{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:IXRYPLR24OQHWHTNRO2N4TDKLS","short_pith_number":"pith:IXRYPLR2","canonical_record":{"source":{"id":"2501.03181","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-01-02T02:00:15Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"79319c6c7e6129d2d3a97868e67e68d7743a7c5fc15cb0b525c3804da663dc4c","abstract_canon_sha256":"3518a348f46cb5e13c7cddd870e3d9e68060a6a30eb517418b0e2a82140c73ea"},"schema_version":"1.0"},"canonical_sha256":"45e387ae3ae3a07b1e6d8bb4de4c6a5c806790c4b5d54873ab3e73f7713bf758","source":{"kind":"arxiv","id":"2501.03181","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.03181","created_at":"2026-07-05T10:49:35Z"},{"alias_kind":"arxiv_version","alias_value":"2501.03181v2","created_at":"2026-07-05T10:49:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.03181","created_at":"2026-07-05T10:49:35Z"},{"alias_kind":"pith_short_12","alias_value":"IXRYPLR24OQH","created_at":"2026-07-05T10:49:35Z"},{"alias_kind":"pith_short_16","alias_value":"IXRYPLR24OQHWHTN","created_at":"2026-07-05T10:49:35Z"},{"alias_kind":"pith_short_8","alias_value":"IXRYPLR2","created_at":"2026-07-05T10:49:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:IXRYPLR24OQHWHTNRO2N4TDKLS","target":"record","payload":{"canonical_record":{"source":{"id":"2501.03181","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-01-02T02:00:15Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"79319c6c7e6129d2d3a97868e67e68d7743a7c5fc15cb0b525c3804da663dc4c","abstract_canon_sha256":"3518a348f46cb5e13c7cddd870e3d9e68060a6a30eb517418b0e2a82140c73ea"},"schema_version":"1.0"},"canonical_sha256":"45e387ae3ae3a07b1e6d8bb4de4c6a5c806790c4b5d54873ab3e73f7713bf758","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:49:35.150185Z","signature_b64":"JuCr6fn1iNNxJgBtbKVzI3JhY5vcEVfhw7pJGC0zplvxh441DmV9xqFX7ckrFrlIGctNWgXD6Cu6tAFO71eBDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"45e387ae3ae3a07b1e6d8bb4de4c6a5c806790c4b5d54873ab3e73f7713bf758","last_reissued_at":"2026-07-05T10:49:35.149761Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:49:35.149761Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.03181","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":"2026-07-05T10:49:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MrMp3ZYUk9Rxl2HZUM7lGXiqlggfIAe3hcRGv6Hz6dZ04J0FlF0NM355WcW3y8t2S8hFd3ZDpxsvjlDnize8CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T00:58:03.495079Z"},"content_sha256":"f8f1734d2ae830ac2aed14f2c8eb9b3693b7e9c13d2419622f2915a6ec2d7acb","schema_version":"1.0","event_id":"sha256:f8f1734d2ae830ac2aed14f2c8eb9b3693b7e9c13d2419622f2915a6ec2d7acb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:IXRYPLR24OQHWHTNRO2N4TDKLS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FaceSpeak: Expressive and High-Quality Speech Synthesis from Human Portraits of Different Styles","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Jiawei Zhang, Jun Wang, Tian-Hao Zhang, Xinyuan Qian, Xu-Cheng Yin","submitted_at":"2025-01-02T02:00:15Z","abstract_excerpt":"Humans can perceive speakers' characteristics (e.g., identity, gender, personality and emotion) by their appearance, which are generally aligned to their voice style. Recently, vision-driven Text-to-speech (TTS) scholars grounded their investigations on real-person faces, thereby restricting effective speech synthesis from applying to vast potential usage scenarios with diverse characters and image styles. To solve this issue, we introduce a novel FaceSpeak approach. It extracts salient identity characteristics and emotional representations from a wide variety of image styles. Meanwhile, it mi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.03181","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/2501.03181/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":"2026-07-05T10:49:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BAAMd7J9HFjIQHdUlsz7GGzE3vviMhTfjoJ7+4kwoKdmIJqJPaToKo3e7ixXU7kVKEK+RYn32zKPLsDONMinCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T00:58:03.495867Z"},"content_sha256":"552e444d68ad2d599f1da00e2c1efb25bd8bf1787ef7cf80a1f5555ecf06216f","schema_version":"1.0","event_id":"sha256:552e444d68ad2d599f1da00e2c1efb25bd8bf1787ef7cf80a1f5555ecf06216f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IXRYPLR24OQHWHTNRO2N4TDKLS/bundle.json","state_url":"https://pith.science/pith/IXRYPLR24OQHWHTNRO2N4TDKLS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IXRYPLR24OQHWHTNRO2N4TDKLS/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":"2026-08-05T00:58:03Z","links":{"resolver":"https://pith.science/pith/IXRYPLR24OQHWHTNRO2N4TDKLS","bundle":"https://pith.science/pith/IXRYPLR24OQHWHTNRO2N4TDKLS/bundle.json","state":"https://pith.science/pith/IXRYPLR24OQHWHTNRO2N4TDKLS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IXRYPLR24OQHWHTNRO2N4TDKLS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IXRYPLR24OQHWHTNRO2N4TDKLS","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":"3518a348f46cb5e13c7cddd870e3d9e68060a6a30eb517418b0e2a82140c73ea","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-01-02T02:00:15Z","title_canon_sha256":"79319c6c7e6129d2d3a97868e67e68d7743a7c5fc15cb0b525c3804da663dc4c"},"schema_version":"1.0","source":{"id":"2501.03181","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.03181","created_at":"2026-07-05T10:49:35Z"},{"alias_kind":"arxiv_version","alias_value":"2501.03181v2","created_at":"2026-07-05T10:49:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.03181","created_at":"2026-07-05T10:49:35Z"},{"alias_kind":"pith_short_12","alias_value":"IXRYPLR24OQH","created_at":"2026-07-05T10:49:35Z"},{"alias_kind":"pith_short_16","alias_value":"IXRYPLR24OQHWHTN","created_at":"2026-07-05T10:49:35Z"},{"alias_kind":"pith_short_8","alias_value":"IXRYPLR2","created_at":"2026-07-05T10:49:35Z"}],"graph_snapshots":[{"event_id":"sha256:552e444d68ad2d599f1da00e2c1efb25bd8bf1787ef7cf80a1f5555ecf06216f","target":"graph","created_at":"2026-07-05T10:49:35Z","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/2501.03181/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Humans can perceive speakers' characteristics (e.g., identity, gender, personality and emotion) by their appearance, which are generally aligned to their voice style. Recently, vision-driven Text-to-speech (TTS) scholars grounded their investigations on real-person faces, thereby restricting effective speech synthesis from applying to vast potential usage scenarios with diverse characters and image styles. To solve this issue, we introduce a novel FaceSpeak approach. It extracts salient identity characteristics and emotional representations from a wide variety of image styles. Meanwhile, it mi","authors_text":"Jiawei Zhang, Jun Wang, Tian-Hao Zhang, Xinyuan Qian, Xu-Cheng Yin","cross_cats":["cs.AI","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-01-02T02:00:15Z","title":"FaceSpeak: Expressive and High-Quality Speech Synthesis from Human Portraits of Different Styles"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.03181","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:f8f1734d2ae830ac2aed14f2c8eb9b3693b7e9c13d2419622f2915a6ec2d7acb","target":"record","created_at":"2026-07-05T10:49:35Z","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":"3518a348f46cb5e13c7cddd870e3d9e68060a6a30eb517418b0e2a82140c73ea","cross_cats_sorted":["cs.AI","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-01-02T02:00:15Z","title_canon_sha256":"79319c6c7e6129d2d3a97868e67e68d7743a7c5fc15cb0b525c3804da663dc4c"},"schema_version":"1.0","source":{"id":"2501.03181","kind":"arxiv","version":2}},"canonical_sha256":"45e387ae3ae3a07b1e6d8bb4de4c6a5c806790c4b5d54873ab3e73f7713bf758","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"45e387ae3ae3a07b1e6d8bb4de4c6a5c806790c4b5d54873ab3e73f7713bf758","first_computed_at":"2026-07-05T10:49:35.149761Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:49:35.149761Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JuCr6fn1iNNxJgBtbKVzI3JhY5vcEVfhw7pJGC0zplvxh441DmV9xqFX7ckrFrlIGctNWgXD6Cu6tAFO71eBDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:49:35.150185Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.03181","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f8f1734d2ae830ac2aed14f2c8eb9b3693b7e9c13d2419622f2915a6ec2d7acb","sha256:552e444d68ad2d599f1da00e2c1efb25bd8bf1787ef7cf80a1f5555ecf06216f"],"state_sha256":"b9d4688f2acf6f497958f18c48ca9048d365e2c60fd1dca3dc3eda6b6ed091e0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qhUzYW9GeqPDfPhPxv+5QQy9b0oH/fc8UtbLWF6SmW4oMFiV98aXG4+474aQ2YquNgvCoEg93V9zeq07e8EiDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T00:58:03.502667Z","bundle_sha256":"be651180270e003170511ddbc80ec888e6240a250aa02df3bd5faba2e50ee0b3"}}