{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:IB4HYEJULXP3MEXJUHVBGNFL4W","short_pith_number":"pith:IB4HYEJU","canonical_record":{"source":{"id":"2010.08895","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-18T00:34:21Z","cross_cats_sorted":["cs.NA","math.NA"],"title_canon_sha256":"8c170862cf281c6177a27d55780e1629b4d4d6edd268116a9f332db20284a5aa","abstract_canon_sha256":"e2d288011678a3245ddc56d98ef2f70d9618298b9e2fa1081601ece26893720d"},"schema_version":"1.0"},"canonical_sha256":"40787c11345ddfb612e9a1ea1334abe59e0f327c34677caf4bd39837f5da12b8","source":{"kind":"arxiv","id":"2010.08895","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.08895","created_at":"2026-07-05T02:40:29Z"},{"alias_kind":"arxiv_version","alias_value":"2010.08895v3","created_at":"2026-07-05T02:40:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.08895","created_at":"2026-07-05T02:40:29Z"},{"alias_kind":"pith_short_12","alias_value":"IB4HYEJULXP3","created_at":"2026-07-05T02:40:29Z"},{"alias_kind":"pith_short_16","alias_value":"IB4HYEJULXP3MEXJ","created_at":"2026-07-05T02:40:29Z"},{"alias_kind":"pith_short_8","alias_value":"IB4HYEJU","created_at":"2026-07-05T02:40:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:IB4HYEJULXP3MEXJUHVBGNFL4W","target":"record","payload":{"canonical_record":{"source":{"id":"2010.08895","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-18T00:34:21Z","cross_cats_sorted":["cs.NA","math.NA"],"title_canon_sha256":"8c170862cf281c6177a27d55780e1629b4d4d6edd268116a9f332db20284a5aa","abstract_canon_sha256":"e2d288011678a3245ddc56d98ef2f70d9618298b9e2fa1081601ece26893720d"},"schema_version":"1.0"},"canonical_sha256":"40787c11345ddfb612e9a1ea1334abe59e0f327c34677caf4bd39837f5da12b8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:40:29.470482Z","signature_b64":"wMu5X5Rlc0P45B4jnicMgIB11IqTryfcoSO7YkTX01JqyWNpcbb++RpEhKZrm9KiWPqTzX/x+5LE4dklB4rsAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"40787c11345ddfb612e9a1ea1334abe59e0f327c34677caf4bd39837f5da12b8","last_reissued_at":"2026-07-05T02:40:29.470078Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:40:29.470078Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2010.08895","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:40:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dUX7eIfYVRlM7HpCm1qcfTEKxAxcv+vmviQDNwEN8rLRYmqDw7IRCqVcnaPe7WHtcEIxKP6uK7K+WMCQKSaYCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T02:10:51.541793Z"},"content_sha256":"b130d2f68324f3ca540cc072c6904ed58e761e94e034ba39d1f2f0d68f11a8fb","schema_version":"1.0","event_id":"sha256:b130d2f68324f3ca540cc072c6904ed58e761e94e034ba39d1f2f0d68f11a8fb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:IB4HYEJULXP3MEXJUHVBGNFL4W","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fourier Neural Operator for Parametric Partial Differential Equations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Parameterizing the integral kernel directly in Fourier space creates a neural operator that learns solution mappings for entire families of PDEs with high accuracy and speed.","cross_cats":["cs.NA","math.NA"],"primary_cat":"cs.LG","authors_text":"Andrew Stuart, Anima Anandkumar, Burigede Liu, Kamyar Azizzadenesheli, Kaushik Bhattacharya, Nikola Kovachki, Zongyi Li","submitted_at":"2020-10-18T00:34:21Z","abstract_excerpt":"The classical development of neural networks has primarily focused on learning mappings between finite-dimensional Euclidean spaces. Recently, this has been generalized to neural operators that learn mappings between function spaces. For partial differential equations (PDEs), neural operators directly learn the mapping from any functional parametric dependence to the solution. Thus, they learn an entire family of PDEs, in contrast to classical methods which solve one instance of the equation. In this work, we formulate a new neural operator by parameterizing the integral kernel directly in Fou"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"The Fourier neural operator is the first ML-based method to successfully model turbulent flows with zero-shot super-resolution. It is up to three orders of magnitude faster compared to traditional PDE solvers.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That directly parameterizing the integral kernel in Fourier space yields sufficient expressivity and stability for the target PDE families without introducing artifacts or requiring prohibitive amounts of training data.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Fourier Neural Operator parameterizes integral kernels in Fourier space to learn parametric PDE solution operators, delivering up to 1000x speedups and zero-shot super-resolution on turbulent Navier-Stokes flows.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Parameterizing the integral kernel directly in Fourier space creates a neural operator that learns solution mappings for entire families of PDEs with high accuracy and speed.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"ea1b95444d6b0abd24f33c47d5d1481bad6dab9d927e037f709d27dcfc1d7929"},"source":{"id":"2010.08895","kind":"arxiv","version":3},"verdict":{"id":"e38dafb4-8bcf-4981-ad5b-2fcca471c466","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-11T00:51:55.821593Z","strongest_claim":"The Fourier neural operator is the first ML-based method to successfully model turbulent flows with zero-shot super-resolution. It is up to three orders of magnitude faster compared to traditional PDE solvers.","one_line_summary":"Fourier Neural Operator parameterizes integral kernels in Fourier space to learn parametric PDE solution operators, delivering up to 1000x speedups and zero-shot super-resolution on turbulent Navier-Stokes flows.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That directly parameterizing the integral kernel in Fourier space yields sufficient expressivity and stability for the target PDE families without introducing artifacts or requiring prohibitive amounts of training data.","pith_extraction_headline":"Parameterizing the integral kernel directly in Fourier space creates a neural operator that learns solution mappings for entire families of PDEs with high accuracy and speed."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2010.08895/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":18,"sample":[{"doi":"10.1088/1361-6420/aa9581","year":1904,"title":"Solving ill-posed inverse problems using iterative deep neural networks","work_id":"5a22329f-17b2-4931-9355-dbbcf9d8d1f2","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1214/13-sts421","year":null,"title":"doi: 10.1214/13-sts421","work_id":"8cf42938-2aaf-4ee3-b43a-77027d0432f9","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1137/1.9781611974829.ch3","year":null,"title":"DeVore , title =","work_id":"f05a18cb-c059-499f-83ff-2384b2399c40","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1007/s40304-018-0127-z","year":null,"title":"The Deep Ritz Method: A Deep Learning-Based Numerical Algo- rithm for Solving Variational Problems","work_id":"51c83fb3-e61c-4d19-a298-870ef6ab2f84","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"Deep residual learning for image recog- nition","work_id":"b3c11012-45f3-48fc-9279-277c2c9af44f","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":18,"snapshot_sha256":"921d16aff666a4f3200d80a20bd437fcdd8a6462d7140b07a01a0e1679ebddb5","internal_anchors":2},"formal_canon":{"evidence_count":2,"snapshot_sha256":"368e7ff69be47e4bfe4bc2c58bf57d4f9113b0508aa1147476e8aa2d4cc807e1"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"e38dafb4-8bcf-4981-ad5b-2fcca471c466"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:40:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pJWDLcjjCBk36ie54f/UWBLw9G1nEMbAHi7tjkzan0ovVv09CMCiLBaZg4enpRJUSiMrueZsNJi8HH7C8NF+Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T02:10:51.542606Z"},"content_sha256":"5cf9035ad740d4709afdb4351dff1b0d05918eb3155fe72bf128b3f533b0862d","schema_version":"1.0","event_id":"sha256:5cf9035ad740d4709afdb4351dff1b0d05918eb3155fe72bf128b3f533b0862d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IB4HYEJULXP3MEXJUHVBGNFL4W/bundle.json","state_url":"https://pith.science/pith/IB4HYEJULXP3MEXJUHVBGNFL4W/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IB4HYEJULXP3MEXJUHVBGNFL4W/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":"2026-08-11T02:10:51Z","links":{"resolver":"https://pith.science/pith/IB4HYEJULXP3MEXJUHVBGNFL4W","bundle":"https://pith.science/pith/IB4HYEJULXP3MEXJUHVBGNFL4W/bundle.json","state":"https://pith.science/pith/IB4HYEJULXP3MEXJUHVBGNFL4W/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IB4HYEJULXP3MEXJUHVBGNFL4W/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:IB4HYEJULXP3MEXJUHVBGNFL4W","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":"e2d288011678a3245ddc56d98ef2f70d9618298b9e2fa1081601ece26893720d","cross_cats_sorted":["cs.NA","math.NA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-18T00:34:21Z","title_canon_sha256":"8c170862cf281c6177a27d55780e1629b4d4d6edd268116a9f332db20284a5aa"},"schema_version":"1.0","source":{"id":"2010.08895","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.08895","created_at":"2026-07-05T02:40:29Z"},{"alias_kind":"arxiv_version","alias_value":"2010.08895v3","created_at":"2026-07-05T02:40:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.08895","created_at":"2026-07-05T02:40:29Z"},{"alias_kind":"pith_short_12","alias_value":"IB4HYEJULXP3","created_at":"2026-07-05T02:40:29Z"},{"alias_kind":"pith_short_16","alias_value":"IB4HYEJULXP3MEXJ","created_at":"2026-07-05T02:40:29Z"},{"alias_kind":"pith_short_8","alias_value":"IB4HYEJU","created_at":"2026-07-05T02:40:29Z"}],"graph_snapshots":[{"event_id":"sha256:5cf9035ad740d4709afdb4351dff1b0d05918eb3155fe72bf128b3f533b0862d","target":"graph","created_at":"2026-07-05T02:40:29Z","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 Fourier neural operator is the first ML-based method to successfully model turbulent flows with zero-shot super-resolution. It is up to three orders of magnitude faster compared to traditional PDE solvers."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That directly parameterizing the integral kernel in Fourier space yields sufficient expressivity and stability for the target PDE families without introducing artifacts or requiring prohibitive amounts of training data."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Fourier Neural Operator parameterizes integral kernels in Fourier space to learn parametric PDE solution operators, delivering up to 1000x speedups and zero-shot super-resolution on turbulent Navier-Stokes flows."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Parameterizing the integral kernel directly in Fourier space creates a neural operator that learns solution mappings for entire families of PDEs with high accuracy and speed."}],"snapshot_sha256":"ea1b95444d6b0abd24f33c47d5d1481bad6dab9d927e037f709d27dcfc1d7929"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"368e7ff69be47e4bfe4bc2c58bf57d4f9113b0508aa1147476e8aa2d4cc807e1"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2010.08895/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The classical development of neural networks has primarily focused on learning mappings between finite-dimensional Euclidean spaces. Recently, this has been generalized to neural operators that learn mappings between function spaces. For partial differential equations (PDEs), neural operators directly learn the mapping from any functional parametric dependence to the solution. Thus, they learn an entire family of PDEs, in contrast to classical methods which solve one instance of the equation. In this work, we formulate a new neural operator by parameterizing the integral kernel directly in Fou","authors_text":"Andrew Stuart, Anima Anandkumar, Burigede Liu, Kamyar Azizzadenesheli, Kaushik Bhattacharya, Nikola Kovachki, Zongyi Li","cross_cats":["cs.NA","math.NA"],"headline":"Parameterizing the integral kernel directly in Fourier space creates a neural operator that learns solution mappings for entire families of PDEs with high accuracy and speed.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-18T00:34:21Z","title":"Fourier Neural Operator for Parametric Partial Differential Equations"},"references":{"count":18,"internal_anchors":2,"resolved_work":18,"sample":[{"cited_arxiv_id":"","doi":"10.1088/1361-6420/aa9581","is_internal_anchor":false,"ref_index":1,"title":"Solving ill-posed inverse problems using iterative deep neural networks","work_id":"5a22329f-17b2-4931-9355-dbbcf9d8d1f2","year":1904},{"cited_arxiv_id":"","doi":"10.1214/13-sts421","is_internal_anchor":false,"ref_index":2,"title":"doi: 10.1214/13-sts421","work_id":"8cf42938-2aaf-4ee3-b43a-77027d0432f9","year":null},{"cited_arxiv_id":"","doi":"10.1137/1.9781611974829.ch3","is_internal_anchor":false,"ref_index":3,"title":"DeVore , title =","work_id":"f05a18cb-c059-499f-83ff-2384b2399c40","year":null},{"cited_arxiv_id":"","doi":"10.1007/s40304-018-0127-z","is_internal_anchor":false,"ref_index":4,"title":"The Deep Ritz Method: A Deep Learning-Based Numerical Algo- rithm for Solving Variational Problems","work_id":"51c83fb3-e61c-4d19-a298-870ef6ab2f84","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Deep residual learning for image recog- nition","work_id":"b3c11012-45f3-48fc-9279-277c2c9af44f","year":2021}],"snapshot_sha256":"921d16aff666a4f3200d80a20bd437fcdd8a6462d7140b07a01a0e1679ebddb5"},"source":{"id":"2010.08895","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-11T00:51:55.821593Z","id":"e38dafb4-8bcf-4981-ad5b-2fcca471c466","model_set":{"reader":"grok-4.3"},"one_line_summary":"Fourier Neural Operator parameterizes integral kernels in Fourier space to learn parametric PDE solution operators, delivering up to 1000x speedups and zero-shot super-resolution on turbulent Navier-Stokes flows.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Parameterizing the integral kernel directly in Fourier space creates a neural operator that learns solution mappings for entire families of PDEs with high accuracy and speed.","strongest_claim":"The Fourier neural operator is the first ML-based method to successfully model turbulent flows with zero-shot super-resolution. It is up to three orders of magnitude faster compared to traditional PDE solvers.","weakest_assumption":"That directly parameterizing the integral kernel in Fourier space yields sufficient expressivity and stability for the target PDE families without introducing artifacts or requiring prohibitive amounts of training data."}},"verdict_id":"e38dafb4-8bcf-4981-ad5b-2fcca471c466"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b130d2f68324f3ca540cc072c6904ed58e761e94e034ba39d1f2f0d68f11a8fb","target":"record","created_at":"2026-07-05T02:40:29Z","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":"e2d288011678a3245ddc56d98ef2f70d9618298b9e2fa1081601ece26893720d","cross_cats_sorted":["cs.NA","math.NA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-18T00:34:21Z","title_canon_sha256":"8c170862cf281c6177a27d55780e1629b4d4d6edd268116a9f332db20284a5aa"},"schema_version":"1.0","source":{"id":"2010.08895","kind":"arxiv","version":3}},"canonical_sha256":"40787c11345ddfb612e9a1ea1334abe59e0f327c34677caf4bd39837f5da12b8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"40787c11345ddfb612e9a1ea1334abe59e0f327c34677caf4bd39837f5da12b8","first_computed_at":"2026-07-05T02:40:29.470078Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:40:29.470078Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wMu5X5Rlc0P45B4jnicMgIB11IqTryfcoSO7YkTX01JqyWNpcbb++RpEhKZrm9KiWPqTzX/x+5LE4dklB4rsAA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:40:29.470482Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.08895","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b130d2f68324f3ca540cc072c6904ed58e761e94e034ba39d1f2f0d68f11a8fb","sha256:5cf9035ad740d4709afdb4351dff1b0d05918eb3155fe72bf128b3f533b0862d"],"state_sha256":"69726c522f72c44995c8206d6e22501dbba80b19af1c8b7c98201db47d5960e4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X4ddO/P4Tb4DpB3k/60lz/+jR14mlxK0wtoaSVzprTDf8uGSSGEqH3pUVnS+34FFgXv8gzPHOW5NviVTNyYCDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T02:10:51.546911Z","bundle_sha256":"b79b327e80c6baaccc6dd849ae66e1928a819a4a1427eae9562ab6efde27b3b2"}}