{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TT5FETZWD6HXAT7JK4DTAA5GSQ","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":"620dae80de74b96fbbbf45088bd7429a9c57cbba21f09efff7b64edf8532a0d9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-20T01:28:34Z","title_canon_sha256":"4184471ade15aac3f2b7379754ca34a52f482f05cd0053d4e420b98d12c4dc5f"},"schema_version":"1.0","source":{"id":"2402.12636","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.12636","created_at":"2026-07-05T08:38:57Z"},{"alias_kind":"arxiv_version","alias_value":"2402.12636v3","created_at":"2026-07-05T08:38:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.12636","created_at":"2026-07-05T08:38:57Z"},{"alias_kind":"pith_short_12","alias_value":"TT5FETZWD6HX","created_at":"2026-07-05T08:38:57Z"},{"alias_kind":"pith_short_16","alias_value":"TT5FETZWD6HXAT7J","created_at":"2026-07-05T08:38:57Z"},{"alias_kind":"pith_short_8","alias_value":"TT5FETZW","created_at":"2026-07-05T08:38:57Z"}],"graph_snapshots":[{"event_id":"sha256:610cd5ef23bf25530e07d730b395b13b747700c73b15ab3046cbf269c2a9e78c","target":"graph","created_at":"2026-07-05T08:38:57Z","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/2402.12636/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Given a script, the challenge in Movie Dubbing (Visual Voice Cloning, V2C) is to generate speech that aligns well with the video in both time and emotion, based on the tone of a reference audio track. Existing state-of-the-art V2C models break the phonemes in the script according to the divisions between video frames, which solves the temporal alignment problem but leads to incomplete phoneme pronunciation and poor identity stability. To address this problem, we propose StyleDubber, which switches dubbing learning from the frame level to phoneme level. It contains three main components: (1) A ","authors_text":"Amin Beheshti, Anton van den Hengel, Chenggang Yan, Gaoxiang Cong, Liang Li, Ming-Hsuan Yang, Qingming Huang, Yuankai Qi, Zhedong Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-20T01:28:34Z","title":"StyleDubber: Towards Multi-Scale Style Learning for Movie Dubbing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.12636","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:efa4189dd0e459ab327a4f12b8acf96c8ba62662657bde16a7c4e724231a0ce4","target":"record","created_at":"2026-07-05T08:38:57Z","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":"620dae80de74b96fbbbf45088bd7429a9c57cbba21f09efff7b64edf8532a0d9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-20T01:28:34Z","title_canon_sha256":"4184471ade15aac3f2b7379754ca34a52f482f05cd0053d4e420b98d12c4dc5f"},"schema_version":"1.0","source":{"id":"2402.12636","kind":"arxiv","version":3}},"canonical_sha256":"9cfa524f361f8f704fe957073003a694366a2a5acd59eda5837f0d4f133577d5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9cfa524f361f8f704fe957073003a694366a2a5acd59eda5837f0d4f133577d5","first_computed_at":"2026-07-05T08:38:57.652383Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:38:57.652383Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jiociPhjJMF9tGguBcW9eVEmqAJtAv7SYbejC2+8OzvaQscBtfx4TKb9rzhBvf6miIrkmt1eD+A8AOZ4iCUUDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:38:57.652799Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.12636","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:efa4189dd0e459ab327a4f12b8acf96c8ba62662657bde16a7c4e724231a0ce4","sha256:610cd5ef23bf25530e07d730b395b13b747700c73b15ab3046cbf269c2a9e78c"],"state_sha256":"d08dfea58af331ee7440244534181cbaeebcd35343e4781434d93013601433c1"}