{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:23FV3LEWRLL65SR6MFXZX5WKYJ","short_pith_number":"pith:23FV3LEW","canonical_record":{"source":{"id":"2605.13887","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2026-05-12T02:08:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2aa866a479987b95e0323ff3bc7f78c43a384ea8c9ef779527f1408d3870a06c","abstract_canon_sha256":"16f34e93d0167b2c5c603890f9d123b9b2749215f01940c5d0fdcf341e129b09"},"schema_version":"1.0"},"canonical_sha256":"d6cb5dac968ad7eeca3e616f9bf6cac2496204447e9e398b754355ae26cd3302","source":{"kind":"arxiv","id":"2605.13887","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13887","created_at":"2026-05-17T23:39:19Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13887v1","created_at":"2026-05-17T23:39:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13887","created_at":"2026-05-17T23:39:19Z"},{"alias_kind":"pith_short_12","alias_value":"23FV3LEWRLL6","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"23FV3LEWRLL65SR6","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"23FV3LEW","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:23FV3LEWRLL65SR6MFXZX5WKYJ","target":"record","payload":{"canonical_record":{"source":{"id":"2605.13887","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2026-05-12T02:08:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2aa866a479987b95e0323ff3bc7f78c43a384ea8c9ef779527f1408d3870a06c","abstract_canon_sha256":"16f34e93d0167b2c5c603890f9d123b9b2749215f01940c5d0fdcf341e129b09"},"schema_version":"1.0"},"canonical_sha256":"d6cb5dac968ad7eeca3e616f9bf6cac2496204447e9e398b754355ae26cd3302","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:19.119810Z","signature_b64":"/JqL7fUobz3a1ZirwQss5mmMDsHAQnilg3Si4GQ3ccvIzmtXwyBSUUjqrAXNrgm6wI3l/deQaZTNVc+QBEOpBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d6cb5dac968ad7eeca3e616f9bf6cac2496204447e9e398b754355ae26cd3302","last_reissued_at":"2026-05-17T23:39:19.119099Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:19.119099Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.13887","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":"2026-05-17T23:39:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zX3B5vrKHVmQLoZwTav991SRrwWsA4inm4rLZeOgwrwPLCFhXpdMHcL1OUJiJYXDlBip0UNSp5kNBlQyB3rCBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T10:24:35.689409Z"},"content_sha256":"be3541bfa28a68710821244af250d934311e3a3eb219321c1765eb3da41c2b86","schema_version":"1.0","event_id":"sha256:be3541bfa28a68710821244af250d934311e3a3eb219321c1765eb3da41c2b86"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:23FV3LEWRLL65SR6MFXZX5WKYJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Breaking Global Self-Attention Bottlenecks in Transformer-based Spiking Neural Networks with Local Structure-Aware Self-Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Local dilated-window self-attention and spiking response pooling let transformer-based spiking networks preserve regional features while cutting quadratic redundancy.","cross_cats":["cs.AI"],"primary_cat":"cs.NE","authors_text":"Hangming Zhang, Lingdong Li, Qiang Yu","submitted_at":"2026-05-12T02:08:08Z","abstract_excerpt":"Transformer-based Spiking Neural Networks (SNNs) integrate SNNs with global self-attention and have demonstrated impressive performance. However, existing Transformer-based SNNs suffer from two fundamental limitations. First, they typically employ max pooling layers to reduce the size of feature maps, but the max pooling captures only the strongest response and fails to comprehensively preserve representative regional features. Second, the global self-attention involves all global feature interactions, resulting in computational redundancy and quadratic computational complexity, thus conflicti"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"On the more challenging static dataset Tiny-ImageNet and neuromorphic dataset N-CALTECH101, LSFormer substantially outperforms state-of-the-art baselines by 4.3% and 8.6% in top-1 classification accuracy, respectively.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the reported accuracy improvements arise from the local structure-aware mechanism and spiking response pooling rather than from unstated hyper-parameter tuning, longer training, or dataset-specific engineering choices not controlled in the baselines.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"LSFormer uses local structure-aware spiking self-attention and spiking response pooling to cut global attention bottlenecks, delivering 4.3% and 8.6% accuracy gains on Tiny-ImageNet and N-CALTECH101 over prior transformer-based SNNs.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Local dilated-window self-attention and spiking response pooling let transformer-based spiking networks preserve regional features while cutting quadratic redundancy.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"d81ef854f6b9d9a66de4aad79194598088038d5577be2724ddb8c02eae40fa40"},"source":{"id":"2605.13887","kind":"arxiv","version":1},"verdict":{"id":"e500220a-3419-4202-baeb-bbf46a2d617c","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T06:13:46.547240Z","strongest_claim":"On the more challenging static dataset Tiny-ImageNet and neuromorphic dataset N-CALTECH101, LSFormer substantially outperforms state-of-the-art baselines by 4.3% and 8.6% in top-1 classification accuracy, respectively.","one_line_summary":"LSFormer uses local structure-aware spiking self-attention and spiking response pooling to cut global attention bottlenecks, delivering 4.3% and 8.6% accuracy gains on Tiny-ImageNet and N-CALTECH101 over prior transformer-based SNNs.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the reported accuracy improvements arise from the local structure-aware mechanism and spiking response pooling rather than from unstated hyper-parameter tuning, longer training, or dataset-specific engineering choices not controlled in the baselines.","pith_extraction_headline":"Local dilated-window self-attention and spiking response pooling let transformer-based spiking networks preserve regional features while cutting quadratic redundancy."},"references":{"count":73,"sample":[{"doi":"","year":2014,"title":"S. B. Furber, F. Galluppi, S. Temple, and L. A. Plana, “The spinnaker project,”Proceedings of the IEEE, vol. 102, no. 5, pp. 652–665, 2014","work_id":"2e9f9503-c874-4292-b4ef-70a9228b6458","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Trainable spiking-yolo for low-latency and high-performance object detection,","work_id":"34351c01-9968-45cb-aec4-4cad68b92ae4","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"Event stream learning using spatio-temporal event surface,","work_id":"8c2a44e3-c778-428f-a49c-c9266a4fe49d","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Event-driven spiking neural network based on membrane potential modulation for remote sensing image classification,","work_id":"e2e0f21b-8d19-4c09-9755-8501f8c8a35f","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"Spiking neural network-based multi- task autonomous learning for mobile robots,","work_id":"26ab6aea-9dae-450a-9dfc-163f945dd79c","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":73,"snapshot_sha256":"ea7a968cdfd3f81511b6a3c79ec28878dc84843f7559c1078b14bdeccb84e64a","internal_anchors":1},"formal_canon":{"evidence_count":2,"snapshot_sha256":"385932571f1a4a340c54cdd867a00884724e9809cb27b97f37da8a1f942d1dab"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"e500220a-3419-4202-baeb-bbf46a2d617c"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bdpHpISwhNB4tQo2k+sA18yTG4S+IQqrr1IsvBzdAjRiIWA1NJk84Zk5zty6mUd3n0nnItL99oFM4dlkBe6GBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T10:24:35.690056Z"},"content_sha256":"7ee6c7c18ff130c4e6a4a12d0672e25b604d52ce2d1ad824b67713dd2732bd2b","schema_version":"1.0","event_id":"sha256:7ee6c7c18ff130c4e6a4a12d0672e25b604d52ce2d1ad824b67713dd2732bd2b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/23FV3LEWRLL65SR6MFXZX5WKYJ/bundle.json","state_url":"https://pith.science/pith/23FV3LEWRLL65SR6MFXZX5WKYJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/23FV3LEWRLL65SR6MFXZX5WKYJ/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":"2026-06-01T10:24:35Z","links":{"resolver":"https://pith.science/pith/23FV3LEWRLL65SR6MFXZX5WKYJ","bundle":"https://pith.science/pith/23FV3LEWRLL65SR6MFXZX5WKYJ/bundle.json","state":"https://pith.science/pith/23FV3LEWRLL65SR6MFXZX5WKYJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/23FV3LEWRLL65SR6MFXZX5WKYJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:23FV3LEWRLL65SR6MFXZX5WKYJ","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":"16f34e93d0167b2c5c603890f9d123b9b2749215f01940c5d0fdcf341e129b09","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2026-05-12T02:08:08Z","title_canon_sha256":"2aa866a479987b95e0323ff3bc7f78c43a384ea8c9ef779527f1408d3870a06c"},"schema_version":"1.0","source":{"id":"2605.13887","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13887","created_at":"2026-05-17T23:39:19Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13887v1","created_at":"2026-05-17T23:39:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13887","created_at":"2026-05-17T23:39:19Z"},{"alias_kind":"pith_short_12","alias_value":"23FV3LEWRLL6","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"23FV3LEWRLL65SR6","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"23FV3LEW","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:7ee6c7c18ff130c4e6a4a12d0672e25b604d52ce2d1ad824b67713dd2732bd2b","target":"graph","created_at":"2026-05-17T23:39:19Z","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":"On the more challenging static dataset Tiny-ImageNet and neuromorphic dataset N-CALTECH101, LSFormer substantially outperforms state-of-the-art baselines by 4.3% and 8.6% in top-1 classification accuracy, respectively."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the reported accuracy improvements arise from the local structure-aware mechanism and spiking response pooling rather than from unstated hyper-parameter tuning, longer training, or dataset-specific engineering choices not controlled in the baselines."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"LSFormer uses local structure-aware spiking self-attention and spiking response pooling to cut global attention bottlenecks, delivering 4.3% and 8.6% accuracy gains on Tiny-ImageNet and N-CALTECH101 over prior transformer-based SNNs."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Local dilated-window self-attention and spiking response pooling let transformer-based spiking networks preserve regional features while cutting quadratic redundancy."}],"snapshot_sha256":"d81ef854f6b9d9a66de4aad79194598088038d5577be2724ddb8c02eae40fa40"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"385932571f1a4a340c54cdd867a00884724e9809cb27b97f37da8a1f942d1dab"},"paper":{"abstract_excerpt":"Transformer-based Spiking Neural Networks (SNNs) integrate SNNs with global self-attention and have demonstrated impressive performance. However, existing Transformer-based SNNs suffer from two fundamental limitations. First, they typically employ max pooling layers to reduce the size of feature maps, but the max pooling captures only the strongest response and fails to comprehensively preserve representative regional features. Second, the global self-attention involves all global feature interactions, resulting in computational redundancy and quadratic computational complexity, thus conflicti","authors_text":"Hangming Zhang, Lingdong Li, Qiang Yu","cross_cats":["cs.AI"],"headline":"Local dilated-window self-attention and spiking response pooling let transformer-based spiking networks preserve regional features while cutting quadratic redundancy.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2026-05-12T02:08:08Z","title":"Breaking Global Self-Attention Bottlenecks in Transformer-based Spiking Neural Networks with Local Structure-Aware Self-Attention"},"references":{"count":73,"internal_anchors":1,"resolved_work":73,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"S. B. Furber, F. Galluppi, S. Temple, and L. A. Plana, “The spinnaker project,”Proceedings of the IEEE, vol. 102, no. 5, pp. 652–665, 2014","work_id":"2e9f9503-c874-4292-b4ef-70a9228b6458","year":2014},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Trainable spiking-yolo for low-latency and high-performance object detection,","work_id":"34351c01-9968-45cb-aec4-4cad68b92ae4","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Event stream learning using spatio-temporal event surface,","work_id":"8c2a44e3-c778-428f-a49c-c9266a4fe49d","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Event-driven spiking neural network based on membrane potential modulation for remote sensing image classification,","work_id":"e2e0f21b-8d19-4c09-9755-8501f8c8a35f","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Spiking neural network-based multi- task autonomous learning for mobile robots,","work_id":"26ab6aea-9dae-450a-9dfc-163f945dd79c","year":2021}],"snapshot_sha256":"ea7a968cdfd3f81511b6a3c79ec28878dc84843f7559c1078b14bdeccb84e64a"},"source":{"id":"2605.13887","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-15T06:13:46.547240Z","id":"e500220a-3419-4202-baeb-bbf46a2d617c","model_set":{"reader":"grok-4.3"},"one_line_summary":"LSFormer uses local structure-aware spiking self-attention and spiking response pooling to cut global attention bottlenecks, delivering 4.3% and 8.6% accuracy gains on Tiny-ImageNet and N-CALTECH101 over prior transformer-based SNNs.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Local dilated-window self-attention and spiking response pooling let transformer-based spiking networks preserve regional features while cutting quadratic redundancy.","strongest_claim":"On the more challenging static dataset Tiny-ImageNet and neuromorphic dataset N-CALTECH101, LSFormer substantially outperforms state-of-the-art baselines by 4.3% and 8.6% in top-1 classification accuracy, respectively.","weakest_assumption":"That the reported accuracy improvements arise from the local structure-aware mechanism and spiking response pooling rather than from unstated hyper-parameter tuning, longer training, or dataset-specific engineering choices not controlled in the baselines."}},"verdict_id":"e500220a-3419-4202-baeb-bbf46a2d617c"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:be3541bfa28a68710821244af250d934311e3a3eb219321c1765eb3da41c2b86","target":"record","created_at":"2026-05-17T23:39:19Z","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":"16f34e93d0167b2c5c603890f9d123b9b2749215f01940c5d0fdcf341e129b09","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2026-05-12T02:08:08Z","title_canon_sha256":"2aa866a479987b95e0323ff3bc7f78c43a384ea8c9ef779527f1408d3870a06c"},"schema_version":"1.0","source":{"id":"2605.13887","kind":"arxiv","version":1}},"canonical_sha256":"d6cb5dac968ad7eeca3e616f9bf6cac2496204447e9e398b754355ae26cd3302","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d6cb5dac968ad7eeca3e616f9bf6cac2496204447e9e398b754355ae26cd3302","first_computed_at":"2026-05-17T23:39:19.119099Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:19.119099Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/JqL7fUobz3a1ZirwQss5mmMDsHAQnilg3Si4GQ3ccvIzmtXwyBSUUjqrAXNrgm6wI3l/deQaZTNVc+QBEOpBA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:19.119810Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.13887","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:be3541bfa28a68710821244af250d934311e3a3eb219321c1765eb3da41c2b86","sha256:7ee6c7c18ff130c4e6a4a12d0672e25b604d52ce2d1ad824b67713dd2732bd2b"],"state_sha256":"c9765690ae1e5be650343205bb82b5ac182376739f4ba6e95cf7d6512fcf6776"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c7OOAp1XGrskejoCAce0V1kL+nPfpjoyhmWxV6iQtmpFsUww5oI0WHNuf7ikFPI7pJk4W/bfrPMu65UTe0j6CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T10:24:35.692717Z","bundle_sha256":"47fc0fead87472791f099c4d60c7a7b4eca98e2e05f84ea28eee5c7dab8a3194"}}