{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:IYR6WFUPK3ARB4IXEW6KQOTW3A","short_pith_number":"pith:IYR6WFUP","canonical_record":{"source":{"id":"2605.13133","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T08:02:59Z","cross_cats_sorted":["eess.SP"],"title_canon_sha256":"9c38d663dd54ccd2664540530330aaef9feb82490e9df43da796f9658d3f55b4","abstract_canon_sha256":"23de649e81e3b58d50422ac6d0b5bd962a34fa5d1bd4b91ed0c8b44de29bbc71"},"schema_version":"1.0"},"canonical_sha256":"4623eb168f56c110f11725bca83a76d82e7d79db9f52cf50f87274bef4f77dc9","source":{"kind":"arxiv","id":"2605.13133","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13133","created_at":"2026-05-18T03:08:57Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13133v1","created_at":"2026-05-18T03:08:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13133","created_at":"2026-05-18T03:08:57Z"},{"alias_kind":"pith_short_12","alias_value":"IYR6WFUPK3AR","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"IYR6WFUPK3ARB4IX","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"IYR6WFUP","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:IYR6WFUPK3ARB4IXEW6KQOTW3A","target":"record","payload":{"canonical_record":{"source":{"id":"2605.13133","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T08:02:59Z","cross_cats_sorted":["eess.SP"],"title_canon_sha256":"9c38d663dd54ccd2664540530330aaef9feb82490e9df43da796f9658d3f55b4","abstract_canon_sha256":"23de649e81e3b58d50422ac6d0b5bd962a34fa5d1bd4b91ed0c8b44de29bbc71"},"schema_version":"1.0"},"canonical_sha256":"4623eb168f56c110f11725bca83a76d82e7d79db9f52cf50f87274bef4f77dc9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:08:57.673983Z","signature_b64":"VuE5YG12bTPijiX4gNXbuN777MvBmSHfI/m9PKlcXYEKAAuvG3+uuzrTivFS4qc6fDus4twQZxGmIawtNU9HCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4623eb168f56c110f11725bca83a76d82e7d79db9f52cf50f87274bef4f77dc9","last_reissued_at":"2026-05-18T03:08:57.673028Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:08:57.673028Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.13133","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":"2026-05-18T03:08:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TgUzzvhM8Kax6v3lFJUKNuBONlATkrPBwMTVPBBYCTejI7mdV/tiC10pbVX3pf4RnkSA52YB3C4pO1ewGOzbDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T05:10:58.309119Z"},"content_sha256":"198e48df004638987824e6a3ff6b4bb358c22a8011bfd25fda7da3d55571e553","schema_version":"1.0","event_id":"sha256:198e48df004638987824e6a3ff6b4bb358c22a8011bfd25fda7da3d55571e553"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:IYR6WFUPK3ARB4IXEW6KQOTW3A","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"KAST-BAR: Knowledge-Anchored Semantically-Dynamic Topology Brain Autoregressive Modeling for Universal Neural Interpretation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"KAST-BAR builds an EEG foundation model that aligns brain signals with medical knowledge using dynamic topology modeling and achieves better results on six tasks.","cross_cats":["eess.SP"],"primary_cat":"cs.LG","authors_text":"Haoning Wang, Shuai Shen, Wenchao Yang, Yang Li","submitted_at":"2026-05-13T08:02:59Z","abstract_excerpt":"While EEG foundation models have shown significant potential in universal neural decoding across tasks, their advancement remains constrained by the inadequacy modeling of complex spatiotemporal topology, as well as the inherent modality gap between low-level physiological signals and high-level textual semantics. To address these challenges, we propose a Knowledge-Anchored Semantically-Dynamic Topology Brain Autoregressive Model (KAST-BAR), which dynamically aligns physiological representations derived from multi-level brain topology with an expert-level semantic space. Specifically, we desig"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"By conducting large-scale pre-training on 21 diverse datasets to build a foundation model, KAST-BAR effectively integrates expert-level medical knowledge into EEG signal representations, consistently achieving superior performance across six downstream tasks.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The assumption that the Dual-Stream Hierarchical Attention encoder, Knowledge-Anchored Semantic Profiler, and Semantic Text-Aware Refiner can accurately capture non-Euclidean brain topology and dynamically align low-level physiological signals with high-level textual semantics without introducing artifacts or overfitting to the pre-training data.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"KAST-BAR builds an EEG foundation model by dynamically modeling non-Euclidean brain topology with DSHA and aligning signals to expert semantic space via KASP and STAR, achieving superior performance on six downstream tasks after pre-training on 21 datasets.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"KAST-BAR builds an EEG foundation model that aligns brain signals with medical knowledge using dynamic topology modeling and achieves better results on six tasks.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"b97c6314bbd616c3e0115de227d29af83056f316952aabbdfb8e230ef4f3d490"},"source":{"id":"2605.13133","kind":"arxiv","version":1},"verdict":{"id":"f92dcab3-dd43-4032-b0d0-f64575659217","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T19:23:44.022160Z","strongest_claim":"By conducting large-scale pre-training on 21 diverse datasets to build a foundation model, KAST-BAR effectively integrates expert-level medical knowledge into EEG signal representations, consistently achieving superior performance across six downstream tasks.","one_line_summary":"KAST-BAR builds an EEG foundation model by dynamically modeling non-Euclidean brain topology with DSHA and aligning signals to expert semantic space via KASP and STAR, achieving superior performance on six downstream tasks after pre-training on 21 datasets.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The assumption that the Dual-Stream Hierarchical Attention encoder, Knowledge-Anchored Semantic Profiler, and Semantic Text-Aware Refiner can accurately capture non-Euclidean brain topology and dynamically align low-level physiological signals with high-level textual semantics without introducing artifacts or overfitting to the pre-training data.","pith_extraction_headline":"KAST-BAR builds an EEG foundation model that aligns brain signals with medical knowledge using dynamic topology modeling and achieves better results on six tasks."},"references":{"count":23,"sample":[{"doi":"10.1109/spmb.2017.8257018","year":2017,"title":"universal neural representations","work_id":"1b6e601b-491d-4848-bc19-66571b8d4ad5","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2026,"title":"Topological Mismatch","work_id":"db774d38-5cbb-47b5-9a44-48b79b11f33f","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Brain Invaders","work_id":"d3a785a7-7537-4c2a-88e8-cbdc13c23e5f","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2017,"title":"Detailed network architecture specifications are provided in Table 7","work_id":"8b400035-2576-400d-afb9-5b13f7b4b4c3","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"DSHA Structure: Dual-Stream Interaction Mechanism.Going beyond simple unidirectional multi-scale feature aggregation, DSHA adopts an explicitBidirectional Progressive Interaction Strategyto address th","work_id":"6fd005dd-5deb-47c0-98ed-10e37740c302","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":23,"snapshot_sha256":"336422e8436e6346d39d41d6ec8048ca12d83c5624b15809939b9be8ec92074b","internal_anchors":0},"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":"f92dcab3-dd43-4032-b0d0-f64575659217"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:08:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VtgKM42pmB0JGm6d8XW2mIStW1xa9vmVOXS0uG5Nn6SEScjf3+p/I4Xl99hgJgl87StAQaHnrNgl/4t3y0ybDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T05:10:58.310040Z"},"content_sha256":"6eefaa34003af265b857f0dac5f8e42e92ac313eb71d9bab7fbe5b24098eff92","schema_version":"1.0","event_id":"sha256:6eefaa34003af265b857f0dac5f8e42e92ac313eb71d9bab7fbe5b24098eff92"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IYR6WFUPK3ARB4IXEW6KQOTW3A/bundle.json","state_url":"https://pith.science/pith/IYR6WFUPK3ARB4IXEW6KQOTW3A/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IYR6WFUPK3ARB4IXEW6KQOTW3A/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":"2026-05-30T05:10:58Z","links":{"resolver":"https://pith.science/pith/IYR6WFUPK3ARB4IXEW6KQOTW3A","bundle":"https://pith.science/pith/IYR6WFUPK3ARB4IXEW6KQOTW3A/bundle.json","state":"https://pith.science/pith/IYR6WFUPK3ARB4IXEW6KQOTW3A/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IYR6WFUPK3ARB4IXEW6KQOTW3A/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:IYR6WFUPK3ARB4IXEW6KQOTW3A","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":"23de649e81e3b58d50422ac6d0b5bd962a34fa5d1bd4b91ed0c8b44de29bbc71","cross_cats_sorted":["eess.SP"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T08:02:59Z","title_canon_sha256":"9c38d663dd54ccd2664540530330aaef9feb82490e9df43da796f9658d3f55b4"},"schema_version":"1.0","source":{"id":"2605.13133","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13133","created_at":"2026-05-18T03:08:57Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13133v1","created_at":"2026-05-18T03:08:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13133","created_at":"2026-05-18T03:08:57Z"},{"alias_kind":"pith_short_12","alias_value":"IYR6WFUPK3AR","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"IYR6WFUPK3ARB4IX","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"IYR6WFUP","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:6eefaa34003af265b857f0dac5f8e42e92ac313eb71d9bab7fbe5b24098eff92","target":"graph","created_at":"2026-05-18T03:08:57Z","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":"By conducting large-scale pre-training on 21 diverse datasets to build a foundation model, KAST-BAR effectively integrates expert-level medical knowledge into EEG signal representations, consistently achieving superior performance across six downstream tasks."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The assumption that the Dual-Stream Hierarchical Attention encoder, Knowledge-Anchored Semantic Profiler, and Semantic Text-Aware Refiner can accurately capture non-Euclidean brain topology and dynamically align low-level physiological signals with high-level textual semantics without introducing artifacts or overfitting to the pre-training data."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"KAST-BAR builds an EEG foundation model by dynamically modeling non-Euclidean brain topology with DSHA and aligning signals to expert semantic space via KASP and STAR, achieving superior performance on six downstream tasks after pre-training on 21 datasets."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"KAST-BAR builds an EEG foundation model that aligns brain signals with medical knowledge using dynamic topology modeling and achieves better results on six tasks."}],"snapshot_sha256":"b97c6314bbd616c3e0115de227d29af83056f316952aabbdfb8e230ef4f3d490"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"While EEG foundation models have shown significant potential in universal neural decoding across tasks, their advancement remains constrained by the inadequacy modeling of complex spatiotemporal topology, as well as the inherent modality gap between low-level physiological signals and high-level textual semantics. To address these challenges, we propose a Knowledge-Anchored Semantically-Dynamic Topology Brain Autoregressive Model (KAST-BAR), which dynamically aligns physiological representations derived from multi-level brain topology with an expert-level semantic space. Specifically, we desig","authors_text":"Haoning Wang, Shuai Shen, Wenchao Yang, Yang Li","cross_cats":["eess.SP"],"headline":"KAST-BAR builds an EEG foundation model that aligns brain signals with medical knowledge using dynamic topology modeling and achieves better results on six tasks.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T08:02:59Z","title":"KAST-BAR: Knowledge-Anchored Semantically-Dynamic Topology Brain Autoregressive Modeling for Universal Neural Interpretation"},"references":{"count":23,"internal_anchors":0,"resolved_work":23,"sample":[{"cited_arxiv_id":"","doi":"10.1109/spmb.2017.8257018","is_internal_anchor":false,"ref_index":1,"title":"universal neural representations","work_id":"1b6e601b-491d-4848-bc19-66571b8d4ad5","year":2017},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Topological Mismatch","work_id":"db774d38-5cbb-47b5-9a44-48b79b11f33f","year":2026},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Brain Invaders","work_id":"d3a785a7-7537-4c2a-88e8-cbdc13c23e5f","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Detailed network architecture specifications are provided in Table 7","work_id":"8b400035-2576-400d-afb9-5b13f7b4b4c3","year":2017},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"DSHA Structure: Dual-Stream Interaction Mechanism.Going beyond simple unidirectional multi-scale feature aggregation, DSHA adopts an explicitBidirectional Progressive Interaction Strategyto address th","work_id":"6fd005dd-5deb-47c0-98ed-10e37740c302","year":null}],"snapshot_sha256":"336422e8436e6346d39d41d6ec8048ca12d83c5624b15809939b9be8ec92074b"},"source":{"id":"2605.13133","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T19:23:44.022160Z","id":"f92dcab3-dd43-4032-b0d0-f64575659217","model_set":{"reader":"grok-4.3"},"one_line_summary":"KAST-BAR builds an EEG foundation model by dynamically modeling non-Euclidean brain topology with DSHA and aligning signals to expert semantic space via KASP and STAR, achieving superior performance on six downstream tasks after pre-training on 21 datasets.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"KAST-BAR builds an EEG foundation model that aligns brain signals with medical knowledge using dynamic topology modeling and achieves better results on six tasks.","strongest_claim":"By conducting large-scale pre-training on 21 diverse datasets to build a foundation model, KAST-BAR effectively integrates expert-level medical knowledge into EEG signal representations, consistently achieving superior performance across six downstream tasks.","weakest_assumption":"The assumption that the Dual-Stream Hierarchical Attention encoder, Knowledge-Anchored Semantic Profiler, and Semantic Text-Aware Refiner can accurately capture non-Euclidean brain topology and dynamically align low-level physiological signals with high-level textual semantics without introducing artifacts or overfitting to the pre-training data."}},"verdict_id":"f92dcab3-dd43-4032-b0d0-f64575659217"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:198e48df004638987824e6a3ff6b4bb358c22a8011bfd25fda7da3d55571e553","target":"record","created_at":"2026-05-18T03:08:57Z","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":"23de649e81e3b58d50422ac6d0b5bd962a34fa5d1bd4b91ed0c8b44de29bbc71","cross_cats_sorted":["eess.SP"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T08:02:59Z","title_canon_sha256":"9c38d663dd54ccd2664540530330aaef9feb82490e9df43da796f9658d3f55b4"},"schema_version":"1.0","source":{"id":"2605.13133","kind":"arxiv","version":1}},"canonical_sha256":"4623eb168f56c110f11725bca83a76d82e7d79db9f52cf50f87274bef4f77dc9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4623eb168f56c110f11725bca83a76d82e7d79db9f52cf50f87274bef4f77dc9","first_computed_at":"2026-05-18T03:08:57.673028Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:08:57.673028Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VuE5YG12bTPijiX4gNXbuN777MvBmSHfI/m9PKlcXYEKAAuvG3+uuzrTivFS4qc6fDus4twQZxGmIawtNU9HCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T03:08:57.673983Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.13133","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:198e48df004638987824e6a3ff6b4bb358c22a8011bfd25fda7da3d55571e553","sha256:6eefaa34003af265b857f0dac5f8e42e92ac313eb71d9bab7fbe5b24098eff92"],"state_sha256":"d5dcc0a6039521ffad5abaa7a642cf9cd8e7457b7ae12a1f8ac86b80712071c1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"teFLCdFypSQrWuHy6JmEJqlqjhQpS97NPEI5nYaTR0kEDGP1Q4Q0WXfN0HvdfXtjwNIuwHkmjGr/igLs/d0vBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T05:10:58.313445Z","bundle_sha256":"16764b39397370ad75f17b86cfad057f2ce46241368ad622798c1dc80d548835"}}