{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RBYBX64YB5GQP2I5THG63CF6LS","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":"12a344504aa40ebf5ce834e03cf51653ba43912885b99f5054f70e00b767a2db","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.SD"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2024-04-04T05:15:07Z","title_canon_sha256":"bd0d30525091e04b8b688aaf90223ce5424e2e5e4709787e15dee59006b4e96e"},"schema_version":"1.0","source":{"id":"2404.03204","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.03204","created_at":"2026-07-05T08:20:28Z"},{"alias_kind":"arxiv_version","alias_value":"2404.03204v3","created_at":"2026-07-05T08:20:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.03204","created_at":"2026-07-05T08:20:28Z"},{"alias_kind":"pith_short_12","alias_value":"RBYBX64YB5GQ","created_at":"2026-07-05T08:20:28Z"},{"alias_kind":"pith_short_16","alias_value":"RBYBX64YB5GQP2I5","created_at":"2026-07-05T08:20:28Z"},{"alias_kind":"pith_short_8","alias_value":"RBYBX64Y","created_at":"2026-07-05T08:20:28Z"}],"graph_snapshots":[{"event_id":"sha256:205d637845fcf6af37d0e5d6ec0f895c9b664d43255ce2090ccc3a1e270bde69","target":"graph","created_at":"2026-07-05T08:20:28Z","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/2404.03204/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present RALL-E, a robust language modeling method for text-to-speech (TTS) synthesis. While previous work based on large language models (LLMs) shows impressive performance on zero-shot TTS, such methods often suffer from poor robustness, such as unstable prosody (weird pitch and rhythm/duration) and a high word error rate (WER), due to the autoregressive prediction style of language models. The core idea behind RALL-E is chain-of-thought (CoT) prompting, which decomposes the task into simpler steps to enhance the robustness of LLM-based TTS. To accomplish this idea, RALL-E first predicts p","authors_text":"Detai Xin, Dongchao Yang, Hiroshi Saruwatari, Jinyu Li, Kai Shen, Sheng Zhao, Shinnosuke Takamichi, Shujie Liu, Xu Tan, Yuancheng Wang, Zeqian Ju","cross_cats":["cs.AI","cs.CL","cs.LG","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2024-04-04T05:15:07Z","title":"RALL-E: Robust Codec Language Modeling with Chain-of-Thought Prompting for Text-to-Speech Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.03204","kind":"arxiv","version":3},"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:ac96c65da076efe2195152cd1571aa323c124a6a2fda0fa1a23b383559a19229","target":"record","created_at":"2026-07-05T08:20:28Z","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":"12a344504aa40ebf5ce834e03cf51653ba43912885b99f5054f70e00b767a2db","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.SD"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2024-04-04T05:15:07Z","title_canon_sha256":"bd0d30525091e04b8b688aaf90223ce5424e2e5e4709787e15dee59006b4e96e"},"schema_version":"1.0","source":{"id":"2404.03204","kind":"arxiv","version":3}},"canonical_sha256":"88701bfb980f4d07e91d99cded88be5ca6b33e74844ac0a98cf09249d245a829","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"88701bfb980f4d07e91d99cded88be5ca6b33e74844ac0a98cf09249d245a829","first_computed_at":"2026-07-05T08:20:28.874910Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:20:28.874910Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"e5gEoEXX6D4Syj0ZeZnmALHWKNM0t7aa/kuahOhsmNd4j/h0SMzKlflxkM4Dc8xwUzvWqtF+txKEZ+IqQfe9Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:20:28.875440Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.03204","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ac96c65da076efe2195152cd1571aa323c124a6a2fda0fa1a23b383559a19229","sha256:205d637845fcf6af37d0e5d6ec0f895c9b664d43255ce2090ccc3a1e270bde69"],"state_sha256":"44a423649971309ed369cddbc0b2ede78f824adca213e70f54048fa445408afd"}