{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:WRQIFOZUYANB2IGIGCPDXSDY3D","short_pith_number":"pith:WRQIFOZU","canonical_record":{"source":{"id":"2605.14370","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.geo-ph","submitted_at":"2026-05-14T04:49:23Z","cross_cats_sorted":["cs.AI","physics.comp-ph"],"title_canon_sha256":"7da4d44bd103febe0b814eff503998003474d7876c449c1089553aa58065d37c","abstract_canon_sha256":"e1f639d485d90c0da452fa391b57323bb100ab8df71f89abcbcfb5f4104b78a5"},"schema_version":"1.0"},"canonical_sha256":"b46082bb34c01a1d20c8309e3bc878d8e72633a1dcef7da0af4ea991e5066aeb","source":{"kind":"arxiv","id":"2605.14370","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14370","created_at":"2026-05-17T23:39:07Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14370v1","created_at":"2026-05-17T23:39:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14370","created_at":"2026-05-17T23:39:07Z"},{"alias_kind":"pith_short_12","alias_value":"WRQIFOZUYANB","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"WRQIFOZUYANB2IGI","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"WRQIFOZU","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:WRQIFOZUYANB2IGIGCPDXSDY3D","target":"record","payload":{"canonical_record":{"source":{"id":"2605.14370","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.geo-ph","submitted_at":"2026-05-14T04:49:23Z","cross_cats_sorted":["cs.AI","physics.comp-ph"],"title_canon_sha256":"7da4d44bd103febe0b814eff503998003474d7876c449c1089553aa58065d37c","abstract_canon_sha256":"e1f639d485d90c0da452fa391b57323bb100ab8df71f89abcbcfb5f4104b78a5"},"schema_version":"1.0"},"canonical_sha256":"b46082bb34c01a1d20c8309e3bc878d8e72633a1dcef7da0af4ea991e5066aeb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:07.841151Z","signature_b64":"M92gMfoGWLBEP7mtLqPhnL2t4nJLwIJ1UbI1/4PaqFzhWsy4HoI7fRApJYdXad8TQyZZQCpaAMKI2ThunmYBDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b46082bb34c01a1d20c8309e3bc878d8e72633a1dcef7da0af4ea991e5066aeb","last_reissued_at":"2026-05-17T23:39:07.840490Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:07.840490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.14370","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":"2026-05-17T23:39:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pUzFjskocJOGAb1BJ+KFey512/RUk9g7xBTpKRNa2aK/GThQvb8LBn3ZvLcuxiqZEfij4dtJ7BLjNWFy3DK4BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T23:19:27.337222Z"},"content_sha256":"1235d074a795736088d622d1b33ee767e1cf68012835b8456f35f1fa721ea94a","schema_version":"1.0","event_id":"sha256:1235d074a795736088d622d1b33ee767e1cf68012835b8456f35f1fa721ea94a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:WRQIFOZUYANB2IGIGCPDXSDY3D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deciphering Neural Reparameterized Full-Waveform Inversion with Neural Sensitivity Kernel and Wave Tangent Kernel","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"The neural tangent kernel from neural reparameterization modulates sensitivity and wave tangent kernels in full-waveform inversion, producing spectral filtering and wavenumber shifts that govern convergence.","cross_cats":["cs.AI","physics.comp-ph"],"primary_cat":"physics.geo-ph","authors_text":"Bangyu Wu, Deyu Meng, Ruihua Chen, Xile Zhao, Yisi Luo","submitted_at":"2026-05-14T04:49:23Z","abstract_excerpt":"Full-waveform inversion (FWI) estimates unknown parameters in the wave equation from limited boundary measurements. Recent advances in neural reparameterized FWI (NeurFWI) demonstrate that representing the parameters using a neural network can reduce the reliance on the high-quality initial model and wavefield data, at the cost of slow high-resolution convergence. However, its underlying theoretical mechanism remains unclear. In this study, we establish the neural sensitivity kernel (NSK) and the wave tangent kernel (WTK) to analyze their convergence behavior from both model and data domains. "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"The neural tangent kernel induced by neural representation adaptively modulates the original sensitivity and wave tangent kernels. This modulation leads to the spectral filtering effect, the gradient wavenumber modulation, and the wave frequency bias, connecting the convergence behavior of NeurFWI with the eigen-structures of NSK and WTK.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the modulation effects of the neural tangent kernel on NSK and WTK can be directly connected to convergence behavior through eigen-structure analysis without unstated approximations or domain-specific assumptions in the derivation.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Neural tangent kernel from neural reparameterization modulates sensitivity and wave tangent kernels to produce spectral filtering, wavenumber modulation, and frequency bias that improve NeurFWI convergence.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"The neural tangent kernel from neural reparameterization modulates sensitivity and wave tangent kernels in full-waveform inversion, producing spectral filtering and wavenumber shifts that govern convergence.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"fc1bada556b26fdb725826ba2070251678a54b6d5aceff3516a653cc62b3a044"},"source":{"id":"2605.14370","kind":"arxiv","version":1},"verdict":{"id":"471397a8-1e93-4779-b042-99fae568ab02","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T01:54:14.823698Z","strongest_claim":"The neural tangent kernel induced by neural representation adaptively modulates the original sensitivity and wave tangent kernels. This modulation leads to the spectral filtering effect, the gradient wavenumber modulation, and the wave frequency bias, connecting the convergence behavior of NeurFWI with the eigen-structures of NSK and WTK.","one_line_summary":"Neural tangent kernel from neural reparameterization modulates sensitivity and wave tangent kernels to produce spectral filtering, wavenumber modulation, and frequency bias that improve NeurFWI convergence.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the modulation effects of the neural tangent kernel on NSK and WTK can be directly connected to convergence behavior through eigen-structure analysis without unstated approximations or domain-specific assumptions in the derivation.","pith_extraction_headline":"The neural tangent kernel from neural reparameterization modulates sensitivity and wave tangent kernels in full-waveform inversion, producing spectral filtering and wavenumber shifts that govern convergence."},"references":{"count":174,"sample":[{"doi":"","year":2009,"title":"An overview of full-waveform inversion in exploration geophysics , author=. Geophysics , volume=. 2009 , publisher=","work_id":"f221d96f-c2e5-4634-8598-b8fb1bd56623","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2006,"title":"International Conference on Computational Learning Theory , pages=","work_id":"5294cedf-65fe-4f82-b669-f6f878b1c6c1","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Geophysical Prospecting , volume=","work_id":"f536f4ee-68b6-4085-a22e-9933759bf346","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"Reparameterized full-waveform inversion using deep neural networks , author=. Geophysics , volume=. 2021 , publisher=","work_id":"ff30b2a7-f732-493c-8f21-32d2a34ad941","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2007,"title":"Topology and its Applications , volume=","work_id":"a2d99aca-77c3-4d5e-9b3b-07817d12d386","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":174,"snapshot_sha256":"9df36f839d69d5e994417e104877fa95859f249d8d82d29d65a0b5be418c82da","internal_anchors":1},"formal_canon":{"evidence_count":2,"snapshot_sha256":"1b4be9833e0daaebd056703ff7150f372e1bb6a3b98af51c79eada1b8333b8db"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"471397a8-1e93-4779-b042-99fae568ab02"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VgFn3aVvGSMZUXmeXdioV9PQ0gUPvyqvP4vuxXoQjWbvefqa//32Glbj2lFCmRTgnbxtuOtbI9lOxJaOZVkMDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T23:19:27.338255Z"},"content_sha256":"953ed48ecb8f3dd4d7e782cbfb87704e82880177e250009a0cdaa92456411e3c","schema_version":"1.0","event_id":"sha256:953ed48ecb8f3dd4d7e782cbfb87704e82880177e250009a0cdaa92456411e3c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WRQIFOZUYANB2IGIGCPDXSDY3D/bundle.json","state_url":"https://pith.science/pith/WRQIFOZUYANB2IGIGCPDXSDY3D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WRQIFOZUYANB2IGIGCPDXSDY3D/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":"2026-05-27T23:19:27Z","links":{"resolver":"https://pith.science/pith/WRQIFOZUYANB2IGIGCPDXSDY3D","bundle":"https://pith.science/pith/WRQIFOZUYANB2IGIGCPDXSDY3D/bundle.json","state":"https://pith.science/pith/WRQIFOZUYANB2IGIGCPDXSDY3D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WRQIFOZUYANB2IGIGCPDXSDY3D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:WRQIFOZUYANB2IGIGCPDXSDY3D","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":"e1f639d485d90c0da452fa391b57323bb100ab8df71f89abcbcfb5f4104b78a5","cross_cats_sorted":["cs.AI","physics.comp-ph"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.geo-ph","submitted_at":"2026-05-14T04:49:23Z","title_canon_sha256":"7da4d44bd103febe0b814eff503998003474d7876c449c1089553aa58065d37c"},"schema_version":"1.0","source":{"id":"2605.14370","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14370","created_at":"2026-05-17T23:39:07Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14370v1","created_at":"2026-05-17T23:39:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14370","created_at":"2026-05-17T23:39:07Z"},{"alias_kind":"pith_short_12","alias_value":"WRQIFOZUYANB","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"WRQIFOZUYANB2IGI","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"WRQIFOZU","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:953ed48ecb8f3dd4d7e782cbfb87704e82880177e250009a0cdaa92456411e3c","target":"graph","created_at":"2026-05-17T23:39:07Z","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 neural tangent kernel induced by neural representation adaptively modulates the original sensitivity and wave tangent kernels. This modulation leads to the spectral filtering effect, the gradient wavenumber modulation, and the wave frequency bias, connecting the convergence behavior of NeurFWI with the eigen-structures of NSK and WTK."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the modulation effects of the neural tangent kernel on NSK and WTK can be directly connected to convergence behavior through eigen-structure analysis without unstated approximations or domain-specific assumptions in the derivation."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Neural tangent kernel from neural reparameterization modulates sensitivity and wave tangent kernels to produce spectral filtering, wavenumber modulation, and frequency bias that improve NeurFWI convergence."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"The neural tangent kernel from neural reparameterization modulates sensitivity and wave tangent kernels in full-waveform inversion, producing spectral filtering and wavenumber shifts that govern convergence."}],"snapshot_sha256":"fc1bada556b26fdb725826ba2070251678a54b6d5aceff3516a653cc62b3a044"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"1b4be9833e0daaebd056703ff7150f372e1bb6a3b98af51c79eada1b8333b8db"},"paper":{"abstract_excerpt":"Full-waveform inversion (FWI) estimates unknown parameters in the wave equation from limited boundary measurements. Recent advances in neural reparameterized FWI (NeurFWI) demonstrate that representing the parameters using a neural network can reduce the reliance on the high-quality initial model and wavefield data, at the cost of slow high-resolution convergence. However, its underlying theoretical mechanism remains unclear. In this study, we establish the neural sensitivity kernel (NSK) and the wave tangent kernel (WTK) to analyze their convergence behavior from both model and data domains. ","authors_text":"Bangyu Wu, Deyu Meng, Ruihua Chen, Xile Zhao, Yisi Luo","cross_cats":["cs.AI","physics.comp-ph"],"headline":"The neural tangent kernel from neural reparameterization modulates sensitivity and wave tangent kernels in full-waveform inversion, producing spectral filtering and wavenumber shifts that govern convergence.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.geo-ph","submitted_at":"2026-05-14T04:49:23Z","title":"Deciphering Neural Reparameterized Full-Waveform Inversion with Neural Sensitivity Kernel and Wave Tangent Kernel"},"references":{"count":174,"internal_anchors":1,"resolved_work":174,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"An overview of full-waveform inversion in exploration geophysics , author=. Geophysics , volume=. 2009 , publisher=","work_id":"f221d96f-c2e5-4634-8598-b8fb1bd56623","year":2009},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"International Conference on Computational Learning Theory , pages=","work_id":"5294cedf-65fe-4f82-b669-f6f878b1c6c1","year":2006},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Geophysical Prospecting , volume=","work_id":"f536f4ee-68b6-4085-a22e-9933759bf346","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Reparameterized full-waveform inversion using deep neural networks , author=. Geophysics , volume=. 2021 , publisher=","work_id":"ff30b2a7-f732-493c-8f21-32d2a34ad941","year":2021},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Topology and its Applications , volume=","work_id":"a2d99aca-77c3-4d5e-9b3b-07817d12d386","year":2007}],"snapshot_sha256":"9df36f839d69d5e994417e104877fa95859f249d8d82d29d65a0b5be418c82da"},"source":{"id":"2605.14370","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-15T01:54:14.823698Z","id":"471397a8-1e93-4779-b042-99fae568ab02","model_set":{"reader":"grok-4.3"},"one_line_summary":"Neural tangent kernel from neural reparameterization modulates sensitivity and wave tangent kernels to produce spectral filtering, wavenumber modulation, and frequency bias that improve NeurFWI convergence.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"The neural tangent kernel from neural reparameterization modulates sensitivity and wave tangent kernels in full-waveform inversion, producing spectral filtering and wavenumber shifts that govern convergence.","strongest_claim":"The neural tangent kernel induced by neural representation adaptively modulates the original sensitivity and wave tangent kernels. This modulation leads to the spectral filtering effect, the gradient wavenumber modulation, and the wave frequency bias, connecting the convergence behavior of NeurFWI with the eigen-structures of NSK and WTK.","weakest_assumption":"That the modulation effects of the neural tangent kernel on NSK and WTK can be directly connected to convergence behavior through eigen-structure analysis without unstated approximations or domain-specific assumptions in the derivation."}},"verdict_id":"471397a8-1e93-4779-b042-99fae568ab02"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1235d074a795736088d622d1b33ee767e1cf68012835b8456f35f1fa721ea94a","target":"record","created_at":"2026-05-17T23:39:07Z","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":"e1f639d485d90c0da452fa391b57323bb100ab8df71f89abcbcfb5f4104b78a5","cross_cats_sorted":["cs.AI","physics.comp-ph"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.geo-ph","submitted_at":"2026-05-14T04:49:23Z","title_canon_sha256":"7da4d44bd103febe0b814eff503998003474d7876c449c1089553aa58065d37c"},"schema_version":"1.0","source":{"id":"2605.14370","kind":"arxiv","version":1}},"canonical_sha256":"b46082bb34c01a1d20c8309e3bc878d8e72633a1dcef7da0af4ea991e5066aeb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b46082bb34c01a1d20c8309e3bc878d8e72633a1dcef7da0af4ea991e5066aeb","first_computed_at":"2026-05-17T23:39:07.840490Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:07.840490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"M92gMfoGWLBEP7mtLqPhnL2t4nJLwIJ1UbI1/4PaqFzhWsy4HoI7fRApJYdXad8TQyZZQCpaAMKI2ThunmYBDQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:07.841151Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.14370","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1235d074a795736088d622d1b33ee767e1cf68012835b8456f35f1fa721ea94a","sha256:953ed48ecb8f3dd4d7e782cbfb87704e82880177e250009a0cdaa92456411e3c"],"state_sha256":"476ce257da4729e5158a22c0b4c1a34bf6ac4c85c145cdb85745ecc85404efff"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lKokGW39MIwNRDhrBvuQkBtl85kWiBGWCXXlmxkYw6NCqi8F7U6XzPkx1aS4OxDdS5DHNx5tUbSU2gdjLbeZDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T23:19:27.342660Z","bundle_sha256":"4e30d26a7822ebeec6af9911577c9e83268f2bfe689c47996f13207bfa8d3f4d"}}