{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:YQRW5RPBUVOSA5XPEWRUZNEJQF","short_pith_number":"pith:YQRW5RPB","canonical_record":{"source":{"id":"2605.13496","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DC","submitted_at":"2026-05-13T13:20:02Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7b948215a9cacc432ed7028ed0cc036a64f19dfc66239cd8c4a12ab5b580b0f8","abstract_canon_sha256":"c9e4b4e3c75af6f561928af8cadae91f0b3ae0adb12844f51d8e96816581d0a6"},"schema_version":"1.0"},"canonical_sha256":"c4236ec5e1a55d2076ef25a34cb489815d5fa097985dd940b98164510df697ed","source":{"kind":"arxiv","id":"2605.13496","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13496","created_at":"2026-05-18T02:44:41Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13496v1","created_at":"2026-05-18T02:44:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13496","created_at":"2026-05-18T02:44:41Z"},{"alias_kind":"pith_short_12","alias_value":"YQRW5RPBUVOS","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"YQRW5RPBUVOSA5XP","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"YQRW5RPB","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:YQRW5RPBUVOSA5XPEWRUZNEJQF","target":"record","payload":{"canonical_record":{"source":{"id":"2605.13496","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DC","submitted_at":"2026-05-13T13:20:02Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7b948215a9cacc432ed7028ed0cc036a64f19dfc66239cd8c4a12ab5b580b0f8","abstract_canon_sha256":"c9e4b4e3c75af6f561928af8cadae91f0b3ae0adb12844f51d8e96816581d0a6"},"schema_version":"1.0"},"canonical_sha256":"c4236ec5e1a55d2076ef25a34cb489815d5fa097985dd940b98164510df697ed","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:44:41.087332Z","signature_b64":"rvJ2BPys7AK1iJLCHXsiF3yxox6aIpU2aVnWL2lM6QxbSTv1GYyIGgnzjtKQXNYziL0mNpH3lGZME60YIR5uDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c4236ec5e1a55d2076ef25a34cb489815d5fa097985dd940b98164510df697ed","last_reissued_at":"2026-05-18T02:44:41.086776Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:44:41.086776Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.13496","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":"2026-05-18T02:44:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nmR2kQYh+2GNPXkvEYI0Bl8VLkjWKWAhX8B5ihWwvssckYA49cagDSK98+8IbDbzUm25pJfef9OAGhzcwWaRDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T02:20:11.640357Z"},"content_sha256":"41d857107dbd6db34196efa882bc8161b8c3e2d018d25a79ebe10e12e2d4e016","schema_version":"1.0","event_id":"sha256:41d857107dbd6db34196efa882bc8161b8c3e2d018d25a79ebe10e12e2d4e016"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:YQRW5RPBUVOSA5XPEWRUZNEJQF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MARLIN: Multi-Agent Game-Theoretic Reinforcement Learning for Sustainable LLM Inference in Cloud Datacenters","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"MARLIN uses multi-agent game-theoretic reinforcement learning to cut TTFT by 18 percent, carbon emissions by 33 percent, water usage by 43 percent, and energy costs by 11 percent for LLM inference in cloud datacenters.","cross_cats":["cs.LG"],"primary_cat":"cs.DC","authors_text":"C. Bash, D. Milojicic, H. Moore, S. Pasricha, S. Qi","submitted_at":"2026-05-13T13:20:02Z","abstract_excerpt":"Large Language Models (LLMs) have become increasingly prevalent in cloud-based platforms, propelled by the introduction of AI-based consumer and enterprise services. LLM inference requests in particular account for up to 90% of total LLM lifecycle energy use, dwarfing training energy costs. The rising volume of LLM inference requests is increasing environmental footprints, particularly carbon emissions and water consumption. To improve sustainability for LLM inference serving in cloud datacenter environments, we propose a novel multi-agent game-theoretic reinforcement learning framework called"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"MARLIN demonstrates a reduction of at least 18% in TTFT, 33% in carbon emissions, 43% in water usage, and 11% in energy costs compared to state-of-the-art LLM inference management frameworks.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the simulation environment and workload traces used to train and evaluate the multi-agent system accurately capture the dynamics, constraints, and measurement noise of real cloud datacenters running production LLM inference.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"MARLIN applies multi-agent game-theoretic RL to cut TTFT by at least 18%, carbon emissions by 33%, water usage by 43%, and energy costs by 11% versus prior LLM inference managers.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"MARLIN uses multi-agent game-theoretic reinforcement learning to cut TTFT by 18 percent, carbon emissions by 33 percent, water usage by 43 percent, and energy costs by 11 percent for LLM inference in cloud datacenters.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"b9a180a1d9c6426b210c632b22daa954173f8fe4152aa1ca90ca832016676c63"},"source":{"id":"2605.13496","kind":"arxiv","version":1},"verdict":{"id":"8b06afb9-4a5b-4569-a6a8-cdffcfb98ad0","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T18:07:40.795856Z","strongest_claim":"MARLIN demonstrates a reduction of at least 18% in TTFT, 33% in carbon emissions, 43% in water usage, and 11% in energy costs compared to state-of-the-art LLM inference management frameworks.","one_line_summary":"MARLIN applies multi-agent game-theoretic RL to cut TTFT by at least 18%, carbon emissions by 33%, water usage by 43%, and energy costs by 11% versus prior LLM inference managers.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the simulation environment and workload traces used to train and evaluate the multi-agent system accurately capture the dynamics, constraints, and measurement noise of real cloud datacenters running production LLM inference.","pith_extraction_headline":"MARLIN uses multi-agent game-theoretic reinforcement learning to cut TTFT by 18 percent, carbon emissions by 33 percent, water usage by 43 percent, and energy costs by 11 percent for LLM inference in cloud datacenters."},"references":{"count":36,"sample":[{"doi":"","year":2026,"title":"Llm statistics 2026: Comprehensive insights into market trends and integration,","work_id":"72ec7e8c-cd8e-4ea4-87b0-428cb469ee8b","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2026,"title":"Chatgpt users statistics (2026) – active users & global growth data,","work_id":"d52513df-19b1-4f3f-ba51-29bc2376770d","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2026,"title":"Accessed on Mar.31.2026","work_id":"74a14a5b-15b9-42e7-92d0-4731ce460f05","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"The unseen ai disruptions for power grids: Llm-induced transients,","work_id":"cdcec9e3-3b99-4185-a43e-584bb8082804","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2026,"title":"What we know about energy use at u.s. data centers amid the ai boom,","work_id":"f838f492-c88b-4d49-b27d-83f6ca9f3a7d","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":36,"snapshot_sha256":"29c4a537e4e3e3f23cd5dd783a1bcc265b52a4bfe645d426b0ef3733c2804486","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":"8b06afb9-4a5b-4569-a6a8-cdffcfb98ad0"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:44:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JRhRvTvOsEb7qUAJJcx6wrGhz9L2VVS7eYsJaemKLDvmBUBqWJbXPtwELXlkJAZk3UrvZFlviQ/1yZOML6WrCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T02:20:11.641518Z"},"content_sha256":"75923be9c7adfef8e1b1f9ac4f8d701c36f0c47813a7ec6b8db93af9129bb27b","schema_version":"1.0","event_id":"sha256:75923be9c7adfef8e1b1f9ac4f8d701c36f0c47813a7ec6b8db93af9129bb27b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YQRW5RPBUVOSA5XPEWRUZNEJQF/bundle.json","state_url":"https://pith.science/pith/YQRW5RPBUVOSA5XPEWRUZNEJQF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YQRW5RPBUVOSA5XPEWRUZNEJQF/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":"2026-06-09T02:20:11Z","links":{"resolver":"https://pith.science/pith/YQRW5RPBUVOSA5XPEWRUZNEJQF","bundle":"https://pith.science/pith/YQRW5RPBUVOSA5XPEWRUZNEJQF/bundle.json","state":"https://pith.science/pith/YQRW5RPBUVOSA5XPEWRUZNEJQF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YQRW5RPBUVOSA5XPEWRUZNEJQF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:YQRW5RPBUVOSA5XPEWRUZNEJQF","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":"c9e4b4e3c75af6f561928af8cadae91f0b3ae0adb12844f51d8e96816581d0a6","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DC","submitted_at":"2026-05-13T13:20:02Z","title_canon_sha256":"7b948215a9cacc432ed7028ed0cc036a64f19dfc66239cd8c4a12ab5b580b0f8"},"schema_version":"1.0","source":{"id":"2605.13496","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13496","created_at":"2026-05-18T02:44:41Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13496v1","created_at":"2026-05-18T02:44:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13496","created_at":"2026-05-18T02:44:41Z"},{"alias_kind":"pith_short_12","alias_value":"YQRW5RPBUVOS","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"YQRW5RPBUVOSA5XP","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"YQRW5RPB","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:75923be9c7adfef8e1b1f9ac4f8d701c36f0c47813a7ec6b8db93af9129bb27b","target":"graph","created_at":"2026-05-18T02:44:41Z","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":"MARLIN demonstrates a reduction of at least 18% in TTFT, 33% in carbon emissions, 43% in water usage, and 11% in energy costs compared to state-of-the-art LLM inference management frameworks."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the simulation environment and workload traces used to train and evaluate the multi-agent system accurately capture the dynamics, constraints, and measurement noise of real cloud datacenters running production LLM inference."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"MARLIN applies multi-agent game-theoretic RL to cut TTFT by at least 18%, carbon emissions by 33%, water usage by 43%, and energy costs by 11% versus prior LLM inference managers."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"MARLIN uses multi-agent game-theoretic reinforcement learning to cut TTFT by 18 percent, carbon emissions by 33 percent, water usage by 43 percent, and energy costs by 11 percent for LLM inference in cloud datacenters."}],"snapshot_sha256":"b9a180a1d9c6426b210c632b22daa954173f8fe4152aa1ca90ca832016676c63"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have become increasingly prevalent in cloud-based platforms, propelled by the introduction of AI-based consumer and enterprise services. LLM inference requests in particular account for up to 90% of total LLM lifecycle energy use, dwarfing training energy costs. The rising volume of LLM inference requests is increasing environmental footprints, particularly carbon emissions and water consumption. To improve sustainability for LLM inference serving in cloud datacenter environments, we propose a novel multi-agent game-theoretic reinforcement learning framework called","authors_text":"C. Bash, D. Milojicic, H. Moore, S. Pasricha, S. Qi","cross_cats":["cs.LG"],"headline":"MARLIN uses multi-agent game-theoretic reinforcement learning to cut TTFT by 18 percent, carbon emissions by 33 percent, water usage by 43 percent, and energy costs by 11 percent for LLM inference in cloud datacenters.","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DC","submitted_at":"2026-05-13T13:20:02Z","title":"MARLIN: Multi-Agent Game-Theoretic Reinforcement Learning for Sustainable LLM Inference in Cloud Datacenters"},"references":{"count":36,"internal_anchors":0,"resolved_work":36,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Llm statistics 2026: Comprehensive insights into market trends and integration,","work_id":"72ec7e8c-cd8e-4ea4-87b0-428cb469ee8b","year":2026},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Chatgpt users statistics (2026) – active users & global growth data,","work_id":"d52513df-19b1-4f3f-ba51-29bc2376770d","year":2026},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Accessed on Mar.31.2026","work_id":"74a14a5b-15b9-42e7-92d0-4731ce460f05","year":2026},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"The unseen ai disruptions for power grids: Llm-induced transients,","work_id":"cdcec9e3-3b99-4185-a43e-584bb8082804","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"What we know about energy use at u.s. data centers amid the ai boom,","work_id":"f838f492-c88b-4d49-b27d-83f6ca9f3a7d","year":2026}],"snapshot_sha256":"29c4a537e4e3e3f23cd5dd783a1bcc265b52a4bfe645d426b0ef3733c2804486"},"source":{"id":"2605.13496","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T18:07:40.795856Z","id":"8b06afb9-4a5b-4569-a6a8-cdffcfb98ad0","model_set":{"reader":"grok-4.3"},"one_line_summary":"MARLIN applies multi-agent game-theoretic RL to cut TTFT by at least 18%, carbon emissions by 33%, water usage by 43%, and energy costs by 11% versus prior LLM inference managers.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"MARLIN uses multi-agent game-theoretic reinforcement learning to cut TTFT by 18 percent, carbon emissions by 33 percent, water usage by 43 percent, and energy costs by 11 percent for LLM inference in cloud datacenters.","strongest_claim":"MARLIN demonstrates a reduction of at least 18% in TTFT, 33% in carbon emissions, 43% in water usage, and 11% in energy costs compared to state-of-the-art LLM inference management frameworks.","weakest_assumption":"That the simulation environment and workload traces used to train and evaluate the multi-agent system accurately capture the dynamics, constraints, and measurement noise of real cloud datacenters running production LLM inference."}},"verdict_id":"8b06afb9-4a5b-4569-a6a8-cdffcfb98ad0"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:41d857107dbd6db34196efa882bc8161b8c3e2d018d25a79ebe10e12e2d4e016","target":"record","created_at":"2026-05-18T02:44:41Z","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":"c9e4b4e3c75af6f561928af8cadae91f0b3ae0adb12844f51d8e96816581d0a6","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DC","submitted_at":"2026-05-13T13:20:02Z","title_canon_sha256":"7b948215a9cacc432ed7028ed0cc036a64f19dfc66239cd8c4a12ab5b580b0f8"},"schema_version":"1.0","source":{"id":"2605.13496","kind":"arxiv","version":1}},"canonical_sha256":"c4236ec5e1a55d2076ef25a34cb489815d5fa097985dd940b98164510df697ed","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c4236ec5e1a55d2076ef25a34cb489815d5fa097985dd940b98164510df697ed","first_computed_at":"2026-05-18T02:44:41.086776Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:44:41.086776Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rvJ2BPys7AK1iJLCHXsiF3yxox6aIpU2aVnWL2lM6QxbSTv1GYyIGgnzjtKQXNYziL0mNpH3lGZME60YIR5uDA==","signature_status":"signed_v1","signed_at":"2026-05-18T02:44:41.087332Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.13496","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:41d857107dbd6db34196efa882bc8161b8c3e2d018d25a79ebe10e12e2d4e016","sha256:75923be9c7adfef8e1b1f9ac4f8d701c36f0c47813a7ec6b8db93af9129bb27b"],"state_sha256":"61b283739a590460ddee14a9b68b80c9861e4fdf2b4090e86fd2d16e769d5700"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SuL7Y7l0iZ/RsJ4FZXTr0gMPSxBEKd1cyf6JvKP9oXsUjXyWJZYT9GhKAsKsO8DguS1lhAousjSt2dNNCT0cCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T02:20:11.647365Z","bundle_sha256":"85ab8e20600561896e34b70350c262d3477f5c430f8c62e7841dbf0b468bab4e"}}