{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DRLOER4XUL76JLLJSOOWSA7MWM","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":"478757af28fb81d26e888f9962824b8063d71a002557dd0978d8c5f983506273","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-11-02T07:04:02Z","title_canon_sha256":"7a31fa4e4932260da12a428c834bedd73d1691275ad728d40de2d8e1aff4df18"},"schema_version":"1.0","source":{"id":"2411.01156","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.01156","created_at":"2026-07-05T09:33:10Z"},{"alias_kind":"arxiv_version","alias_value":"2411.01156v2","created_at":"2026-07-05T09:33:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.01156","created_at":"2026-07-05T09:33:10Z"},{"alias_kind":"pith_short_12","alias_value":"DRLOER4XUL76","created_at":"2026-07-05T09:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"DRLOER4XUL76JLLJ","created_at":"2026-07-05T09:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"DRLOER4X","created_at":"2026-07-05T09:33:10Z"}],"graph_snapshots":[{"event_id":"sha256:85571b82800c9d3aa96a21849269d7d340153e45c71686bd15db9ea1a8e35d95","target":"graph","created_at":"2026-07-05T09:33:10Z","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/2411.01156/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text-to-Speech (TTS) systems face ongoing challenges in processing complex linguistic features, handling polyphonic expressions, and producing natural-sounding multilingual speech - capabilities that are crucial for future AI applications. In this paper, we present Fish-Speech, a novel framework that implements a serial fast-slow Dual Autoregressive (Dual-AR) architecture to enhance the stability of Grouped Finite Scalar Vector Quantization (GFSQ) in sequence generation tasks. This architecture improves codebook processing efficiency while maintaining high-fidelity outputs, making it particula","authors_text":"Rongzhi Zhou, Ruoyi Zhang, Shijia Liao, Tianyu Li, Yifan Cheng, Yijin Xing, Yuxuan Wang","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-11-02T07:04:02Z","title":"Fish-Speech: Leveraging Large Language Models for Advanced Multilingual Text-to-Speech Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.01156","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:b4eb492f472b83d5aeedf51e0eec34cdca81bacb01ba3d2a91c6e89415fa5109","target":"record","created_at":"2026-07-05T09:33:10Z","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":"478757af28fb81d26e888f9962824b8063d71a002557dd0978d8c5f983506273","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-11-02T07:04:02Z","title_canon_sha256":"7a31fa4e4932260da12a428c834bedd73d1691275ad728d40de2d8e1aff4df18"},"schema_version":"1.0","source":{"id":"2411.01156","kind":"arxiv","version":2}},"canonical_sha256":"1c56e24797a2ffe4ad69939d6903ecb33598926d8a7f419d4536fa5be57626f4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1c56e24797a2ffe4ad69939d6903ecb33598926d8a7f419d4536fa5be57626f4","first_computed_at":"2026-07-05T09:33:10.912291Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:33:10.912291Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IjKVeZqD0xTYbZ0PHrBFP00DIp5BH/GSApI/4eZhG+AEkdJOXx696dUIhZYpf2UtoP5VXJ6AWkKMPBVM9JuNBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:33:10.912806Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.01156","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b4eb492f472b83d5aeedf51e0eec34cdca81bacb01ba3d2a91c6e89415fa5109","sha256:85571b82800c9d3aa96a21849269d7d340153e45c71686bd15db9ea1a8e35d95"],"state_sha256":"11598ec46b5b873ebfd51acc2c73b33decf3652c272742249bf202368b8357d4"}