{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:NFHYJS42ST2NTUCPUZOEWLJOEA","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":"7ff1551469e95218086981257d5d647316731dc1b2b69fac3eb5fcd995f6d2b1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-04-03T10:17:39Z","title_canon_sha256":"ae428a3e486aa52d15511d0ca7e4b51e935db6a5bf027e5ec89dc779a6f94065"},"schema_version":"1.0","source":{"id":"2604.02941","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.02941","created_at":"2026-06-02T01:04:16Z"},{"alias_kind":"arxiv_version","alias_value":"2604.02941v2","created_at":"2026-06-02T01:04:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.02941","created_at":"2026-06-02T01:04:16Z"},{"alias_kind":"pith_short_12","alias_value":"NFHYJS42ST2N","created_at":"2026-06-02T01:04:16Z"},{"alias_kind":"pith_short_16","alias_value":"NFHYJS42ST2NTUCP","created_at":"2026-06-02T01:04:16Z"},{"alias_kind":"pith_short_8","alias_value":"NFHYJS42","created_at":"2026-06-02T01:04:16Z"}],"graph_snapshots":[{"event_id":"sha256:216100c9d75ebce8df3f0c693bac25a43a100d0f2ebb02c7c9291b3bb3392ed3","target":"graph","created_at":"2026-06-02T01:04:16Z","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":"MMTalker can accurately reconstruct the rich details of 3D facial motion and achieves significant improvements over state-of-the-art methods, especially in the synchronization accuracy of lip and eye movements."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the combination of non-uniform differentiable sampling on UV-parameterized meshes and dual cross-attention fusion will resolve the ill-posed speech-to-3D-motion mapping without introducing artifacts or requiring extensive post-processing."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"MMTalker combines multi-resolution mesh sampling with residual graph convolutions and dual cross-attention to synthesize accurate 3D talking head motions from audio."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"MMTalker synthesizes detailed 3D talking heads from speech by combining UV mesh parameterization with dual cross-attention fusion of audio and geometric features."}],"snapshot_sha256":"e09bc56e81fcaa308190a6a89eda3f0593c4cbce5554b00468c6d6c22b1cb547"},"formal_canon":{"evidence_count":1,"snapshot_sha256":"6eb294c43f91bdebe296fcf460f86187f20249dfa51e514bb98296680b13ae4d"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.02941/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Speech-driven three-dimensional (3D) facial animation synthesis aims to build a mapping from one-dimensional (1D) speech signals to time-varying 3D facial motion signals. Current methods still face challenges in maintaining lip-sync accuracy and producing realistic facial expressions, primarily due to the highly ill-posed nature of this cross-modal mapping. In this paper, we introduce a novel 3D audio-driven facial animation synthesis method through multi-resolution representation and multi-modal feature fusion, called MMTalker which can accurately reconstruct the rich details of 3D facial mot","authors_text":"Bin Liu, Bo Li, Zhifen He, Zhixiang Xiong","cross_cats":[],"headline":"MMTalker synthesizes detailed 3D talking heads from speech by combining UV mesh parameterization with dual cross-attention fusion of audio and geometric features.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-04-03T10:17:39Z","title":"MMTalker: Multiresolution 3D Talking Head Synthesis with Multimodal Feature Fusion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.02941","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-13T19:43:00.793617Z","id":"c5d10b79-6e4a-48c7-914d-712d63bd7642","model_set":{"reader":"grok-4.3"},"one_line_summary":"MMTalker combines multi-resolution mesh sampling with residual graph convolutions and dual cross-attention to synthesize accurate 3D talking head motions from audio.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"MMTalker synthesizes detailed 3D talking heads from speech by combining UV mesh parameterization with dual cross-attention fusion of audio and geometric features.","strongest_claim":"MMTalker can accurately reconstruct the rich details of 3D facial motion and achieves significant improvements over state-of-the-art methods, especially in the synchronization accuracy of lip and eye movements.","weakest_assumption":"That the combination of non-uniform differentiable sampling on UV-parameterized meshes and dual cross-attention fusion will resolve the ill-posed speech-to-3D-motion mapping without introducing artifacts or requiring extensive post-processing."}},"verdict_id":"c5d10b79-6e4a-48c7-914d-712d63bd7642"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:30390ce3e911244973b646937114859e80c5083712d1079d6e0b3a172b13abfe","target":"record","created_at":"2026-06-02T01:04:16Z","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":"7ff1551469e95218086981257d5d647316731dc1b2b69fac3eb5fcd995f6d2b1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-04-03T10:17:39Z","title_canon_sha256":"ae428a3e486aa52d15511d0ca7e4b51e935db6a5bf027e5ec89dc779a6f94065"},"schema_version":"1.0","source":{"id":"2604.02941","kind":"arxiv","version":2}},"canonical_sha256":"694f84cb9a94f4d9d04fa65c4b2d2e200e69030fa3eddad2fa4dd17e7654451b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"694f84cb9a94f4d9d04fa65c4b2d2e200e69030fa3eddad2fa4dd17e7654451b","first_computed_at":"2026-06-02T01:04:16.215262Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T01:04:16.215262Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"K/LkhcbibGpa6jK8sxVQGH0xblIalRmxqcUWrMHiQ77PUM6FeXrql4owOmaw2+4om4uzDhGXvdLdP+3uI+cUBw==","signature_status":"signed_v1","signed_at":"2026-06-02T01:04:16.215718Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.02941","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:30390ce3e911244973b646937114859e80c5083712d1079d6e0b3a172b13abfe","sha256:216100c9d75ebce8df3f0c693bac25a43a100d0f2ebb02c7c9291b3bb3392ed3"],"state_sha256":"719fa0894f19e93978ba6daacf1a3ca35b6272d0500b1d3e5f04a9ca27eb0849"}