{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NTVMJH2KOPEH3LJEVJZD5ZUHOJ","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":"44e9ed202a9d6cda40d55236e2eb4a929294d63ba46f3651c3686b195c24542f","cross_cats_sorted":["cs.CV","cs.LG","cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-03-14T02:48:43Z","title_canon_sha256":"0b0e5ce3bdaf7bf0905e56ecc9fe27e1cf457220192ebee61e53e7751ab5057b"},"schema_version":"1.0","source":{"id":"2503.11026","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.11026","created_at":"2026-07-05T11:45:32Z"},{"alias_kind":"arxiv_version","alias_value":"2503.11026v2","created_at":"2026-07-05T11:45:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.11026","created_at":"2026-07-05T11:45:32Z"},{"alias_kind":"pith_short_12","alias_value":"NTVMJH2KOPEH","created_at":"2026-07-05T11:45:32Z"},{"alias_kind":"pith_short_16","alias_value":"NTVMJH2KOPEH3LJE","created_at":"2026-07-05T11:45:32Z"},{"alias_kind":"pith_short_8","alias_value":"NTVMJH2K","created_at":"2026-07-05T11:45:32Z"}],"graph_snapshots":[{"event_id":"sha256:8bd66cfcfc6067a0e127f30eb7109c5fcf665816d794055d6ab0687c2def84b1","target":"graph","created_at":"2026-07-05T11:45:32Z","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/2503.11026/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite recent advances in text-to-speech (TTS) models, audio-visual-to-audio-visual (AV2AV) translation still faces a critical challenge: maintaining speaker consistency between the original and translated vocal and facial features. To address this issue, we propose a conditional flow matching (CFM) zero-shot audio-visual renderer that utilizes strong dual guidance from both audio and visual modalities. By leveraging multimodal guidance with CFM, our model robustly preserves speaker-specific characteristics and enhances zero-shot AV2AV translation abilities. For the audio modality, we enhance","authors_text":"Jeongsoo Choi, Se-Young Yun, Sungnyun Kim, Sungwoo Cho","cross_cats":["cs.CV","cs.LG","cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-03-14T02:48:43Z","title":"MAVFlow: Preserving Paralinguistic Elements with Conditional Flow Matching for Zero-Shot AV2AV Multilingual Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.11026","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:e9837090f414a20c47e5484229f9da907dec9abab35af080a636ee87c6a1da81","target":"record","created_at":"2026-07-05T11:45:32Z","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":"44e9ed202a9d6cda40d55236e2eb4a929294d63ba46f3651c3686b195c24542f","cross_cats_sorted":["cs.CV","cs.LG","cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-03-14T02:48:43Z","title_canon_sha256":"0b0e5ce3bdaf7bf0905e56ecc9fe27e1cf457220192ebee61e53e7751ab5057b"},"schema_version":"1.0","source":{"id":"2503.11026","kind":"arxiv","version":2}},"canonical_sha256":"6ceac49f4a73c87dad24aa723ee6877243936b9ba53a139e9dc8dd19cbbae5c3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6ceac49f4a73c87dad24aa723ee6877243936b9ba53a139e9dc8dd19cbbae5c3","first_computed_at":"2026-07-05T11:45:32.771574Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:45:32.771574Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"P/dVmdduauyNMXq1xyTbLHcfQb0sciUjpJif47pjBewMlb06HkKeatH5nI8viFrnfAJxDGPCeAEiHNvhlU1hBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:45:32.772205Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.11026","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e9837090f414a20c47e5484229f9da907dec9abab35af080a636ee87c6a1da81","sha256:8bd66cfcfc6067a0e127f30eb7109c5fcf665816d794055d6ab0687c2def84b1"],"state_sha256":"f86612b9dbfa6bb57561f1d0a1ef1b2c4dea4555f84fde64eaf347f15cab2b28"}