{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:LYYTNG6JLJVGXXQAGY3F4ZFFL6","short_pith_number":"pith:LYYTNG6J","canonical_record":{"source":{"id":"2607.26742","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2026-07-29T10:33:56Z","cross_cats_sorted":["cs.AI","cs.SD"],"title_canon_sha256":"57d3f52640a27451034936c6af342219336d70496d61929faee07e44054d6c73","abstract_canon_sha256":"41dcf2b2565500be93c24e9729f4b273e653c2e2466c911b2d105a3ac757dc68"},"schema_version":"1.0"},"canonical_sha256":"5e31369bc95a6a6bde0036365e64a55f8a007e331909ed15eef155afcfd06c6c","source":{"kind":"arxiv","id":"2607.26742","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.26742","created_at":"2026-07-30T01:22:09Z"},{"alias_kind":"arxiv_version","alias_value":"2607.26742v1","created_at":"2026-07-30T01:22:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.26742","created_at":"2026-07-30T01:22:09Z"},{"alias_kind":"pith_short_12","alias_value":"LYYTNG6JLJVG","created_at":"2026-07-30T01:22:09Z"},{"alias_kind":"pith_short_16","alias_value":"LYYTNG6JLJVGXXQA","created_at":"2026-07-30T01:22:09Z"},{"alias_kind":"pith_short_8","alias_value":"LYYTNG6J","created_at":"2026-07-30T01:22:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:LYYTNG6JLJVGXXQAGY3F4ZFFL6","target":"record","payload":{"canonical_record":{"source":{"id":"2607.26742","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2026-07-29T10:33:56Z","cross_cats_sorted":["cs.AI","cs.SD"],"title_canon_sha256":"57d3f52640a27451034936c6af342219336d70496d61929faee07e44054d6c73","abstract_canon_sha256":"41dcf2b2565500be93c24e9729f4b273e653c2e2466c911b2d105a3ac757dc68"},"schema_version":"1.0"},"canonical_sha256":"5e31369bc95a6a6bde0036365e64a55f8a007e331909ed15eef155afcfd06c6c","receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e31369bc95a6a6bde0036365e64a55f8a007e331909ed15eef155afcfd06c6c","last_reissued_at":"2026-07-30T01:22:09.789097Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-30T01:22:09.789097Z"},"source_kind":"arxiv","source_id":"2607.26742","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":"2026-07-30T01:22:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+29o6nQr1fzw3nn9k2tBAIfpwU8f/zx/EV+JYUGn08euDbsfivPiuaxPfRVj43/9SEEWoINQqgu/sHzSRNY6BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T05:50:51.680728Z"},"content_sha256":"2054ae05160d66930dda943f6057a983b150c0e58fed3296079af812fe70292f","schema_version":"1.0","event_id":"sha256:2054ae05160d66930dda943f6057a983b150c0e58fed3296079af812fe70292f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:LYYTNG6JLJVGXXQAGY3F4ZFFL6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Zero-Shot Face-to-Speech Synthesis via Latent Space Adaptation of a Style-Diffusion TTS Model","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.SD"],"primary_cat":"eess.AS","authors_text":"Carlos Mu\\~noz-Romero, Jose A. Gonzalez-Lopez","submitted_at":"2026-07-29T10:33:56Z","abstract_excerpt":"Zero-shot text-to-speech (TTS) clones a voice from a short audio prompt, but this reliance on reference audio is a barrier when only visual information is available, e.g. for historical figures or video-game characters. In this work, we propose a Face-to-Speech (F2S) framework that predicts a plausible voice from a static facial image. A lightweight Face Adapter, together with soft-tuning of the face encoder's upper blocks, aligns face-recognition features with the style space of a frozen StyleTTS 2 model, kept frozen during training. We evaluate on held-out identities from LRS3, a large-scale"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.26742","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/2607.26742/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":"2026-07-30T01:22:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZEHP7+yXbENnrVgKj1ZpmvfsDummWzCGSwQhjKYpO7mOfSuq08uaXweOduh/b7zboG/AD5oVDy8PDlj13vxNBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T05:50:51.681238Z"},"content_sha256":"01fb06f416214371347cf7c8691eed9869a4f9fac0e5928203c8e1d2fbe545d4","schema_version":"1.0","event_id":"sha256:01fb06f416214371347cf7c8691eed9869a4f9fac0e5928203c8e1d2fbe545d4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LYYTNG6JLJVGXXQAGY3F4ZFFL6/bundle.json","state_url":"https://pith.science/pith/LYYTNG6JLJVGXXQAGY3F4ZFFL6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LYYTNG6JLJVGXXQAGY3F4ZFFL6/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":"2026-08-23T05:50:51Z","links":{"resolver":"https://pith.science/pith/LYYTNG6JLJVGXXQAGY3F4ZFFL6","bundle":"https://pith.science/pith/LYYTNG6JLJVGXXQAGY3F4ZFFL6/bundle.json","state":"https://pith.science/pith/LYYTNG6JLJVGXXQAGY3F4ZFFL6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LYYTNG6JLJVGXXQAGY3F4ZFFL6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:LYYTNG6JLJVGXXQAGY3F4ZFFL6","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":"41dcf2b2565500be93c24e9729f4b273e653c2e2466c911b2d105a3ac757dc68","cross_cats_sorted":["cs.AI","cs.SD"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2026-07-29T10:33:56Z","title_canon_sha256":"57d3f52640a27451034936c6af342219336d70496d61929faee07e44054d6c73"},"schema_version":"1.0","source":{"id":"2607.26742","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.26742","created_at":"2026-07-30T01:22:09Z"},{"alias_kind":"arxiv_version","alias_value":"2607.26742v1","created_at":"2026-07-30T01:22:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.26742","created_at":"2026-07-30T01:22:09Z"},{"alias_kind":"pith_short_12","alias_value":"LYYTNG6JLJVG","created_at":"2026-07-30T01:22:09Z"},{"alias_kind":"pith_short_16","alias_value":"LYYTNG6JLJVGXXQA","created_at":"2026-07-30T01:22:09Z"},{"alias_kind":"pith_short_8","alias_value":"LYYTNG6J","created_at":"2026-07-30T01:22:09Z"}],"graph_snapshots":[{"event_id":"sha256:01fb06f416214371347cf7c8691eed9869a4f9fac0e5928203c8e1d2fbe545d4","target":"graph","created_at":"2026-07-30T01:22:09Z","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/2607.26742/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Zero-shot text-to-speech (TTS) clones a voice from a short audio prompt, but this reliance on reference audio is a barrier when only visual information is available, e.g. for historical figures or video-game characters. In this work, we propose a Face-to-Speech (F2S) framework that predicts a plausible voice from a static facial image. A lightweight Face Adapter, together with soft-tuning of the face encoder's upper blocks, aligns face-recognition features with the style space of a frozen StyleTTS 2 model, kept frozen during training. We evaluate on held-out identities from LRS3, a large-scale","authors_text":"Carlos Mu\\~noz-Romero, Jose A. Gonzalez-Lopez","cross_cats":["cs.AI","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2026-07-29T10:33:56Z","title":"Zero-Shot Face-to-Speech Synthesis via Latent Space Adaptation of a Style-Diffusion TTS Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.26742","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":"sha256:2054ae05160d66930dda943f6057a983b150c0e58fed3296079af812fe70292f","target":"record","created_at":"2026-07-30T01:22:09Z","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":"41dcf2b2565500be93c24e9729f4b273e653c2e2466c911b2d105a3ac757dc68","cross_cats_sorted":["cs.AI","cs.SD"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2026-07-29T10:33:56Z","title_canon_sha256":"57d3f52640a27451034936c6af342219336d70496d61929faee07e44054d6c73"},"schema_version":"1.0","source":{"id":"2607.26742","kind":"arxiv","version":1}},"canonical_sha256":"5e31369bc95a6a6bde0036365e64a55f8a007e331909ed15eef155afcfd06c6c","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5e31369bc95a6a6bde0036365e64a55f8a007e331909ed15eef155afcfd06c6c","first_computed_at":"2026-07-30T01:22:09.789097Z","kind":"pith_receipt","last_reissued_at":"2026-07-30T01:22:09.789097Z","receipt_version":"0.3","signature_status":"unsigned_v0"},"source_id":"2607.26742","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2054ae05160d66930dda943f6057a983b150c0e58fed3296079af812fe70292f","sha256:01fb06f416214371347cf7c8691eed9869a4f9fac0e5928203c8e1d2fbe545d4"],"state_sha256":"45e00ea9dec415c46d326cc5325809c47e37971104bf0f344619d6a6ee8ac7c8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E4FR2qkKTnoFfCwd1aFt8l2jeGy5iMnR0V9nQVn/HbaU3c4qbcvqeJj7zSD1wg9j6UKlFh6KsA9fR6RuKF3qDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T05:50:51.686012Z","bundle_sha256":"f499aad7b8e7f64e9e383a25030c9487d4ebbb4dcfb10ab32c78e92c28299d02"}}