{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:7ECUHSTQ5CC2OAFLPAI46BRIJJ","short_pith_number":"pith:7ECUHSTQ","canonical_record":{"source":{"id":"2301.02111","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-01-05T15:37:15Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"a1340b691a4443c77f1c0332c41825a78b75b900e926a9f9704ff5264d99ce3b","abstract_canon_sha256":"03a250924891bee0c958f85be8ac59832fe3c73d9a42fbd31067a56154453a38"},"schema_version":"1.0"},"canonical_sha256":"f90543ca70e885a700ab7811cf06284a7f621375ed4090a5276cf0092a92ca56","source":{"kind":"arxiv","id":"2301.02111","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.02111","created_at":"2026-07-05T05:30:56Z"},{"alias_kind":"arxiv_version","alias_value":"2301.02111v1","created_at":"2026-07-05T05:30:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.02111","created_at":"2026-07-05T05:30:56Z"},{"alias_kind":"pith_short_12","alias_value":"7ECUHSTQ5CC2","created_at":"2026-07-05T05:30:56Z"},{"alias_kind":"pith_short_16","alias_value":"7ECUHSTQ5CC2OAFL","created_at":"2026-07-05T05:30:56Z"},{"alias_kind":"pith_short_8","alias_value":"7ECUHSTQ","created_at":"2026-07-05T05:30:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:7ECUHSTQ5CC2OAFLPAI46BRIJJ","target":"record","payload":{"canonical_record":{"source":{"id":"2301.02111","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-01-05T15:37:15Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"a1340b691a4443c77f1c0332c41825a78b75b900e926a9f9704ff5264d99ce3b","abstract_canon_sha256":"03a250924891bee0c958f85be8ac59832fe3c73d9a42fbd31067a56154453a38"},"schema_version":"1.0"},"canonical_sha256":"f90543ca70e885a700ab7811cf06284a7f621375ed4090a5276cf0092a92ca56","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:30:56.998833Z","signature_b64":"i7BZ5WXJiAee6lbIG2TYeJjnCIXDo/iG/UFUq/6o4Yf0/zmkmt4C+Rcaf5VJWmF9mOcTUEdTVTO3SVRF2xCxBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f90543ca70e885a700ab7811cf06284a7f621375ed4090a5276cf0092a92ca56","last_reissued_at":"2026-07-05T05:30:56.998394Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:30:56.998394Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2301.02111","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":"2026-07-05T05:30:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+GVCQjKxdQhpeYuifHBPaYe8AaRR9T3pt6AZg7l2jFjBxIRClUWVZRcrX3h46fjzHIt3vAXzx9CyjUwVdJf6Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T04:08:51.732248Z"},"content_sha256":"c8f0f649512f52f127f7c59b259456a123b59ea89caa0148d1fa208c5bfc3d2e","schema_version":"1.0","event_id":"sha256:c8f0f649512f52f127f7c59b259456a123b59ea89caa0148d1fa208c5bfc3d2e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:7ECUHSTQ5CC2OAFLPAI46BRIJJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Vall-E treats text-to-speech as conditional language modeling over discrete audio codes to enable zero-shot personalized synthesis from a 3-second prompt.","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Chengyi Wang, Furu Wei, Huaming Wang, Jinyu Li, Lei He, Long Zhou, Sanyuan Chen, Sheng Zhao, Shujie Liu, Yanqing Liu, Yu Wu, Zhuo Chen, Ziqiang Zhang","submitted_at":"2023-01-05T15:37:15Z","abstract_excerpt":"We introduce a language modeling approach for text to speech synthesis (TTS). Specifically, we train a neural codec language model (called Vall-E) using discrete codes derived from an off-the-shelf neural audio codec model, and regard TTS as a conditional language modeling task rather than continuous signal regression as in previous work. During the pre-training stage, we scale up the TTS training data to 60K hours of English speech which is hundreds of times larger than existing systems. Vall-E emerges in-context learning capabilities and can be used to synthesize high-quality personalized sp"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Vall-E emerges in-context learning capabilities and can be used to synthesize high-quality personalized speech with only a 3-second enrolled recording of an unseen speaker as an acoustic prompt. Experiment results show that Vall-E significantly outperforms the state-of-the-art zero-shot TTS system in terms of speech naturalness and speaker similarity.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the discrete codes produced by the off-the-shelf neural audio codec preserve sufficient acoustic detail (including speaker identity, emotion, and environment) for the language model to reconstruct high-fidelity, natural speech without additional continuous-signal modeling.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"VALL-E is a neural codec language model trained on 60K hours of speech that performs zero-shot TTS, synthesizing natural speech that matches an unseen speaker's voice, emotion, and environment from a 3-second prompt.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Vall-E treats text-to-speech as conditional language modeling over discrete audio codes to enable zero-shot personalized synthesis from a 3-second prompt.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"88c5495a18841cc5a6ad8f9e427b97989ac08049d67f3f7c6598f66c5f8ebb68"},"source":{"id":"2301.02111","kind":"arxiv","version":1},"verdict":{"id":"6a8fbd3e-c43b-4c4f-bad9-b64c74d15a47","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-13T01:25:48.445219Z","strongest_claim":"Vall-E emerges in-context learning capabilities and can be used to synthesize high-quality personalized speech with only a 3-second enrolled recording of an unseen speaker as an acoustic prompt. Experiment results show that Vall-E significantly outperforms the state-of-the-art zero-shot TTS system in terms of speech naturalness and speaker similarity.","one_line_summary":"VALL-E is a neural codec language model trained on 60K hours of speech that performs zero-shot TTS, synthesizing natural speech that matches an unseen speaker's voice, emotion, and environment from a 3-second prompt.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the discrete codes produced by the off-the-shelf neural audio codec preserve sufficient acoustic detail (including speaker identity, emotion, and environment) for the language model to reconstruct high-fidelity, natural speech without additional continuous-signal modeling.","pith_extraction_headline":"Vall-E treats text-to-speech as conditional language modeling over discrete audio codes to enable zero-shot personalized synthesis from a 3-second prompt."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2301.02111/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":20,"sample":[{"doi":"","year":null,"title":"The Emotional Voices Database: Towards Controlling the Emotion Dimension in Voice Generation Systems","work_id":"f30e2dab-601f-4b23-bce0-3f345bf9a7ed","ref_index":1,"cited_arxiv_id":"1806.09514","is_internal_anchor":false},{"doi":"","year":2022,"title":"vq-wav2vec: Self-supervised learning of discrete speech representations","work_id":"974b1627-21a5-4214-bd57-d811b750abec","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Audiolm: a language modeling approach to audio generation","work_id":"3a2aea1c-8117-4436-9100-0536aea3cf47","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2018,"title":"Exploring the encoding layer and loss function in end- to-end speaker and language recognition system","work_id":"87172dc5-43ad-40c6-b5e8-90d622c31ceb","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"PaLM: Scaling Language Modeling with Pathways","work_id":"a94f3ef7-2c49-4445-93fe-6ec16aafd966","ref_index":5,"cited_arxiv_id":"2204.02311","is_internal_anchor":true}],"resolved_work":20,"snapshot_sha256":"d095e12259d6e8c1ef58555e115c9c34e7d112bff2cb32aebabee493d65ee6a3","internal_anchors":3},"formal_canon":{"evidence_count":2,"snapshot_sha256":"0ae7729f0f13dba7cd2370318bcc73e9949b5dae90ea5321a06585f864c5bb0a"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"6a8fbd3e-c43b-4c4f-bad9-b64c74d15a47"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:30:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L54aiSPjZH5xdrXJCnTQoJnOj/TuXvLhUGjotSnWgq8NI8tjY5/pJo3Duyoy7f+Hvjx+AwKQIcOrm5ALWnj5Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T04:08:51.733137Z"},"content_sha256":"0e035f83c9fe750d1b100eee69b57a66d1615f4532e17e5788cbcba8fdd4c1da","schema_version":"1.0","event_id":"sha256:0e035f83c9fe750d1b100eee69b57a66d1615f4532e17e5788cbcba8fdd4c1da"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7ECUHSTQ5CC2OAFLPAI46BRIJJ/bundle.json","state_url":"https://pith.science/pith/7ECUHSTQ5CC2OAFLPAI46BRIJJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7ECUHSTQ5CC2OAFLPAI46BRIJJ/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":"2026-08-08T04:08:51Z","links":{"resolver":"https://pith.science/pith/7ECUHSTQ5CC2OAFLPAI46BRIJJ","bundle":"https://pith.science/pith/7ECUHSTQ5CC2OAFLPAI46BRIJJ/bundle.json","state":"https://pith.science/pith/7ECUHSTQ5CC2OAFLPAI46BRIJJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7ECUHSTQ5CC2OAFLPAI46BRIJJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:7ECUHSTQ5CC2OAFLPAI46BRIJJ","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":"03a250924891bee0c958f85be8ac59832fe3c73d9a42fbd31067a56154453a38","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-01-05T15:37:15Z","title_canon_sha256":"a1340b691a4443c77f1c0332c41825a78b75b900e926a9f9704ff5264d99ce3b"},"schema_version":"1.0","source":{"id":"2301.02111","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.02111","created_at":"2026-07-05T05:30:56Z"},{"alias_kind":"arxiv_version","alias_value":"2301.02111v1","created_at":"2026-07-05T05:30:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.02111","created_at":"2026-07-05T05:30:56Z"},{"alias_kind":"pith_short_12","alias_value":"7ECUHSTQ5CC2","created_at":"2026-07-05T05:30:56Z"},{"alias_kind":"pith_short_16","alias_value":"7ECUHSTQ5CC2OAFL","created_at":"2026-07-05T05:30:56Z"},{"alias_kind":"pith_short_8","alias_value":"7ECUHSTQ","created_at":"2026-07-05T05:30:56Z"}],"graph_snapshots":[{"event_id":"sha256:0e035f83c9fe750d1b100eee69b57a66d1615f4532e17e5788cbcba8fdd4c1da","target":"graph","created_at":"2026-07-05T05:30:56Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Vall-E emerges in-context learning capabilities and can be used to synthesize high-quality personalized speech with only a 3-second enrolled recording of an unseen speaker as an acoustic prompt. Experiment results show that Vall-E significantly outperforms the state-of-the-art zero-shot TTS system in terms of speech naturalness and speaker similarity."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the discrete codes produced by the off-the-shelf neural audio codec preserve sufficient acoustic detail (including speaker identity, emotion, and environment) for the language model to reconstruct high-fidelity, natural speech without additional continuous-signal modeling."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"VALL-E is a neural codec language model trained on 60K hours of speech that performs zero-shot TTS, synthesizing natural speech that matches an unseen speaker's voice, emotion, and environment from a 3-second prompt."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Vall-E treats text-to-speech as conditional language modeling over discrete audio codes to enable zero-shot personalized synthesis from a 3-second prompt."}],"snapshot_sha256":"88c5495a18841cc5a6ad8f9e427b97989ac08049d67f3f7c6598f66c5f8ebb68"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"0ae7729f0f13dba7cd2370318bcc73e9949b5dae90ea5321a06585f864c5bb0a"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2301.02111/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce a language modeling approach for text to speech synthesis (TTS). Specifically, we train a neural codec language model (called Vall-E) using discrete codes derived from an off-the-shelf neural audio codec model, and regard TTS as a conditional language modeling task rather than continuous signal regression as in previous work. During the pre-training stage, we scale up the TTS training data to 60K hours of English speech which is hundreds of times larger than existing systems. Vall-E emerges in-context learning capabilities and can be used to synthesize high-quality personalized sp","authors_text":"Chengyi Wang, Furu Wei, Huaming Wang, Jinyu Li, Lei He, Long Zhou, Sanyuan Chen, Sheng Zhao, Shujie Liu, Yanqing Liu, Yu Wu, Zhuo Chen, Ziqiang Zhang","cross_cats":["cs.SD","eess.AS"],"headline":"Vall-E treats text-to-speech as conditional language modeling over discrete audio codes to enable zero-shot personalized synthesis from a 3-second prompt.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-01-05T15:37:15Z","title":"Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers"},"references":{"count":20,"internal_anchors":3,"resolved_work":20,"sample":[{"cited_arxiv_id":"1806.09514","doi":"","is_internal_anchor":false,"ref_index":1,"title":"The Emotional Voices Database: Towards Controlling the Emotion Dimension in Voice Generation Systems","work_id":"f30e2dab-601f-4b23-bce0-3f345bf9a7ed","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"vq-wav2vec: Self-supervised learning of discrete speech representations","work_id":"974b1627-21a5-4214-bd57-d811b750abec","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Audiolm: a language modeling approach to audio generation","work_id":"3a2aea1c-8117-4436-9100-0536aea3cf47","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Exploring the encoding layer and loss function in end- to-end speaker and language recognition system","work_id":"87172dc5-43ad-40c6-b5e8-90d622c31ceb","year":2018},{"cited_arxiv_id":"2204.02311","doi":"","is_internal_anchor":true,"ref_index":5,"title":"PaLM: Scaling Language Modeling with Pathways","work_id":"a94f3ef7-2c49-4445-93fe-6ec16aafd966","year":null}],"snapshot_sha256":"d095e12259d6e8c1ef58555e115c9c34e7d112bff2cb32aebabee493d65ee6a3"},"source":{"id":"2301.02111","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-13T01:25:48.445219Z","id":"6a8fbd3e-c43b-4c4f-bad9-b64c74d15a47","model_set":{"reader":"grok-4.3"},"one_line_summary":"VALL-E is a neural codec language model trained on 60K hours of speech that performs zero-shot TTS, synthesizing natural speech that matches an unseen speaker's voice, emotion, and environment from a 3-second prompt.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Vall-E treats text-to-speech as conditional language modeling over discrete audio codes to enable zero-shot personalized synthesis from a 3-second prompt.","strongest_claim":"Vall-E emerges in-context learning capabilities and can be used to synthesize high-quality personalized speech with only a 3-second enrolled recording of an unseen speaker as an acoustic prompt. Experiment results show that Vall-E significantly outperforms the state-of-the-art zero-shot TTS system in terms of speech naturalness and speaker similarity.","weakest_assumption":"That the discrete codes produced by the off-the-shelf neural audio codec preserve sufficient acoustic detail (including speaker identity, emotion, and environment) for the language model to reconstruct high-fidelity, natural speech without additional continuous-signal modeling."}},"verdict_id":"6a8fbd3e-c43b-4c4f-bad9-b64c74d15a47"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c8f0f649512f52f127f7c59b259456a123b59ea89caa0148d1fa208c5bfc3d2e","target":"record","created_at":"2026-07-05T05:30:56Z","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":"03a250924891bee0c958f85be8ac59832fe3c73d9a42fbd31067a56154453a38","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-01-05T15:37:15Z","title_canon_sha256":"a1340b691a4443c77f1c0332c41825a78b75b900e926a9f9704ff5264d99ce3b"},"schema_version":"1.0","source":{"id":"2301.02111","kind":"arxiv","version":1}},"canonical_sha256":"f90543ca70e885a700ab7811cf06284a7f621375ed4090a5276cf0092a92ca56","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f90543ca70e885a700ab7811cf06284a7f621375ed4090a5276cf0092a92ca56","first_computed_at":"2026-07-05T05:30:56.998394Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:30:56.998394Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"i7BZ5WXJiAee6lbIG2TYeJjnCIXDo/iG/UFUq/6o4Yf0/zmkmt4C+Rcaf5VJWmF9mOcTUEdTVTO3SVRF2xCxBg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:30:56.998833Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.02111","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c8f0f649512f52f127f7c59b259456a123b59ea89caa0148d1fa208c5bfc3d2e","sha256:0e035f83c9fe750d1b100eee69b57a66d1615f4532e17e5788cbcba8fdd4c1da"],"state_sha256":"c8dfe97c5cd29ca7e8c5ed20f0207e5b06bb733fd9073b6aabfc49c2186ba1f2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lUMEtxLAQFAxuYuG4vKAoHdy7jq4n4MMsk1KVOkrbrzcrS7hBQZXy4L62c+yoZzr/gPjUcMQQPGLIOZh4O+GCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T04:08:51.738817Z","bundle_sha256":"f3bdefb6e5ad9d2a19477eaec7308f7f1aba20db022846dad8d9cc943a68d3cc"}}