{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:XWBRKILEFP27BXOX4RN6765BON","short_pith_number":"pith:XWBRKILE","canonical_record":{"source":{"id":"2505.19384","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-26T00:58:16Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"31d068e1f31d44abca50de49522e5ebd2f6068ca25a992b0b22fe618710c6122","abstract_canon_sha256":"d9eb774777950961c24d974df11d4a2b9a9b99a44c8f128ef2a9f4bf5ed01243"},"schema_version":"1.0"},"canonical_sha256":"bd831521642bf5f0ddd7e45beffba1735c5e1538600695c484747275f840f9eb","source":{"kind":"arxiv","id":"2505.19384","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.19384","created_at":"2026-07-05T11:09:29Z"},{"alias_kind":"arxiv_version","alias_value":"2505.19384v1","created_at":"2026-07-05T11:09:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19384","created_at":"2026-07-05T11:09:29Z"},{"alias_kind":"pith_short_12","alias_value":"XWBRKILEFP27","created_at":"2026-07-05T11:09:29Z"},{"alias_kind":"pith_short_16","alias_value":"XWBRKILEFP27BXOX","created_at":"2026-07-05T11:09:29Z"},{"alias_kind":"pith_short_8","alias_value":"XWBRKILE","created_at":"2026-07-05T11:09:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:XWBRKILEFP27BXOX4RN6765BON","target":"record","payload":{"canonical_record":{"source":{"id":"2505.19384","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-26T00:58:16Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"31d068e1f31d44abca50de49522e5ebd2f6068ca25a992b0b22fe618710c6122","abstract_canon_sha256":"d9eb774777950961c24d974df11d4a2b9a9b99a44c8f128ef2a9f4bf5ed01243"},"schema_version":"1.0"},"canonical_sha256":"bd831521642bf5f0ddd7e45beffba1735c5e1538600695c484747275f840f9eb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:29.440501Z","signature_b64":"C6WwpHJF2pP04PtMgbb+gFUu/g+70FBO+Z3Wj6Sa7KoEHx5BLn3BDq2x4/zFYH9QOw9NUO5a3iqkfFrZPFu+Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd831521642bf5f0ddd7e45beffba1735c5e1538600695c484747275f840f9eb","last_reissued_at":"2026-07-05T11:09:29.440095Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:29.440095Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.19384","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":"2026-07-05T11:09:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zB39xLhywFXDPak7u6gkjzMZ1IQtdvr0wP/P6hAKUZ3mBxqBjCVAAq3uevCCWov7BLS2MLBQ5rYV0cCxmdQ1Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T08:54:12.267867Z"},"content_sha256":"558696dd80b1e9c0aaeab6a7e98da8dfa62f3761826aee401e0fc0fdbfd58273","schema_version":"1.0","event_id":"sha256:558696dd80b1e9c0aaeab6a7e98da8dfa62f3761826aee401e0fc0fdbfd58273"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:XWBRKILEFP27BXOX4RN6765BON","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GSA-TTS : Toward Zero-Shot Speech Synthesis based on Gradual Style Adaptor","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Jungjun Kim, Seokgi Lee","submitted_at":"2025-05-26T00:58:16Z","abstract_excerpt":"We present the gradual style adaptor TTS (GSA-TTS) with a novel style encoder that gradually encodes speaking styles from an acoustic reference for zero-shot speech synthesis. GSA first captures the local style of each semantic sound unit. Then the local styles are combined by self-attention to obtain a global style condition. This semantic and hierarchical encoding strategy provides a robust and rich style representation for an acoustic model. We test GSA-TTS on unseen speakers and obtain promising results regarding naturalness, speaker similarity, and intelligibility. Additionally, we explor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19384","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/2505.19384/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":"2026-07-05T11:09:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Wkqq8NU+pB/YyPRid2vArQnELrklYLiUu//yLt3dEb/2HRwI9qnDzM1l5Pj9p570tf/YUfZVyc4qkytY1t1fBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T08:54:12.268392Z"},"content_sha256":"38fd4ac547c7ee21e17b7f7ba53e25337f0957b38223193bac08636b33d6492f","schema_version":"1.0","event_id":"sha256:38fd4ac547c7ee21e17b7f7ba53e25337f0957b38223193bac08636b33d6492f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XWBRKILEFP27BXOX4RN6765BON/bundle.json","state_url":"https://pith.science/pith/XWBRKILEFP27BXOX4RN6765BON/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XWBRKILEFP27BXOX4RN6765BON/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":"2026-08-08T08:54:12Z","links":{"resolver":"https://pith.science/pith/XWBRKILEFP27BXOX4RN6765BON","bundle":"https://pith.science/pith/XWBRKILEFP27BXOX4RN6765BON/bundle.json","state":"https://pith.science/pith/XWBRKILEFP27BXOX4RN6765BON/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XWBRKILEFP27BXOX4RN6765BON/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XWBRKILEFP27BXOX4RN6765BON","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":"d9eb774777950961c24d974df11d4a2b9a9b99a44c8f128ef2a9f4bf5ed01243","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-26T00:58:16Z","title_canon_sha256":"31d068e1f31d44abca50de49522e5ebd2f6068ca25a992b0b22fe618710c6122"},"schema_version":"1.0","source":{"id":"2505.19384","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.19384","created_at":"2026-07-05T11:09:29Z"},{"alias_kind":"arxiv_version","alias_value":"2505.19384v1","created_at":"2026-07-05T11:09:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19384","created_at":"2026-07-05T11:09:29Z"},{"alias_kind":"pith_short_12","alias_value":"XWBRKILEFP27","created_at":"2026-07-05T11:09:29Z"},{"alias_kind":"pith_short_16","alias_value":"XWBRKILEFP27BXOX","created_at":"2026-07-05T11:09:29Z"},{"alias_kind":"pith_short_8","alias_value":"XWBRKILE","created_at":"2026-07-05T11:09:29Z"}],"graph_snapshots":[{"event_id":"sha256:38fd4ac547c7ee21e17b7f7ba53e25337f0957b38223193bac08636b33d6492f","target":"graph","created_at":"2026-07-05T11:09:29Z","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/2505.19384/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present the gradual style adaptor TTS (GSA-TTS) with a novel style encoder that gradually encodes speaking styles from an acoustic reference for zero-shot speech synthesis. GSA first captures the local style of each semantic sound unit. Then the local styles are combined by self-attention to obtain a global style condition. This semantic and hierarchical encoding strategy provides a robust and rich style representation for an acoustic model. We test GSA-TTS on unseen speakers and obtain promising results regarding naturalness, speaker similarity, and intelligibility. Additionally, we explor","authors_text":"Jungjun Kim, Seokgi Lee","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-26T00:58:16Z","title":"GSA-TTS : Toward Zero-Shot Speech Synthesis based on Gradual Style Adaptor"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19384","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":"sha256:558696dd80b1e9c0aaeab6a7e98da8dfa62f3761826aee401e0fc0fdbfd58273","target":"record","created_at":"2026-07-05T11:09:29Z","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":"d9eb774777950961c24d974df11d4a2b9a9b99a44c8f128ef2a9f4bf5ed01243","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-26T00:58:16Z","title_canon_sha256":"31d068e1f31d44abca50de49522e5ebd2f6068ca25a992b0b22fe618710c6122"},"schema_version":"1.0","source":{"id":"2505.19384","kind":"arxiv","version":1}},"canonical_sha256":"bd831521642bf5f0ddd7e45beffba1735c5e1538600695c484747275f840f9eb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bd831521642bf5f0ddd7e45beffba1735c5e1538600695c484747275f840f9eb","first_computed_at":"2026-07-05T11:09:29.440095Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:09:29.440095Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"C6WwpHJF2pP04PtMgbb+gFUu/g+70FBO+Z3Wj6Sa7KoEHx5BLn3BDq2x4/zFYH9QOw9NUO5a3iqkfFrZPFu+Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:09:29.440501Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.19384","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:558696dd80b1e9c0aaeab6a7e98da8dfa62f3761826aee401e0fc0fdbfd58273","sha256:38fd4ac547c7ee21e17b7f7ba53e25337f0957b38223193bac08636b33d6492f"],"state_sha256":"e1ea046377e019640c1c6c08ae24c741e13c66bdf3ec1201545b01f4680df739"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8XWRKKeVB9D98huI0QjyfCI6aE3YOhOF6VH9zS0r6iruI5GgRAkWIu/0ghZrkF9m5nJxb97ul6hucDwTZ7HVCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T08:54:12.271568Z","bundle_sha256":"a5aa3796ca15bba164a19a4edc4871a68e58d00727973385ad82e6c5bbf2750c"}}