{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:3EQ76VC7AHNWD6EORUL24YRR6R","short_pith_number":"pith:3EQ76VC7","canonical_record":{"source":{"id":"2604.11283","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-04-13T10:42:31Z","cross_cats_sorted":[],"title_canon_sha256":"78a14ddbd0c748ba2de52695e6b839fdd5ca2ba7b597bc672c6527171629ac68","abstract_canon_sha256":"439181257122bb11c4d3229170d6c91009c79630af4868cd908ab45dd1c857e6"},"schema_version":"1.0"},"canonical_sha256":"d921ff545f01db61f88e8d17ae6231f46d2335e02ad12edc747268fad807015b","source":{"kind":"arxiv","id":"2604.11283","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.11283","created_at":"2026-06-02T02:04:53Z"},{"alias_kind":"arxiv_version","alias_value":"2604.11283v2","created_at":"2026-06-02T02:04:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.11283","created_at":"2026-06-02T02:04:53Z"},{"alias_kind":"pith_short_12","alias_value":"3EQ76VC7AHNW","created_at":"2026-06-02T02:04:53Z"},{"alias_kind":"pith_short_16","alias_value":"3EQ76VC7AHNWD6EO","created_at":"2026-06-02T02:04:53Z"},{"alias_kind":"pith_short_8","alias_value":"3EQ76VC7","created_at":"2026-06-02T02:04:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:3EQ76VC7AHNWD6EORUL24YRR6R","target":"record","payload":{"canonical_record":{"source":{"id":"2604.11283","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-04-13T10:42:31Z","cross_cats_sorted":[],"title_canon_sha256":"78a14ddbd0c748ba2de52695e6b839fdd5ca2ba7b597bc672c6527171629ac68","abstract_canon_sha256":"439181257122bb11c4d3229170d6c91009c79630af4868cd908ab45dd1c857e6"},"schema_version":"1.0"},"canonical_sha256":"d921ff545f01db61f88e8d17ae6231f46d2335e02ad12edc747268fad807015b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:53.001238Z","signature_b64":"51HM9I9IvHikOeEyMeyGDDrxr9+vhpfKWQVBaSwrYDLPrMIgoYhEGkte7Fys6p2NjZXpLOUSndY3cT5QD0OKDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d921ff545f01db61f88e8d17ae6231f46d2335e02ad12edc747268fad807015b","last_reissued_at":"2026-06-02T02:04:53.000851Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:53.000851Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2604.11283","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-02T02:04:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JNv9CUeGn0MGSIOlrK+iBBEyFWTCgR+kvIorIFPtIifungZ4r5d4rU8dEysLN44gvimR2MWWpfxVaEIrGTWHBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T00:41:09.201612Z"},"content_sha256":"e435ddf7cbdb26c330d0e5d9cf4132fc343e62d259aa145f6b884ce043241748","schema_version":"1.0","event_id":"sha256:e435ddf7cbdb26c330d0e5d9cf4132fc343e62d259aa145f6b884ce043241748"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:3EQ76VC7AHNWD6EORUL24YRR6R","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multimodal Large Language Model-Enabled Video Translation: A Role-Oriented Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Multimodal large language models unify video translation through semantic reasoning, expressive speech, and visual synthesis.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingzheng QU, Kehai Chen, Min Zhang, Xuefeng Bai","submitted_at":"2026-04-13T10:42:31Z","abstract_excerpt":"Recent progress in multimodal large language models (MLLMs) is reshaping video translation from a cascaded pipeline of automatic speech recognition, machine translation, text-to-speech, and lip synchronization into a unified multimodal reasoning and generation problem. High-quality video translation requires not only semantic fidelity, but also temporal alignment, speaker consistency, and emotional expressiveness across visual, acoustic, and linguistic streams. This survey provides a focused review of MLLM-enabled video translation through a role-oriented taxonomy. We organize MLLM-enabled and"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"we provide the first comprehensive overview of MLLMs-based video translation, organized around a three-role taxonomy: 1) Semantic Reasoner, which characterizes how MLLMs perform video understanding, temporal reasoning, and multimodal fusion; 2) Expressive Performer...; and 3) Visual Synthesizer...","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the reviewed MLLM approaches genuinely overcome the limitations of cascaded pipelines in zero-shot settings and multi-speaker scenarios, as asserted without detailed evidence in the abstract.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"The paper offers the first focused review of MLLM-based video translation organized by a three-role taxonomy of Semantic Reasoner, Expressive Performer, and Visual Synthesizer, plus open challenges.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Multimodal large language models unify video translation through semantic reasoning, expressive speech, and visual synthesis.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"76b43d4d091471487cc666f3077ebb3ac174e1d7b294c119d267469a09e0881b"},"source":{"id":"2604.11283","kind":"arxiv","version":2},"verdict":{"id":"d9863b29-c64e-4706-9e0f-ba7aa2c7f2d3","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T16:31:42.385670Z","strongest_claim":"we provide the first comprehensive overview of MLLMs-based video translation, organized around a three-role taxonomy: 1) Semantic Reasoner, which characterizes how MLLMs perform video understanding, temporal reasoning, and multimodal fusion; 2) Expressive Performer...; and 3) Visual Synthesizer...","one_line_summary":"The paper offers the first focused review of MLLM-based video translation organized by a three-role taxonomy of Semantic Reasoner, Expressive Performer, and Visual Synthesizer, plus open challenges.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the reviewed MLLM approaches genuinely overcome the limitations of cascaded pipelines in zero-shot settings and multi-speaker scenarios, as asserted without detailed evidence in the abstract.","pith_extraction_headline":"Multimodal large language models unify video translation through semantic reasoning, expressive speech, and visual synthesis."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.11283/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":"d9863b29-c64e-4706-9e0f-ba7aa2c7f2d3"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-02T02:04:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0y+H3qL8tDSlSpWJvx5JSwngbbUHB+kES/zxCikOHzLa8Obfin0CbSbhr4IZgs6YLi4OlgGmYqThJB+iKUecBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T00:41:09.202676Z"},"content_sha256":"0f7e5d0e53900d9e76b9608c2b2ff4d82094d943274f84f69ce3f72659fd8201","schema_version":"1.0","event_id":"sha256:0f7e5d0e53900d9e76b9608c2b2ff4d82094d943274f84f69ce3f72659fd8201"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3EQ76VC7AHNWD6EORUL24YRR6R/bundle.json","state_url":"https://pith.science/pith/3EQ76VC7AHNWD6EORUL24YRR6R/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3EQ76VC7AHNWD6EORUL24YRR6R/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":"2026-08-04T00:41:09Z","links":{"resolver":"https://pith.science/pith/3EQ76VC7AHNWD6EORUL24YRR6R","bundle":"https://pith.science/pith/3EQ76VC7AHNWD6EORUL24YRR6R/bundle.json","state":"https://pith.science/pith/3EQ76VC7AHNWD6EORUL24YRR6R/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3EQ76VC7AHNWD6EORUL24YRR6R/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3EQ76VC7AHNWD6EORUL24YRR6R","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":"439181257122bb11c4d3229170d6c91009c79630af4868cd908ab45dd1c857e6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-04-13T10:42:31Z","title_canon_sha256":"78a14ddbd0c748ba2de52695e6b839fdd5ca2ba7b597bc672c6527171629ac68"},"schema_version":"1.0","source":{"id":"2604.11283","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.11283","created_at":"2026-06-02T02:04:53Z"},{"alias_kind":"arxiv_version","alias_value":"2604.11283v2","created_at":"2026-06-02T02:04:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.11283","created_at":"2026-06-02T02:04:53Z"},{"alias_kind":"pith_short_12","alias_value":"3EQ76VC7AHNW","created_at":"2026-06-02T02:04:53Z"},{"alias_kind":"pith_short_16","alias_value":"3EQ76VC7AHNWD6EO","created_at":"2026-06-02T02:04:53Z"},{"alias_kind":"pith_short_8","alias_value":"3EQ76VC7","created_at":"2026-06-02T02:04:53Z"}],"graph_snapshots":[{"event_id":"sha256:0f7e5d0e53900d9e76b9608c2b2ff4d82094d943274f84f69ce3f72659fd8201","target":"graph","created_at":"2026-06-02T02:04:53Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"we provide the first comprehensive overview of MLLMs-based video translation, organized around a three-role taxonomy: 1) Semantic Reasoner, which characterizes how MLLMs perform video understanding, temporal reasoning, and multimodal fusion; 2) Expressive Performer...; and 3) Visual Synthesizer..."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the reviewed MLLM approaches genuinely overcome the limitations of cascaded pipelines in zero-shot settings and multi-speaker scenarios, as asserted without detailed evidence in the abstract."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"The paper offers the first focused review of MLLM-based video translation organized by a three-role taxonomy of Semantic Reasoner, Expressive Performer, and Visual Synthesizer, plus open challenges."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Multimodal large language models unify video translation through semantic reasoning, expressive speech, and visual synthesis."}],"snapshot_sha256":"76b43d4d091471487cc666f3077ebb3ac174e1d7b294c119d267469a09e0881b"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.11283/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent progress in multimodal large language models (MLLMs) is reshaping video translation from a cascaded pipeline of automatic speech recognition, machine translation, text-to-speech, and lip synchronization into a unified multimodal reasoning and generation problem. High-quality video translation requires not only semantic fidelity, but also temporal alignment, speaker consistency, and emotional expressiveness across visual, acoustic, and linguistic streams. This survey provides a focused review of MLLM-enabled video translation through a role-oriented taxonomy. We organize MLLM-enabled and","authors_text":"Bingzheng QU, Kehai Chen, Min Zhang, Xuefeng Bai","cross_cats":[],"headline":"Multimodal large language models unify video translation through semantic reasoning, expressive speech, and visual synthesis.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-04-13T10:42:31Z","title":"Multimodal Large Language Model-Enabled Video Translation: A Role-Oriented Survey"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.11283","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-10T16:31:42.385670Z","id":"d9863b29-c64e-4706-9e0f-ba7aa2c7f2d3","model_set":{"reader":"grok-4.3"},"one_line_summary":"The paper offers the first focused review of MLLM-based video translation organized by a three-role taxonomy of Semantic Reasoner, Expressive Performer, and Visual Synthesizer, plus open challenges.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Multimodal large language models unify video translation through semantic reasoning, expressive speech, and visual synthesis.","strongest_claim":"we provide the first comprehensive overview of MLLMs-based video translation, organized around a three-role taxonomy: 1) Semantic Reasoner, which characterizes how MLLMs perform video understanding, temporal reasoning, and multimodal fusion; 2) Expressive Performer...; and 3) Visual Synthesizer...","weakest_assumption":"That the reviewed MLLM approaches genuinely overcome the limitations of cascaded pipelines in zero-shot settings and multi-speaker scenarios, as asserted without detailed evidence in the abstract."}},"verdict_id":"d9863b29-c64e-4706-9e0f-ba7aa2c7f2d3"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e435ddf7cbdb26c330d0e5d9cf4132fc343e62d259aa145f6b884ce043241748","target":"record","created_at":"2026-06-02T02:04:53Z","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":"439181257122bb11c4d3229170d6c91009c79630af4868cd908ab45dd1c857e6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-04-13T10:42:31Z","title_canon_sha256":"78a14ddbd0c748ba2de52695e6b839fdd5ca2ba7b597bc672c6527171629ac68"},"schema_version":"1.0","source":{"id":"2604.11283","kind":"arxiv","version":2}},"canonical_sha256":"d921ff545f01db61f88e8d17ae6231f46d2335e02ad12edc747268fad807015b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d921ff545f01db61f88e8d17ae6231f46d2335e02ad12edc747268fad807015b","first_computed_at":"2026-06-02T02:04:53.000851Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T02:04:53.000851Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"51HM9I9IvHikOeEyMeyGDDrxr9+vhpfKWQVBaSwrYDLPrMIgoYhEGkte7Fys6p2NjZXpLOUSndY3cT5QD0OKDQ==","signature_status":"signed_v1","signed_at":"2026-06-02T02:04:53.001238Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.11283","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e435ddf7cbdb26c330d0e5d9cf4132fc343e62d259aa145f6b884ce043241748","sha256:0f7e5d0e53900d9e76b9608c2b2ff4d82094d943274f84f69ce3f72659fd8201"],"state_sha256":"9fc03f05dc522cc4813d7d1eb1370323485daf3f6788a729cefb5b8271569d92"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TMP/DSGEUQJo3H0ozPWDZyv0+WpVzpV2l2S1ifVVKk5k9ziLxRAiLY9DLs+LnyyHn5y4dER+XNwey1CMRkONAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T00:41:09.218218Z","bundle_sha256":"2c2c29bf33a551043513babea5aee338cf415deab1b80640cad1a5bc0ed30cbc"}}