{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:YKSBUN43CT6SHTRQU3KQ6A2VBN","short_pith_number":"pith:YKSBUN43","canonical_record":{"source":{"id":"2410.04380","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-10-06T07:20:58Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"1941c7c830dc772af6a76eda6a597db1f05f148322c1f52558b8861ab0af9531","abstract_canon_sha256":"1d722c476f08cf9395635eddde363f05589a4a218673e9b33f5048cef8debaa7"},"schema_version":"1.0"},"canonical_sha256":"c2a41a379b14fd23ce30a6d50f03550b61abb58755277b0b755cc90b0d828a3c","source":{"kind":"arxiv","id":"2410.04380","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.04380","created_at":"2026-07-05T09:18:30Z"},{"alias_kind":"arxiv_version","alias_value":"2410.04380v1","created_at":"2026-07-05T09:18:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.04380","created_at":"2026-07-05T09:18:30Z"},{"alias_kind":"pith_short_12","alias_value":"YKSBUN43CT6S","created_at":"2026-07-05T09:18:30Z"},{"alias_kind":"pith_short_16","alias_value":"YKSBUN43CT6SHTRQ","created_at":"2026-07-05T09:18:30Z"},{"alias_kind":"pith_short_8","alias_value":"YKSBUN43","created_at":"2026-07-05T09:18:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:YKSBUN43CT6SHTRQU3KQ6A2VBN","target":"record","payload":{"canonical_record":{"source":{"id":"2410.04380","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-10-06T07:20:58Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"1941c7c830dc772af6a76eda6a597db1f05f148322c1f52558b8861ab0af9531","abstract_canon_sha256":"1d722c476f08cf9395635eddde363f05589a4a218673e9b33f5048cef8debaa7"},"schema_version":"1.0"},"canonical_sha256":"c2a41a379b14fd23ce30a6d50f03550b61abb58755277b0b755cc90b0d828a3c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:18:30.893677Z","signature_b64":"rvzxyelL1MilT3ED6jZT3ddke25nb04dEtks9/rSyYzmrtqOWdjyB41OP6AB/HEn1Jg/sJ0kweN8Iylt4uvpCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c2a41a379b14fd23ce30a6d50f03550b61abb58755277b0b755cc90b0d828a3c","last_reissued_at":"2026-07-05T09:18:30.893275Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:18:30.893275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.04380","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":"2026-07-05T09:18:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MjFvPli6bpddMv+i/QXOEu3+JMixjs4K7EF59WGM9itwt2KIeg9gCITQRtUNX02wfdvxmZXPpQGz1v1ntRqiCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T17:26:34.897743Z"},"content_sha256":"f189e3ecb0fcdc0d11304d4f59f163dfe3c91ead9ff3eac498b8923d1f017ab5","schema_version":"1.0","event_id":"sha256:f189e3ecb0fcdc0d11304d4f59f163dfe3c91ead9ff3eac498b8923d1f017ab5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:YKSBUN43CT6SHTRQU3KQ6A2VBN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"HALL-E: Hierarchical Neural Codec Language Model for Minute-Long Zero-Shot Text-to-Speech Synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Hideki Nakayama, Masanari Ohi, Nakamasa Inoue, Takumi Hirose, Yuto Nishimura","submitted_at":"2024-10-06T07:20:58Z","abstract_excerpt":"Recently, Text-to-speech (TTS) models based on large language models (LLMs) that translate natural language text into sequences of discrete audio tokens have gained great research attention, with advances in neural audio codec (NAC) models using residual vector quantization (RVQ). However, long-form speech synthesis remains a significant challenge due to the high frame rate, which increases the length of audio tokens and makes it difficult for autoregressive language models to generate audio tokens for even a minute of speech. To address this challenge, this paper introduces two novel post-tra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.04380","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/2410.04380/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":"2026-07-05T09:18:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AhTP4xIttTDUUqIh0S8I06sYwuAq75LbYDcZkqK/BmuLYTCpcHGrzdLbr7D/04jfP2q+hCUMTN3ZFhbmonO+Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T17:26:34.898551Z"},"content_sha256":"d7adaf50c74713b427e341094197864e338f2cc4c7adad909b2bf7bc1bc8bcd8","schema_version":"1.0","event_id":"sha256:d7adaf50c74713b427e341094197864e338f2cc4c7adad909b2bf7bc1bc8bcd8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YKSBUN43CT6SHTRQU3KQ6A2VBN/bundle.json","state_url":"https://pith.science/pith/YKSBUN43CT6SHTRQU3KQ6A2VBN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YKSBUN43CT6SHTRQU3KQ6A2VBN/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":"2026-08-14T17:26:34Z","links":{"resolver":"https://pith.science/pith/YKSBUN43CT6SHTRQU3KQ6A2VBN","bundle":"https://pith.science/pith/YKSBUN43CT6SHTRQU3KQ6A2VBN/bundle.json","state":"https://pith.science/pith/YKSBUN43CT6SHTRQU3KQ6A2VBN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YKSBUN43CT6SHTRQU3KQ6A2VBN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YKSBUN43CT6SHTRQU3KQ6A2VBN","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":"1d722c476f08cf9395635eddde363f05589a4a218673e9b33f5048cef8debaa7","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-10-06T07:20:58Z","title_canon_sha256":"1941c7c830dc772af6a76eda6a597db1f05f148322c1f52558b8861ab0af9531"},"schema_version":"1.0","source":{"id":"2410.04380","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.04380","created_at":"2026-07-05T09:18:30Z"},{"alias_kind":"arxiv_version","alias_value":"2410.04380v1","created_at":"2026-07-05T09:18:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.04380","created_at":"2026-07-05T09:18:30Z"},{"alias_kind":"pith_short_12","alias_value":"YKSBUN43CT6S","created_at":"2026-07-05T09:18:30Z"},{"alias_kind":"pith_short_16","alias_value":"YKSBUN43CT6SHTRQ","created_at":"2026-07-05T09:18:30Z"},{"alias_kind":"pith_short_8","alias_value":"YKSBUN43","created_at":"2026-07-05T09:18:30Z"}],"graph_snapshots":[{"event_id":"sha256:d7adaf50c74713b427e341094197864e338f2cc4c7adad909b2bf7bc1bc8bcd8","target":"graph","created_at":"2026-07-05T09:18:30Z","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/2410.04380/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, Text-to-speech (TTS) models based on large language models (LLMs) that translate natural language text into sequences of discrete audio tokens have gained great research attention, with advances in neural audio codec (NAC) models using residual vector quantization (RVQ). However, long-form speech synthesis remains a significant challenge due to the high frame rate, which increases the length of audio tokens and makes it difficult for autoregressive language models to generate audio tokens for even a minute of speech. To address this challenge, this paper introduces two novel post-tra","authors_text":"Hideki Nakayama, Masanari Ohi, Nakamasa Inoue, Takumi Hirose, Yuto Nishimura","cross_cats":["cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-10-06T07:20:58Z","title":"HALL-E: Hierarchical Neural Codec Language Model for Minute-Long Zero-Shot Text-to-Speech Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.04380","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:f189e3ecb0fcdc0d11304d4f59f163dfe3c91ead9ff3eac498b8923d1f017ab5","target":"record","created_at":"2026-07-05T09:18:30Z","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":"1d722c476f08cf9395635eddde363f05589a4a218673e9b33f5048cef8debaa7","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-10-06T07:20:58Z","title_canon_sha256":"1941c7c830dc772af6a76eda6a597db1f05f148322c1f52558b8861ab0af9531"},"schema_version":"1.0","source":{"id":"2410.04380","kind":"arxiv","version":1}},"canonical_sha256":"c2a41a379b14fd23ce30a6d50f03550b61abb58755277b0b755cc90b0d828a3c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c2a41a379b14fd23ce30a6d50f03550b61abb58755277b0b755cc90b0d828a3c","first_computed_at":"2026-07-05T09:18:30.893275Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:18:30.893275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rvzxyelL1MilT3ED6jZT3ddke25nb04dEtks9/rSyYzmrtqOWdjyB41OP6AB/HEn1Jg/sJ0kweN8Iylt4uvpCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:18:30.893677Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.04380","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f189e3ecb0fcdc0d11304d4f59f163dfe3c91ead9ff3eac498b8923d1f017ab5","sha256:d7adaf50c74713b427e341094197864e338f2cc4c7adad909b2bf7bc1bc8bcd8"],"state_sha256":"d78734962e08095f577ad74a13a6a80f5069ce30cc086e9aca0edf4c4c0f2f17"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y/VCd/6Xw/0oNrI14jj4mPRqeEPEWCS8QopqvplEKHd202yaYDhFBYAsShgqZUwncxV0pbClmXaYEEWpQL2OCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T17:26:34.919591Z","bundle_sha256":"f69117676f60fcfe8ce38e16dcb217d487a60b29ed1a6e476f075675ce91deb1"}}