{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:LBATHC6EJUDCLT3E6ANQ2GVQX2","short_pith_number":"pith:LBATHC6E","canonical_record":{"source":{"id":"2408.11593","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2024-08-21T12:59:42Z","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"title_canon_sha256":"9591cabd0ea7f5a9e583b706c7d756e403918b8f53007fb668af9515f06101e7","abstract_canon_sha256":"6bcc22a1c30fc67dac230374194c678b42e511d7b3c9ba72dd89f8e02701167a"},"schema_version":"1.0"},"canonical_sha256":"5841338bc44d0625cf64f01b0d1ab0bea11f1ee8e9ad89d3a5d66845186220f0","source":{"kind":"arxiv","id":"2408.11593","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.11593","created_at":"2026-07-05T09:02:41Z"},{"alias_kind":"arxiv_version","alias_value":"2408.11593v3","created_at":"2026-07-05T09:02:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.11593","created_at":"2026-07-05T09:02:41Z"},{"alias_kind":"pith_short_12","alias_value":"LBATHC6EJUDC","created_at":"2026-07-05T09:02:41Z"},{"alias_kind":"pith_short_16","alias_value":"LBATHC6EJUDCLT3E","created_at":"2026-07-05T09:02:41Z"},{"alias_kind":"pith_short_8","alias_value":"LBATHC6E","created_at":"2026-07-05T09:02:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:LBATHC6EJUDCLT3E6ANQ2GVQX2","target":"record","payload":{"canonical_record":{"source":{"id":"2408.11593","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2024-08-21T12:59:42Z","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"title_canon_sha256":"9591cabd0ea7f5a9e583b706c7d756e403918b8f53007fb668af9515f06101e7","abstract_canon_sha256":"6bcc22a1c30fc67dac230374194c678b42e511d7b3c9ba72dd89f8e02701167a"},"schema_version":"1.0"},"canonical_sha256":"5841338bc44d0625cf64f01b0d1ab0bea11f1ee8e9ad89d3a5d66845186220f0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:02:41.763877Z","signature_b64":"iY+kdZuBxrKRiVLIU0jN+6HeP8NSsVYJILEcmnXhSFyQh86FDZXXCGq7Ux+pDPWwoPjRkmuqfbqHu52nNUQyAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5841338bc44d0625cf64f01b0d1ab0bea11f1ee8e9ad89d3a5d66845186220f0","last_reissued_at":"2026-07-05T09:02:41.763361Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:02:41.763361Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.11593","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:02:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jVALumTMaOJltx9/C6VTMZiG1jKo9wqhMdUyHLXt2uHNt1RMsamZpdigl2lKa79mkY/7zc7TTOTQ9PbsmnF9Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T15:47:32.031378Z"},"content_sha256":"acf39cff5095059a9fdd58c987fe587b6f1625f0622606b9485c58560850153f","schema_version":"1.0","event_id":"sha256:acf39cff5095059a9fdd58c987fe587b6f1625f0622606b9485c58560850153f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:LBATHC6EJUDCLT3E6ANQ2GVQX2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MCDubber: Multimodal Context-Aware Expressive Video Dubbing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.SD","eess.AS"],"primary_cat":"cs.MM","authors_text":"De Hu, Feilong Bao, Guanglai Gao, Rui Liu, Yuan Zhao, Zhenqi Jia","submitted_at":"2024-08-21T12:59:42Z","abstract_excerpt":"Automatic Video Dubbing (AVD) aims to take the given script and generate speech that aligns with lip motion and prosody expressiveness. Current AVD models mainly utilize visual information of the current sentence to enhance the prosody of synthesized speech. However, it is crucial to consider whether the prosody of the generated dubbing aligns with the multimodal context, as the dubbing will be combined with the original context in the final video. This aspect has been overlooked in previous studies. To address this issue, we propose a Multimodal Context-aware video Dubbing model, termed \\text"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.11593","kind":"arxiv","version":3},"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/2408.11593/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":"2026-07-05T09:02:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/x3kydMdMWDt4r4fKhTxKuJMvZNv2oRqW1PxzrtnpBlb/+FjaSHOieHC9OpkccpZf5wiw4GM6OlBYtOJrxuuCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T15:47:32.032244Z"},"content_sha256":"6cdd94e13447b732fe41d0685931368d850adc90e837388bab09d68cd51333ba","schema_version":"1.0","event_id":"sha256:6cdd94e13447b732fe41d0685931368d850adc90e837388bab09d68cd51333ba"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LBATHC6EJUDCLT3E6ANQ2GVQX2/bundle.json","state_url":"https://pith.science/pith/LBATHC6EJUDCLT3E6ANQ2GVQX2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LBATHC6EJUDCLT3E6ANQ2GVQX2/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":"2026-08-11T15:47:32Z","links":{"resolver":"https://pith.science/pith/LBATHC6EJUDCLT3E6ANQ2GVQX2","bundle":"https://pith.science/pith/LBATHC6EJUDCLT3E6ANQ2GVQX2/bundle.json","state":"https://pith.science/pith/LBATHC6EJUDCLT3E6ANQ2GVQX2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LBATHC6EJUDCLT3E6ANQ2GVQX2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LBATHC6EJUDCLT3E6ANQ2GVQX2","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":"6bcc22a1c30fc67dac230374194c678b42e511d7b3c9ba72dd89f8e02701167a","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2024-08-21T12:59:42Z","title_canon_sha256":"9591cabd0ea7f5a9e583b706c7d756e403918b8f53007fb668af9515f06101e7"},"schema_version":"1.0","source":{"id":"2408.11593","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.11593","created_at":"2026-07-05T09:02:41Z"},{"alias_kind":"arxiv_version","alias_value":"2408.11593v3","created_at":"2026-07-05T09:02:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.11593","created_at":"2026-07-05T09:02:41Z"},{"alias_kind":"pith_short_12","alias_value":"LBATHC6EJUDC","created_at":"2026-07-05T09:02:41Z"},{"alias_kind":"pith_short_16","alias_value":"LBATHC6EJUDCLT3E","created_at":"2026-07-05T09:02:41Z"},{"alias_kind":"pith_short_8","alias_value":"LBATHC6E","created_at":"2026-07-05T09:02:41Z"}],"graph_snapshots":[{"event_id":"sha256:6cdd94e13447b732fe41d0685931368d850adc90e837388bab09d68cd51333ba","target":"graph","created_at":"2026-07-05T09:02:41Z","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/2408.11593/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Automatic Video Dubbing (AVD) aims to take the given script and generate speech that aligns with lip motion and prosody expressiveness. Current AVD models mainly utilize visual information of the current sentence to enhance the prosody of synthesized speech. However, it is crucial to consider whether the prosody of the generated dubbing aligns with the multimodal context, as the dubbing will be combined with the original context in the final video. This aspect has been overlooked in previous studies. To address this issue, we propose a Multimodal Context-aware video Dubbing model, termed \\text","authors_text":"De Hu, Feilong Bao, Guanglai Gao, Rui Liu, Yuan Zhao, Zhenqi Jia","cross_cats":["cs.CV","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2024-08-21T12:59:42Z","title":"MCDubber: Multimodal Context-Aware Expressive Video Dubbing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.11593","kind":"arxiv","version":3},"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:acf39cff5095059a9fdd58c987fe587b6f1625f0622606b9485c58560850153f","target":"record","created_at":"2026-07-05T09:02:41Z","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":"6bcc22a1c30fc67dac230374194c678b42e511d7b3c9ba72dd89f8e02701167a","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2024-08-21T12:59:42Z","title_canon_sha256":"9591cabd0ea7f5a9e583b706c7d756e403918b8f53007fb668af9515f06101e7"},"schema_version":"1.0","source":{"id":"2408.11593","kind":"arxiv","version":3}},"canonical_sha256":"5841338bc44d0625cf64f01b0d1ab0bea11f1ee8e9ad89d3a5d66845186220f0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5841338bc44d0625cf64f01b0d1ab0bea11f1ee8e9ad89d3a5d66845186220f0","first_computed_at":"2026-07-05T09:02:41.763361Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:02:41.763361Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iY+kdZuBxrKRiVLIU0jN+6HeP8NSsVYJILEcmnXhSFyQh86FDZXXCGq7Ux+pDPWwoPjRkmuqfbqHu52nNUQyAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:02:41.763877Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.11593","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:acf39cff5095059a9fdd58c987fe587b6f1625f0622606b9485c58560850153f","sha256:6cdd94e13447b732fe41d0685931368d850adc90e837388bab09d68cd51333ba"],"state_sha256":"da20ffc81cc075051603a8427a4cf91d8c47bf5623ee2f9bf072d2c1ba631e2e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bhm1Ty9ZvjWXfD7vcU+s8cAvnY2ifUlBeHqZMm93dl2eOM6nTz77P6olq4pYaV/nJghbYfSSzKLrnbRVX+ZwBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T15:47:32.035883Z","bundle_sha256":"f2f7005d74168b2de155db4fdc1e11b0e5198c31256d86c8967d58b0582867c9"}}