{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:6HBJCMO7Z4R5BKQILH25HMRPRM","short_pith_number":"pith:6HBJCMO7","canonical_record":{"source":{"id":"2408.15676","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-08-28T09:57:17Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"d1ead333f233e08ba33609ad48a9a5d4e6b4043c1eaf243cb9fcae8d29de8ea8","abstract_canon_sha256":"79e5bb3e8a28e8f3b0ab9a2bc500a227ff9c6560ec0d13935137b118b2bed16c"},"schema_version":"1.0"},"canonical_sha256":"f1c29131dfcf23d0aa0859f5d3b22f8b2d8b1da1e570cbf1d9b501f09d0d94d2","source":{"kind":"arxiv","id":"2408.15676","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.15676","created_at":"2026-07-05T09:00:15Z"},{"alias_kind":"arxiv_version","alias_value":"2408.15676v1","created_at":"2026-07-05T09:00:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.15676","created_at":"2026-07-05T09:00:15Z"},{"alias_kind":"pith_short_12","alias_value":"6HBJCMO7Z4R5","created_at":"2026-07-05T09:00:15Z"},{"alias_kind":"pith_short_16","alias_value":"6HBJCMO7Z4R5BKQI","created_at":"2026-07-05T09:00:15Z"},{"alias_kind":"pith_short_8","alias_value":"6HBJCMO7","created_at":"2026-07-05T09:00:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:6HBJCMO7Z4R5BKQILH25HMRPRM","target":"record","payload":{"canonical_record":{"source":{"id":"2408.15676","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-08-28T09:57:17Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"d1ead333f233e08ba33609ad48a9a5d4e6b4043c1eaf243cb9fcae8d29de8ea8","abstract_canon_sha256":"79e5bb3e8a28e8f3b0ab9a2bc500a227ff9c6560ec0d13935137b118b2bed16c"},"schema_version":"1.0"},"canonical_sha256":"f1c29131dfcf23d0aa0859f5d3b22f8b2d8b1da1e570cbf1d9b501f09d0d94d2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:00:15.615271Z","signature_b64":"B0E3pLi3O131UnBOvQ4iFzEZ+JatnJIbAsBdwDn1+ZkhIQZrZWJnabQFR1d4NS7etVK6Xdb+13pLEdKNtWrxCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f1c29131dfcf23d0aa0859f5d3b22f8b2d8b1da1e570cbf1d9b501f09d0d94d2","last_reissued_at":"2026-07-05T09:00:15.614765Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:00:15.614765Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.15676","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":"2026-07-05T09:00:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HQ98hGI5O8iBaqbRBqHIUMPU8o9V5ourc303cevswltBh1OIAudvUUu3g+WWAel6JYI/NDIM6lSRkYL/Gzg6CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-20T15:23:22.461308Z"},"content_sha256":"e50aa2da5249b576bec15af419acd748cc17ad185618e44c926039219643544f","schema_version":"1.0","event_id":"sha256:e50aa2da5249b576bec15af419acd748cc17ad185618e44c926039219643544f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:6HBJCMO7Z4R5BKQILH25HMRPRM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VoxInstruct: Expressive Human Instruction-to-Speech Generation with Unified Multilingual Codec Language Modelling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Jia Jia, Shun Lei, Shuoyi Zhou, Songtao Zhou, Xiaoyu Qin, Yixuan Zhou, Zeyu Jin, Zhiyong Wu","submitted_at":"2024-08-28T09:57:17Z","abstract_excerpt":"Recent AIGC systems possess the capability to generate digital multimedia content based on human language instructions, such as text, image and video. However, when it comes to speech, existing methods related to human instruction-to-speech generation exhibit two limitations. Firstly, they require the division of inputs into content prompt (transcript) and description prompt (style and speaker), instead of directly supporting human instruction. This division is less natural in form and does not align with other AIGC models. Secondly, the practice of utilizing an independent description prompt "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.15676","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/2408.15676/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":"2026-07-05T09:00:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XqL21b9pvknJP85nAEXwNZ7nIUcSqy89nWs7ddpJrZTS5mRi2D//UkilbQoh6nA3iwktbRrhDklGOKkcP3J+AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-20T15:23:22.461702Z"},"content_sha256":"cb711ea8e72bd1bc56af07732520df38af1788bebd9692f89043890ddb547fa6","schema_version":"1.0","event_id":"sha256:cb711ea8e72bd1bc56af07732520df38af1788bebd9692f89043890ddb547fa6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6HBJCMO7Z4R5BKQILH25HMRPRM/bundle.json","state_url":"https://pith.science/pith/6HBJCMO7Z4R5BKQILH25HMRPRM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6HBJCMO7Z4R5BKQILH25HMRPRM/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":"2026-07-20T15:23:22Z","links":{"resolver":"https://pith.science/pith/6HBJCMO7Z4R5BKQILH25HMRPRM","bundle":"https://pith.science/pith/6HBJCMO7Z4R5BKQILH25HMRPRM/bundle.json","state":"https://pith.science/pith/6HBJCMO7Z4R5BKQILH25HMRPRM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6HBJCMO7Z4R5BKQILH25HMRPRM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6HBJCMO7Z4R5BKQILH25HMRPRM","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":"79e5bb3e8a28e8f3b0ab9a2bc500a227ff9c6560ec0d13935137b118b2bed16c","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-08-28T09:57:17Z","title_canon_sha256":"d1ead333f233e08ba33609ad48a9a5d4e6b4043c1eaf243cb9fcae8d29de8ea8"},"schema_version":"1.0","source":{"id":"2408.15676","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.15676","created_at":"2026-07-05T09:00:15Z"},{"alias_kind":"arxiv_version","alias_value":"2408.15676v1","created_at":"2026-07-05T09:00:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.15676","created_at":"2026-07-05T09:00:15Z"},{"alias_kind":"pith_short_12","alias_value":"6HBJCMO7Z4R5","created_at":"2026-07-05T09:00:15Z"},{"alias_kind":"pith_short_16","alias_value":"6HBJCMO7Z4R5BKQI","created_at":"2026-07-05T09:00:15Z"},{"alias_kind":"pith_short_8","alias_value":"6HBJCMO7","created_at":"2026-07-05T09:00:15Z"}],"graph_snapshots":[{"event_id":"sha256:cb711ea8e72bd1bc56af07732520df38af1788bebd9692f89043890ddb547fa6","target":"graph","created_at":"2026-07-05T09:00:15Z","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/2408.15676/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent AIGC systems possess the capability to generate digital multimedia content based on human language instructions, such as text, image and video. However, when it comes to speech, existing methods related to human instruction-to-speech generation exhibit two limitations. Firstly, they require the division of inputs into content prompt (transcript) and description prompt (style and speaker), instead of directly supporting human instruction. This division is less natural in form and does not align with other AIGC models. Secondly, the practice of utilizing an independent description prompt ","authors_text":"Jia Jia, Shun Lei, Shuoyi Zhou, Songtao Zhou, Xiaoyu Qin, Yixuan Zhou, Zeyu Jin, Zhiyong Wu","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-08-28T09:57:17Z","title":"VoxInstruct: Expressive Human Instruction-to-Speech Generation with Unified Multilingual Codec Language Modelling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.15676","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:e50aa2da5249b576bec15af419acd748cc17ad185618e44c926039219643544f","target":"record","created_at":"2026-07-05T09:00:15Z","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":"79e5bb3e8a28e8f3b0ab9a2bc500a227ff9c6560ec0d13935137b118b2bed16c","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-08-28T09:57:17Z","title_canon_sha256":"d1ead333f233e08ba33609ad48a9a5d4e6b4043c1eaf243cb9fcae8d29de8ea8"},"schema_version":"1.0","source":{"id":"2408.15676","kind":"arxiv","version":1}},"canonical_sha256":"f1c29131dfcf23d0aa0859f5d3b22f8b2d8b1da1e570cbf1d9b501f09d0d94d2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f1c29131dfcf23d0aa0859f5d3b22f8b2d8b1da1e570cbf1d9b501f09d0d94d2","first_computed_at":"2026-07-05T09:00:15.614765Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:00:15.614765Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"B0E3pLi3O131UnBOvQ4iFzEZ+JatnJIbAsBdwDn1+ZkhIQZrZWJnabQFR1d4NS7etVK6Xdb+13pLEdKNtWrxCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:00:15.615271Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.15676","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e50aa2da5249b576bec15af419acd748cc17ad185618e44c926039219643544f","sha256:cb711ea8e72bd1bc56af07732520df38af1788bebd9692f89043890ddb547fa6"],"state_sha256":"c3ec44dfab734737677980c17339b1c48d4be48d9c511a1da70d400493e0ce38"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BY3zyHlZBqvk8CcPW0WYA9mp8NcXilvIWPXFbFTQGOw1u1ce0cU/a/yxlEfmKnin1VB+kTmXK9Qem4vXgopYDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-20T15:23:22.466760Z","bundle_sha256":"9ebbfddd3f7519f4a07866f8de1138fab4ebb9beb2696ca834e3577acdf6af29"}}