{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:KVOO4G4HNOSRYD6PGCCH2JJO3T","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":"a7fab1c7a81debba5f0a21c64efdeac1e6e2b5853829171f4584ca5afe259b01","cross_cats_sorted":["cs.GR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-10T04:21:59Z","title_canon_sha256":"4e7bdc883e8609bea952a7a459d6a1a5fde356dc5182c26e9da29f83b8b81442"},"schema_version":"1.0","source":{"id":"2112.05329","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.05329","created_at":"2026-07-05T04:06:01Z"},{"alias_kind":"arxiv_version","alias_value":"2112.05329v4","created_at":"2026-07-05T04:06:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.05329","created_at":"2026-07-05T04:06:01Z"},{"alias_kind":"pith_short_12","alias_value":"KVOO4G4HNOSR","created_at":"2026-07-05T04:06:01Z"},{"alias_kind":"pith_short_16","alias_value":"KVOO4G4HNOSRYD6P","created_at":"2026-07-05T04:06:01Z"},{"alias_kind":"pith_short_8","alias_value":"KVOO4G4H","created_at":"2026-07-05T04:06:01Z"}],"graph_snapshots":[{"event_id":"sha256:8c6aff4ecb01a2024f6c2e603c3713f0ea8ac134c58931c6f0ff2fa462dfd885","target":"graph","created_at":"2026-07-05T04:06:01Z","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/2112.05329/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Speech-driven 3D facial animation is challenging due to the complex geometry of human faces and the limited availability of 3D audio-visual data. Prior works typically focus on learning phoneme-level features of short audio windows with limited context, occasionally resulting in inaccurate lip movements. To tackle this limitation, we propose a Transformer-based autoregressive model, FaceFormer, which encodes the long-term audio context and autoregressively predicts a sequence of animated 3D face meshes. To cope with the data scarcity issue, we integrate the self-supervised pre-trained speech r","authors_text":"Jun Saito, Taku Komura, Wenping Wang, Yingruo Fan, Zhaojiang Lin","cross_cats":["cs.GR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-10T04:21:59Z","title":"FaceFormer: Speech-Driven 3D Facial Animation with Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.05329","kind":"arxiv","version":4},"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:d98c26ba7f2f4524009be8b7b57c819401a1a8d7db46f1b6bd129aa56174b670","target":"record","created_at":"2026-07-05T04:06:01Z","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":"a7fab1c7a81debba5f0a21c64efdeac1e6e2b5853829171f4584ca5afe259b01","cross_cats_sorted":["cs.GR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-10T04:21:59Z","title_canon_sha256":"4e7bdc883e8609bea952a7a459d6a1a5fde356dc5182c26e9da29f83b8b81442"},"schema_version":"1.0","source":{"id":"2112.05329","kind":"arxiv","version":4}},"canonical_sha256":"555cee1b876ba51c0fcf30847d252edcde3e4f8a16e3dbd8b955f94b43f5e085","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"555cee1b876ba51c0fcf30847d252edcde3e4f8a16e3dbd8b955f94b43f5e085","first_computed_at":"2026-07-05T04:06:01.378494Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:06:01.378494Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RgCBrb4zR/bcLTtlBHieldm2BDTllvgD9bDOMSjvu+GKXeLnzHQs98Gioc8Gr5CgM7f1d8V1vPZjH+Nb6VJqDg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:06:01.378876Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.05329","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d98c26ba7f2f4524009be8b7b57c819401a1a8d7db46f1b6bd129aa56174b670","sha256:8c6aff4ecb01a2024f6c2e603c3713f0ea8ac134c58931c6f0ff2fa462dfd885"],"state_sha256":"5779ae1e9cc1749653ad19fac87feca6739038dfff3ff641af18e3d753165b4d"}