{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:TJK5NSPP4LUJCPVVURKEMR26OY","short_pith_number":"pith:TJK5NSPP","canonical_record":{"source":{"id":"2605.12753","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.IV","submitted_at":"2026-05-12T21:06:53Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"0a20724d1e6a6e05df63deb052698c048c275ebc0ca841b14f6f124addc22279","abstract_canon_sha256":"3d76a28a9f3c1cb0801af6cef2eadb0a7dc0e932b43781ac0125e60219814a0d"},"schema_version":"1.0"},"canonical_sha256":"9a55d6c9efe2e8913eb5a45446475e761fb8d97b6e221583977c9d8b9443063d","source":{"kind":"arxiv","id":"2605.12753","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.12753","created_at":"2026-05-18T03:09:48Z"},{"alias_kind":"arxiv_version","alias_value":"2605.12753v1","created_at":"2026-05-18T03:09:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12753","created_at":"2026-05-18T03:09:48Z"},{"alias_kind":"pith_short_12","alias_value":"TJK5NSPP4LUJ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"TJK5NSPP4LUJCPVV","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"TJK5NSPP","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:TJK5NSPP4LUJCPVVURKEMR26OY","target":"record","payload":{"canonical_record":{"source":{"id":"2605.12753","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.IV","submitted_at":"2026-05-12T21:06:53Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"0a20724d1e6a6e05df63deb052698c048c275ebc0ca841b14f6f124addc22279","abstract_canon_sha256":"3d76a28a9f3c1cb0801af6cef2eadb0a7dc0e932b43781ac0125e60219814a0d"},"schema_version":"1.0"},"canonical_sha256":"9a55d6c9efe2e8913eb5a45446475e761fb8d97b6e221583977c9d8b9443063d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:09:48.680575Z","signature_b64":"6va0XAbofMq1lJkrjElFT8g4TnwBrev24eXfPSgxwLqRXPU+Wve43vQ4hU6771YC55jqO4y8cttAvj0HvHGhBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a55d6c9efe2e8913eb5a45446475e761fb8d97b6e221583977c9d8b9443063d","last_reissued_at":"2026-05-18T03:09:48.679742Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:09:48.679742Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.12753","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":"2026-05-18T03:09:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uyFvw2NmIIe8QqOSh0Mgf/OrWEGEXms07xGB2DvNSAH4uYnaciWeZnt/JhDeZq/gedm9Gt4up74YmhnxPeNTAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T07:03:40.705309Z"},"content_sha256":"bf32222c01975e4f8c5566cb0c7d93462b510d20eefd5c237016fc4d6123ce9e","schema_version":"1.0","event_id":"sha256:bf32222c01975e4f8c5566cb0c7d93462b510d20eefd5c237016fc4d6123ce9e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:TJK5NSPP4LUJCPVVURKEMR26OY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Optimization in Sparse 2D to Dense 3D Weakly Supervised Learning: Application to Multi-Label Segmentation of Large ex vivo MRI Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"2D and 3D segmentation models require distinct regularization when trained from sparse 2D MRI annotations.","cross_cats":["cs.CV","cs.LG"],"primary_cat":"eess.IV","authors_text":"Brandon Bujak, Charidimos Tsagkas, Daniel Reich, Govind Nair, Irene Cortese, Julien Cohen-Adad, Kuan Yi Wang, Paul Hoareau, Roy Sun","submitted_at":"2026-05-12T21:06:53Z","abstract_excerpt":"INTRODUCTION | Fully supervised 3D segmentation of high-resolution ex vivo MRI is limited by the prohibitive cost of volumetric annotation, forcing reliance on sparse 2D slices. Weakly supervised Sparse-to-Dense frameworks bridge this gap, but guidelines remain ambiguous regarding human-centric visual enhancements and transferring optimization strategies across dimensions. We analyze divergent regularization needs for multi-class segmentation of high-resolution ex vivo spinal cord MRI.\n  METHODS | We used 9.4T MRI of multiple sclerosis spinal cords (>104,000 slices) with sparse annotations (42"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"The 2D Teacher required strong spatial augmentation and soft-labeling to overcome data scarcity, improving White Matter Lesion Dice scores by >11 points. However, propagating these techniques to the 3D Student degraded its performance. Furthermore, human-centric preprocessing (e.g., CLAHE) disrupted global statistical cues, dropping Gray Matter Lesion Dice scores by ~25 points.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the pseudo-labels generated by the 2D teacher model are accurate enough to serve as reliable training targets for the 3D student without introducing systematic errors that explain the observed performance differences.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Sparse-to-dense 3D segmentation from 2D slices shows divergent regularization needs: 2D benefits from strong augmentation and soft labels while 3D does not, and human-centric preprocessing harms performance.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"2D and 3D segmentation models require distinct regularization when trained from sparse 2D MRI annotations.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"b7c8ec647bd399121c38773d8f8698e2f013759fac60c2926619c5c1e96f99aa"},"source":{"id":"2605.12753","kind":"arxiv","version":1},"verdict":{"id":"46d2ddb0-2813-4d04-936d-118ce718e9ae","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T19:32:59.085289Z","strongest_claim":"The 2D Teacher required strong spatial augmentation and soft-labeling to overcome data scarcity, improving White Matter Lesion Dice scores by >11 points. However, propagating these techniques to the 3D Student degraded its performance. Furthermore, human-centric preprocessing (e.g., CLAHE) disrupted global statistical cues, dropping Gray Matter Lesion Dice scores by ~25 points.","one_line_summary":"Sparse-to-dense 3D segmentation from 2D slices shows divergent regularization needs: 2D benefits from strong augmentation and soft labels while 3D does not, and human-centric preprocessing harms performance.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the pseudo-labels generated by the 2D teacher model are accurate enough to serve as reliable training targets for the 3D student without introducing systematic errors that explain the observed performance differences.","pith_extraction_headline":"2D and 3D segmentation models require distinct regularization when trained from sparse 2D MRI annotations."},"references":{"count":24,"sample":[{"doi":"","year":null,"title":"Image Augmentation Techniques for Mammogram Analysis","work_id":"5c1354f1-5c31-492d-acf6-bd7995125de5","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Yoshimi, Yuki and Mine, Yuichi and Ito, Shota and Takeda, Saori and Okazaki, Shota and Nakamoto, Takashi and Nagasaki, Toshikazu and Kakimoto, Naoya and Murayama, Takeshi and Tanimoto, Kotaro. Image p","work_id":"6d48bcf2-7a28-411f-921e-3f2a464ac7a5","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","work_id":"2d9e320f-8442-4895-b3f6-f360bd2b2289","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Contrastive learning of global and local features for medical image segmentation with limited annotations","work_id":"ec1c032a-b10d-499e-a968-dc5e6df2377b","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Grey matter pathology in multiple sclerosis","work_id":"acb1ff15-956d-4775-9e99-85d11e0ba765","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":24,"snapshot_sha256":"677f87caa42b3b881d0824aa4ef960e47c99a91462714e929d889920ca7185f5","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":"46d2ddb0-2813-4d04-936d-118ce718e9ae"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:09:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H/flzcQJFhLNKLluakW8K+PaklyhZ3UO0tPOkwbC//zTpiBEX2HgAUbfIc3crjFK0WNmrIYFKAQNHfnjjeTzCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T07:03:40.706429Z"},"content_sha256":"c4ffa26ce0c90cb70ae43b5c340829fe82a2009a6c1d456703c73e86c37c9d23","schema_version":"1.0","event_id":"sha256:c4ffa26ce0c90cb70ae43b5c340829fe82a2009a6c1d456703c73e86c37c9d23"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TJK5NSPP4LUJCPVVURKEMR26OY/bundle.json","state_url":"https://pith.science/pith/TJK5NSPP4LUJCPVVURKEMR26OY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TJK5NSPP4LUJCPVVURKEMR26OY/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":"2026-05-22T07:03:40Z","links":{"resolver":"https://pith.science/pith/TJK5NSPP4LUJCPVVURKEMR26OY","bundle":"https://pith.science/pith/TJK5NSPP4LUJCPVVURKEMR26OY/bundle.json","state":"https://pith.science/pith/TJK5NSPP4LUJCPVVURKEMR26OY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TJK5NSPP4LUJCPVVURKEMR26OY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TJK5NSPP4LUJCPVVURKEMR26OY","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":"3d76a28a9f3c1cb0801af6cef2eadb0a7dc0e932b43781ac0125e60219814a0d","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.IV","submitted_at":"2026-05-12T21:06:53Z","title_canon_sha256":"0a20724d1e6a6e05df63deb052698c048c275ebc0ca841b14f6f124addc22279"},"schema_version":"1.0","source":{"id":"2605.12753","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.12753","created_at":"2026-05-18T03:09:48Z"},{"alias_kind":"arxiv_version","alias_value":"2605.12753v1","created_at":"2026-05-18T03:09:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12753","created_at":"2026-05-18T03:09:48Z"},{"alias_kind":"pith_short_12","alias_value":"TJK5NSPP4LUJ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"TJK5NSPP4LUJCPVV","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"TJK5NSPP","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:c4ffa26ce0c90cb70ae43b5c340829fe82a2009a6c1d456703c73e86c37c9d23","target":"graph","created_at":"2026-05-18T03:09:48Z","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":"The 2D Teacher required strong spatial augmentation and soft-labeling to overcome data scarcity, improving White Matter Lesion Dice scores by >11 points. However, propagating these techniques to the 3D Student degraded its performance. Furthermore, human-centric preprocessing (e.g., CLAHE) disrupted global statistical cues, dropping Gray Matter Lesion Dice scores by ~25 points."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the pseudo-labels generated by the 2D teacher model are accurate enough to serve as reliable training targets for the 3D student without introducing systematic errors that explain the observed performance differences."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Sparse-to-dense 3D segmentation from 2D slices shows divergent regularization needs: 2D benefits from strong augmentation and soft labels while 3D does not, and human-centric preprocessing harms performance."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"2D and 3D segmentation models require distinct regularization when trained from sparse 2D MRI annotations."}],"snapshot_sha256":"b7c8ec647bd399121c38773d8f8698e2f013759fac60c2926619c5c1e96f99aa"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"INTRODUCTION | Fully supervised 3D segmentation of high-resolution ex vivo MRI is limited by the prohibitive cost of volumetric annotation, forcing reliance on sparse 2D slices. Weakly supervised Sparse-to-Dense frameworks bridge this gap, but guidelines remain ambiguous regarding human-centric visual enhancements and transferring optimization strategies across dimensions. We analyze divergent regularization needs for multi-class segmentation of high-resolution ex vivo spinal cord MRI.\n  METHODS | We used 9.4T MRI of multiple sclerosis spinal cords (>104,000 slices) with sparse annotations (42","authors_text":"Brandon Bujak, Charidimos Tsagkas, Daniel Reich, Govind Nair, Irene Cortese, Julien Cohen-Adad, Kuan Yi Wang, Paul Hoareau, Roy Sun","cross_cats":["cs.CV","cs.LG"],"headline":"2D and 3D segmentation models require distinct regularization when trained from sparse 2D MRI annotations.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.IV","submitted_at":"2026-05-12T21:06:53Z","title":"Optimization in Sparse 2D to Dense 3D Weakly Supervised Learning: Application to Multi-Label Segmentation of Large ex vivo MRI Data"},"references":{"count":24,"internal_anchors":0,"resolved_work":24,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Image Augmentation Techniques for Mammogram Analysis","work_id":"5c1354f1-5c31-492d-acf6-bd7995125de5","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Yoshimi, Yuki and Mine, Yuichi and Ito, Shota and Takeda, Saori and Okazaki, Shota and Nakamoto, Takashi and Nagasaki, Toshikazu and Kakimoto, Naoya and Murayama, Takeshi and Tanimoto, Kotaro. Image p","work_id":"6d48bcf2-7a28-411f-921e-3f2a464ac7a5","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","work_id":"2d9e320f-8442-4895-b3f6-f360bd2b2289","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Contrastive learning of global and local features for medical image segmentation with limited annotations","work_id":"ec1c032a-b10d-499e-a968-dc5e6df2377b","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Grey matter pathology in multiple sclerosis","work_id":"acb1ff15-956d-4775-9e99-85d11e0ba765","year":null}],"snapshot_sha256":"677f87caa42b3b881d0824aa4ef960e47c99a91462714e929d889920ca7185f5"},"source":{"id":"2605.12753","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T19:32:59.085289Z","id":"46d2ddb0-2813-4d04-936d-118ce718e9ae","model_set":{"reader":"grok-4.3"},"one_line_summary":"Sparse-to-dense 3D segmentation from 2D slices shows divergent regularization needs: 2D benefits from strong augmentation and soft labels while 3D does not, and human-centric preprocessing harms performance.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"2D and 3D segmentation models require distinct regularization when trained from sparse 2D MRI annotations.","strongest_claim":"The 2D Teacher required strong spatial augmentation and soft-labeling to overcome data scarcity, improving White Matter Lesion Dice scores by >11 points. However, propagating these techniques to the 3D Student degraded its performance. Furthermore, human-centric preprocessing (e.g., CLAHE) disrupted global statistical cues, dropping Gray Matter Lesion Dice scores by ~25 points.","weakest_assumption":"That the pseudo-labels generated by the 2D teacher model are accurate enough to serve as reliable training targets for the 3D student without introducing systematic errors that explain the observed performance differences."}},"verdict_id":"46d2ddb0-2813-4d04-936d-118ce718e9ae"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:bf32222c01975e4f8c5566cb0c7d93462b510d20eefd5c237016fc4d6123ce9e","target":"record","created_at":"2026-05-18T03:09:48Z","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":"3d76a28a9f3c1cb0801af6cef2eadb0a7dc0e932b43781ac0125e60219814a0d","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.IV","submitted_at":"2026-05-12T21:06:53Z","title_canon_sha256":"0a20724d1e6a6e05df63deb052698c048c275ebc0ca841b14f6f124addc22279"},"schema_version":"1.0","source":{"id":"2605.12753","kind":"arxiv","version":1}},"canonical_sha256":"9a55d6c9efe2e8913eb5a45446475e761fb8d97b6e221583977c9d8b9443063d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9a55d6c9efe2e8913eb5a45446475e761fb8d97b6e221583977c9d8b9443063d","first_computed_at":"2026-05-18T03:09:48.679742Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:09:48.679742Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6va0XAbofMq1lJkrjElFT8g4TnwBrev24eXfPSgxwLqRXPU+Wve43vQ4hU6771YC55jqO4y8cttAvj0HvHGhBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T03:09:48.680575Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.12753","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bf32222c01975e4f8c5566cb0c7d93462b510d20eefd5c237016fc4d6123ce9e","sha256:c4ffa26ce0c90cb70ae43b5c340829fe82a2009a6c1d456703c73e86c37c9d23"],"state_sha256":"e9a3a9fe81eb9fd5829cc1702b96f18f3efbc48a5383b200191543f11f739763"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xhuiTXtKDtFGbaKXfq2yZrogPHUIEwDiCh4ZeSlMqDE5pcIH6YS85OaArCBn5KhwK6VL85HPpIzNoy4saoBFDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-22T07:03:40.711129Z","bundle_sha256":"631a98127ed293c577ab5c58cfa95fb3641135c68ba0d087549c2909feec08f6"}}