{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MWW6KVJWSNXCSOESQUOORRCRFN","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":"2d0d9b41a78023ea78c442d6e0382e620d0d5249b1417d91c90bec2ff2ded3a1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-27T17:49:01Z","title_canon_sha256":"b3fbfdcc5d8e3fda54d486c8cb2cc58e20b91fbd11cd548b789b1b5bbf80387a"},"schema_version":"1.0","source":{"id":"2502.20323","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.20323","created_at":"2026-07-05T12:04:31Z"},{"alias_kind":"arxiv_version","alias_value":"2502.20323v5","created_at":"2026-07-05T12:04:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.20323","created_at":"2026-07-05T12:04:31Z"},{"alias_kind":"pith_short_12","alias_value":"MWW6KVJWSNXC","created_at":"2026-07-05T12:04:31Z"},{"alias_kind":"pith_short_16","alias_value":"MWW6KVJWSNXCSOES","created_at":"2026-07-05T12:04:31Z"},{"alias_kind":"pith_short_8","alias_value":"MWW6KVJW","created_at":"2026-07-05T12:04:31Z"}],"graph_snapshots":[{"event_id":"sha256:bf0e251028bf8f30b1499da9482c1a470227999063b84f4da1dbe1eb81f2a161","target":"graph","created_at":"2026-07-05T12:04:31Z","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/2502.20323/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Speech-driven 3D facial animation aims to generate realistic lip movements and facial expressions for 3D head models from arbitrary audio clips. Although existing diffusion-based methods are capable of producing natural motions, their slow generation speed limits their application potential. In this paper, we introduce a novel autoregressive model that achieves real-time generation of highly synchronized lip movements and realistic head poses and eye blinks by learning a mapping from speech to a multi-scale motion codebook. Furthermore, our model can adapt to unseen speaking styles, enabling t","authors_text":"Hanqin Wang, Nabarun Goswami, Tatsuya Harada, Xuangeng Chu, Ziteng Cui","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-27T17:49:01Z","title":"ARTalk: Speech-Driven 3D Head Animation via Autoregressive Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.20323","kind":"arxiv","version":5},"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:a38eaebb63cec974e3a315e21d9064a40e8b6ffae8bae371a94b132df74c551b","target":"record","created_at":"2026-07-05T12:04:31Z","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":"2d0d9b41a78023ea78c442d6e0382e620d0d5249b1417d91c90bec2ff2ded3a1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-27T17:49:01Z","title_canon_sha256":"b3fbfdcc5d8e3fda54d486c8cb2cc58e20b91fbd11cd548b789b1b5bbf80387a"},"schema_version":"1.0","source":{"id":"2502.20323","kind":"arxiv","version":5}},"canonical_sha256":"65ade55536936e293892851ce8c4512b433382c9a983c8ea5caae0f415440426","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"65ade55536936e293892851ce8c4512b433382c9a983c8ea5caae0f415440426","first_computed_at":"2026-07-05T12:04:31.714530Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:04:31.714530Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Nq4OOJQBZRTLA32UOf7dFpCZ6ho0TfJUv23rJsY3ZF2iKIiyngcCfZUSqAGd7xD0+t0R6OVr1XjNqSBa4DhoAg==","signature_status":"signed_v1","signed_at":"2026-07-05T12:04:31.715041Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.20323","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a38eaebb63cec974e3a315e21d9064a40e8b6ffae8bae371a94b132df74c551b","sha256:bf0e251028bf8f30b1499da9482c1a470227999063b84f4da1dbe1eb81f2a161"],"state_sha256":"544ba65b161bf7dc696d5b90b09cdda261a32bc02972e624358a59dc01d9ba12"}