{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:M7TGAC7UO7ZV7SUF6T2MSAWQED","short_pith_number":"pith:M7TGAC7U","canonical_record":{"source":{"id":"2605.12648","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-12T18:44:47Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"1e02e97f9e5ab34cc82f17c4dcd5e579a03a3da0c626e433ce3e42ac9befccff","abstract_canon_sha256":"c54f656a77754743df6d79191fd6a4123751bc21eb3d32f502d8b221995df9bf"},"schema_version":"1.0"},"canonical_sha256":"67e6600bf477f35fca85f4f4c902d020ed6526acc64b2a4ddb27a7ac38dcec77","source":{"kind":"arxiv","id":"2605.12648","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.12648","created_at":"2026-05-18T03:09:59Z"},{"alias_kind":"arxiv_version","alias_value":"2605.12648v1","created_at":"2026-05-18T03:09:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12648","created_at":"2026-05-18T03:09:59Z"},{"alias_kind":"pith_short_12","alias_value":"M7TGAC7UO7ZV","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"M7TGAC7UO7ZV7SUF","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"M7TGAC7U","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:M7TGAC7UO7ZV7SUF6T2MSAWQED","target":"record","payload":{"canonical_record":{"source":{"id":"2605.12648","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-12T18:44:47Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"1e02e97f9e5ab34cc82f17c4dcd5e579a03a3da0c626e433ce3e42ac9befccff","abstract_canon_sha256":"c54f656a77754743df6d79191fd6a4123751bc21eb3d32f502d8b221995df9bf"},"schema_version":"1.0"},"canonical_sha256":"67e6600bf477f35fca85f4f4c902d020ed6526acc64b2a4ddb27a7ac38dcec77","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:09:59.801840Z","signature_b64":"s5RDffIVD8X26LwbdjqFNmizmaIprihAuE5dWPoETdOvGCk4HcVcvNi2nYUzGLFFACUu4ytnVqN+IUxykTCDCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67e6600bf477f35fca85f4f4c902d020ed6526acc64b2a4ddb27a7ac38dcec77","last_reissued_at":"2026-05-18T03:09:59.801298Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:09:59.801298Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.12648","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":"2026-05-18T03:09:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tlu6paiwHUBeTOgscv/aV1vZ7+sJ/rGtKwdU4eRw6cV92dca2ElAjR3G6IcptgVic2/86E1z+jLkKMZqgy9tDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T03:54:13.896510Z"},"content_sha256":"2317b241cb015f7139df33b0f20bae4f07237881642bb872d6f7b1835cf7389d","schema_version":"1.0","event_id":"sha256:2317b241cb015f7139df33b0f20bae4f07237881642bb872d6f7b1835cf7389d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:M7TGAC7UO7ZV7SUF6T2MSAWQED","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Population Risk Bounds for Kolmogorov-Arnold Networks Trained by DP-SGD with Correlated Noise","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Kolmogorov-Arnold Networks receive population risk bounds under mini-batch DP-SGD with correlated noise.","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Christoph Lampert, Jan Schuchardt, Junyu Zhou, Marius Kloft, Nikita Kalinin, Puyu Wang, Sophie Fellenz","submitted_at":"2026-05-12T18:44:47Z","abstract_excerpt":"We establish the first population risk bounds for Kolmogorov-Arnold Networks (KANs) trained by mini-batch SGD with gradient clipping, covering non-private SGD as well as differentially private SGD (DP-SGD) with Gaussian perturbations that interpolate between independent and temporally correlated noise. This setting is substantially closer to practice than prior KAN theory along two axes: training is by mini-batch SGD, the standard recipe for modern networks, rather than full-batch gradient descent (GD); and correlated-noise mechanisms have empirically shown a more favorable privacy-utility tra"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We establish the first population risk bounds for Kolmogorov-Arnold Networks (KANs) trained by mini-batch SGD with gradient clipping, covering non-private SGD as well as differentially private SGD (DP-SGD) with Gaussian perturbations that interpolate between independent and temporally correlated noise.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The new analysis route for correlated-noise DP training in the non-convex regime relies on an auxiliary unprojected dynamics, a shifted iterate absorbing noise, and a high-probability bootstrap certifying projection inactivity; if these constructs fail to control the temporal dependence or clipping effects under the paper's noise model, the population risk bounds do not hold.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"First population risk bounds for KANs under mini-batch DP-SGD with correlated noise, using a new non-convex optimization analysis combined with stability-based generalization.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Kolmogorov-Arnold Networks receive population risk bounds under mini-batch DP-SGD with correlated noise.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"ab1bbb4363b562f10002f51631b88a8ca9cb5720649a2b78be370d606080231e"},"source":{"id":"2605.12648","kind":"arxiv","version":1},"verdict":{"id":"f4bd3885-a81c-48b4-8c24-3c8eeb83e0da","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T21:34:44.874838Z","strongest_claim":"We establish the first population risk bounds for Kolmogorov-Arnold Networks (KANs) trained by mini-batch SGD with gradient clipping, covering non-private SGD as well as differentially private SGD (DP-SGD) with Gaussian perturbations that interpolate between independent and temporally correlated noise.","one_line_summary":"First population risk bounds for KANs under mini-batch DP-SGD with correlated noise, using a new non-convex optimization analysis combined with stability-based generalization.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The new analysis route for correlated-noise DP training in the non-convex regime relies on an auxiliary unprojected dynamics, a shifted iterate absorbing noise, and a high-probability bootstrap certifying projection inactivity; if these constructs fail to control the temporal dependence or clipping effects under the paper's noise model, the population risk bounds do not hold.","pith_extraction_headline":"Kolmogorov-Arnold Networks receive population risk bounds under mini-batch DP-SGD with correlated noise."},"references":{"count":70,"sample":[{"doi":"","year":2019,"title":"A convergence theory for deep learning via over- parameterization","work_id":"2a252a94-ee15-4740-ac95-48e4c0bfa182","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"A smooth binary mechanism for efficient private continual observation.Advances in Neural Information Processing Systems, 36:49133–49145, 2023","work_id":"1906ab45-e80c-4c97-bb7d-7a0dc9890a0c","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"The hitchhiker’s guide to efficient, end-to-end, and tight dp auditing","work_id":"aab8c523-1506-462e-9db1-af6944f76fe3","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2019,"title":"Fine-grained analysis of optimization and generalization for overparameterized two-layer neural networks","work_id":"2f8744c1-d98b-482b-acc4-22e10362f492","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2013,"title":"Beyond differential privacy: Composition theorems and relational logic for f-divergences between probabilistic programs","work_id":"323bbaa3-5240-4f18-9ba7-ca58a10e0c23","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":70,"snapshot_sha256":"c1b3269b1e8d00867cf9a927756b0c8cd579fc3562e0a994c53e73e67642967d","internal_anchors":2},"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":"f4bd3885-a81c-48b4-8c24-3c8eeb83e0da"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:09:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IK1GkusB3uBSKAIOb04ls9c5LRVu95pq9RGHLF87BAzbCPn9vcSX+xDCo9MEISA64+Hj9pYLlYpELjSlpFv+Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T03:54:13.897665Z"},"content_sha256":"e9116f4801280221ba23efffa27461782e9c204e66854c4c05c37d7fe1ff19a8","schema_version":"1.0","event_id":"sha256:e9116f4801280221ba23efffa27461782e9c204e66854c4c05c37d7fe1ff19a8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/M7TGAC7UO7ZV7SUF6T2MSAWQED/bundle.json","state_url":"https://pith.science/pith/M7TGAC7UO7ZV7SUF6T2MSAWQED/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/M7TGAC7UO7ZV7SUF6T2MSAWQED/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":"2026-05-24T03:54:13Z","links":{"resolver":"https://pith.science/pith/M7TGAC7UO7ZV7SUF6T2MSAWQED","bundle":"https://pith.science/pith/M7TGAC7UO7ZV7SUF6T2MSAWQED/bundle.json","state":"https://pith.science/pith/M7TGAC7UO7ZV7SUF6T2MSAWQED/state.json","well_known_bundle":"https://pith.science/.well-known/pith/M7TGAC7UO7ZV7SUF6T2MSAWQED/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:M7TGAC7UO7ZV7SUF6T2MSAWQED","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":"c54f656a77754743df6d79191fd6a4123751bc21eb3d32f502d8b221995df9bf","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-12T18:44:47Z","title_canon_sha256":"1e02e97f9e5ab34cc82f17c4dcd5e579a03a3da0c626e433ce3e42ac9befccff"},"schema_version":"1.0","source":{"id":"2605.12648","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.12648","created_at":"2026-05-18T03:09:59Z"},{"alias_kind":"arxiv_version","alias_value":"2605.12648v1","created_at":"2026-05-18T03:09:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12648","created_at":"2026-05-18T03:09:59Z"},{"alias_kind":"pith_short_12","alias_value":"M7TGAC7UO7ZV","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"M7TGAC7UO7ZV7SUF","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"M7TGAC7U","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:e9116f4801280221ba23efffa27461782e9c204e66854c4c05c37d7fe1ff19a8","target":"graph","created_at":"2026-05-18T03:09:59Z","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 the first population risk bounds for Kolmogorov-Arnold Networks (KANs) trained by mini-batch SGD with gradient clipping, covering non-private SGD as well as differentially private SGD (DP-SGD) with Gaussian perturbations that interpolate between independent and temporally correlated noise."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The new analysis route for correlated-noise DP training in the non-convex regime relies on an auxiliary unprojected dynamics, a shifted iterate absorbing noise, and a high-probability bootstrap certifying projection inactivity; if these constructs fail to control the temporal dependence or clipping effects under the paper's noise model, the population risk bounds do not hold."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"First population risk bounds for KANs under mini-batch DP-SGD with correlated noise, using a new non-convex optimization analysis combined with stability-based generalization."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Kolmogorov-Arnold Networks receive population risk bounds under mini-batch DP-SGD with correlated noise."}],"snapshot_sha256":"ab1bbb4363b562f10002f51631b88a8ca9cb5720649a2b78be370d606080231e"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"We establish the first population risk bounds for Kolmogorov-Arnold Networks (KANs) trained by mini-batch SGD with gradient clipping, covering non-private SGD as well as differentially private SGD (DP-SGD) with Gaussian perturbations that interpolate between independent and temporally correlated noise. This setting is substantially closer to practice than prior KAN theory along two axes: training is by mini-batch SGD, the standard recipe for modern networks, rather than full-batch gradient descent (GD); and correlated-noise mechanisms have empirically shown a more favorable privacy-utility tra","authors_text":"Christoph Lampert, Jan Schuchardt, Junyu Zhou, Marius Kloft, Nikita Kalinin, Puyu Wang, Sophie Fellenz","cross_cats":["stat.ML"],"headline":"Kolmogorov-Arnold Networks receive population risk bounds under mini-batch DP-SGD with correlated noise.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-12T18:44:47Z","title":"Population Risk Bounds for Kolmogorov-Arnold Networks Trained by DP-SGD with Correlated Noise"},"references":{"count":70,"internal_anchors":2,"resolved_work":70,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"A convergence theory for deep learning via over- parameterization","work_id":"2a252a94-ee15-4740-ac95-48e4c0bfa182","year":2019},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"A smooth binary mechanism for efficient private continual observation.Advances in Neural Information Processing Systems, 36:49133–49145, 2023","work_id":"1906ab45-e80c-4c97-bb7d-7a0dc9890a0c","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"The hitchhiker’s guide to efficient, end-to-end, and tight dp auditing","work_id":"aab8c523-1506-462e-9db1-af6944f76fe3","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Fine-grained analysis of optimization and generalization for overparameterized two-layer neural networks","work_id":"2f8744c1-d98b-482b-acc4-22e10362f492","year":2019},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Beyond differential privacy: Composition theorems and relational logic for f-divergences between probabilistic programs","work_id":"323bbaa3-5240-4f18-9ba7-ca58a10e0c23","year":2013}],"snapshot_sha256":"c1b3269b1e8d00867cf9a927756b0c8cd579fc3562e0a994c53e73e67642967d"},"source":{"id":"2605.12648","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T21:34:44.874838Z","id":"f4bd3885-a81c-48b4-8c24-3c8eeb83e0da","model_set":{"reader":"grok-4.3"},"one_line_summary":"First population risk bounds for KANs under mini-batch DP-SGD with correlated noise, using a new non-convex optimization analysis combined with stability-based generalization.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Kolmogorov-Arnold Networks receive population risk bounds under mini-batch DP-SGD with correlated noise.","strongest_claim":"We establish the first population risk bounds for Kolmogorov-Arnold Networks (KANs) trained by mini-batch SGD with gradient clipping, covering non-private SGD as well as differentially private SGD (DP-SGD) with Gaussian perturbations that interpolate between independent and temporally correlated noise.","weakest_assumption":"The new analysis route for correlated-noise DP training in the non-convex regime relies on an auxiliary unprojected dynamics, a shifted iterate absorbing noise, and a high-probability bootstrap certifying projection inactivity; if these constructs fail to control the temporal dependence or clipping effects under the paper's noise model, the population risk bounds do not hold."}},"verdict_id":"f4bd3885-a81c-48b4-8c24-3c8eeb83e0da"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:2317b241cb015f7139df33b0f20bae4f07237881642bb872d6f7b1835cf7389d","target":"record","created_at":"2026-05-18T03:09:59Z","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":"c54f656a77754743df6d79191fd6a4123751bc21eb3d32f502d8b221995df9bf","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-12T18:44:47Z","title_canon_sha256":"1e02e97f9e5ab34cc82f17c4dcd5e579a03a3da0c626e433ce3e42ac9befccff"},"schema_version":"1.0","source":{"id":"2605.12648","kind":"arxiv","version":1}},"canonical_sha256":"67e6600bf477f35fca85f4f4c902d020ed6526acc64b2a4ddb27a7ac38dcec77","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"67e6600bf477f35fca85f4f4c902d020ed6526acc64b2a4ddb27a7ac38dcec77","first_computed_at":"2026-05-18T03:09:59.801298Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:09:59.801298Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"s5RDffIVD8X26LwbdjqFNmizmaIprihAuE5dWPoETdOvGCk4HcVcvNi2nYUzGLFFACUu4ytnVqN+IUxykTCDCA==","signature_status":"signed_v1","signed_at":"2026-05-18T03:09:59.801840Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.12648","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2317b241cb015f7139df33b0f20bae4f07237881642bb872d6f7b1835cf7389d","sha256:e9116f4801280221ba23efffa27461782e9c204e66854c4c05c37d7fe1ff19a8"],"state_sha256":"808d859cf500a4d4db49a4015ca733b1c6f31ec9ab77e59bfe8da7261272ac3e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w9tKJuygSr4vzwJf9vB4r0VnCFhM08EeatGkkofODyT9NkpRC2GRErTZppJGum7DLHEjbxx0LjqQ5FOLOOckBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-24T03:54:13.901478Z","bundle_sha256":"becb8274a9e09b5f581599e55d9295fbb8d018a441231ec45fa4b547627689b5"}}