{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:HA5MWQ6P2A4HY5ZL57YNPCGMVD","short_pith_number":"pith:HA5MWQ6P","canonical_record":{"source":{"id":"2505.16279","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2025-05-22T06:23:05Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"709556b058b9924c90a42040a1274149531d83f57e51382d990ff16e0f43f194","abstract_canon_sha256":"f84e244ae675aaec8cef837ab6b978817230d9ca53db33824d842d0509a3ba0c"},"schema_version":"1.0"},"canonical_sha256":"383acb43cfd0387c772beff0d788cca8e9cf60c0d07c7dfb99f37d4b1a8ba10b","source":{"kind":"arxiv","id":"2505.16279","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.16279","created_at":"2026-07-05T11:07:32Z"},{"alias_kind":"arxiv_version","alias_value":"2505.16279v1","created_at":"2026-07-05T11:07:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16279","created_at":"2026-07-05T11:07:32Z"},{"alias_kind":"pith_short_12","alias_value":"HA5MWQ6P2A4H","created_at":"2026-07-05T11:07:32Z"},{"alias_kind":"pith_short_16","alias_value":"HA5MWQ6P2A4HY5ZL","created_at":"2026-07-05T11:07:32Z"},{"alias_kind":"pith_short_8","alias_value":"HA5MWQ6P","created_at":"2026-07-05T11:07:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:HA5MWQ6P2A4HY5ZL57YNPCGMVD","target":"record","payload":{"canonical_record":{"source":{"id":"2505.16279","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2025-05-22T06:23:05Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"709556b058b9924c90a42040a1274149531d83f57e51382d990ff16e0f43f194","abstract_canon_sha256":"f84e244ae675aaec8cef837ab6b978817230d9ca53db33824d842d0509a3ba0c"},"schema_version":"1.0"},"canonical_sha256":"383acb43cfd0387c772beff0d788cca8e9cf60c0d07c7dfb99f37d4b1a8ba10b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:07:32.656021Z","signature_b64":"UUYcm4cFfCT/Q2/WP5EZBVyAGpee/16BFOjk5/MQEMWTCxYRjJnx0rN9MV/1zOkSgdRb+8OmgEdW9i55BV3CAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"383acb43cfd0387c772beff0d788cca8e9cf60c0d07c7dfb99f37d4b1a8ba10b","last_reissued_at":"2026-07-05T11:07:32.655396Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:07:32.655396Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.16279","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":"2026-07-05T11:07:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9DxHk6khLtlVFBZfZ8Fu/bYer3Wo61nX6MwZedI8um6J1wQpAWDfe+kebu0LsDcilymxLaRjGj739AxbvlPzBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T16:17:31.441293Z"},"content_sha256":"888e437e271d5f3d1af70ebd1866610915c1ef740884e3df8b107c656e835bd3","schema_version":"1.0","event_id":"sha256:888e437e271d5f3d1af70ebd1866610915c1ef740884e3df8b107c656e835bd3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:HA5MWQ6P2A4HY5ZL57YNPCGMVD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MM-MovieDubber: Towards Multi-Modal Learning for Multi-Modal Movie Dubbing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.MM","authors_text":"Chaofan Ding, Huan Yang, Junjie Zheng, Lei Xie, Xinhan Di, Yihan Fan, Yunming Liang, Zihao Chen","submitted_at":"2025-05-22T06:23:05Z","abstract_excerpt":"Current movie dubbing technology can produce the desired speech using a reference voice and input video, maintaining perfect synchronization with the visuals while effectively conveying the intended emotions. However, crucial aspects of movie dubbing, including adaptation to various dubbing styles, effective handling of dialogue, narration, and monologues, as well as consideration of subtle details such as speaker age and gender, remain insufficiently explored. To tackle these challenges, we introduce a multi-modal generative framework. First, it utilizes a multi-modal large vision-language mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16279","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/2505.16279/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":"2026-07-05T11:07:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VWePfycUB+lG9kQmfobD8yZFmAlo0214UF8uB3iDxDW7u9TiXA1xcX2cSqqXmPL47OwLzAYIsZr3F5JuWoEzAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T16:17:31.442135Z"},"content_sha256":"4a4bc8c149520b0a1d3a7dbbd232992d0e27002ed6cfdb5c50b344d16349e888","schema_version":"1.0","event_id":"sha256:4a4bc8c149520b0a1d3a7dbbd232992d0e27002ed6cfdb5c50b344d16349e888"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HA5MWQ6P2A4HY5ZL57YNPCGMVD/bundle.json","state_url":"https://pith.science/pith/HA5MWQ6P2A4HY5ZL57YNPCGMVD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HA5MWQ6P2A4HY5ZL57YNPCGMVD/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":"2026-08-08T16:17:31Z","links":{"resolver":"https://pith.science/pith/HA5MWQ6P2A4HY5ZL57YNPCGMVD","bundle":"https://pith.science/pith/HA5MWQ6P2A4HY5ZL57YNPCGMVD/bundle.json","state":"https://pith.science/pith/HA5MWQ6P2A4HY5ZL57YNPCGMVD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HA5MWQ6P2A4HY5ZL57YNPCGMVD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HA5MWQ6P2A4HY5ZL57YNPCGMVD","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":"f84e244ae675aaec8cef837ab6b978817230d9ca53db33824d842d0509a3ba0c","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2025-05-22T06:23:05Z","title_canon_sha256":"709556b058b9924c90a42040a1274149531d83f57e51382d990ff16e0f43f194"},"schema_version":"1.0","source":{"id":"2505.16279","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.16279","created_at":"2026-07-05T11:07:32Z"},{"alias_kind":"arxiv_version","alias_value":"2505.16279v1","created_at":"2026-07-05T11:07:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16279","created_at":"2026-07-05T11:07:32Z"},{"alias_kind":"pith_short_12","alias_value":"HA5MWQ6P2A4H","created_at":"2026-07-05T11:07:32Z"},{"alias_kind":"pith_short_16","alias_value":"HA5MWQ6P2A4HY5ZL","created_at":"2026-07-05T11:07:32Z"},{"alias_kind":"pith_short_8","alias_value":"HA5MWQ6P","created_at":"2026-07-05T11:07:32Z"}],"graph_snapshots":[{"event_id":"sha256:4a4bc8c149520b0a1d3a7dbbd232992d0e27002ed6cfdb5c50b344d16349e888","target":"graph","created_at":"2026-07-05T11:07:32Z","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/2505.16279/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current movie dubbing technology can produce the desired speech using a reference voice and input video, maintaining perfect synchronization with the visuals while effectively conveying the intended emotions. However, crucial aspects of movie dubbing, including adaptation to various dubbing styles, effective handling of dialogue, narration, and monologues, as well as consideration of subtle details such as speaker age and gender, remain insufficiently explored. To tackle these challenges, we introduce a multi-modal generative framework. First, it utilizes a multi-modal large vision-language mo","authors_text":"Chaofan Ding, Huan Yang, Junjie Zheng, Lei Xie, Xinhan Di, Yihan Fan, Yunming Liang, Zihao Chen","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2025-05-22T06:23:05Z","title":"MM-MovieDubber: Towards Multi-Modal Learning for Multi-Modal Movie Dubbing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16279","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":"sha256:888e437e271d5f3d1af70ebd1866610915c1ef740884e3df8b107c656e835bd3","target":"record","created_at":"2026-07-05T11:07:32Z","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":"f84e244ae675aaec8cef837ab6b978817230d9ca53db33824d842d0509a3ba0c","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2025-05-22T06:23:05Z","title_canon_sha256":"709556b058b9924c90a42040a1274149531d83f57e51382d990ff16e0f43f194"},"schema_version":"1.0","source":{"id":"2505.16279","kind":"arxiv","version":1}},"canonical_sha256":"383acb43cfd0387c772beff0d788cca8e9cf60c0d07c7dfb99f37d4b1a8ba10b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"383acb43cfd0387c772beff0d788cca8e9cf60c0d07c7dfb99f37d4b1a8ba10b","first_computed_at":"2026-07-05T11:07:32.655396Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:07:32.655396Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UUYcm4cFfCT/Q2/WP5EZBVyAGpee/16BFOjk5/MQEMWTCxYRjJnx0rN9MV/1zOkSgdRb+8OmgEdW9i55BV3CAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:07:32.656021Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.16279","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:888e437e271d5f3d1af70ebd1866610915c1ef740884e3df8b107c656e835bd3","sha256:4a4bc8c149520b0a1d3a7dbbd232992d0e27002ed6cfdb5c50b344d16349e888"],"state_sha256":"8cf55b96f1ff3982b99f6411afbeaaf121ca50b9052f45e2205f53ed0ff748c1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SlOgZ5qkwoOhD/Fzhadjn8obVHVz4P/JsB7A2ZNIkp9HtpnqqWbI5CeiVP6RbNfGtOEWGjrvx+dj+NhipUNjDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T16:17:31.447568Z","bundle_sha256":"08f8b4b0ac0843c1c60856f75382fa912356f3754e83fee0efc3275ed547291f"}}