{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:XYJ45QGUY6AQTTQPF43VFIUU76","short_pith_number":"pith:XYJ45QGU","canonical_record":{"source":{"id":"2307.07218","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-07-14T08:21:25Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"d408a2b2b62ec94f4c3031cc131548d86033f6cb3cac85e04cfbae2a4da60b93","abstract_canon_sha256":"0b52fb3916b2f1cfcf82672f0f8c4e5b2cf8cdf504e0503c5c4b80df64b4ead6"},"schema_version":"1.0"},"canonical_sha256":"be13cec0d4c78109ce0f2f3752a294ffb4150a96152bc8e87eb7b5487ba55127","source":{"kind":"arxiv","id":"2307.07218","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.07218","created_at":"2026-07-05T08:06:24Z"},{"alias_kind":"arxiv_version","alias_value":"2307.07218v4","created_at":"2026-07-05T08:06:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.07218","created_at":"2026-07-05T08:06:24Z"},{"alias_kind":"pith_short_12","alias_value":"XYJ45QGUY6AQ","created_at":"2026-07-05T08:06:24Z"},{"alias_kind":"pith_short_16","alias_value":"XYJ45QGUY6AQTTQP","created_at":"2026-07-05T08:06:24Z"},{"alias_kind":"pith_short_8","alias_value":"XYJ45QGU","created_at":"2026-07-05T08:06:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:XYJ45QGUY6AQTTQPF43VFIUU76","target":"record","payload":{"canonical_record":{"source":{"id":"2307.07218","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-07-14T08:21:25Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"d408a2b2b62ec94f4c3031cc131548d86033f6cb3cac85e04cfbae2a4da60b93","abstract_canon_sha256":"0b52fb3916b2f1cfcf82672f0f8c4e5b2cf8cdf504e0503c5c4b80df64b4ead6"},"schema_version":"1.0"},"canonical_sha256":"be13cec0d4c78109ce0f2f3752a294ffb4150a96152bc8e87eb7b5487ba55127","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:06:24.035769Z","signature_b64":"KD/lUPBU7hZEyi0BFAW+1Wja0mbAPFCyoQLAAM1OCTuYXSSFYXURIr8nSTzTWCovnPbnK1cxkkCgNDNvGDZcBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"be13cec0d4c78109ce0f2f3752a294ffb4150a96152bc8e87eb7b5487ba55127","last_reissued_at":"2026-07-05T08:06:24.035280Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:06:24.035280Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.07218","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:06:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fMj2JKCDay79vK7J/H2GetrcUPmaDfiQemveDSgyxKkr6OJEXQqwQv+jGXdzpbxAu1EGIsyfvYrM2n5Q2MfYCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T07:06:01.566560Z"},"content_sha256":"27d29c337d2a11469fe3c18293c022d1fafdce5a6879ac8b9467b4cdbb080381","schema_version":"1.0","event_id":"sha256:27d29c337d2a11469fe3c18293c022d1fafdce5a6879ac8b9467b4cdbb080381"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:XYJ45QGUY6AQTTQPF43VFIUU76","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mega-TTS 2: Boosting Prompting Mechanisms for Zero-Shot Speech Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Chen Zhang, Chunfeng Wang, Jinglin Liu, Jinzheng He, Pengfei Wei, Qian Yang, Shengpeng Ji, Xiang Yin, Yi Ren, Zejun Ma, Zhenhui Ye, Zhou Zhao, Ziyue Jiang","submitted_at":"2023-07-14T08:21:25Z","abstract_excerpt":"Zero-shot text-to-speech (TTS) aims to synthesize voices with unseen speech prompts, which significantly reduces the data and computation requirements for voice cloning by skipping the fine-tuning process. However, the prompting mechanisms of zero-shot TTS still face challenges in the following aspects: 1) previous works of zero-shot TTS are typically trained with single-sentence prompts, which significantly restricts their performance when the data is relatively sufficient during the inference stage. 2) The prosodic information in prompts is highly coupled with timbre, making it untransferabl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.07218","kind":"arxiv","version":4},"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/2307.07218/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":"2026-07-05T08:06:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/EI6iMcWFovuR5qLaohb8Rb4nj/aT3kK4Bf/k2p9PRicNoFolaIINu9NRotkFloIP/UtWTQFR39Efy7gV/7XBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T07:06:01.567105Z"},"content_sha256":"d6a44e928686f822c023564f151e23a191b33b02e7b9e62439caa48a234a95c3","schema_version":"1.0","event_id":"sha256:d6a44e928686f822c023564f151e23a191b33b02e7b9e62439caa48a234a95c3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XYJ45QGUY6AQTTQPF43VFIUU76/bundle.json","state_url":"https://pith.science/pith/XYJ45QGUY6AQTTQPF43VFIUU76/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XYJ45QGUY6AQTTQPF43VFIUU76/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":"2026-08-14T07:06:01Z","links":{"resolver":"https://pith.science/pith/XYJ45QGUY6AQTTQPF43VFIUU76","bundle":"https://pith.science/pith/XYJ45QGUY6AQTTQPF43VFIUU76/bundle.json","state":"https://pith.science/pith/XYJ45QGUY6AQTTQPF43VFIUU76/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XYJ45QGUY6AQTTQPF43VFIUU76/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:XYJ45QGUY6AQTTQPF43VFIUU76","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":"0b52fb3916b2f1cfcf82672f0f8c4e5b2cf8cdf504e0503c5c4b80df64b4ead6","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-07-14T08:21:25Z","title_canon_sha256":"d408a2b2b62ec94f4c3031cc131548d86033f6cb3cac85e04cfbae2a4da60b93"},"schema_version":"1.0","source":{"id":"2307.07218","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.07218","created_at":"2026-07-05T08:06:24Z"},{"alias_kind":"arxiv_version","alias_value":"2307.07218v4","created_at":"2026-07-05T08:06:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.07218","created_at":"2026-07-05T08:06:24Z"},{"alias_kind":"pith_short_12","alias_value":"XYJ45QGUY6AQ","created_at":"2026-07-05T08:06:24Z"},{"alias_kind":"pith_short_16","alias_value":"XYJ45QGUY6AQTTQP","created_at":"2026-07-05T08:06:24Z"},{"alias_kind":"pith_short_8","alias_value":"XYJ45QGU","created_at":"2026-07-05T08:06:24Z"}],"graph_snapshots":[{"event_id":"sha256:d6a44e928686f822c023564f151e23a191b33b02e7b9e62439caa48a234a95c3","target":"graph","created_at":"2026-07-05T08:06:24Z","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/2307.07218/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Zero-shot text-to-speech (TTS) aims to synthesize voices with unseen speech prompts, which significantly reduces the data and computation requirements for voice cloning by skipping the fine-tuning process. However, the prompting mechanisms of zero-shot TTS still face challenges in the following aspects: 1) previous works of zero-shot TTS are typically trained with single-sentence prompts, which significantly restricts their performance when the data is relatively sufficient during the inference stage. 2) The prosodic information in prompts is highly coupled with timbre, making it untransferabl","authors_text":"Chen Zhang, Chunfeng Wang, Jinglin Liu, Jinzheng He, Pengfei Wei, Qian Yang, Shengpeng Ji, Xiang Yin, Yi Ren, Zejun Ma, Zhenhui Ye, Zhou Zhao, Ziyue Jiang","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-07-14T08:21:25Z","title":"Mega-TTS 2: Boosting Prompting Mechanisms for Zero-Shot Speech Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.07218","kind":"arxiv","version":4},"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":"sha256:27d29c337d2a11469fe3c18293c022d1fafdce5a6879ac8b9467b4cdbb080381","target":"record","created_at":"2026-07-05T08:06:24Z","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":"0b52fb3916b2f1cfcf82672f0f8c4e5b2cf8cdf504e0503c5c4b80df64b4ead6","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-07-14T08:21:25Z","title_canon_sha256":"d408a2b2b62ec94f4c3031cc131548d86033f6cb3cac85e04cfbae2a4da60b93"},"schema_version":"1.0","source":{"id":"2307.07218","kind":"arxiv","version":4}},"canonical_sha256":"be13cec0d4c78109ce0f2f3752a294ffb4150a96152bc8e87eb7b5487ba55127","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"be13cec0d4c78109ce0f2f3752a294ffb4150a96152bc8e87eb7b5487ba55127","first_computed_at":"2026-07-05T08:06:24.035280Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:06:24.035280Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KD/lUPBU7hZEyi0BFAW+1Wja0mbAPFCyoQLAAM1OCTuYXSSFYXURIr8nSTzTWCovnPbnK1cxkkCgNDNvGDZcBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:06:24.035769Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.07218","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:27d29c337d2a11469fe3c18293c022d1fafdce5a6879ac8b9467b4cdbb080381","sha256:d6a44e928686f822c023564f151e23a191b33b02e7b9e62439caa48a234a95c3"],"state_sha256":"c3c9d7664d9ee07f7d0446424179400589f4fee0544b263b64ce493e62876de7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lRGPSB0hefknJfP5kRoSSuImKqECarPPtSbQ5oAbV8ud/RE2/g6xy2VhY5PatmTAmqdHuTY5bwWAbn/mGgz0Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T07:06:01.571615Z","bundle_sha256":"118f29490e401af997f25ce6d024e81039183e5cc84d455a2b170345c6b4a508"}}