{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:G2ILKQKCGS36MI2EX46GQPUV5V","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":"2e2d803d8ce73bcf9281fb4804a8e6733575ce432f92b0ae4092ca6e8931dde0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-04-21T17:22:39Z","title_canon_sha256":"1a0920c5b30e0bd009bdfd3a4d86b145668d6a4d3ef143dbcd94d9ac74282d99"},"schema_version":"1.0","source":{"id":"2604.19702","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.19702","created_at":"2026-06-30T02:17:21Z"},{"alias_kind":"arxiv_version","alias_value":"2604.19702v2","created_at":"2026-06-30T02:17:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.19702","created_at":"2026-06-30T02:17:21Z"},{"alias_kind":"pith_short_12","alias_value":"G2ILKQKCGS36","created_at":"2026-06-30T02:17:21Z"},{"alias_kind":"pith_short_16","alias_value":"G2ILKQKCGS36MI2E","created_at":"2026-06-30T02:17:21Z"},{"alias_kind":"pith_short_8","alias_value":"G2ILKQKC","created_at":"2026-06-30T02:17:21Z"}],"graph_snapshots":[{"event_id":"sha256:f00948fe81e840bf40947a48ad36c0a2356176c70fa1769a549104b99de6325c","target":"graph","created_at":"2026-06-30T02:17:21Z","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":"By jointly predicting depth and canonical coordinates, our method enables accurate depth estimation, temporally stable reconstruction, dense 3D geometry, and robust facial point tracking within a single architecture."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That multi-view geometry data can be reliably non-rigidly warped into a shared canonical space to train a model that then generalizes to arbitrary single-view image sequences without additional constraints or post-processing."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"A single transformer model jointly predicts depth and normalized canonical coordinates to deliver state-of-the-art 4D facial geometry and tracking with 3x lower correspondence error and 16% better depth accuracy."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Canonical facial point prediction unifies depth estimation, dense 3D geometry, and point tracking for 4D face reconstruction from single-view sequences."}],"snapshot_sha256":"0c973eedaf73717e87a7c0c4ec4e891fbd622e54a8db687148c229a89559509a"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-21T16:33:35.140812Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-20T02:38:43.976560Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2604.19702/integrity.json","findings":[],"snapshot_sha256":"1ba399b336e0736b6e79eade72f0e67c10684a7e920254469fa34e01b24e72c8","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Accurate reconstruction and tracking of dynamic human faces from image sequences is challenging because non-rigid deformations, expression changes, and viewpoint variations occur simultaneously, creating significant ambiguity in geometry and correspondence estimation. We present a unified method for high-fidelity 4D facial reconstruction based on canonical facial point prediction, a representation that assigns each pixel a normalized facial coordinate in a shared canonical space. This formulation transforms dense tracking and dynamic reconstruction into a canonical reconstruction problem, enab","authors_text":"Matthias Nie{\\ss}ner, Richard Shaw, Simon Giebenhain, Umut Kocasari","cross_cats":[],"headline":"Canonical facial point prediction unifies depth estimation, dense 3D geometry, and point tracking for 4D face reconstruction from single-view sequences.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-04-21T17:22:39Z","title":"Face Anything: 4D Face Reconstruction from Any Image Sequence"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.19702","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-10T02:35:12.216586Z","id":"b3bba5ef-5e97-4d41-a539-ac790fad971d","model_set":{"reader":"grok-4.3"},"one_line_summary":"A single transformer model jointly predicts depth and normalized canonical coordinates to deliver state-of-the-art 4D facial geometry and tracking with 3x lower correspondence error and 16% better depth accuracy.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Canonical facial point prediction unifies depth estimation, dense 3D geometry, and point tracking for 4D face reconstruction from single-view sequences.","strongest_claim":"By jointly predicting depth and canonical coordinates, our method enables accurate depth estimation, temporally stable reconstruction, dense 3D geometry, and robust facial point tracking within a single architecture.","weakest_assumption":"That multi-view geometry data can be reliably non-rigidly warped into a shared canonical space to train a model that then generalizes to arbitrary single-view image sequences without additional constraints or post-processing."}},"verdict_id":"b3bba5ef-5e97-4d41-a539-ac790fad971d"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ca2d2a0f65d9e1da3a9ee5d97a474a99c975b3fa4275008a36c8fc0ed524bec4","target":"record","created_at":"2026-06-30T02:17:21Z","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":"2e2d803d8ce73bcf9281fb4804a8e6733575ce432f92b0ae4092ca6e8931dde0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-04-21T17:22:39Z","title_canon_sha256":"1a0920c5b30e0bd009bdfd3a4d86b145668d6a4d3ef143dbcd94d9ac74282d99"},"schema_version":"1.0","source":{"id":"2604.19702","kind":"arxiv","version":2}},"canonical_sha256":"3690b5414234b7e62344bf3c683e95ed4bf83de142aa36da3f8e8524c9f85cc9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3690b5414234b7e62344bf3c683e95ed4bf83de142aa36da3f8e8524c9f85cc9","first_computed_at":"2026-06-30T02:17:21.348221Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T02:17:21.348221Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8i3QGxPgVX7KvpMPjwWamkMrO6JMzuBM3sdOtcF77SHenLNhov6nmvA5Z9sYXVVIY7BJmXXlWT6VC3mgxXpWBg==","signature_status":"signed_v1","signed_at":"2026-06-30T02:17:21.348797Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.19702","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ca2d2a0f65d9e1da3a9ee5d97a474a99c975b3fa4275008a36c8fc0ed524bec4","sha256:f00948fe81e840bf40947a48ad36c0a2356176c70fa1769a549104b99de6325c"],"state_sha256":"6f8aee75f2dfc193b6ca5c57c22a6c8c303a26b0cf1979518155d379a62981f2"}