{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:TP44CXAXAIS52TH5YP5NP57C7B","short_pith_number":"pith:TP44CXAX","canonical_record":{"source":{"id":"2605.13853","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GR","submitted_at":"2026-03-25T21:34:06Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"c67e045275443a97df434247443aa36a255ae06b3fda62ce94773791b49d2c54","abstract_canon_sha256":"c1fa66eebbc68e74029036b3100f92078207ca8255bf340736cccd8b8b25cf17"},"schema_version":"1.0"},"canonical_sha256":"9bf9c15c170225dd4cfdc3fad7f7e2f8764fe9550bf31582df8b47640f392a1b","source":{"kind":"arxiv","id":"2605.13853","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13853","created_at":"2026-05-17T23:39:19Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13853v1","created_at":"2026-05-17T23:39:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13853","created_at":"2026-05-17T23:39:19Z"},{"alias_kind":"pith_short_12","alias_value":"TP44CXAXAIS5","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"TP44CXAXAIS52TH5","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"TP44CXAX","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:TP44CXAXAIS52TH5YP5NP57C7B","target":"record","payload":{"canonical_record":{"source":{"id":"2605.13853","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GR","submitted_at":"2026-03-25T21:34:06Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"c67e045275443a97df434247443aa36a255ae06b3fda62ce94773791b49d2c54","abstract_canon_sha256":"c1fa66eebbc68e74029036b3100f92078207ca8255bf340736cccd8b8b25cf17"},"schema_version":"1.0"},"canonical_sha256":"9bf9c15c170225dd4cfdc3fad7f7e2f8764fe9550bf31582df8b47640f392a1b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:19.580596Z","signature_b64":"pHFBG6r7OHm52b6OdRILRp/WCfMYNMxnMl6eQM5iMeHnpn2z3t6B8MutubZiJCdrxtWPdwxGvJbjGCGS4N6UAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9bf9c15c170225dd4cfdc3fad7f7e2f8764fe9550bf31582df8b47640f392a1b","last_reissued_at":"2026-05-17T23:39:19.579823Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:19.579823Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.13853","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l2GcEpZe3Pwl8UVIlg5QXt90mcydmMZc436z1sDDlrLs4EqV+V6vffDsEjaYvmbiHx52Sbs6bvrAUgQAFTtoDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T23:07:59.455694Z"},"content_sha256":"2cfff04b6019b56163f8d8a90045cd9a29ece8245f8eb82ba7a977583a2afa86","schema_version":"1.0","event_id":"sha256:2cfff04b6019b56163f8d8a90045cd9a29ece8245f8eb82ba7a977583a2afa86"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:TP44CXAXAIS52TH5YP5NP57C7B","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FaceParts: Segmentation and Editing of Gaussian Splatting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Unsupervised segmentation decomposes Gaussian splatting avatars into editable facial parts like eyes and beards.","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.GR","authors_text":"Dominik Galus, Julia Farganus, Miko{\\l}aj Czachorowski, Piotr Syga, Przemys{\\l}aw Spurek, Tymoteusz Zapa{\\l}a","submitted_at":"2026-03-25T21:34:06Z","abstract_excerpt":"Facial editing is an important task with applications in entertainment, virtual reality, and digital avatars. Most existing approaches rely on generative models in the 2D image domain, while in 3D the task is typically performed through labor-intensive manual editing. We propose FaceParts, a framework for unsupervised segmentation and editing of Gaussian Splatting avatars. Unlike existing 2D or mesh-assisted methods, our approach operates directly in the Gaussian domain, decomposing avatars into semantically coherent facial parts without supervision. The method integrates feature disentangleme"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"our approach operates directly in the Gaussian domain, decomposing avatars into semantically coherent facial parts without supervision... enabling precise editing and cross-avatar part swapping. Experiments... demonstrate robust isolation of features such as beards, eyebrows, eyes and mustaches. Quantitative evaluation confirms that transferred segments adapt to pose and expression, while maintaining identity consistency (ID = 0.943), low Average Expression Distance (AED = 0.021) and low Average Pose Distance (APD = 0.004).","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That feature disentanglement followed by density-based clustering will reliably produce semantically coherent facial parts across varied identities and expressions without supervision or post-hoc tuning.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"FaceParts performs unsupervised segmentation of facial features in Gaussian Splatting avatars and supports precise editing and cross-avatar part transfer using feature disentanglement, density clustering, and FLAME anchoring.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Unsupervised segmentation decomposes Gaussian splatting avatars into editable facial parts like eyes and beards.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"6d1b3d49dc1c90172a71decc4832ee945a03ffedaed8da4a5bd87814c2e3cb74"},"source":{"id":"2605.13853","kind":"arxiv","version":1},"verdict":{"id":"bc7943a2-b5c3-4ca2-8d0d-ed89b374d47e","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T07:07:26.794137Z","strongest_claim":"our approach operates directly in the Gaussian domain, decomposing avatars into semantically coherent facial parts without supervision... enabling precise editing and cross-avatar part swapping. Experiments... demonstrate robust isolation of features such as beards, eyebrows, eyes and mustaches. Quantitative evaluation confirms that transferred segments adapt to pose and expression, while maintaining identity consistency (ID = 0.943), low Average Expression Distance (AED = 0.021) and low Average Pose Distance (APD = 0.004).","one_line_summary":"FaceParts performs unsupervised segmentation of facial features in Gaussian Splatting avatars and supports precise editing and cross-avatar part transfer using feature disentanglement, density clustering, and FLAME anchoring.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That feature disentanglement followed by density-based clustering will reliably produce semantically coherent facial parts across varied identities and expressions without supervision or post-hoc tuning.","pith_extraction_headline":"Unsupervised segmentation decomposes Gaussian splatting avatars into editable facial parts like eyes and beards."},"references":{"count":48,"sample":[{"doi":"","year":null,"title":"Scaling Learning Algorithms Towards","work_id":"bb2761cc-98d0-411b-92f6-803773d64460","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , month =","work_id":"9e0af3ea-a41b-4b55-88f0-56dba6de4681","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , month =","work_id":"2bd60b4d-3f80-40a9-93c3-7128bc0b12d7","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"and Osindero, Simon and Teh, Yee Whye , journal =","work_id":"0a5921e3-ac4e-46f1-85ae-866119a87be0","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=","work_id":"ecbb0949-3c12-4696-92c9-f5fd459986e8","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":48,"snapshot_sha256":"341f87c183a3f64219c3d67a2f5864a746913e179699e26c92f1d242228b7122","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"bc7943a2-b5c3-4ca2-8d0d-ed89b374d47e"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GHC9OUWhbt7wNMbpIijooHsa41EgKnOECoP/NiSTjWyIxKuVaKlPIfgNkI19QhfNvHIoRXZ7/ByMTjvqBA1/DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T23:07:59.456408Z"},"content_sha256":"9f21bc4fb327a74207cf781efb181c3ec9a13cc95186cd2ce6d794a24193bbee","schema_version":"1.0","event_id":"sha256:9f21bc4fb327a74207cf781efb181c3ec9a13cc95186cd2ce6d794a24193bbee"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TP44CXAXAIS52TH5YP5NP57C7B/bundle.json","state_url":"https://pith.science/pith/TP44CXAXAIS52TH5YP5NP57C7B/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TP44CXAXAIS52TH5YP5NP57C7B/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-24T23:07:59Z","links":{"resolver":"https://pith.science/pith/TP44CXAXAIS52TH5YP5NP57C7B","bundle":"https://pith.science/pith/TP44CXAXAIS52TH5YP5NP57C7B/bundle.json","state":"https://pith.science/pith/TP44CXAXAIS52TH5YP5NP57C7B/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TP44CXAXAIS52TH5YP5NP57C7B/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TP44CXAXAIS52TH5YP5NP57C7B","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":"c1fa66eebbc68e74029036b3100f92078207ca8255bf340736cccd8b8b25cf17","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GR","submitted_at":"2026-03-25T21:34:06Z","title_canon_sha256":"c67e045275443a97df434247443aa36a255ae06b3fda62ce94773791b49d2c54"},"schema_version":"1.0","source":{"id":"2605.13853","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13853","created_at":"2026-05-17T23:39:19Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13853v1","created_at":"2026-05-17T23:39:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13853","created_at":"2026-05-17T23:39:19Z"},{"alias_kind":"pith_short_12","alias_value":"TP44CXAXAIS5","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"TP44CXAXAIS52TH5","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"TP44CXAX","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:9f21bc4fb327a74207cf781efb181c3ec9a13cc95186cd2ce6d794a24193bbee","target":"graph","created_at":"2026-05-17T23:39:19Z","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":"our approach operates directly in the Gaussian domain, decomposing avatars into semantically coherent facial parts without supervision... enabling precise editing and cross-avatar part swapping. Experiments... demonstrate robust isolation of features such as beards, eyebrows, eyes and mustaches. Quantitative evaluation confirms that transferred segments adapt to pose and expression, while maintaining identity consistency (ID = 0.943), low Average Expression Distance (AED = 0.021) and low Average Pose Distance (APD = 0.004)."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That feature disentanglement followed by density-based clustering will reliably produce semantically coherent facial parts across varied identities and expressions without supervision or post-hoc tuning."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"FaceParts performs unsupervised segmentation of facial features in Gaussian Splatting avatars and supports precise editing and cross-avatar part transfer using feature disentanglement, density clustering, and FLAME anchoring."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Unsupervised segmentation decomposes Gaussian splatting avatars into editable facial parts like eyes and beards."}],"snapshot_sha256":"6d1b3d49dc1c90172a71decc4832ee945a03ffedaed8da4a5bd87814c2e3cb74"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Facial editing is an important task with applications in entertainment, virtual reality, and digital avatars. Most existing approaches rely on generative models in the 2D image domain, while in 3D the task is typically performed through labor-intensive manual editing. We propose FaceParts, a framework for unsupervised segmentation and editing of Gaussian Splatting avatars. Unlike existing 2D or mesh-assisted methods, our approach operates directly in the Gaussian domain, decomposing avatars into semantically coherent facial parts without supervision. The method integrates feature disentangleme","authors_text":"Dominik Galus, Julia Farganus, Miko{\\l}aj Czachorowski, Piotr Syga, Przemys{\\l}aw Spurek, Tymoteusz Zapa{\\l}a","cross_cats":["cs.AI","cs.CV"],"headline":"Unsupervised segmentation decomposes Gaussian splatting avatars into editable facial parts like eyes and beards.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GR","submitted_at":"2026-03-25T21:34:06Z","title":"FaceParts: Segmentation and Editing of Gaussian Splatting"},"references":{"count":48,"internal_anchors":0,"resolved_work":48,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Scaling Learning Algorithms Towards","work_id":"bb2761cc-98d0-411b-92f6-803773d64460","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , month =","work_id":"9e0af3ea-a41b-4b55-88f0-56dba6de4681","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , month =","work_id":"2bd60b4d-3f80-40a9-93c3-7128bc0b12d7","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"and Osindero, Simon and Teh, Yee Whye , journal =","work_id":"0a5921e3-ac4e-46f1-85ae-866119a87be0","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=","work_id":"ecbb0949-3c12-4696-92c9-f5fd459986e8","year":null}],"snapshot_sha256":"341f87c183a3f64219c3d67a2f5864a746913e179699e26c92f1d242228b7122"},"source":{"id":"2605.13853","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-15T07:07:26.794137Z","id":"bc7943a2-b5c3-4ca2-8d0d-ed89b374d47e","model_set":{"reader":"grok-4.3"},"one_line_summary":"FaceParts performs unsupervised segmentation of facial features in Gaussian Splatting avatars and supports precise editing and cross-avatar part transfer using feature disentanglement, density clustering, and FLAME anchoring.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Unsupervised segmentation decomposes Gaussian splatting avatars into editable facial parts like eyes and beards.","strongest_claim":"our approach operates directly in the Gaussian domain, decomposing avatars into semantically coherent facial parts without supervision... enabling precise editing and cross-avatar part swapping. Experiments... demonstrate robust isolation of features such as beards, eyebrows, eyes and mustaches. Quantitative evaluation confirms that transferred segments adapt to pose and expression, while maintaining identity consistency (ID = 0.943), low Average Expression Distance (AED = 0.021) and low Average Pose Distance (APD = 0.004).","weakest_assumption":"That feature disentanglement followed by density-based clustering will reliably produce semantically coherent facial parts across varied identities and expressions without supervision or post-hoc tuning."}},"verdict_id":"bc7943a2-b5c3-4ca2-8d0d-ed89b374d47e"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:2cfff04b6019b56163f8d8a90045cd9a29ece8245f8eb82ba7a977583a2afa86","target":"record","created_at":"2026-05-17T23:39:19Z","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":"c1fa66eebbc68e74029036b3100f92078207ca8255bf340736cccd8b8b25cf17","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GR","submitted_at":"2026-03-25T21:34:06Z","title_canon_sha256":"c67e045275443a97df434247443aa36a255ae06b3fda62ce94773791b49d2c54"},"schema_version":"1.0","source":{"id":"2605.13853","kind":"arxiv","version":1}},"canonical_sha256":"9bf9c15c170225dd4cfdc3fad7f7e2f8764fe9550bf31582df8b47640f392a1b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9bf9c15c170225dd4cfdc3fad7f7e2f8764fe9550bf31582df8b47640f392a1b","first_computed_at":"2026-05-17T23:39:19.579823Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:19.579823Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pHFBG6r7OHm52b6OdRILRp/WCfMYNMxnMl6eQM5iMeHnpn2z3t6B8MutubZiJCdrxtWPdwxGvJbjGCGS4N6UAQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:19.580596Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.13853","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2cfff04b6019b56163f8d8a90045cd9a29ece8245f8eb82ba7a977583a2afa86","sha256:9f21bc4fb327a74207cf781efb181c3ec9a13cc95186cd2ce6d794a24193bbee"],"state_sha256":"4f1e56b4ffad77636dd12e1865b85c7561e780581ae0825ca02e050dbbe2a770"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wtIJAG0A2TQboaeQYZYel6VZmrmAykfBXcMop2dopdJTa+z6qvqXviJmi9ZB0BPiMQNaR10idwm1NXZeKTrCBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-24T23:07:59.459191Z","bundle_sha256":"006f6845d694a3e25dc1d7f0069d8c0393ad12fcbd14f110a57022ecd4253c6c"}}