{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:MLE442ZAPQ65TYINYNSESAU6IO","short_pith_number":"pith:MLE442ZA","canonical_record":{"source":{"id":"2409.10058","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2024-09-16T07:39:58Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"8981384a9babfe73a9372315702ebdf4405676c4637028d6ec8eec13ed7d5827","abstract_canon_sha256":"7f1dff23ce4d23deab383ad206ab9e03585abb24708c8af18b59afae2e9bc9e3"},"schema_version":"1.0"},"canonical_sha256":"62c9ce6b207c3dd9e10dc36449029e43b030e7ae4685ec00511019e88d30e7fc","source":{"kind":"arxiv","id":"2409.10058","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.10058","created_at":"2026-07-05T09:07:34Z"},{"alias_kind":"arxiv_version","alias_value":"2409.10058v1","created_at":"2026-07-05T09:07:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.10058","created_at":"2026-07-05T09:07:34Z"},{"alias_kind":"pith_short_12","alias_value":"MLE442ZAPQ65","created_at":"2026-07-05T09:07:34Z"},{"alias_kind":"pith_short_16","alias_value":"MLE442ZAPQ65TYIN","created_at":"2026-07-05T09:07:34Z"},{"alias_kind":"pith_short_8","alias_value":"MLE442ZA","created_at":"2026-07-05T09:07:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:MLE442ZAPQ65TYINYNSESAU6IO","target":"record","payload":{"canonical_record":{"source":{"id":"2409.10058","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2024-09-16T07:39:58Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"8981384a9babfe73a9372315702ebdf4405676c4637028d6ec8eec13ed7d5827","abstract_canon_sha256":"7f1dff23ce4d23deab383ad206ab9e03585abb24708c8af18b59afae2e9bc9e3"},"schema_version":"1.0"},"canonical_sha256":"62c9ce6b207c3dd9e10dc36449029e43b030e7ae4685ec00511019e88d30e7fc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:07:34.079106Z","signature_b64":"kNenfH6T25BKGHLs5b2OEqOYh6Gr2DaKXMQd9IIJ9CrDVbwpET3rTjI9aTo9qPX/zL+hevotcNGEyAd8WJPHAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"62c9ce6b207c3dd9e10dc36449029e43b030e7ae4685ec00511019e88d30e7fc","last_reissued_at":"2026-07-05T09:07:34.078630Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:07:34.078630Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.10058","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":"2026-07-05T09:07:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EoqCRFaUAUC4HiPpbeqjkIXodlPLonEvmgi066j0cSC2RREU1jcnJjEtYVA1O2WeOJRFQjQ4mh4R5KEK6+XRAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T05:56:22.363625Z"},"content_sha256":"e9d2e8c84a23ac349389a20fb655c175168b5c3b1e4dd8b2a0fa3b3607b9b8be","schema_version":"1.0","event_id":"sha256:e9d2e8c84a23ac349389a20fb655c175168b5c3b1e4dd8b2a0fa3b3607b9b8be"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:MLE442ZAPQ65TYINYNSESAU6IO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"StyleTTS-ZS: Efficient High-Quality Zero-Shot Text-to-Speech Synthesis with Distilled Time-Varying Style Diffusion","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Cong Han, Nima Mesgarani, Xilin Jiang, Yinghao Aaron Li","submitted_at":"2024-09-16T07:39:58Z","abstract_excerpt":"The rapid development of large-scale text-to-speech (TTS) models has led to significant advancements in modeling diverse speaker prosody and voices. However, these models often face issues such as slow inference speeds, reliance on complex pre-trained neural codec representations, and difficulties in achieving naturalness and high similarity to reference speakers. To address these challenges, this work introduces StyleTTS-ZS, an efficient zero-shot TTS model that leverages distilled time-varying style diffusion to capture diverse speaker identities and prosodies. We propose a novel approach th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.10058","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/2409.10058/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":"2026-07-05T09:07:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P+2SLexfxKTjRkdrItSHHuoIqVAEOqmYjzanbpxxT/DjPQTaCjT3i5dLNOwtEvGuE38875mEOcnk9ohejH1JAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T05:56:22.364304Z"},"content_sha256":"b5b12e68312cd480274bcba50b532a6aa138450c810ed2ef42b484dcebcc6abb","schema_version":"1.0","event_id":"sha256:b5b12e68312cd480274bcba50b532a6aa138450c810ed2ef42b484dcebcc6abb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MLE442ZAPQ65TYINYNSESAU6IO/bundle.json","state_url":"https://pith.science/pith/MLE442ZAPQ65TYINYNSESAU6IO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MLE442ZAPQ65TYINYNSESAU6IO/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":"2026-07-09T05:56:22Z","links":{"resolver":"https://pith.science/pith/MLE442ZAPQ65TYINYNSESAU6IO","bundle":"https://pith.science/pith/MLE442ZAPQ65TYINYNSESAU6IO/bundle.json","state":"https://pith.science/pith/MLE442ZAPQ65TYINYNSESAU6IO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MLE442ZAPQ65TYINYNSESAU6IO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MLE442ZAPQ65TYINYNSESAU6IO","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":"7f1dff23ce4d23deab383ad206ab9e03585abb24708c8af18b59afae2e9bc9e3","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2024-09-16T07:39:58Z","title_canon_sha256":"8981384a9babfe73a9372315702ebdf4405676c4637028d6ec8eec13ed7d5827"},"schema_version":"1.0","source":{"id":"2409.10058","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.10058","created_at":"2026-07-05T09:07:34Z"},{"alias_kind":"arxiv_version","alias_value":"2409.10058v1","created_at":"2026-07-05T09:07:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.10058","created_at":"2026-07-05T09:07:34Z"},{"alias_kind":"pith_short_12","alias_value":"MLE442ZAPQ65","created_at":"2026-07-05T09:07:34Z"},{"alias_kind":"pith_short_16","alias_value":"MLE442ZAPQ65TYIN","created_at":"2026-07-05T09:07:34Z"},{"alias_kind":"pith_short_8","alias_value":"MLE442ZA","created_at":"2026-07-05T09:07:34Z"}],"graph_snapshots":[{"event_id":"sha256:b5b12e68312cd480274bcba50b532a6aa138450c810ed2ef42b484dcebcc6abb","target":"graph","created_at":"2026-07-05T09:07:34Z","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/2409.10058/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The rapid development of large-scale text-to-speech (TTS) models has led to significant advancements in modeling diverse speaker prosody and voices. However, these models often face issues such as slow inference speeds, reliance on complex pre-trained neural codec representations, and difficulties in achieving naturalness and high similarity to reference speakers. To address these challenges, this work introduces StyleTTS-ZS, an efficient zero-shot TTS model that leverages distilled time-varying style diffusion to capture diverse speaker identities and prosodies. We propose a novel approach th","authors_text":"Cong Han, Nima Mesgarani, Xilin Jiang, Yinghao Aaron Li","cross_cats":["cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2024-09-16T07:39:58Z","title":"StyleTTS-ZS: Efficient High-Quality Zero-Shot Text-to-Speech Synthesis with Distilled Time-Varying Style Diffusion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.10058","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:e9d2e8c84a23ac349389a20fb655c175168b5c3b1e4dd8b2a0fa3b3607b9b8be","target":"record","created_at":"2026-07-05T09:07:34Z","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":"7f1dff23ce4d23deab383ad206ab9e03585abb24708c8af18b59afae2e9bc9e3","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2024-09-16T07:39:58Z","title_canon_sha256":"8981384a9babfe73a9372315702ebdf4405676c4637028d6ec8eec13ed7d5827"},"schema_version":"1.0","source":{"id":"2409.10058","kind":"arxiv","version":1}},"canonical_sha256":"62c9ce6b207c3dd9e10dc36449029e43b030e7ae4685ec00511019e88d30e7fc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"62c9ce6b207c3dd9e10dc36449029e43b030e7ae4685ec00511019e88d30e7fc","first_computed_at":"2026-07-05T09:07:34.078630Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:07:34.078630Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kNenfH6T25BKGHLs5b2OEqOYh6Gr2DaKXMQd9IIJ9CrDVbwpET3rTjI9aTo9qPX/zL+hevotcNGEyAd8WJPHAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:07:34.079106Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.10058","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e9d2e8c84a23ac349389a20fb655c175168b5c3b1e4dd8b2a0fa3b3607b9b8be","sha256:b5b12e68312cd480274bcba50b532a6aa138450c810ed2ef42b484dcebcc6abb"],"state_sha256":"f6652625c87f85569c362503b86d77e6774c8664312b84507248080f1d60cd88"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fZcQx0WL5F4+t04htUvLsSjrEGDv32OqdUia4PZd2z/tH33oHPD9jGZ2Qrp1jiMxt+Yr/MN+J9tLzulvzvERAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T05:56:22.367973Z","bundle_sha256":"4deab8e03f42c97e95174fc60d5b36ca727b89abc0a8eb98aaadd5aeaa9dde4f"}}