a314c14ab0122bba0f8d"},"schema_version":"1.0","source":{"id":"2502.18924","kind":"arxiv","version":4}},"canonical_sha256":"0dfa2df368fb6912a4880ddca38932a1978203fef73aa3237b3dc2c4d64e925e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0dfa2df368fb6912a4880ddca38932a1978203fef73aa3237b3dc2c4d64e925e","first_computed_at":"2026-07-05T10:40:38.856808Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:40:38.856808Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aVdDWCXeezsGEXw/OCuS9aCYHo6PDlM/AvWAoGBfhPP5AszHy3Gaxf2TyNqfe39RrPVAz5wQihVGcXnbeu9dAg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:40:38.857308Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.18924","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c38dd414af6817eaa42e3e03f00267d00b87a3c82208a859062b115c31fd80ba","sha256:055046bb9f79b805764fa33befd18c226aa97a07799fc739160185d0e78db5c1"],"state_sha256":"8a291d7b0564d077689a2cb16aa9844ce3c840bbde0803897c9d0fe38d0e2584"}