{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:7GYXLXVCKMHTI77UVSPVOFS5UD","short_pith_number":"pith:7GYXLXVC","canonical_record":{"source":{"id":"2406.07855","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-12T04:09:44Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"5c9b682b567e23af8700b63aac4edc9f7625671f0824eb66ec789e50d4c2fd5d","abstract_canon_sha256":"e710f8bd7d605dde2f1c9f63abbc15c53d9719e0b10d7ad028f24f810caa6ae0"},"schema_version":"1.0"},"canonical_sha256":"f9b175dea2530f347ff4ac9f57165da0c6926b79cd22002d46bfb655d4fef580","source":{"kind":"arxiv","id":"2406.07855","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.07855","created_at":"2026-07-05T08:30:39Z"},{"alias_kind":"arxiv_version","alias_value":"2406.07855v1","created_at":"2026-07-05T08:30:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.07855","created_at":"2026-07-05T08:30:39Z"},{"alias_kind":"pith_short_12","alias_value":"7GYXLXVCKMHT","created_at":"2026-07-05T08:30:39Z"},{"alias_kind":"pith_short_16","alias_value":"7GYXLXVCKMHTI77U","created_at":"2026-07-05T08:30:39Z"},{"alias_kind":"pith_short_8","alias_value":"7GYXLXVC","created_at":"2026-07-05T08:30:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:7GYXLXVCKMHTI77UVSPVOFS5UD","target":"record","payload":{"canonical_record":{"source":{"id":"2406.07855","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-12T04:09:44Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"5c9b682b567e23af8700b63aac4edc9f7625671f0824eb66ec789e50d4c2fd5d","abstract_canon_sha256":"e710f8bd7d605dde2f1c9f63abbc15c53d9719e0b10d7ad028f24f810caa6ae0"},"schema_version":"1.0"},"canonical_sha256":"f9b175dea2530f347ff4ac9f57165da0c6926b79cd22002d46bfb655d4fef580","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:30:39.542221Z","signature_b64":"lytlT3uT+WrDGye0I4SttuFKK0GNsUmmaE/uY9BazCJKDEqfBxFKar7ilxmiLbuErn1J1LF011TFTLmVi3U+DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f9b175dea2530f347ff4ac9f57165da0c6926b79cd22002d46bfb655d4fef580","last_reissued_at":"2026-07-05T08:30:39.541717Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:30:39.541717Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.07855","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:30:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Aswz1Nq0ET83MbQk2O/+F3CoeNFT+28w5+Gw5GZxNshDzGdId9Z7WULC3PjIWK0FQldPnWyaEZ+e3bVIrrE5DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T04:37:11.423699Z"},"content_sha256":"a0b31c6b9fa670d5062fdac357e6871473e9d95536ecad51571dda74b874afc6","schema_version":"1.0","event_id":"sha256:a0b31c6b9fa670d5062fdac357e6871473e9d95536ecad51571dda74b874afc6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:7GYXLXVCKMHTI77UVSPVOFS5UD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VALL-E R: Robust and Efficient Zero-Shot Text-to-Speech Synthesis via Monotonic Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Bing Han, Furu Wei, Jinyu Li, Lingwei Meng, Long Zhou, Sanyuan Chen, Sheng Zhao, Shujie Liu, Yanming Qian, Yanqing Liu","submitted_at":"2024-06-12T04:09:44Z","abstract_excerpt":"With the help of discrete neural audio codecs, large language models (LLM) have increasingly been recognized as a promising methodology for zero-shot Text-to-Speech (TTS) synthesis. However, sampling based decoding strategies bring astonishing diversity to generation, but also pose robustness issues such as typos, omissions and repetition. In addition, the high sampling rate of audio also brings huge computational overhead to the inference process of autoregression. To address these issues, we propose VALL-E R, a robust and efficient zero-shot TTS system, building upon the foundation of VALL-E"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.07855","kind":"arxiv","version":1},"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/2406.07855/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":"2026-07-05T08:30:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dnx6/rnHZqUf5l8FYfYy9sNKGR/yfhFLALWgtfbVM7p4Puy7xrZ9JgUWnUbNWV7ai2V8LVjX1/+tPsC5jEX0CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T04:37:11.424286Z"},"content_sha256":"bdb550a2b589841abf74f017d116bbcb04f16c956c7d9c52b58b205c22beaed9","schema_version":"1.0","event_id":"sha256:bdb550a2b589841abf74f017d116bbcb04f16c956c7d9c52b58b205c22beaed9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7GYXLXVCKMHTI77UVSPVOFS5UD/bundle.json","state_url":"https://pith.science/pith/7GYXLXVCKMHTI77UVSPVOFS5UD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7GYXLXVCKMHTI77UVSPVOFS5UD/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":"2026-08-05T04:37:11Z","links":{"resolver":"https://pith.science/pith/7GYXLXVCKMHTI77UVSPVOFS5UD","bundle":"https://pith.science/pith/7GYXLXVCKMHTI77UVSPVOFS5UD/bundle.json","state":"https://pith.science/pith/7GYXLXVCKMHTI77UVSPVOFS5UD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7GYXLXVCKMHTI77UVSPVOFS5UD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7GYXLXVCKMHTI77UVSPVOFS5UD","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":"e710f8bd7d605dde2f1c9f63abbc15c53d9719e0b10d7ad028f24f810caa6ae0","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-12T04:09:44Z","title_canon_sha256":"5c9b682b567e23af8700b63aac4edc9f7625671f0824eb66ec789e50d4c2fd5d"},"schema_version":"1.0","source":{"id":"2406.07855","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.07855","created_at":"2026-07-05T08:30:39Z"},{"alias_kind":"arxiv_version","alias_value":"2406.07855v1","created_at":"2026-07-05T08:30:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.07855","created_at":"2026-07-05T08:30:39Z"},{"alias_kind":"pith_short_12","alias_value":"7GYXLXVCKMHT","created_at":"2026-07-05T08:30:39Z"},{"alias_kind":"pith_short_16","alias_value":"7GYXLXVCKMHTI77U","created_at":"2026-07-05T08:30:39Z"},{"alias_kind":"pith_short_8","alias_value":"7GYXLXVC","created_at":"2026-07-05T08:30:39Z"}],"graph_snapshots":[{"event_id":"sha256:bdb550a2b589841abf74f017d116bbcb04f16c956c7d9c52b58b205c22beaed9","target":"graph","created_at":"2026-07-05T08:30:39Z","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/2406.07855/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the help of discrete neural audio codecs, large language models (LLM) have increasingly been recognized as a promising methodology for zero-shot Text-to-Speech (TTS) synthesis. However, sampling based decoding strategies bring astonishing diversity to generation, but also pose robustness issues such as typos, omissions and repetition. In addition, the high sampling rate of audio also brings huge computational overhead to the inference process of autoregression. To address these issues, we propose VALL-E R, a robust and efficient zero-shot TTS system, building upon the foundation of VALL-E","authors_text":"Bing Han, Furu Wei, Jinyu Li, Lingwei Meng, Long Zhou, Sanyuan Chen, Sheng Zhao, Shujie Liu, Yanming Qian, Yanqing Liu","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-12T04:09:44Z","title":"VALL-E R: Robust and Efficient Zero-Shot Text-to-Speech Synthesis via Monotonic Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.07855","kind":"arxiv","version":1},"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:a0b31c6b9fa670d5062fdac357e6871473e9d95536ecad51571dda74b874afc6","target":"record","created_at":"2026-07-05T08:30:39Z","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":"e710f8bd7d605dde2f1c9f63abbc15c53d9719e0b10d7ad028f24f810caa6ae0","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-12T04:09:44Z","title_canon_sha256":"5c9b682b567e23af8700b63aac4edc9f7625671f0824eb66ec789e50d4c2fd5d"},"schema_version":"1.0","source":{"id":"2406.07855","kind":"arxiv","version":1}},"canonical_sha256":"f9b175dea2530f347ff4ac9f57165da0c6926b79cd22002d46bfb655d4fef580","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f9b175dea2530f347ff4ac9f57165da0c6926b79cd22002d46bfb655d4fef580","first_computed_at":"2026-07-05T08:30:39.541717Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:30:39.541717Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lytlT3uT+WrDGye0I4SttuFKK0GNsUmmaE/uY9BazCJKDEqfBxFKar7ilxmiLbuErn1J1LF011TFTLmVi3U+DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:30:39.542221Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.07855","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a0b31c6b9fa670d5062fdac357e6871473e9d95536ecad51571dda74b874afc6","sha256:bdb550a2b589841abf74f017d116bbcb04f16c956c7d9c52b58b205c22beaed9"],"state_sha256":"35b85d4014066beced53477b51626cea3dd8262413c792a17be51f4f49d663b0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cKyIDzuqgIHnlnSD+A6l8qx7d2sH4QGbylNnSWrV2y/s7B/lpJr4owdlmMtnXCJUyyEEOy42demdN70cCzl9DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T04:37:11.429473Z","bundle_sha256":"a927d3a15ada34cd254b3a3f315ed090578467433b4aa637a05287a450eb9714"}}