{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:RBYBX64YB5GQP2I5THG63CF6LS","short_pith_number":"pith:RBYBX64Y","canonical_record":{"source":{"id":"2404.03204","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2024-04-04T05:15:07Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.SD"],"title_canon_sha256":"bd0d30525091e04b8b688aaf90223ce5424e2e5e4709787e15dee59006b4e96e","abstract_canon_sha256":"12a344504aa40ebf5ce834e03cf51653ba43912885b99f5054f70e00b767a2db"},"schema_version":"1.0"},"canonical_sha256":"88701bfb980f4d07e91d99cded88be5ca6b33e74844ac0a98cf09249d245a829","source":{"kind":"arxiv","id":"2404.03204","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:RBYBX64YB5GQP2I5THG63CF6LS","target":"record","payload":{"canonical_record":{"source":{"id":"2404.03204","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2024-04-04T05:15:07Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG","cs.SD"],"title_canon_sha256":"bd0d30525091e04b8b688aaf90223ce5424e2e5e4709787e15dee59006b4e96e","abstract_canon_sha256":"12a344504aa40ebf5ce834e03cf51653ba43912885b99f5054f70e00b767a2db"},"schema_version":"1.0"},"canonical_sha256":"88701bfb980f4d07e91d99cded88be5ca6b33e74844ac0a98cf09249d245a829","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:20:28.875440Z","signature_b64":"e5gEoEXX6D4Syj0ZeZnmALHWKNM0t7aa/kuahOhsmNd4j/h0SMzKlflxkM4Dc8xwUzvWqtF+txKEZ+IqQfe9Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"88701bfb980f4d07e91d99cded88be5ca6b33e74844ac0a98cf09249d245a829","last_reissued_at":"2026-07-05T08:20:28.874910Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:20:28.874910Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.03204","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:20:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4P450Tgml1vTKbEjJPtztfyWooMkV2pqMYTQCrWdcSyrvC2VUQV8SuqKUJ65oLmuWY/JIdv9JVgNlY7BjnZ4Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T17:18:57.877930Z"},"content_sha256":"ac96c65da076efe2195152cd1571aa323c124a6a2fda0fa1a23b383559a19229","schema_version":"1.0","event_id":"sha256:ac96c65da076efe2195152cd1571aa323c124a6a2fda0fa1a23b383559a19229"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:RBYBX64YB5GQP2I5THG63CF6LS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RALL-E: Robust Codec Language Modeling with Chain-of-Thought Prompting for Text-to-Speech Synthesis","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Detai Xin, Dongchao Yang, Hiroshi Saruwatari, Jinyu Li, Kai Shen, Sheng Zhao, Shinnosuke Takamichi, Shujie Liu, Xu Tan, Yuancheng Wang, Zeqian Ju","submitted_at":"2024-04-04T05:15:07Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.03204","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2404.03204/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:20:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0wxyo9RzLllXBwwiiedhQevyq7f7UQ+9QTEKNpryjB5197WSZgycnI13fGdLPDVOW71f54cG17X/W85PSLWaAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T17:18:57.878377Z"},"content_sha256":"205d637845fcf6af37d0e5d6ec0f895c9b664d43255ce2090ccc3a1e270bde69","schema_version":"1.0","event_id":"sha256:205d637845fcf6af37d0e5d6ec0f895c9b664d43255ce2090ccc3a1e270bde69"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RBYBX64YB5GQP2I5THG63CF6LS/bundle.json","state_url":"https://pith.science/pith/RBYBX64YB5GQP2I5THG63CF6LS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RBYBX64YB5GQP2I5THG63CF6LS/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-06T17:18:57Z","links":{"resolver":"https://pith.science/pith/RBYBX64YB5GQP2I5THG63CF6LS","bundle":"https://pith.science/pith/RBYBX64YB5GQP2I5THG63CF6LS/bundle.json","state":"https://pith.science/pith/RBYBX64YB5GQP2I5THG63CF6LS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RBYBX64YB5GQP2I5THG63CF6LS/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Uj9QsOoWcRLTc1gjYbRSn9x/lkGRqBBACKJNhc8xRd4hKMUriY/5Jgs+dQS2a2zfuGuFlAeUCDEshvz+V6XuCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T17:18:57.880322Z","bundle_sha256":"bc9e2cd06ac9eeda94ed7b202f98bff4097a2830cde38ec3a805c41df5c7783b"}}