{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:H22O2LDL42NJGVILKAUNKA7WAK","short_pith_number":"pith:H22O2LDL","canonical_record":{"source":{"id":"2605.13391","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-13T11:49:18Z","cross_cats_sorted":[],"title_canon_sha256":"6e92538b8c53720e3e36a92751f4f7fb77171578d6a2db9c84edf54245990596","abstract_canon_sha256":"f238e2396f82ace79c7f1e43ae5b40508e44e1aa3db2cb9962ba3714af1d5f9e"},"schema_version":"1.0"},"canonical_sha256":"3eb4ed2c6be69a93550b5028d503f60298c472f6b3209e101c9c77540b8f63ee","source":{"kind":"arxiv","id":"2605.13391","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13391","created_at":"2026-05-18T02:44:47Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13391v1","created_at":"2026-05-18T02:44:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13391","created_at":"2026-05-18T02:44:47Z"},{"alias_kind":"pith_short_12","alias_value":"H22O2LDL42NJ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"H22O2LDL42NJGVIL","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"H22O2LDL","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:H22O2LDL42NJGVILKAUNKA7WAK","target":"record","payload":{"canonical_record":{"source":{"id":"2605.13391","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-13T11:49:18Z","cross_cats_sorted":[],"title_canon_sha256":"6e92538b8c53720e3e36a92751f4f7fb77171578d6a2db9c84edf54245990596","abstract_canon_sha256":"f238e2396f82ace79c7f1e43ae5b40508e44e1aa3db2cb9962ba3714af1d5f9e"},"schema_version":"1.0"},"canonical_sha256":"3eb4ed2c6be69a93550b5028d503f60298c472f6b3209e101c9c77540b8f63ee","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:44:47.713374Z","signature_b64":"7e3gSv1SoGGVm1S9HmD8+iLhnIPR27Sh99Zf0zHYOA9XkXIRF4HzKkC//+tABoTRJvMfBsNnWIxinu17cIDsCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3eb4ed2c6be69a93550b5028d503f60298c472f6b3209e101c9c77540b8f63ee","last_reissued_at":"2026-05-18T02:44:47.712860Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:44:47.712860Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.13391","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":"2026-05-18T02:44:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lldYlQBkniVVNL2MZXymV0bFmwD326eNorLAfHlVhNCI6gQRG4J/g0QzkPBq5Zx3k5g8XSYRJkvKyMg8tJvqCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T06:26:22.422906Z"},"content_sha256":"b957ee4fa04f6419b4c13a78360ed884bb6c5577d59d22b47f7165ee6eb7ad78","schema_version":"1.0","event_id":"sha256:b957ee4fa04f6419b4c13a78360ed884bb6c5577d59d22b47f7165ee6eb7ad78"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:H22O2LDL42NJGVILKAUNKA7WAK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RS-Claw: Progressive Active Tool Exploration via Hierarchical Skill Trees for Remote Sensing Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"RS-Claw lets remote sensing agents actively explore tools via hierarchical skill trees, achieving up to 86% token compression while outperforming flat and RAG baselines.","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chengfu Liu, Cheng Yang, Dongyang Hou, Haifeng Li, Hanwen Yu, Kai Ouyang, Liangtian Liu, Wentao Yang, Zeyuan Wang, Zichao Tang, Ziyu Li","submitted_at":"2026-05-13T11:49:18Z","abstract_excerpt":"The rise of multi-modal large language models (MLLMs) is shifting remote sensing (RS) intelligence from \"see\" to \"action\", as OpenClaw-style frameworks enable agents to autonomously operate massive RS image-processing tools for complex tasks. Existing RS agents adopt a passive selection paradigm for tool invocation, relying on either full tool registration (Flat) or retrieval-augmented generation (RAG). However, in the massive and multi-source heterogeneous RS tool ecosystem, such passive mechanisms struggle to dynamically balance \"context load\" and \"toolset completeness\" throughout task reaso"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"RS-Claw's active exploration mechanism effectively filters semantic noise and substantially frees up reasoning space, achieving an input token compression ratio of up to 86%, and comprehensively outperforming existing Flat and RAG baselines across complex reasoning evaluations on the Earth-Bench benchmark.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That hierarchically structuring tool descriptions via skill encapsulation allows the agent to perform on-demand sequential decision-making that accurately hits critical tools without omissions during long-horizon reasoning in the massive heterogeneous RS tool ecosystem.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"RS-Claw enables remote sensing agents to actively explore tools via hierarchical skill trees, achieving up to 86% token compression and outperforming flat registration and RAG baselines on Earth-Bench.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"RS-Claw lets remote sensing agents actively explore tools via hierarchical skill trees, achieving up to 86% token compression while outperforming flat and RAG baselines.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"2989d5ee3df2351c8211ebcc349e83c20e91daf1f9ef566661fb6c04a725a8a1"},"source":{"id":"2605.13391","kind":"arxiv","version":1},"verdict":{"id":"07611a89-d405-41c8-a250-fd1ebabb06d6","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T19:29:20.903863Z","strongest_claim":"RS-Claw's active exploration mechanism effectively filters semantic noise and substantially frees up reasoning space, achieving an input token compression ratio of up to 86%, and comprehensively outperforming existing Flat and RAG baselines across complex reasoning evaluations on the Earth-Bench benchmark.","one_line_summary":"RS-Claw enables remote sensing agents to actively explore tools via hierarchical skill trees, achieving up to 86% token compression and outperforming flat registration and RAG baselines on Earth-Bench.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That hierarchically structuring tool descriptions via skill encapsulation allows the agent to perform on-demand sequential decision-making that accurately hits critical tools without omissions during long-horizon reasoning in the massive heterogeneous RS tool ecosystem.","pith_extraction_headline":"RS-Claw lets remote sensing agents actively explore tools via hierarchical skill trees, achieving up to 86% token compression while outperforming flat and RAG baselines."},"references":{"count":45,"sample":[{"doi":"","year":2023,"title":"Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models","work_id":"077c8bd4-de74-49bd-be87-4cb72bac1b73","ref_index":1,"cited_arxiv_id":"2305.04091","is_internal_anchor":true},{"doi":"","year":2023,"title":"Toolformer: Language models can teach themselves to use tools,","work_id":"ded388d7-62d9-4a3e-8260-791dcd633fda","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"HuggingGPT: Solving AI tasks with ChatGPT and its friends in Hugging Face,","work_id":"279c79ad-d324-493d-b3cf-5b712e012f7e","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"A survey on large language model based autonomous agents","work_id":"4aa1f101-d987-4096-969f-b7c6e616bc59","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2026,"title":"OpenClaw: Open-source personal AI assistant,","work_id":"ebda7aaa-80aa-4ee2-9315-e625f5352316","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":45,"snapshot_sha256":"dca06e5e1c698796e8eeb2ec46265e989c25c579501d82c37d095cb1d90ca3a5","internal_anchors":5},"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":"07611a89-d405-41c8-a250-fd1ebabb06d6"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:44:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w8sBJtBUtEMqNOi+Z1SC/GW+cJLqu1eqo+KdHCJi827R9CCXHgO0UmJda0l5LAkn0ESK20zDDCOvSz96PrvPDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T06:26:22.423890Z"},"content_sha256":"1c0938f793580a1c8618b414f629e19d9b32eee3b8d7ecff14d48c7cb00df515","schema_version":"1.0","event_id":"sha256:1c0938f793580a1c8618b414f629e19d9b32eee3b8d7ecff14d48c7cb00df515"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/H22O2LDL42NJGVILKAUNKA7WAK/bundle.json","state_url":"https://pith.science/pith/H22O2LDL42NJGVILKAUNKA7WAK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/H22O2LDL42NJGVILKAUNKA7WAK/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":"2026-05-27T06:26:22Z","links":{"resolver":"https://pith.science/pith/H22O2LDL42NJGVILKAUNKA7WAK","bundle":"https://pith.science/pith/H22O2LDL42NJGVILKAUNKA7WAK/bundle.json","state":"https://pith.science/pith/H22O2LDL42NJGVILKAUNKA7WAK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/H22O2LDL42NJGVILKAUNKA7WAK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:H22O2LDL42NJGVILKAUNKA7WAK","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":"f238e2396f82ace79c7f1e43ae5b40508e44e1aa3db2cb9962ba3714af1d5f9e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-13T11:49:18Z","title_canon_sha256":"6e92538b8c53720e3e36a92751f4f7fb77171578d6a2db9c84edf54245990596"},"schema_version":"1.0","source":{"id":"2605.13391","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13391","created_at":"2026-05-18T02:44:47Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13391v1","created_at":"2026-05-18T02:44:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13391","created_at":"2026-05-18T02:44:47Z"},{"alias_kind":"pith_short_12","alias_value":"H22O2LDL42NJ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"H22O2LDL42NJGVIL","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"H22O2LDL","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:1c0938f793580a1c8618b414f629e19d9b32eee3b8d7ecff14d48c7cb00df515","target":"graph","created_at":"2026-05-18T02:44:47Z","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":"RS-Claw's active exploration mechanism effectively filters semantic noise and substantially frees up reasoning space, achieving an input token compression ratio of up to 86%, and comprehensively outperforming existing Flat and RAG baselines across complex reasoning evaluations on the Earth-Bench benchmark."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That hierarchically structuring tool descriptions via skill encapsulation allows the agent to perform on-demand sequential decision-making that accurately hits critical tools without omissions during long-horizon reasoning in the massive heterogeneous RS tool ecosystem."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"RS-Claw enables remote sensing agents to actively explore tools via hierarchical skill trees, achieving up to 86% token compression and outperforming flat registration and RAG baselines on Earth-Bench."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"RS-Claw lets remote sensing agents actively explore tools via hierarchical skill trees, achieving up to 86% token compression while outperforming flat and RAG baselines."}],"snapshot_sha256":"2989d5ee3df2351c8211ebcc349e83c20e91daf1f9ef566661fb6c04a725a8a1"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"The rise of multi-modal large language models (MLLMs) is shifting remote sensing (RS) intelligence from \"see\" to \"action\", as OpenClaw-style frameworks enable agents to autonomously operate massive RS image-processing tools for complex tasks. Existing RS agents adopt a passive selection paradigm for tool invocation, relying on either full tool registration (Flat) or retrieval-augmented generation (RAG). However, in the massive and multi-source heterogeneous RS tool ecosystem, such passive mechanisms struggle to dynamically balance \"context load\" and \"toolset completeness\" throughout task reaso","authors_text":"Chengfu Liu, Cheng Yang, Dongyang Hou, Haifeng Li, Hanwen Yu, Kai Ouyang, Liangtian Liu, Wentao Yang, Zeyuan Wang, Zichao Tang, Ziyu Li","cross_cats":[],"headline":"RS-Claw lets remote sensing agents actively explore tools via hierarchical skill trees, achieving up to 86% token compression while outperforming flat and RAG baselines.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-13T11:49:18Z","title":"RS-Claw: Progressive Active Tool Exploration via Hierarchical Skill Trees for Remote Sensing Agents"},"references":{"count":45,"internal_anchors":5,"resolved_work":45,"sample":[{"cited_arxiv_id":"2305.04091","doi":"","is_internal_anchor":true,"ref_index":1,"title":"Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models","work_id":"077c8bd4-de74-49bd-be87-4cb72bac1b73","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Toolformer: Language models can teach themselves to use tools,","work_id":"ded388d7-62d9-4a3e-8260-791dcd633fda","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"HuggingGPT: Solving AI tasks with ChatGPT and its friends in Hugging Face,","work_id":"279c79ad-d324-493d-b3cf-5b712e012f7e","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"A survey on large language model based autonomous agents","work_id":"4aa1f101-d987-4096-969f-b7c6e616bc59","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"OpenClaw: Open-source personal AI assistant,","work_id":"ebda7aaa-80aa-4ee2-9315-e625f5352316","year":2026}],"snapshot_sha256":"dca06e5e1c698796e8eeb2ec46265e989c25c579501d82c37d095cb1d90ca3a5"},"source":{"id":"2605.13391","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T19:29:20.903863Z","id":"07611a89-d405-41c8-a250-fd1ebabb06d6","model_set":{"reader":"grok-4.3"},"one_line_summary":"RS-Claw enables remote sensing agents to actively explore tools via hierarchical skill trees, achieving up to 86% token compression and outperforming flat registration and RAG baselines on Earth-Bench.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"RS-Claw lets remote sensing agents actively explore tools via hierarchical skill trees, achieving up to 86% token compression while outperforming flat and RAG baselines.","strongest_claim":"RS-Claw's active exploration mechanism effectively filters semantic noise and substantially frees up reasoning space, achieving an input token compression ratio of up to 86%, and comprehensively outperforming existing Flat and RAG baselines across complex reasoning evaluations on the Earth-Bench benchmark.","weakest_assumption":"That hierarchically structuring tool descriptions via skill encapsulation allows the agent to perform on-demand sequential decision-making that accurately hits critical tools without omissions during long-horizon reasoning in the massive heterogeneous RS tool ecosystem."}},"verdict_id":"07611a89-d405-41c8-a250-fd1ebabb06d6"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b957ee4fa04f6419b4c13a78360ed884bb6c5577d59d22b47f7165ee6eb7ad78","target":"record","created_at":"2026-05-18T02:44:47Z","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":"f238e2396f82ace79c7f1e43ae5b40508e44e1aa3db2cb9962ba3714af1d5f9e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-13T11:49:18Z","title_canon_sha256":"6e92538b8c53720e3e36a92751f4f7fb77171578d6a2db9c84edf54245990596"},"schema_version":"1.0","source":{"id":"2605.13391","kind":"arxiv","version":1}},"canonical_sha256":"3eb4ed2c6be69a93550b5028d503f60298c472f6b3209e101c9c77540b8f63ee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3eb4ed2c6be69a93550b5028d503f60298c472f6b3209e101c9c77540b8f63ee","first_computed_at":"2026-05-18T02:44:47.712860Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:44:47.712860Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7e3gSv1SoGGVm1S9HmD8+iLhnIPR27Sh99Zf0zHYOA9XkXIRF4HzKkC//+tABoTRJvMfBsNnWIxinu17cIDsCw==","signature_status":"signed_v1","signed_at":"2026-05-18T02:44:47.713374Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.13391","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b957ee4fa04f6419b4c13a78360ed884bb6c5577d59d22b47f7165ee6eb7ad78","sha256:1c0938f793580a1c8618b414f629e19d9b32eee3b8d7ecff14d48c7cb00df515"],"state_sha256":"3ea8ad5a58e79ec5224a7b7c20891806f7107d50c7ac009de291aa81958ac66a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3BGJvyBa6Ck+8gIJ4iqlj3+UUr+so14KwR3stxNVHhIzCxSidX3ezeKUaF1fLLSkleWcsnfrY/qQzYcurRgeBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T06:26:22.428180Z","bundle_sha256":"7e4ccbd3309907af2568af4b3503d77864ceb981729a67947eeef82ae38188f0"}}