{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:KYN77HD5I7GCCUFI4ZDCFHKSVO","short_pith_number":"pith:KYN77HD5","canonical_record":{"source":{"id":"2406.05370","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-08T06:31:03Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"5c10f188e87563a3e6466f949a077983a495929600773485f6861524f7f096ec","abstract_canon_sha256":"f44e08f55e704d9a5b4a47025e8f7b5786372de36925eeb9eac259751fe30988"},"schema_version":"1.0"},"canonical_sha256":"561bff9c7d47cc2150a8e646229d52ab96a7fa2f0d81f8e7e7d2d40053af0c08","source":{"kind":"arxiv","id":"2406.05370","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.05370","created_at":"2026-07-05T08:32:41Z"},{"alias_kind":"arxiv_version","alias_value":"2406.05370v2","created_at":"2026-07-05T08:32:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.05370","created_at":"2026-07-05T08:32:41Z"},{"alias_kind":"pith_short_12","alias_value":"KYN77HD5I7GC","created_at":"2026-07-05T08:32:41Z"},{"alias_kind":"pith_short_16","alias_value":"KYN77HD5I7GCCUFI","created_at":"2026-07-05T08:32:41Z"},{"alias_kind":"pith_short_8","alias_value":"KYN77HD5","created_at":"2026-07-05T08:32:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:KYN77HD5I7GCCUFI4ZDCFHKSVO","target":"record","payload":{"canonical_record":{"source":{"id":"2406.05370","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-08T06:31:03Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"5c10f188e87563a3e6466f949a077983a495929600773485f6861524f7f096ec","abstract_canon_sha256":"f44e08f55e704d9a5b4a47025e8f7b5786372de36925eeb9eac259751fe30988"},"schema_version":"1.0"},"canonical_sha256":"561bff9c7d47cc2150a8e646229d52ab96a7fa2f0d81f8e7e7d2d40053af0c08","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:41.932715Z","signature_b64":"Vry+6p9+keI2GrPf8D8tLwt6TOXAj1ZDlJVtWE5l32ihDTpxqtBbCVQJaA/UeO7kxTL4pMGnb0Xg4TgfHCP7BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"561bff9c7d47cc2150a8e646229d52ab96a7fa2f0d81f8e7e7d2d40053af0c08","last_reissued_at":"2026-07-05T08:32:41.932187Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:41.932187Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.05370","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:32:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/AFujLqOuW8hrvE2KMo7kycNEQ3EdRkHtXZJ0Vd/ilYEd7VNrR3NYSKwy29OMJrXgede2zmKg+VSX729AvDiBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T21:38:45.362187Z"},"content_sha256":"63837186a93ab3409a3be26ae3d67298cea3e055504b97afdd9c5dde975884aa","schema_version":"1.0","event_id":"sha256:63837186a93ab3409a3be26ae3d67298cea3e055504b97afdd9c5dde975884aa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:KYN77HD5I7GCCUFI4ZDCFHKSVO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VALL-E 2: Neural Codec Language Models are Human Parity Zero-Shot Text to Speech Synthesizers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Furu Wei, Jinyu Li, Long Zhou, Sanyuan Chen, Sheng Zhao, Shujie Liu, Xu Tan, Yanqing Liu, Yao Qian","submitted_at":"2024-06-08T06:31:03Z","abstract_excerpt":"This paper introduces VALL-E 2, the latest advancement in neural codec language models that marks a milestone in zero-shot text-to-speech synthesis (TTS), achieving human parity for the first time. Based on its predecessor, VALL-E, the new iteration introduces two significant enhancements: Repetition Aware Sampling refines the original nucleus sampling process by accounting for token repetition in the decoding history. It not only stabilizes the decoding but also circumvents the infinite loop issue. Grouped Code Modeling organizes codec codes into groups to effectively shorten the sequence len"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.05370","kind":"arxiv","version":2},"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/2406.05370/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":"2026-07-05T08:32:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eZxqhmWwyu9bUzsRlMgKKDeCkYgAB/dhh9ftZpUSuPnnXb0kT6T/epfdsiGfv0GPBozNONeuAviehR2mAukTDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T21:38:45.362811Z"},"content_sha256":"a97fef717d28414926eae54cf30e70d0946c1cc47cc481533760b46c5aa2e26b","schema_version":"1.0","event_id":"sha256:a97fef717d28414926eae54cf30e70d0946c1cc47cc481533760b46c5aa2e26b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KYN77HD5I7GCCUFI4ZDCFHKSVO/bundle.json","state_url":"https://pith.science/pith/KYN77HD5I7GCCUFI4ZDCFHKSVO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KYN77HD5I7GCCUFI4ZDCFHKSVO/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":"2026-08-04T21:38:45Z","links":{"resolver":"https://pith.science/pith/KYN77HD5I7GCCUFI4ZDCFHKSVO","bundle":"https://pith.science/pith/KYN77HD5I7GCCUFI4ZDCFHKSVO/bundle.json","state":"https://pith.science/pith/KYN77HD5I7GCCUFI4ZDCFHKSVO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KYN77HD5I7GCCUFI4ZDCFHKSVO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KYN77HD5I7GCCUFI4ZDCFHKSVO","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":"f44e08f55e704d9a5b4a47025e8f7b5786372de36925eeb9eac259751fe30988","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-08T06:31:03Z","title_canon_sha256":"5c10f188e87563a3e6466f949a077983a495929600773485f6861524f7f096ec"},"schema_version":"1.0","source":{"id":"2406.05370","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.05370","created_at":"2026-07-05T08:32:41Z"},{"alias_kind":"arxiv_version","alias_value":"2406.05370v2","created_at":"2026-07-05T08:32:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.05370","created_at":"2026-07-05T08:32:41Z"},{"alias_kind":"pith_short_12","alias_value":"KYN77HD5I7GC","created_at":"2026-07-05T08:32:41Z"},{"alias_kind":"pith_short_16","alias_value":"KYN77HD5I7GCCUFI","created_at":"2026-07-05T08:32:41Z"},{"alias_kind":"pith_short_8","alias_value":"KYN77HD5","created_at":"2026-07-05T08:32:41Z"}],"graph_snapshots":[{"event_id":"sha256:a97fef717d28414926eae54cf30e70d0946c1cc47cc481533760b46c5aa2e26b","target":"graph","created_at":"2026-07-05T08:32:41Z","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/2406.05370/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper introduces VALL-E 2, the latest advancement in neural codec language models that marks a milestone in zero-shot text-to-speech synthesis (TTS), achieving human parity for the first time. Based on its predecessor, VALL-E, the new iteration introduces two significant enhancements: Repetition Aware Sampling refines the original nucleus sampling process by accounting for token repetition in the decoding history. It not only stabilizes the decoding but also circumvents the infinite loop issue. Grouped Code Modeling organizes codec codes into groups to effectively shorten the sequence len","authors_text":"Furu Wei, Jinyu Li, Long Zhou, Sanyuan Chen, Sheng Zhao, Shujie Liu, Xu Tan, Yanqing Liu, Yao Qian","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-08T06:31:03Z","title":"VALL-E 2: Neural Codec Language Models are Human Parity Zero-Shot Text to Speech Synthesizers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.05370","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":"sha256:63837186a93ab3409a3be26ae3d67298cea3e055504b97afdd9c5dde975884aa","target":"record","created_at":"2026-07-05T08:32:41Z","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":"f44e08f55e704d9a5b4a47025e8f7b5786372de36925eeb9eac259751fe30988","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-08T06:31:03Z","title_canon_sha256":"5c10f188e87563a3e6466f949a077983a495929600773485f6861524f7f096ec"},"schema_version":"1.0","source":{"id":"2406.05370","kind":"arxiv","version":2}},"canonical_sha256":"561bff9c7d47cc2150a8e646229d52ab96a7fa2f0d81f8e7e7d2d40053af0c08","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"561bff9c7d47cc2150a8e646229d52ab96a7fa2f0d81f8e7e7d2d40053af0c08","first_computed_at":"2026-07-05T08:32:41.932187Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:32:41.932187Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Vry+6p9+keI2GrPf8D8tLwt6TOXAj1ZDlJVtWE5l32ihDTpxqtBbCVQJaA/UeO7kxTL4pMGnb0Xg4TgfHCP7BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:32:41.932715Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.05370","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:63837186a93ab3409a3be26ae3d67298cea3e055504b97afdd9c5dde975884aa","sha256:a97fef717d28414926eae54cf30e70d0946c1cc47cc481533760b46c5aa2e26b"],"state_sha256":"30e04e35859c50a1d2fa9eaba03de0ffab252b779d5e4c1f8b998e1ae0c388c4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DtXMbU64bbDjkVamq2hvHwOVa9awGTOqJR+B4Gp0MB+SPnI97AvQ4AhIxU6pmnHqK4wr1tONTUVtkHMBEb72Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T21:38:45.368140Z","bundle_sha256":"f55b683da9d0a8215521b9d0322cd1da912bba9a1c3021e197d1abd6a3fa926b"}}