{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MWYYVIFN4KGGDJ4DOLVLOLYYDE","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":"504df8fe8c0bf6b59bcd82336bea37cc947a8cb8f78514207be29892faa1967c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-31T01:51:09Z","title_canon_sha256":"083d039b2c377559e14c248be01c647e842ccbee00e75eb17604049767d6940f"},"schema_version":"1.0","source":{"id":"2503.23660","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.23660","created_at":"2026-07-05T10:41:57Z"},{"alias_kind":"arxiv_version","alias_value":"2503.23660v1","created_at":"2026-07-05T10:41:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.23660","created_at":"2026-07-05T10:41:57Z"},{"alias_kind":"pith_short_12","alias_value":"MWYYVIFN4KGG","created_at":"2026-07-05T10:41:57Z"},{"alias_kind":"pith_short_16","alias_value":"MWYYVIFN4KGGDJ4D","created_at":"2026-07-05T10:41:57Z"},{"alias_kind":"pith_short_8","alias_value":"MWYYVIFN","created_at":"2026-07-05T10:41:57Z"}],"graph_snapshots":[{"event_id":"sha256:d50559ed747c208528121b9bf93acefd23be149dc935ee1b510edfd2d46b82d4","target":"graph","created_at":"2026-07-05T10:41:57Z","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/2503.23660/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current movie dubbing technology can generate the desired voice from a given speech prompt, ensuring good synchronization between speech and visuals while accurately conveying the intended emotions. However, in movie dubbing, key aspects such as adapting to different dubbing styles, handling dialogue, narration, and monologue effectively, and understanding subtle details like the age and gender of speakers, have not been well studied. To address this challenge, we propose a framework of multi-modal large language model. First, it utilizes multimodal Chain-of-Thought (CoT) reasoning methods on ","authors_text":"Chaofan Ding, Junjie Zheng, Xinhan Di, Zihao Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-31T01:51:09Z","title":"DeepDubber-V1: Towards High Quality and Dialogue, Narration, Monologue Adaptive Movie Dubbing Via Multi-Modal Chain-of-Thoughts Reasoning Guidance"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.23660","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:f74378586a1bfcc05b10ab1f4431d00721d664a4de97a876c1b284e25b80ef75","target":"record","created_at":"2026-07-05T10:41:57Z","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":"504df8fe8c0bf6b59bcd82336bea37cc947a8cb8f78514207be29892faa1967c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-31T01:51:09Z","title_canon_sha256":"083d039b2c377559e14c248be01c647e842ccbee00e75eb17604049767d6940f"},"schema_version":"1.0","source":{"id":"2503.23660","kind":"arxiv","version":1}},"canonical_sha256":"65b18aa0ade28c61a78372eab72f18191a16e35f4c09b06b6a3b1f23b7461e32","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"65b18aa0ade28c61a78372eab72f18191a16e35f4c09b06b6a3b1f23b7461e32","first_computed_at":"2026-07-05T10:41:57.289691Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:41:57.289691Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"t21Q910gCOQRfEgvK5mJ6BUfj0ZQpYQEpyzlOTaHF1f2SzKBrOVeJmG/2LLVZpQMa6HvViPHpmh0oLWqmsgUCw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:41:57.290161Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.23660","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f74378586a1bfcc05b10ab1f4431d00721d664a4de97a876c1b284e25b80ef75","sha256:d50559ed747c208528121b9bf93acefd23be149dc935ee1b510edfd2d46b82d4"],"state_sha256":"f585242e16d53de3571de4da56b93d7474953fd258d8d8a51263b3a19285c6d2"}