{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5QRGLHCURUSY2EVVFTMDAARIAO","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":"f6c60989ea6dcaa551a6e0d012ec0d6088a59659fff3f7173ece794ab8eb7ead","cross_cats_sorted":["cs.CL","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2024-12-25T02:41:13Z","title_canon_sha256":"641d034360fb32258c2936e97c4893f676d64abc20651d2b54e470a698dad8b2"},"schema_version":"1.0","source":{"id":"2412.18748","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.18748","created_at":"2026-07-05T09:55:36Z"},{"alias_kind":"arxiv_version","alias_value":"2412.18748v2","created_at":"2026-07-05T09:55:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18748","created_at":"2026-07-05T09:55:36Z"},{"alias_kind":"pith_short_12","alias_value":"5QRGLHCURUSY","created_at":"2026-07-05T09:55:36Z"},{"alias_kind":"pith_short_16","alias_value":"5QRGLHCURUSY2EVV","created_at":"2026-07-05T09:55:36Z"},{"alias_kind":"pith_short_8","alias_value":"5QRGLHCU","created_at":"2026-07-05T09:55:36Z"}],"graph_snapshots":[{"event_id":"sha256:6d38162764888fca23ffb720a83b4168529b904c450e27a7c211b62c8a84b8b8","target":"graph","created_at":"2026-07-05T09:55:36Z","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/2412.18748/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Automatic Video Dubbing (AVD) generates speech aligned with lip motion and facial emotion from scripts. Recent research focuses on modeling multimodal context to enhance prosody expressiveness but overlooks two key issues: 1) Multiscale prosody expression attributes in the context influence the current sentence's prosody. 2) Prosody cues in context interact with the current sentence, impacting the final prosody expressiveness. To tackle these challenges, we propose M2CI-Dubber, a Multiscale Multimodal Context Interaction scheme for AVD. This scheme includes two shared M2CI encoders to model th","authors_text":"Gaoxiang Cong, Rui Liu, Yuan Zhao","cross_cats":["cs.CL","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2024-12-25T02:41:13Z","title":"Towards Expressive Video Dubbing with Multiscale Multimodal Context Interaction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18748","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:c77fc2bada0bc5a29fe3ee81b992bb8e2b57778ef1b4d3b9330282932b87ea04","target":"record","created_at":"2026-07-05T09:55:36Z","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":"f6c60989ea6dcaa551a6e0d012ec0d6088a59659fff3f7173ece794ab8eb7ead","cross_cats_sorted":["cs.CL","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2024-12-25T02:41:13Z","title_canon_sha256":"641d034360fb32258c2936e97c4893f676d64abc20651d2b54e470a698dad8b2"},"schema_version":"1.0","source":{"id":"2412.18748","kind":"arxiv","version":2}},"canonical_sha256":"ec22659c548d258d12b52cd83002280380f6c36e768ec7096b535d7b0fa23a2a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ec22659c548d258d12b52cd83002280380f6c36e768ec7096b535d7b0fa23a2a","first_computed_at":"2026-07-05T09:55:36.165578Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:55:36.165578Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vduq31O5HpAIbInLjjTB5aLDMDH8n32/JBMF+91od2skfFlUhCguUC5DQlfS43kTHtdBVKhNuqN2z/bAZzS/AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:55:36.166047Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.18748","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c77fc2bada0bc5a29fe3ee81b992bb8e2b57778ef1b4d3b9330282932b87ea04","sha256:6d38162764888fca23ffb720a83b4168529b904c450e27a7c211b62c8a84b8b8"],"state_sha256":"b4ef16c3ac963a085ad42f3d19a5abf7594234272ce590741b3e92f067095bcb"}