{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:RQSG5Y2B2BFPEOI2WVKSOXBBAT","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":"ec498ea43cd1d203c2d4451c9c56041b3c2d507434d90a9db151e2a063ea244b","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.GR","submitted_at":"2026-05-14T18:33:49Z","title_canon_sha256":"82bf35c1b3d769c5d7f62f5f4aad2e8ac5fbdf1da4a22dffce554e20ca733a23"},"schema_version":"1.0","source":{"id":"2605.15320","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15320","created_at":"2026-05-20T00:00:52Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15320v1","created_at":"2026-05-20T00:00:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15320","created_at":"2026-05-20T00:00:52Z"},{"alias_kind":"pith_short_12","alias_value":"RQSG5Y2B2BFP","created_at":"2026-05-20T00:00:52Z"},{"alias_kind":"pith_short_16","alias_value":"RQSG5Y2B2BFPEOI2","created_at":"2026-05-20T00:00:52Z"},{"alias_kind":"pith_short_8","alias_value":"RQSG5Y2B","created_at":"2026-05-20T00:00:52Z"}],"graph_snapshots":[{"event_id":"sha256:cc5780030b5bd00803927f2c112c04e37a903e3a3cc4f5a42d4606f095f6e23d","target":"graph","created_at":"2026-05-20T00:00:52Z","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":"FFAvatar reconstructs high-quality, animatable 3D Gaussian head avatars from few-shot unposed portrait images in seconds and sets a new standard for identity preservation, geometric consistency, and animation fidelity, outperforming the state-of-the-art LAM by a substantial 5.5 PSNR gain on the NeRSemble benchmark."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The three-stage training curriculum on monocular video data with over 1M identities followed by multi-view fine-tuning produces priors that generalize to arbitrary few-shot unposed inputs without requiring offline pose or FLAME extraction."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"FFAvatar is a generalizable feed-forward framework that reconstructs high-quality animatable 3D Gaussian head avatars from few-shot unposed portrait images in seconds via Multi-View Query-Former and end-to-end FLAME prediction."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A feed-forward model reconstructs animatable 3D Gaussian head avatars from few unposed photos in seconds without per-subject optimization."}],"snapshot_sha256":"75e34c773e84d4dd26aa2d521303511d5c781e708d8716837205a425aa8f532a"},"formal_canon":{"evidence_count":1,"snapshot_sha256":"4d649faea72ef4155c8dd7c35325a62f0e8e922fac135dcd385a1fd6fe99e05f"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T16:01:18.151828Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T15:41:05.371183Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T14:41:54.209702Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T13:33:22.769391Z","status":"skipped","version":"1.0.0"}],"endpoint":"/pith/2605.15320/integrity.json","findings":[],"snapshot_sha256":"8b1737c078db627f9c72437b31acb22be6c03d33856edd8ad907455dc62826ec","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Avatar reconstruction has traditionally relied on per-subject optimization that requires hours of computation or on expensive preprocessing that limits scalability. We introduce FFAvatar, a generalizable feed-forward framework that reconstructs high-quality, animatable 3D Gaussian head avatars from few-shot unposed portrait images in seconds. FFAvatar fuses information from multiple source images into a unified canonical Gaussian representation through Multi-View Query-Former, which is animated via FLAME parameters predicted end-to-end directly from pixels, eliminating the overhead of offline ","authors_text":"Gordon Guocheng Qian, Hao Li, Jiahao Luo, Jian Wang, Thuan Hoang Nguyen, Yinyu Nie","cross_cats":["cs.CV","cs.LG"],"headline":"A feed-forward model reconstructs animatable 3D Gaussian head avatars from few unposed photos in seconds without per-subject optimization.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.GR","submitted_at":"2026-05-14T18:33:49Z","title":"FFAvatar: Few-Shot, Feed-Forward, and Generalizable Avatar Reconstruction"},"references":{"count":33,"internal_anchors":0,"resolved_work":33,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"A morphable model for the synthesis of 3d faces.Seminal Graphics Papers: Pushing the Boundaries, Volume 2, pages 157–164, 2023","work_id":"4de83edc-46a9-477f-9a2a-8313493f5309","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Generalizable and animatable gaussian head avatar","work_id":"05900833-719b-4725-a2bf-ac1cbe713d72","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"GPA- vatar: Generalizable and precise head avatar from image(s)","work_id":"3222b022-86ea-4e84-9e60-b5593393f9e8","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Black, and Timo Bolkart","work_id":"9fa5c3de-2ba5-4248-842d-1da9f10d0f01","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Arcface: Additive angular margin loss for deep face recognition","work_id":"466a3f28-f5e8-456f-9a6a-a6b0fdb10a43","year":2019}],"snapshot_sha256":"959e3f5bf114f0af6163f2b061a383e6b15eb1948554f6f878ea580eeeb843c7"},"source":{"id":"2605.15320","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-19T15:35:09.932931Z","id":"e4e85eff-722b-483f-9963-b012e2fd7693","model_set":{"reader":"grok-4.3"},"one_line_summary":"FFAvatar is a generalizable feed-forward framework that reconstructs high-quality animatable 3D Gaussian head avatars from few-shot unposed portrait images in seconds via Multi-View Query-Former and end-to-end FLAME prediction.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A feed-forward model reconstructs animatable 3D Gaussian head avatars from few unposed photos in seconds without per-subject optimization.","strongest_claim":"FFAvatar reconstructs high-quality, animatable 3D Gaussian head avatars from few-shot unposed portrait images in seconds and sets a new standard for identity preservation, geometric consistency, and animation fidelity, outperforming the state-of-the-art LAM by a substantial 5.5 PSNR gain on the NeRSemble benchmark.","weakest_assumption":"The three-stage training curriculum on monocular video data with over 1M identities followed by multi-view fine-tuning produces priors that generalize to arbitrary few-shot unposed inputs without requiring offline pose or FLAME extraction."}},"verdict_id":"e4e85eff-722b-483f-9963-b012e2fd7693"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a98890c4963e82a3dc236d3237db61cba3c749b39fd720e5aff362b4cb18072c","target":"record","created_at":"2026-05-20T00:00:52Z","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":"ec498ea43cd1d203c2d4451c9c56041b3c2d507434d90a9db151e2a063ea244b","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.GR","submitted_at":"2026-05-14T18:33:49Z","title_canon_sha256":"82bf35c1b3d769c5d7f62f5f4aad2e8ac5fbdf1da4a22dffce554e20ca733a23"},"schema_version":"1.0","source":{"id":"2605.15320","kind":"arxiv","version":1}},"canonical_sha256":"8c246ee341d04af2391ab555275c2104d00a3361cc446a42c898241701b23b4d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8c246ee341d04af2391ab555275c2104d00a3361cc446a42c898241701b23b4d","first_computed_at":"2026-05-20T00:00:52.480050Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:00:52.480050Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MEMm84Tcb7GNVwa1EoC/SV5ZLYL2KSlhNLdkSKBTaSbKuzUnPTARdNPtyFZE+R8qrXkh8a+UKIuYZVi9We44DA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:00:52.480880Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.15320","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a98890c4963e82a3dc236d3237db61cba3c749b39fd720e5aff362b4cb18072c","sha256:cc5780030b5bd00803927f2c112c04e37a903e3a3cc4f5a42d4606f095f6e23d"],"state_sha256":"8940496924e59609a375c15446253235fdc6b181ec8755b30234ced2ba32ce01"}