{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:PDTB4YC535A5EUGZMDW4VTAXFX","short_pith_number":"pith:PDTB4YC5","canonical_record":{"source":{"id":"2301.13662","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-01-31T14:26:52Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"8c39923defedd12ae1c75f9204baa060a67c7efcf6b32cd8f0f43c17edc06df7","abstract_canon_sha256":"a3d4216d13cd4e8502cf91f90dd641056a3fb7f97f12b9f02507e309e6c6d121"},"schema_version":"1.0"},"canonical_sha256":"78e61e605ddf41d250d960edcacc172deef6d27368159ad7ce5d78340e19e0f1","source":{"kind":"arxiv","id":"2301.13662","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.13662","created_at":"2026-07-05T06:24:27Z"},{"alias_kind":"arxiv_version","alias_value":"2301.13662v2","created_at":"2026-07-05T06:24:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.13662","created_at":"2026-07-05T06:24:27Z"},{"alias_kind":"pith_short_12","alias_value":"PDTB4YC535A5","created_at":"2026-07-05T06:24:27Z"},{"alias_kind":"pith_short_16","alias_value":"PDTB4YC535A5EUGZ","created_at":"2026-07-05T06:24:27Z"},{"alias_kind":"pith_short_8","alias_value":"PDTB4YC5","created_at":"2026-07-05T06:24:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:PDTB4YC535A5EUGZMDW4VTAXFX","target":"record","payload":{"canonical_record":{"source":{"id":"2301.13662","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-01-31T14:26:52Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"8c39923defedd12ae1c75f9204baa060a67c7efcf6b32cd8f0f43c17edc06df7","abstract_canon_sha256":"a3d4216d13cd4e8502cf91f90dd641056a3fb7f97f12b9f02507e309e6c6d121"},"schema_version":"1.0"},"canonical_sha256":"78e61e605ddf41d250d960edcacc172deef6d27368159ad7ce5d78340e19e0f1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:24:27.762669Z","signature_b64":"CiR/VT42y4Dr3TES6eyHKrVhRG+J6yFFbmmXibAy1K+TyR2Q8km/a9QIFiXj59qMnrx6OC13YuaXlzZSdz6ZBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"78e61e605ddf41d250d960edcacc172deef6d27368159ad7ce5d78340e19e0f1","last_reissued_at":"2026-07-05T06:24:27.762266Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:24:27.762266Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2301.13662","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":"2026-07-05T06:24:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WAiYZCGjluc3KbMBUEC3xMs+SLBZBc9uz3vreqhb2RkqTa2rCZyjnDFUJ8dV7qdHKeE4Mx7iDZ3EM8pgJqBKAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T14:59:16.001006Z"},"content_sha256":"627e0fac1c10673c2872e6dd04ec853da7caecfb0417e0e6434e45ddb0073734","schema_version":"1.0","event_id":"sha256:627e0fac1c10673c2872e6dd04ec853da7caecfb0417e0e6434e45ddb0073734"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:PDTB4YC535A5EUGZMDW4VTAXFX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"InstructTTS: Modelling Expressive TTS in Discrete Latent Space with Natural Language Style Prompt","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Chao Weng, Dongchao Yang, Helen Meng, Rongjie Huang, Songxiang Liu","submitted_at":"2023-01-31T14:26:52Z","abstract_excerpt":"Expressive text-to-speech (TTS) aims to synthesize different speaking style speech according to human's demands. Nowadays, there are two common ways to control speaking styles: (1) Pre-defining a group of speaking style and using categorical index to denote different speaking style. However, there are limitations in the diversity of expressiveness, as these models can only generate the pre-defined styles. (2) Using reference speech as style input, which results in a problem that the extracted style information is not intuitive or interpretable. In this study, we attempt to use natural language"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.13662","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/2301.13662/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":"2026-07-05T06:24:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sO+QSNQ3Qzr+9G1hqIYZ5W685pGOBiEt+eJOb+3TYUE1iF3A+HmBIWZp8PpShHmEkA9pajoUXfIivJYukoLaDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T14:59:16.001494Z"},"content_sha256":"3dea26f2dc5903498cc16f4093f8cfb23652b6c3dc193bacc822334e08beea70","schema_version":"1.0","event_id":"sha256:3dea26f2dc5903498cc16f4093f8cfb23652b6c3dc193bacc822334e08beea70"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PDTB4YC535A5EUGZMDW4VTAXFX/bundle.json","state_url":"https://pith.science/pith/PDTB4YC535A5EUGZMDW4VTAXFX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PDTB4YC535A5EUGZMDW4VTAXFX/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":"2026-08-08T14:59:16Z","links":{"resolver":"https://pith.science/pith/PDTB4YC535A5EUGZMDW4VTAXFX","bundle":"https://pith.science/pith/PDTB4YC535A5EUGZMDW4VTAXFX/bundle.json","state":"https://pith.science/pith/PDTB4YC535A5EUGZMDW4VTAXFX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PDTB4YC535A5EUGZMDW4VTAXFX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:PDTB4YC535A5EUGZMDW4VTAXFX","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":"a3d4216d13cd4e8502cf91f90dd641056a3fb7f97f12b9f02507e309e6c6d121","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-01-31T14:26:52Z","title_canon_sha256":"8c39923defedd12ae1c75f9204baa060a67c7efcf6b32cd8f0f43c17edc06df7"},"schema_version":"1.0","source":{"id":"2301.13662","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.13662","created_at":"2026-07-05T06:24:27Z"},{"alias_kind":"arxiv_version","alias_value":"2301.13662v2","created_at":"2026-07-05T06:24:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.13662","created_at":"2026-07-05T06:24:27Z"},{"alias_kind":"pith_short_12","alias_value":"PDTB4YC535A5","created_at":"2026-07-05T06:24:27Z"},{"alias_kind":"pith_short_16","alias_value":"PDTB4YC535A5EUGZ","created_at":"2026-07-05T06:24:27Z"},{"alias_kind":"pith_short_8","alias_value":"PDTB4YC5","created_at":"2026-07-05T06:24:27Z"}],"graph_snapshots":[{"event_id":"sha256:3dea26f2dc5903498cc16f4093f8cfb23652b6c3dc193bacc822334e08beea70","target":"graph","created_at":"2026-07-05T06:24:27Z","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/2301.13662/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Expressive text-to-speech (TTS) aims to synthesize different speaking style speech according to human's demands. Nowadays, there are two common ways to control speaking styles: (1) Pre-defining a group of speaking style and using categorical index to denote different speaking style. However, there are limitations in the diversity of expressiveness, as these models can only generate the pre-defined styles. (2) Using reference speech as style input, which results in a problem that the extracted style information is not intuitive or interpretable. In this study, we attempt to use natural language","authors_text":"Chao Weng, Dongchao Yang, Helen Meng, Rongjie Huang, Songxiang Liu","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-01-31T14:26:52Z","title":"InstructTTS: Modelling Expressive TTS in Discrete Latent Space with Natural Language Style Prompt"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.13662","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":"sha256:627e0fac1c10673c2872e6dd04ec853da7caecfb0417e0e6434e45ddb0073734","target":"record","created_at":"2026-07-05T06:24:27Z","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":"a3d4216d13cd4e8502cf91f90dd641056a3fb7f97f12b9f02507e309e6c6d121","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-01-31T14:26:52Z","title_canon_sha256":"8c39923defedd12ae1c75f9204baa060a67c7efcf6b32cd8f0f43c17edc06df7"},"schema_version":"1.0","source":{"id":"2301.13662","kind":"arxiv","version":2}},"canonical_sha256":"78e61e605ddf41d250d960edcacc172deef6d27368159ad7ce5d78340e19e0f1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"78e61e605ddf41d250d960edcacc172deef6d27368159ad7ce5d78340e19e0f1","first_computed_at":"2026-07-05T06:24:27.762266Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:24:27.762266Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CiR/VT42y4Dr3TES6eyHKrVhRG+J6yFFbmmXibAy1K+TyR2Q8km/a9QIFiXj59qMnrx6OC13YuaXlzZSdz6ZBg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:24:27.762669Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.13662","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:627e0fac1c10673c2872e6dd04ec853da7caecfb0417e0e6434e45ddb0073734","sha256:3dea26f2dc5903498cc16f4093f8cfb23652b6c3dc193bacc822334e08beea70"],"state_sha256":"1bcec779940f15f0ebbffbac7f5a006c603ed668e7c73a2cca2c89271b4f218e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1JK53rTzHBtbGXhkV1uKVFaAKeTVqyw/se3cGUeTMJh1ZkNkXpYO9zfNjGo/cSMHsBdrupPaQX2vOKtqfc5zBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T14:59:16.004752Z","bundle_sha256":"c6949a71feba483043907d2141675baac2587baa0d6b4f640882e15682e574fb"}}