{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:D4YVR5MFZI7OIXCDOWWQUDWTW4","short_pith_number":"pith:D4YVR5MF","canonical_record":{"source":{"id":"2503.14928","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-19T06:28:17Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"d13e331d0a574ff5ed14501b985914a6b47882ea31345a2309d2243aa9afd5f4","abstract_canon_sha256":"5f3f0c6a32b1c896b1489ccb7cfe42931f9a8fc8a05a1ee8ed7b11d988bc493e"},"schema_version":"1.0"},"canonical_sha256":"1f3158f585ca3ee45c4375ad0a0ed3b724cdb886b4153e23793fee4ae0267f2d","source":{"kind":"arxiv","id":"2503.14928","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.14928","created_at":"2026-07-05T10:34:27Z"},{"alias_kind":"arxiv_version","alias_value":"2503.14928v1","created_at":"2026-07-05T10:34:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.14928","created_at":"2026-07-05T10:34:27Z"},{"alias_kind":"pith_short_12","alias_value":"D4YVR5MFZI7O","created_at":"2026-07-05T10:34:27Z"},{"alias_kind":"pith_short_16","alias_value":"D4YVR5MFZI7OIXCD","created_at":"2026-07-05T10:34:27Z"},{"alias_kind":"pith_short_8","alias_value":"D4YVR5MF","created_at":"2026-07-05T10:34:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:D4YVR5MFZI7OIXCDOWWQUDWTW4","target":"record","payload":{"canonical_record":{"source":{"id":"2503.14928","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-19T06:28:17Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"d13e331d0a574ff5ed14501b985914a6b47882ea31345a2309d2243aa9afd5f4","abstract_canon_sha256":"5f3f0c6a32b1c896b1489ccb7cfe42931f9a8fc8a05a1ee8ed7b11d988bc493e"},"schema_version":"1.0"},"canonical_sha256":"1f3158f585ca3ee45c4375ad0a0ed3b724cdb886b4153e23793fee4ae0267f2d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:34:27.591644Z","signature_b64":"EYJ0+cyQp9FA0gtp5K+Qcl/gLK2or2kd9ohszJ27Gq7Jec4qVZUUM+uiyT4EjrugHmQCvj5WCLeQjjtKk66sDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1f3158f585ca3ee45c4375ad0a0ed3b724cdb886b4153e23793fee4ae0267f2d","last_reissued_at":"2026-07-05T10:34:27.591055Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:34:27.591055Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.14928","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":"2026-07-05T10:34:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2vgvTUpg1VyQR9KvjIcP137OmZDl0tM2jyw95OXntthSWisOg7sdFC1HAE98uStXdXyUBtF3rZjBQQ4WT9W5Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T05:55:18.117139Z"},"content_sha256":"b41bf29fd0fa5cf2c342f31eac53065c987431b0fe644d969848e46f635be214","schema_version":"1.0","event_id":"sha256:b41bf29fd0fa5cf2c342f31eac53065c987431b0fe644d969848e46f635be214"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:D4YVR5MFZI7OIXCDOWWQUDWTW4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Shushing! Let's Imagine an Authentic Speech from the Silent Video","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Hongming Shan, Jiaxin Ye","submitted_at":"2025-03-19T06:28:17Z","abstract_excerpt":"Vision-guided speech generation aims to produce authentic speech from facial appearance or lip motions without relying on auditory signals, offering significant potential for applications such as dubbing in filmmaking and assisting individuals with aphonia. Despite recent progress, existing methods struggle to achieve unified cross-modal alignment across semantics, timbre, and emotional prosody from visual cues, prompting us to propose Consistent Video-to-Speech (CV2S) as an extended task to enhance cross-modal consistency. To tackle emerging challenges, we introduce ImaginTalk, a novel cross-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.14928","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/2503.14928/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":"2026-07-05T10:34:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AQM3yTp2qTQP2hM0sacbTohrVo483ZAfVWtw7nVIjRJ5X0NOUb1kmwoDtLt5SyzV8AAMDQWr6A0CK6ZssJuzAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T05:55:18.118418Z"},"content_sha256":"41baba1d6120840371fca455166f105cc6bc76e607ee88f8ba77dce1fa6b6af9","schema_version":"1.0","event_id":"sha256:41baba1d6120840371fca455166f105cc6bc76e607ee88f8ba77dce1fa6b6af9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/D4YVR5MFZI7OIXCDOWWQUDWTW4/bundle.json","state_url":"https://pith.science/pith/D4YVR5MFZI7OIXCDOWWQUDWTW4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/D4YVR5MFZI7OIXCDOWWQUDWTW4/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":"2026-08-05T05:55:18Z","links":{"resolver":"https://pith.science/pith/D4YVR5MFZI7OIXCDOWWQUDWTW4","bundle":"https://pith.science/pith/D4YVR5MFZI7OIXCDOWWQUDWTW4/bundle.json","state":"https://pith.science/pith/D4YVR5MFZI7OIXCDOWWQUDWTW4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/D4YVR5MFZI7OIXCDOWWQUDWTW4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:D4YVR5MFZI7OIXCDOWWQUDWTW4","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":"5f3f0c6a32b1c896b1489ccb7cfe42931f9a8fc8a05a1ee8ed7b11d988bc493e","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-19T06:28:17Z","title_canon_sha256":"d13e331d0a574ff5ed14501b985914a6b47882ea31345a2309d2243aa9afd5f4"},"schema_version":"1.0","source":{"id":"2503.14928","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.14928","created_at":"2026-07-05T10:34:27Z"},{"alias_kind":"arxiv_version","alias_value":"2503.14928v1","created_at":"2026-07-05T10:34:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.14928","created_at":"2026-07-05T10:34:27Z"},{"alias_kind":"pith_short_12","alias_value":"D4YVR5MFZI7O","created_at":"2026-07-05T10:34:27Z"},{"alias_kind":"pith_short_16","alias_value":"D4YVR5MFZI7OIXCD","created_at":"2026-07-05T10:34:27Z"},{"alias_kind":"pith_short_8","alias_value":"D4YVR5MF","created_at":"2026-07-05T10:34:27Z"}],"graph_snapshots":[{"event_id":"sha256:41baba1d6120840371fca455166f105cc6bc76e607ee88f8ba77dce1fa6b6af9","target":"graph","created_at":"2026-07-05T10:34:27Z","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/2503.14928/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-guided speech generation aims to produce authentic speech from facial appearance or lip motions without relying on auditory signals, offering significant potential for applications such as dubbing in filmmaking and assisting individuals with aphonia. Despite recent progress, existing methods struggle to achieve unified cross-modal alignment across semantics, timbre, and emotional prosody from visual cues, prompting us to propose Consistent Video-to-Speech (CV2S) as an extended task to enhance cross-modal consistency. To tackle emerging challenges, we introduce ImaginTalk, a novel cross-","authors_text":"Hongming Shan, Jiaxin Ye","cross_cats":["cs.AI","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-19T06:28:17Z","title":"Shushing! Let's Imagine an Authentic Speech from the Silent Video"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.14928","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:b41bf29fd0fa5cf2c342f31eac53065c987431b0fe644d969848e46f635be214","target":"record","created_at":"2026-07-05T10:34:27Z","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":"5f3f0c6a32b1c896b1489ccb7cfe42931f9a8fc8a05a1ee8ed7b11d988bc493e","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-19T06:28:17Z","title_canon_sha256":"d13e331d0a574ff5ed14501b985914a6b47882ea31345a2309d2243aa9afd5f4"},"schema_version":"1.0","source":{"id":"2503.14928","kind":"arxiv","version":1}},"canonical_sha256":"1f3158f585ca3ee45c4375ad0a0ed3b724cdb886b4153e23793fee4ae0267f2d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1f3158f585ca3ee45c4375ad0a0ed3b724cdb886b4153e23793fee4ae0267f2d","first_computed_at":"2026-07-05T10:34:27.591055Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:34:27.591055Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EYJ0+cyQp9FA0gtp5K+Qcl/gLK2or2kd9ohszJ27Gq7Jec4qVZUUM+uiyT4EjrugHmQCvj5WCLeQjjtKk66sDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:34:27.591644Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.14928","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b41bf29fd0fa5cf2c342f31eac53065c987431b0fe644d969848e46f635be214","sha256:41baba1d6120840371fca455166f105cc6bc76e607ee88f8ba77dce1fa6b6af9"],"state_sha256":"d4d1f603c394eb350cce85f6e7c48ebedce24e11c05ee775bc95b877ef872a15"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8PIqQ64M82baU5i2nZw6kVCHzyUmit8/A7LdYapF+SoGhIJrp0E6im6rEzAMz+AVkvRb0gW7bQP5rQu+uHlJBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T05:55:18.203464Z","bundle_sha256":"5118cda31242609f8f4816294b211940af7c3a6fc889abe3669c97634bfde50c"}}