{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:PME675QGOZHYXQYNBTKRKYCSUG","short_pith_number":"pith:PME675QG","canonical_record":{"source":{"id":"2605.12819","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2026-05-12T23:23:27Z","cross_cats_sorted":["cs.NA","math.NA"],"title_canon_sha256":"6b38b4372bbb1356215fa8892a435c4127c588b12fdd6413b71129c2b83e7d46","abstract_canon_sha256":"be7b9c5a641c71f0923733fa82b5378ae3a341b299b18706b0f0bbfadc122aae"},"schema_version":"1.0"},"canonical_sha256":"7b09eff606764f8bc30d0cd5156052a188379c09cbe5ddf9b3739973ce5c00b0","source":{"kind":"arxiv","id":"2605.12819","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.12819","created_at":"2026-05-18T03:09:12Z"},{"alias_kind":"arxiv_version","alias_value":"2605.12819v1","created_at":"2026-05-18T03:09:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12819","created_at":"2026-05-18T03:09:12Z"},{"alias_kind":"pith_short_12","alias_value":"PME675QGOZHY","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"PME675QGOZHYXQYN","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"PME675QG","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:PME675QGOZHYXQYNBTKRKYCSUG","target":"record","payload":{"canonical_record":{"source":{"id":"2605.12819","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2026-05-12T23:23:27Z","cross_cats_sorted":["cs.NA","math.NA"],"title_canon_sha256":"6b38b4372bbb1356215fa8892a435c4127c588b12fdd6413b71129c2b83e7d46","abstract_canon_sha256":"be7b9c5a641c71f0923733fa82b5378ae3a341b299b18706b0f0bbfadc122aae"},"schema_version":"1.0"},"canonical_sha256":"7b09eff606764f8bc30d0cd5156052a188379c09cbe5ddf9b3739973ce5c00b0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:09:12.259707Z","signature_b64":"D+40QRqx/MiZI8IJqMzTT/OnWAEsPpKARNnTkP6dQ49YoZNs3wc9DEkCm2t1Gx4iLAoHrBKSx5sT1rmZM9XyAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b09eff606764f8bc30d0cd5156052a188379c09cbe5ddf9b3739973ce5c00b0","last_reissued_at":"2026-05-18T03:09:12.259097Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:09:12.259097Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.12819","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":"2026-05-18T03:09:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"liYa0hzHt9MkLY4eu71tjaxZ+BVJKe+c//NBZq+yfIru5poX6O2wXhXANkSV4FE7VBarE5WyCb+WW58AJe27Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T04:36:06.715888Z"},"content_sha256":"5e2d7c86e461fa0dd689f9835565d05f8c28c0d4e9b96a7f934d3eda5561f521","schema_version":"1.0","event_id":"sha256:5e2d7c86e461fa0dd689f9835565d05f8c28c0d4e9b96a7f934d3eda5561f521"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:PME675QGOZHYXQYNBTKRKYCSUG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Accuracy and Relationships of Quadratic Models in Derivative-free Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Three quadratic models in derivative-free optimization all satisfy fully linear error bounds without assuming bounded model Hessians.","cross_cats":["cs.NA","math.NA"],"primary_cat":"math.OC","authors_text":"Lindon Roberts, Warren Hare, Yiwen Chen","submitted_at":"2026-05-12T23:23:27Z","abstract_excerpt":"We study three quadratic models in model-based derivative-free optimization: the minimum norm (MN), minimum Frobenius norm (MFN), and quadratic generalized simplex derivative (QS) models. Despite their widespread use, their approximation accuracy and relationships have not been systematically explored. We establish fully linear error bounds for all three models, removing the uniformly bounded model Hessian assumption required in existing MN analyses and deriving the first such results for the QS model. We further analyze Hessian approximation accuracy via directional error bounds, showing that"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We establish fully linear error bounds for all three models, removing the uniformly bounded model Hessian assumption required in existing MN analyses and deriving the first such results for the QS model. We further analyze Hessian approximation accuracy via directional error bounds, showing that all three models achieve fully quadratic accuracy along sample directions under a mild condition on the sample set.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The mild geometric condition on the sample set required for directional fully quadratic accuracy, together with standard twice-differentiability of the objective function; if the sample geometry fails, the directional Hessian claims may not hold.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"The paper derives fully linear error bounds for minimum norm, minimum Frobenius norm, and quadratic generalized simplex derivative models, establishes directional fully quadratic Hessian accuracy under mild sample set conditions, and characterizes when the models coincide.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Three quadratic models in derivative-free optimization all satisfy fully linear error bounds without assuming bounded model Hessians.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"92b0a5601b5b82243df55a9b0f082c0c74e7786c3c96070d6514e08df5838a11"},"source":{"id":"2605.12819","kind":"arxiv","version":1},"verdict":{"id":"9f003980-06cc-4a8c-b3ee-7be329503143","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T19:38:26.298908Z","strongest_claim":"We establish fully linear error bounds for all three models, removing the uniformly bounded model Hessian assumption required in existing MN analyses and deriving the first such results for the QS model. We further analyze Hessian approximation accuracy via directional error bounds, showing that all three models achieve fully quadratic accuracy along sample directions under a mild condition on the sample set.","one_line_summary":"The paper derives fully linear error bounds for minimum norm, minimum Frobenius norm, and quadratic generalized simplex derivative models, establishes directional fully quadratic Hessian accuracy under mild sample set conditions, and characterizes when the models coincide.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The mild geometric condition on the sample set required for directional fully quadratic accuracy, together with standard twice-differentiability of the objective function; if the sample geometry fails, the directional Hessian claims may not hold.","pith_extraction_headline":"Three quadratic models in derivative-free optimization all satisfy fully linear error bounds without assuming bounded model Hessians."},"references":{"count":24,"sample":[{"doi":"","year":2024,"title":"A matrix algebra approach to approximate Hessians , author=. IMA J. Numer. Anal. , volume=. 2024 , publisher=","work_id":"8be2455f-230e-4bee-99d0-0b641238ddee","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"An introduction to convexity, optimization, and algorithms , author=. 2023 , publisher=","work_id":"cee28940-450a-4706-b818-8cf8b24607ae","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2020,"title":"Calculus identities for generalized simplex gradients: rules and applications , author=. SIAM J. Optim. , volume=. 2020 , publisher=","work_id":"5e5dd7f3-e5b5-4836-b558-07a719b621ec","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Q-fully quadratic modeling and its application in a random subspace derivative-free method , author=. Comput. Optim. Appl. , volume=. 2024 , publisher=","work_id":"5cdfd6ef-d0f6-4405-8dc3-89f6c30d6e8e","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Chen, Y. and Hare, W. , title =. IMA J. Numer. Anal. , year =","work_id":"da269ed2-e6bf-47f3-a649-48c3694d2969","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":24,"snapshot_sha256":"d5f5dc25da0eac8897f131b39f430324f7531ba5f196bd16ebf4457a81e8f97a","internal_anchors":1},"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":"9f003980-06cc-4a8c-b3ee-7be329503143"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:09:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QDT9M1j2qy4LYfqA4OpuQ0AbqaIzjvSHK2O5OBftjhTZrt1+6NMp1VuH/gg0AJSb9F84u0yKAqWPJhsPogGdCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T04:36:06.716842Z"},"content_sha256":"541efa09ab48223ff6e496f779dfbaf20eeabb9adc163c504f361ad5d30aa45a","schema_version":"1.0","event_id":"sha256:541efa09ab48223ff6e496f779dfbaf20eeabb9adc163c504f361ad5d30aa45a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PME675QGOZHYXQYNBTKRKYCSUG/bundle.json","state_url":"https://pith.science/pith/PME675QGOZHYXQYNBTKRKYCSUG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PME675QGOZHYXQYNBTKRKYCSUG/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":"2026-05-22T04:36:06Z","links":{"resolver":"https://pith.science/pith/PME675QGOZHYXQYNBTKRKYCSUG","bundle":"https://pith.science/pith/PME675QGOZHYXQYNBTKRKYCSUG/bundle.json","state":"https://pith.science/pith/PME675QGOZHYXQYNBTKRKYCSUG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PME675QGOZHYXQYNBTKRKYCSUG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:PME675QGOZHYXQYNBTKRKYCSUG","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":"be7b9c5a641c71f0923733fa82b5378ae3a341b299b18706b0f0bbfadc122aae","cross_cats_sorted":["cs.NA","math.NA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2026-05-12T23:23:27Z","title_canon_sha256":"6b38b4372bbb1356215fa8892a435c4127c588b12fdd6413b71129c2b83e7d46"},"schema_version":"1.0","source":{"id":"2605.12819","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.12819","created_at":"2026-05-18T03:09:12Z"},{"alias_kind":"arxiv_version","alias_value":"2605.12819v1","created_at":"2026-05-18T03:09:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12819","created_at":"2026-05-18T03:09:12Z"},{"alias_kind":"pith_short_12","alias_value":"PME675QGOZHY","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"PME675QGOZHYXQYN","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"PME675QG","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:541efa09ab48223ff6e496f779dfbaf20eeabb9adc163c504f361ad5d30aa45a","target":"graph","created_at":"2026-05-18T03:09:12Z","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":"We establish fully linear error bounds for all three models, removing the uniformly bounded model Hessian assumption required in existing MN analyses and deriving the first such results for the QS model. We further analyze Hessian approximation accuracy via directional error bounds, showing that all three models achieve fully quadratic accuracy along sample directions under a mild condition on the sample set."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The mild geometric condition on the sample set required for directional fully quadratic accuracy, together with standard twice-differentiability of the objective function; if the sample geometry fails, the directional Hessian claims may not hold."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"The paper derives fully linear error bounds for minimum norm, minimum Frobenius norm, and quadratic generalized simplex derivative models, establishes directional fully quadratic Hessian accuracy under mild sample set conditions, and characterizes when the models coincide."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Three quadratic models in derivative-free optimization all satisfy fully linear error bounds without assuming bounded model Hessians."}],"snapshot_sha256":"92b0a5601b5b82243df55a9b0f082c0c74e7786c3c96070d6514e08df5838a11"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"We study three quadratic models in model-based derivative-free optimization: the minimum norm (MN), minimum Frobenius norm (MFN), and quadratic generalized simplex derivative (QS) models. Despite their widespread use, their approximation accuracy and relationships have not been systematically explored. We establish fully linear error bounds for all three models, removing the uniformly bounded model Hessian assumption required in existing MN analyses and deriving the first such results for the QS model. We further analyze Hessian approximation accuracy via directional error bounds, showing that","authors_text":"Lindon Roberts, Warren Hare, Yiwen Chen","cross_cats":["cs.NA","math.NA"],"headline":"Three quadratic models in derivative-free optimization all satisfy fully linear error bounds without assuming bounded model Hessians.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2026-05-12T23:23:27Z","title":"Accuracy and Relationships of Quadratic Models in Derivative-free Optimization"},"references":{"count":24,"internal_anchors":1,"resolved_work":24,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"A matrix algebra approach to approximate Hessians , author=. IMA J. Numer. Anal. , volume=. 2024 , publisher=","work_id":"8be2455f-230e-4bee-99d0-0b641238ddee","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"An introduction to convexity, optimization, and algorithms , author=. 2023 , publisher=","work_id":"cee28940-450a-4706-b818-8cf8b24607ae","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Calculus identities for generalized simplex gradients: rules and applications , author=. SIAM J. Optim. , volume=. 2020 , publisher=","work_id":"5e5dd7f3-e5b5-4836-b558-07a719b621ec","year":2020},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Q-fully quadratic modeling and its application in a random subspace derivative-free method , author=. Comput. Optim. Appl. , volume=. 2024 , publisher=","work_id":"5cdfd6ef-d0f6-4405-8dc3-89f6c30d6e8e","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Chen, Y. and Hare, W. , title =. IMA J. Numer. Anal. , year =","work_id":"da269ed2-e6bf-47f3-a649-48c3694d2969","year":null}],"snapshot_sha256":"d5f5dc25da0eac8897f131b39f430324f7531ba5f196bd16ebf4457a81e8f97a"},"source":{"id":"2605.12819","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T19:38:26.298908Z","id":"9f003980-06cc-4a8c-b3ee-7be329503143","model_set":{"reader":"grok-4.3"},"one_line_summary":"The paper derives fully linear error bounds for minimum norm, minimum Frobenius norm, and quadratic generalized simplex derivative models, establishes directional fully quadratic Hessian accuracy under mild sample set conditions, and characterizes when the models coincide.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Three quadratic models in derivative-free optimization all satisfy fully linear error bounds without assuming bounded model Hessians.","strongest_claim":"We establish fully linear error bounds for all three models, removing the uniformly bounded model Hessian assumption required in existing MN analyses and deriving the first such results for the QS model. We further analyze Hessian approximation accuracy via directional error bounds, showing that all three models achieve fully quadratic accuracy along sample directions under a mild condition on the sample set.","weakest_assumption":"The mild geometric condition on the sample set required for directional fully quadratic accuracy, together with standard twice-differentiability of the objective function; if the sample geometry fails, the directional Hessian claims may not hold."}},"verdict_id":"9f003980-06cc-4a8c-b3ee-7be329503143"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5e2d7c86e461fa0dd689f9835565d05f8c28c0d4e9b96a7f934d3eda5561f521","target":"record","created_at":"2026-05-18T03:09:12Z","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":"be7b9c5a641c71f0923733fa82b5378ae3a341b299b18706b0f0bbfadc122aae","cross_cats_sorted":["cs.NA","math.NA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2026-05-12T23:23:27Z","title_canon_sha256":"6b38b4372bbb1356215fa8892a435c4127c588b12fdd6413b71129c2b83e7d46"},"schema_version":"1.0","source":{"id":"2605.12819","kind":"arxiv","version":1}},"canonical_sha256":"7b09eff606764f8bc30d0cd5156052a188379c09cbe5ddf9b3739973ce5c00b0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7b09eff606764f8bc30d0cd5156052a188379c09cbe5ddf9b3739973ce5c00b0","first_computed_at":"2026-05-18T03:09:12.259097Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:09:12.259097Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"D+40QRqx/MiZI8IJqMzTT/OnWAEsPpKARNnTkP6dQ49YoZNs3wc9DEkCm2t1Gx4iLAoHrBKSx5sT1rmZM9XyAA==","signature_status":"signed_v1","signed_at":"2026-05-18T03:09:12.259707Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.12819","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5e2d7c86e461fa0dd689f9835565d05f8c28c0d4e9b96a7f934d3eda5561f521","sha256:541efa09ab48223ff6e496f779dfbaf20eeabb9adc163c504f361ad5d30aa45a"],"state_sha256":"bd35ec5fd4f88d3add08bc6f12e565fe6415569c264c789c0b600c9e9b96297a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3+FEkzUUnoFU61ob3cPgH+3pU1kkGDJzulVN6ojiG0qbUGDHUrIlgbaqJCVRsVF3/PfdDMy96oCFkJHl9DIQBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-22T04:36:06.720455Z","bundle_sha256":"c80e153bf9e28bb88a4bcaf1fbeeffe7f74beba87803ccc2cef4fe3f7da1d155"}}