{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:2JQYCD7NVITUJLHM2CCQEZWXSW","short_pith_number":"pith:2JQYCD7N","canonical_record":{"source":{"id":"2605.14518","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T08:00:46Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6cab28e6644b8e08cf1af335e2b82401435cf5de5daef8d97ebd6aea2fb4a4cd","abstract_canon_sha256":"622bd21337b22f422840a2d46fe54ad3f41d87c5da4744953c1cd854d7824ff7"},"schema_version":"1.0"},"canonical_sha256":"d261810fedaa2744acecd0850266d795a7d19a331a6e5b79c400e062ac1fbf6a","source":{"kind":"arxiv","id":"2605.14518","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14518","created_at":"2026-05-17T23:39:06Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14518v1","created_at":"2026-05-17T23:39:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14518","created_at":"2026-05-17T23:39:06Z"},{"alias_kind":"pith_short_12","alias_value":"2JQYCD7NVITU","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"2JQYCD7NVITUJLHM","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"2JQYCD7N","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:2JQYCD7NVITUJLHM2CCQEZWXSW","target":"record","payload":{"canonical_record":{"source":{"id":"2605.14518","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T08:00:46Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6cab28e6644b8e08cf1af335e2b82401435cf5de5daef8d97ebd6aea2fb4a4cd","abstract_canon_sha256":"622bd21337b22f422840a2d46fe54ad3f41d87c5da4744953c1cd854d7824ff7"},"schema_version":"1.0"},"canonical_sha256":"d261810fedaa2744acecd0850266d795a7d19a331a6e5b79c400e062ac1fbf6a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:06.101069Z","signature_b64":"VMZXAUrIqJFgZwQ54Wrd2EKsdMcVJ56n3Xr4FA2yMq+T/TRSByxSUp4UU1jUwNlzdJKyGiwRlTnSO2xzFIA+AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d261810fedaa2744acecd0850266d795a7d19a331a6e5b79c400e062ac1fbf6a","last_reissued_at":"2026-05-17T23:39:06.100364Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:06.100364Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.14518","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":"2026-05-17T23:39:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6F2VGVW2B4oVJBc8gEuzMr/gz/B/h0UqNSx4Qj5b3Nzzzv3eGf6oFQqAzEE4hnovo6Z6LIhx5UtnvJRzrL0VDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T22:31:22.518725Z"},"content_sha256":"f8bb08ba3cb4a224e991b4154f1f2a32f9958c2a836ec034cab22efc2f3395f8","schema_version":"1.0","event_id":"sha256:f8bb08ba3cb4a224e991b4154f1f2a32f9958c2a836ec034cab22efc2f3395f8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:2JQYCD7NVITUJLHM2CCQEZWXSW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ArcGate: Adaptive Arctangent Gated Activation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"ArcGate uses seven learnable parameters per layer to let networks adapt activation shape to data, improving accuracy on remote sensing classification especially under noise.","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Alejandro C. Frery, Avik Bhattacharya, Biplab Banerjee, Siddhant Dnyanesh Gole, Subhasis Chaudhuri","submitted_at":"2026-05-14T08:00:46Z","abstract_excerpt":"Activation functions are central to deep networks, influencing non-linearity, feature learning, convergence, and robustness. This paper proposes the Adaptive Arctangent Gated Activation (ArcGate) function, a flexible formulation that generates a broad spectrum of activation shapes via a three-stage non-linear transformation. Unlike conventional fixed-shape activations such as ReLU, GELU, or SiLU, ArcGate uses seven learnable parameters per layer, allowing the neural network to autonomously optimize its non-linearity to the specific requirements of the feature hierarchy and data distribution. W"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"ArcGate consistently outperforms standard baselines, achieving a peak overall accuracy of 99.67% on PatternNet. Most notably, ArcGate exhibits superior structural resilience in noisy environments, maintaining a 26.65% performance lead over ReLU under moderate Gaussian noise (standard deviation 0.1).","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The seven learnable parameters per layer can be stably optimized during training without causing overfitting, instability, or excessive computational overhead, and that the observed performance gains are due to the adaptive shape rather than the increased parameter count.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"ArcGate is an adaptive activation with seven learnable parameters that outperforms ReLU and other fixed activations on remote sensing benchmarks, reaching 99.67% accuracy on PatternNet and showing strong noise resilience.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"ArcGate uses seven learnable parameters per layer to let networks adapt activation shape to data, improving accuracy on remote sensing classification especially under noise.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"7c72387399afc0c901f50d98d29eedaebb521d658e0b299c2dfe342458617816"},"source":{"id":"2605.14518","kind":"arxiv","version":1},"verdict":{"id":"86da5808-54a4-4e60-ad46-c2fa531d7348","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T05:09:57.912226Z","strongest_claim":"ArcGate consistently outperforms standard baselines, achieving a peak overall accuracy of 99.67% on PatternNet. Most notably, ArcGate exhibits superior structural resilience in noisy environments, maintaining a 26.65% performance lead over ReLU under moderate Gaussian noise (standard deviation 0.1).","one_line_summary":"ArcGate is an adaptive activation with seven learnable parameters that outperforms ReLU and other fixed activations on remote sensing benchmarks, reaching 99.67% accuracy on PatternNet and showing strong noise resilience.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The seven learnable parameters per layer can be stably optimized during training without causing overfitting, instability, or excessive computational overhead, and that the observed performance gains are due to the adaptive shape rather than the increased parameter count.","pith_extraction_headline":"ArcGate uses seven learnable parameters per layer to let networks adapt activation shape to data, improving accuracy on remote sensing classification especially under noise."},"references":{"count":12,"sample":[{"doi":"","year":1997,"title":"T. Mitchell,Machine Learning. McGraw Hill, 1997. [Online]. Available: /bib/mitchell/Mitchell1997/MachineLearning-TomMitchell.pdf","work_id":"b0a17141-cdc3-4be0-bae0-751ce8b012ed","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"A more general electromagnetic inverse scattering method based on physics- informed neural network,","work_id":"e399c119-2af7-4c33-9fe9-09f7e574364a","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"BiophyNet: A regression network for joint estimation of plant area index and wet biomass from SAR data,","work_id":"564b3673-b35e-4ba4-b8f1-b0f815cb51df","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"Convolutional au- toencoder for Spectral–Spatial hyperspectral unmixing,","work_id":"a274a38b-7446-4297-a53e-3b4231c06618","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Meta-learning classi- fication network for few-shot polarimetric SAR images,","work_id":"f2f367c3-fc71-4cfd-866b-e075888a40d4","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":12,"snapshot_sha256":"0783d579a0cf7f2b584a312df6b076f024306c1acb5a0ce862475596fc5cab47","internal_anchors":5},"formal_canon":{"evidence_count":1,"snapshot_sha256":"ccce4c6c69247d0421e2bd0764c1e1d862a5a2952fa41b6ba50645f0a526ae2c"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"86da5808-54a4-4e60-ad46-c2fa531d7348"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"idSRmKAMysFpNGg9DC0WCzbCLxaaTBeo2pAwAOceVkeHnBc2B2b9nrMCzR6fRNwD07jcaaXiwDoeAja6MY1QBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T22:31:22.519390Z"},"content_sha256":"27149e5709c700ab7e17f9be72719688220ccd26c7eaef12044f03f05627eb1a","schema_version":"1.0","event_id":"sha256:27149e5709c700ab7e17f9be72719688220ccd26c7eaef12044f03f05627eb1a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2JQYCD7NVITUJLHM2CCQEZWXSW/bundle.json","state_url":"https://pith.science/pith/2JQYCD7NVITUJLHM2CCQEZWXSW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2JQYCD7NVITUJLHM2CCQEZWXSW/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":"2026-06-03T22:31:22Z","links":{"resolver":"https://pith.science/pith/2JQYCD7NVITUJLHM2CCQEZWXSW","bundle":"https://pith.science/pith/2JQYCD7NVITUJLHM2CCQEZWXSW/bundle.json","state":"https://pith.science/pith/2JQYCD7NVITUJLHM2CCQEZWXSW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2JQYCD7NVITUJLHM2CCQEZWXSW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2JQYCD7NVITUJLHM2CCQEZWXSW","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":"622bd21337b22f422840a2d46fe54ad3f41d87c5da4744953c1cd854d7824ff7","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T08:00:46Z","title_canon_sha256":"6cab28e6644b8e08cf1af335e2b82401435cf5de5daef8d97ebd6aea2fb4a4cd"},"schema_version":"1.0","source":{"id":"2605.14518","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14518","created_at":"2026-05-17T23:39:06Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14518v1","created_at":"2026-05-17T23:39:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14518","created_at":"2026-05-17T23:39:06Z"},{"alias_kind":"pith_short_12","alias_value":"2JQYCD7NVITU","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"2JQYCD7NVITUJLHM","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"2JQYCD7N","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:27149e5709c700ab7e17f9be72719688220ccd26c7eaef12044f03f05627eb1a","target":"graph","created_at":"2026-05-17T23:39:06Z","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":"ArcGate consistently outperforms standard baselines, achieving a peak overall accuracy of 99.67% on PatternNet. Most notably, ArcGate exhibits superior structural resilience in noisy environments, maintaining a 26.65% performance lead over ReLU under moderate Gaussian noise (standard deviation 0.1)."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The seven learnable parameters per layer can be stably optimized during training without causing overfitting, instability, or excessive computational overhead, and that the observed performance gains are due to the adaptive shape rather than the increased parameter count."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"ArcGate is an adaptive activation with seven learnable parameters that outperforms ReLU and other fixed activations on remote sensing benchmarks, reaching 99.67% accuracy on PatternNet and showing strong noise resilience."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"ArcGate uses seven learnable parameters per layer to let networks adapt activation shape to data, improving accuracy on remote sensing classification especially under noise."}],"snapshot_sha256":"7c72387399afc0c901f50d98d29eedaebb521d658e0b299c2dfe342458617816"},"formal_canon":{"evidence_count":1,"snapshot_sha256":"ccce4c6c69247d0421e2bd0764c1e1d862a5a2952fa41b6ba50645f0a526ae2c"},"paper":{"abstract_excerpt":"Activation functions are central to deep networks, influencing non-linearity, feature learning, convergence, and robustness. This paper proposes the Adaptive Arctangent Gated Activation (ArcGate) function, a flexible formulation that generates a broad spectrum of activation shapes via a three-stage non-linear transformation. Unlike conventional fixed-shape activations such as ReLU, GELU, or SiLU, ArcGate uses seven learnable parameters per layer, allowing the neural network to autonomously optimize its non-linearity to the specific requirements of the feature hierarchy and data distribution. W","authors_text":"Alejandro C. Frery, Avik Bhattacharya, Biplab Banerjee, Siddhant Dnyanesh Gole, Subhasis Chaudhuri","cross_cats":["cs.LG"],"headline":"ArcGate uses seven learnable parameters per layer to let networks adapt activation shape to data, improving accuracy on remote sensing classification especially under noise.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T08:00:46Z","title":"ArcGate: Adaptive Arctangent Gated Activation"},"references":{"count":12,"internal_anchors":5,"resolved_work":12,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"T. Mitchell,Machine Learning. McGraw Hill, 1997. [Online]. Available: /bib/mitchell/Mitchell1997/MachineLearning-TomMitchell.pdf","work_id":"b0a17141-cdc3-4be0-bae0-751ce8b012ed","year":1997},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"A more general electromagnetic inverse scattering method based on physics- informed neural network,","work_id":"e399c119-2af7-4c33-9fe9-09f7e574364a","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"BiophyNet: A regression network for joint estimation of plant area index and wet biomass from SAR data,","work_id":"564b3673-b35e-4ba4-b8f1-b0f815cb51df","year":2021},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Convolutional au- toencoder for Spectral–Spatial hyperspectral unmixing,","work_id":"a274a38b-7446-4297-a53e-3b4231c06618","year":2021},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Meta-learning classi- fication network for few-shot polarimetric SAR images,","work_id":"f2f367c3-fc71-4cfd-866b-e075888a40d4","year":2025}],"snapshot_sha256":"0783d579a0cf7f2b584a312df6b076f024306c1acb5a0ce862475596fc5cab47"},"source":{"id":"2605.14518","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-15T05:09:57.912226Z","id":"86da5808-54a4-4e60-ad46-c2fa531d7348","model_set":{"reader":"grok-4.3"},"one_line_summary":"ArcGate is an adaptive activation with seven learnable parameters that outperforms ReLU and other fixed activations on remote sensing benchmarks, reaching 99.67% accuracy on PatternNet and showing strong noise resilience.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"ArcGate uses seven learnable parameters per layer to let networks adapt activation shape to data, improving accuracy on remote sensing classification especially under noise.","strongest_claim":"ArcGate consistently outperforms standard baselines, achieving a peak overall accuracy of 99.67% on PatternNet. Most notably, ArcGate exhibits superior structural resilience in noisy environments, maintaining a 26.65% performance lead over ReLU under moderate Gaussian noise (standard deviation 0.1).","weakest_assumption":"The seven learnable parameters per layer can be stably optimized during training without causing overfitting, instability, or excessive computational overhead, and that the observed performance gains are due to the adaptive shape rather than the increased parameter count."}},"verdict_id":"86da5808-54a4-4e60-ad46-c2fa531d7348"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f8bb08ba3cb4a224e991b4154f1f2a32f9958c2a836ec034cab22efc2f3395f8","target":"record","created_at":"2026-05-17T23:39:06Z","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":"622bd21337b22f422840a2d46fe54ad3f41d87c5da4744953c1cd854d7824ff7","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T08:00:46Z","title_canon_sha256":"6cab28e6644b8e08cf1af335e2b82401435cf5de5daef8d97ebd6aea2fb4a4cd"},"schema_version":"1.0","source":{"id":"2605.14518","kind":"arxiv","version":1}},"canonical_sha256":"d261810fedaa2744acecd0850266d795a7d19a331a6e5b79c400e062ac1fbf6a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d261810fedaa2744acecd0850266d795a7d19a331a6e5b79c400e062ac1fbf6a","first_computed_at":"2026-05-17T23:39:06.100364Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:06.100364Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VMZXAUrIqJFgZwQ54Wrd2EKsdMcVJ56n3Xr4FA2yMq+T/TRSByxSUp4UU1jUwNlzdJKyGiwRlTnSO2xzFIA+AQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:06.101069Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.14518","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f8bb08ba3cb4a224e991b4154f1f2a32f9958c2a836ec034cab22efc2f3395f8","sha256:27149e5709c700ab7e17f9be72719688220ccd26c7eaef12044f03f05627eb1a"],"state_sha256":"e5ae3e36fb59238fde615cb20f3c04c64eba90e2d7717f344718a6cb0e92af13"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gsDmp/CiJIy01QTvynro5Sgd2HdT12SvvoWTye0qDUMHvceTpymYvIyhdKzBxGDobaIVAgZLFLd3Q4kOgJSgCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T22:31:22.522026Z","bundle_sha256":"2cb179b1a124bca78552cd4d2b51420634f2fb599b7882fb52df04a27e909315"}}