{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:SNTVCG6IWNLKSXNINH2FT4D2GV","short_pith_number":"pith:SNTVCG6I","canonical_record":{"source":{"id":"2504.02386","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-03T08:24:47Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"849f415debbbc5b8b265ce337cdbdae8ad796bbe1eeaa3cf6edf3de1079d589e","abstract_canon_sha256":"14ab27861f161e2b3d8222dac65dcc494e2b89145750ef692ab5e55748758bab"},"schema_version":"1.0"},"canonical_sha256":"9367511bc8b356a95da869f459f07a3551fbd4129196ebee90b7aea87e4e8987","source":{"kind":"arxiv","id":"2504.02386","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.02386","created_at":"2026-07-05T10:43:56Z"},{"alias_kind":"arxiv_version","alias_value":"2504.02386v1","created_at":"2026-07-05T10:43:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.02386","created_at":"2026-07-05T10:43:56Z"},{"alias_kind":"pith_short_12","alias_value":"SNTVCG6IWNLK","created_at":"2026-07-05T10:43:56Z"},{"alias_kind":"pith_short_16","alias_value":"SNTVCG6IWNLKSXNI","created_at":"2026-07-05T10:43:56Z"},{"alias_kind":"pith_short_8","alias_value":"SNTVCG6I","created_at":"2026-07-05T10:43:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:SNTVCG6IWNLKSXNINH2FT4D2GV","target":"record","payload":{"canonical_record":{"source":{"id":"2504.02386","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-03T08:24:47Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"849f415debbbc5b8b265ce337cdbdae8ad796bbe1eeaa3cf6edf3de1079d589e","abstract_canon_sha256":"14ab27861f161e2b3d8222dac65dcc494e2b89145750ef692ab5e55748758bab"},"schema_version":"1.0"},"canonical_sha256":"9367511bc8b356a95da869f459f07a3551fbd4129196ebee90b7aea87e4e8987","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:43:56.117376Z","signature_b64":"4hmlE+TFzzfUvedr89zE84COXx6UGU5kny3OYbcTuLmumvgobSVLTXlkO+3JStGb1QcYSukwl/I+XvFM0iFYAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9367511bc8b356a95da869f459f07a3551fbd4129196ebee90b7aea87e4e8987","last_reissued_at":"2026-07-05T10:43:56.116779Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:43:56.116779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.02386","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":"2026-07-05T10:43:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i4dfGzq45mDRwtn7mlacmzFmBLzjMgA9vOnlh2RHFSyV3GOULc79s06NzCkRlGyUQAV/6UUCELQx+4ZOj2eQCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:44:20.724607Z"},"content_sha256":"a5411a85a40675c2ae5ac561618e3c501729132239fb9f0815ceb451840e2771","schema_version":"1.0","event_id":"sha256:a5411a85a40675c2ae5ac561618e3c501729132239fb9f0815ceb451840e2771"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:SNTVCG6IWNLKSXNINH2FT4D2GV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VoiceCraft-Dub: Automated Video Dubbing with Neural Codec Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CV","authors_text":"David Harwath, Jeongsoo Choi, Joon Son Chung, Kim Sung-Bin, Puyuan Peng, Tae-Hyun Oh","submitted_at":"2025-04-03T08:24:47Z","abstract_excerpt":"We present VoiceCraft-Dub, a novel approach for automated video dubbing that synthesizes high-quality speech from text and facial cues. This task has broad applications in filmmaking, multimedia creation, and assisting voice-impaired individuals. Building on the success of Neural Codec Language Models (NCLMs) for speech synthesis, our method extends their capabilities by incorporating video features, ensuring that synthesized speech is time-synchronized and expressively aligned with facial movements while preserving natural prosody. To inject visual cues, we design adapters to align facial fea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.02386","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/2504.02386/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":"2026-07-05T10:43:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uHnCMyEXjq1tEpyTbSbCzvb0VGmWNSWDPVkgCHv2RupskTxXlQAF+gnRdnDREvJizLtYG5lXkpUjhF+8N3UEDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:44:20.724979Z"},"content_sha256":"303547e874308b347971eb0a6aa304923bd7cf18da303668e87ca82b005b6e10","schema_version":"1.0","event_id":"sha256:303547e874308b347971eb0a6aa304923bd7cf18da303668e87ca82b005b6e10"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SNTVCG6IWNLKSXNINH2FT4D2GV/bundle.json","state_url":"https://pith.science/pith/SNTVCG6IWNLKSXNINH2FT4D2GV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SNTVCG6IWNLKSXNINH2FT4D2GV/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":"2026-07-06T18:44:20Z","links":{"resolver":"https://pith.science/pith/SNTVCG6IWNLKSXNINH2FT4D2GV","bundle":"https://pith.science/pith/SNTVCG6IWNLKSXNINH2FT4D2GV/bundle.json","state":"https://pith.science/pith/SNTVCG6IWNLKSXNINH2FT4D2GV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SNTVCG6IWNLKSXNINH2FT4D2GV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SNTVCG6IWNLKSXNINH2FT4D2GV","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":"14ab27861f161e2b3d8222dac65dcc494e2b89145750ef692ab5e55748758bab","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-03T08:24:47Z","title_canon_sha256":"849f415debbbc5b8b265ce337cdbdae8ad796bbe1eeaa3cf6edf3de1079d589e"},"schema_version":"1.0","source":{"id":"2504.02386","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.02386","created_at":"2026-07-05T10:43:56Z"},{"alias_kind":"arxiv_version","alias_value":"2504.02386v1","created_at":"2026-07-05T10:43:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.02386","created_at":"2026-07-05T10:43:56Z"},{"alias_kind":"pith_short_12","alias_value":"SNTVCG6IWNLK","created_at":"2026-07-05T10:43:56Z"},{"alias_kind":"pith_short_16","alias_value":"SNTVCG6IWNLKSXNI","created_at":"2026-07-05T10:43:56Z"},{"alias_kind":"pith_short_8","alias_value":"SNTVCG6I","created_at":"2026-07-05T10:43:56Z"}],"graph_snapshots":[{"event_id":"sha256:303547e874308b347971eb0a6aa304923bd7cf18da303668e87ca82b005b6e10","target":"graph","created_at":"2026-07-05T10:43:56Z","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/2504.02386/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present VoiceCraft-Dub, a novel approach for automated video dubbing that synthesizes high-quality speech from text and facial cues. This task has broad applications in filmmaking, multimedia creation, and assisting voice-impaired individuals. Building on the success of Neural Codec Language Models (NCLMs) for speech synthesis, our method extends their capabilities by incorporating video features, ensuring that synthesized speech is time-synchronized and expressively aligned with facial movements while preserving natural prosody. To inject visual cues, we design adapters to align facial fea","authors_text":"David Harwath, Jeongsoo Choi, Joon Son Chung, Kim Sung-Bin, Puyuan Peng, Tae-Hyun Oh","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-03T08:24:47Z","title":"VoiceCraft-Dub: Automated Video Dubbing with Neural Codec Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.02386","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:a5411a85a40675c2ae5ac561618e3c501729132239fb9f0815ceb451840e2771","target":"record","created_at":"2026-07-05T10:43:56Z","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":"14ab27861f161e2b3d8222dac65dcc494e2b89145750ef692ab5e55748758bab","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-03T08:24:47Z","title_canon_sha256":"849f415debbbc5b8b265ce337cdbdae8ad796bbe1eeaa3cf6edf3de1079d589e"},"schema_version":"1.0","source":{"id":"2504.02386","kind":"arxiv","version":1}},"canonical_sha256":"9367511bc8b356a95da869f459f07a3551fbd4129196ebee90b7aea87e4e8987","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9367511bc8b356a95da869f459f07a3551fbd4129196ebee90b7aea87e4e8987","first_computed_at":"2026-07-05T10:43:56.116779Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:43:56.116779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4hmlE+TFzzfUvedr89zE84COXx6UGU5kny3OYbcTuLmumvgobSVLTXlkO+3JStGb1QcYSukwl/I+XvFM0iFYAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:43:56.117376Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.02386","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a5411a85a40675c2ae5ac561618e3c501729132239fb9f0815ceb451840e2771","sha256:303547e874308b347971eb0a6aa304923bd7cf18da303668e87ca82b005b6e10"],"state_sha256":"0ccd15204a34965b603753f9503ff4d22e447d9d4281d028bed45750a9d7e84f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vqbYh/uFDkwRQdYZ65nu3RIYcQcUpxrNKAtzYIwkDiXx2GpDvv7RoZa7418CMuBXQSSl7DFb///0VmvPVla6BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T18:44:20.726866Z","bundle_sha256":"7b43d430f5527b7add71aabf4f97a765266a965870d626eb4b6c956db683351b"}}