{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:T5TAHX3BRVAQGEPVQ32ZLBHQAA","short_pith_number":"pith:T5TAHX3B","canonical_record":{"source":{"id":"2502.14802","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-20T18:26:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"328069aa3c1ce500a395303508bcebfdd7e0f9d727dec094984ce4c47707d8eb","abstract_canon_sha256":"f654d7b685b2fe89159830b4af05295abf0236d8455be59c85157462e84296a5"},"schema_version":"1.0"},"canonical_sha256":"9f6603df618d410311f586f59584f000182d65814519a5232ba48889ea3049bf","source":{"kind":"arxiv","id":"2502.14802","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.14802","created_at":"2026-05-17T23:38:45Z"},{"alias_kind":"arxiv_version","alias_value":"2502.14802v2","created_at":"2026-05-17T23:38:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.14802","created_at":"2026-05-17T23:38:45Z"},{"alias_kind":"pith_short_12","alias_value":"T5TAHX3BRVAQ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"T5TAHX3BRVAQGEPV","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"T5TAHX3B","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:T5TAHX3BRVAQGEPVQ32ZLBHQAA","target":"record","payload":{"canonical_record":{"source":{"id":"2502.14802","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-20T18:26:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"328069aa3c1ce500a395303508bcebfdd7e0f9d727dec094984ce4c47707d8eb","abstract_canon_sha256":"f654d7b685b2fe89159830b4af05295abf0236d8455be59c85157462e84296a5"},"schema_version":"1.0"},"canonical_sha256":"9f6603df618d410311f586f59584f000182d65814519a5232ba48889ea3049bf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:45.966818Z","signature_b64":"fhyqW5UPODucyI4g0pq3bCvYsNb2L29ZGLLIxiDVa2EJ7fjn+dRDIa+qEj0jOZmirQGgXL8OG9OzV/ZXpdEnBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f6603df618d410311f586f59584f000182d65814519a5232ba48889ea3049bf","last_reissued_at":"2026-05-17T23:38:45.966151Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:45.966151Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.14802","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y2OflTM0u0n24/wemUCZYlh+9AJEXi7tJSHNYNxmmpHvYb6ZRqOtF3pjrTgxK+4wUjlPR/8KoT9hwhVBsbBRDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T17:26:26.521862Z"},"content_sha256":"fd79be56269fdd626bfcdb790c243c47213d6199858f1d0dc673c550bbad47bb","schema_version":"1.0","event_id":"sha256:fd79be56269fdd626bfcdb790c243c47213d6199858f1d0dc673c550bbad47bb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:T5TAHX3BRVAQGEPVQ32ZLBHQAA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"From RAG to Memory: Non-Parametric Continual Learning for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"HippoRAG 2 enhances Personalized PageRank with deeper passage integration and online LLM use to outperform standard RAG on factual, sense-making, and associative memory tasks.","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bernal Jim\\'enez Guti\\'errez, Sizhe Zhou, Weijian Qi, Yiheng Shu, Yu Su","submitted_at":"2025-02-20T18:26:02Z","abstract_excerpt":"Our ability to continuously acquire, organize, and leverage knowledge is a key feature of human intelligence that AI systems must approximate to unlock their full potential. Given the challenges in continual learning with large language models (LLMs), retrieval-augmented generation (RAG) has become the dominant way to introduce new information. However, its reliance on vector retrieval hinders its ability to mimic the dynamic and interconnected nature of human long-term memory. Recent RAG approaches augment vector embeddings with various structures like knowledge graphs to address some of thes"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"HippoRAG 2 ... achieving a 7% improvement in associative memory tasks over the state-of-the-art embedding model while also exhibiting superior factual knowledge and sense-making memory capabilities.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the specific enhancements to passage integration depth and online LLM usage in the Personalized PageRank process are what drive the reported gains and that the chosen memory-task benchmarks accurately reflect the dynamic, interconnected nature of human long-term memory.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"HippoRAG 2 improves on standard RAG and prior HippoRAG by adding deeper passage integration and more effective LLM use in Personalized PageRank, delivering superior performance on factual, sense-making, and associative memory tasks including a 7% gain in associative memory over state-of-the-art.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"HippoRAG 2 enhances Personalized PageRank with deeper passage integration and online LLM use to outperform standard RAG on factual, sense-making, and associative memory tasks.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"d52b94b5686174a7751a3dabc92a899852c9f5914f2dc35988f0da3f0170f3a4"},"source":{"id":"2502.14802","kind":"arxiv","version":2},"verdict":{"id":"41a68707-565c-42db-a3a7-6d945d3fdc3f","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-17T01:30:40.665831Z","strongest_claim":"HippoRAG 2 ... achieving a 7% improvement in associative memory tasks over the state-of-the-art embedding model while also exhibiting superior factual knowledge and sense-making memory capabilities.","one_line_summary":"HippoRAG 2 improves on standard RAG and prior HippoRAG by adding deeper passage integration and more effective LLM use in Personalized PageRank, delivering superior performance on factual, sense-making, and associative memory tasks including a 7% gain in associative memory over state-of-the-art.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the specific enhancements to passage integration depth and online LLM usage in the Personalized PageRank process are what drive the reported gains and that the chosen memory-task benchmarks accurately reflect the dynamic, interconnected nature of human long-term memory.","pith_extraction_headline":"HippoRAG 2 enhances Personalized PageRank with deeper passage integration and online LLM use to outperform standard RAG on factual, sense-making, and associative memory tasks."},"references":{"count":11,"sample":[{"doi":"","year":2024,"title":"LightRAG: Simple and Fast Retrieval-Augmented Generation","work_id":"6118de04-b8eb-4163-826a-0f91a1bcdf14","ref_index":1,"cited_arxiv_id":"2410.05779","is_internal_anchor":true},{"doi":"10.1145/511446.511513","year":2002,"title":"In: Proceedings of the 11th international conference on World Wide Web (WWW)","work_id":"abdf368e-802b-4a1b-9c71-c31818bf4ff9","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.18653/v1/2024.acl-long.77","year":2023,"title":"Mitigating catastrophic forgetting in large language models with self-synthesized rehearsal","work_id":"0a00fc04-f30a-45f4-8121-b456df382bab","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.18653/v1/2024","year":2024,"title":"Towards General Text Embeddings with Multi-stage Contrastive Learning","work_id":"861a61de-66fe-49d1-b1ab-11f8b082a4cc","ref_index":4,"cited_arxiv_id":"2308.03281","is_internal_anchor":true},{"doi":"10.18653/v1/2022.emnlp-main","year":2022,"title":"Red Teaming Language Models with Language Models.Proceedings of EMNLP 2022, pp","work_id":"3601bd7c-4994-45a6-8587-7fc9c9aa1540","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":11,"snapshot_sha256":"31aefd0bc4e5d9bb6fc4ae5921657b7c00f95b91b30e921261900cc16a8ecc67","internal_anchors":2},"formal_canon":{"evidence_count":3,"snapshot_sha256":"8db3f21166dc6d078143d3af71924013ed4e8d639d48d53c8b4790320dfeba03"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"41a68707-565c-42db-a3a7-6d945d3fdc3f"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S7RS0g3y7wo4bTaaig958W+Jvcm4ypZa/KIVJ0GsCOzkL3wTx5ZwXXazc/scXZZy+1QEWrFnqrjpKd2x7dn3DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T17:26:26.523060Z"},"content_sha256":"0e6f575138f2bfb95407fd9ee50fe76c9ab0fe1cbc8ec74b0d03bb8a536d3ebc","schema_version":"1.0","event_id":"sha256:0e6f575138f2bfb95407fd9ee50fe76c9ab0fe1cbc8ec74b0d03bb8a536d3ebc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/T5TAHX3BRVAQGEPVQ32ZLBHQAA/bundle.json","state_url":"https://pith.science/pith/T5TAHX3BRVAQGEPVQ32ZLBHQAA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/T5TAHX3BRVAQGEPVQ32ZLBHQAA/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":"2026-05-31T17:26:26Z","links":{"resolver":"https://pith.science/pith/T5TAHX3BRVAQGEPVQ32ZLBHQAA","bundle":"https://pith.science/pith/T5TAHX3BRVAQGEPVQ32ZLBHQAA/bundle.json","state":"https://pith.science/pith/T5TAHX3BRVAQGEPVQ32ZLBHQAA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/T5TAHX3BRVAQGEPVQ32ZLBHQAA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:T5TAHX3BRVAQGEPVQ32ZLBHQAA","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":"f654d7b685b2fe89159830b4af05295abf0236d8455be59c85157462e84296a5","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-20T18:26:02Z","title_canon_sha256":"328069aa3c1ce500a395303508bcebfdd7e0f9d727dec094984ce4c47707d8eb"},"schema_version":"1.0","source":{"id":"2502.14802","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.14802","created_at":"2026-05-17T23:38:45Z"},{"alias_kind":"arxiv_version","alias_value":"2502.14802v2","created_at":"2026-05-17T23:38:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.14802","created_at":"2026-05-17T23:38:45Z"},{"alias_kind":"pith_short_12","alias_value":"T5TAHX3BRVAQ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"T5TAHX3BRVAQGEPV","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"T5TAHX3B","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:0e6f575138f2bfb95407fd9ee50fe76c9ab0fe1cbc8ec74b0d03bb8a536d3ebc","target":"graph","created_at":"2026-05-17T23:38:45Z","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":"HippoRAG 2 ... achieving a 7% improvement in associative memory tasks over the state-of-the-art embedding model while also exhibiting superior factual knowledge and sense-making memory capabilities."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the specific enhancements to passage integration depth and online LLM usage in the Personalized PageRank process are what drive the reported gains and that the chosen memory-task benchmarks accurately reflect the dynamic, interconnected nature of human long-term memory."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"HippoRAG 2 improves on standard RAG and prior HippoRAG by adding deeper passage integration and more effective LLM use in Personalized PageRank, delivering superior performance on factual, sense-making, and associative memory tasks including a 7% gain in associative memory over state-of-the-art."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"HippoRAG 2 enhances Personalized PageRank with deeper passage integration and online LLM use to outperform standard RAG on factual, sense-making, and associative memory tasks."}],"snapshot_sha256":"d52b94b5686174a7751a3dabc92a899852c9f5914f2dc35988f0da3f0170f3a4"},"formal_canon":{"evidence_count":3,"snapshot_sha256":"8db3f21166dc6d078143d3af71924013ed4e8d639d48d53c8b4790320dfeba03"},"paper":{"abstract_excerpt":"Our ability to continuously acquire, organize, and leverage knowledge is a key feature of human intelligence that AI systems must approximate to unlock their full potential. Given the challenges in continual learning with large language models (LLMs), retrieval-augmented generation (RAG) has become the dominant way to introduce new information. However, its reliance on vector retrieval hinders its ability to mimic the dynamic and interconnected nature of human long-term memory. Recent RAG approaches augment vector embeddings with various structures like knowledge graphs to address some of thes","authors_text":"Bernal Jim\\'enez Guti\\'errez, Sizhe Zhou, Weijian Qi, Yiheng Shu, Yu Su","cross_cats":["cs.AI"],"headline":"HippoRAG 2 enhances Personalized PageRank with deeper passage integration and online LLM use to outperform standard RAG on factual, sense-making, and associative memory tasks.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-20T18:26:02Z","title":"From RAG to Memory: Non-Parametric Continual Learning for Large Language Models"},"references":{"count":11,"internal_anchors":2,"resolved_work":11,"sample":[{"cited_arxiv_id":"2410.05779","doi":"","is_internal_anchor":true,"ref_index":1,"title":"LightRAG: Simple and Fast Retrieval-Augmented Generation","work_id":"6118de04-b8eb-4163-826a-0f91a1bcdf14","year":2024},{"cited_arxiv_id":"","doi":"10.1145/511446.511513","is_internal_anchor":false,"ref_index":2,"title":"In: Proceedings of the 11th international conference on World Wide Web (WWW)","work_id":"abdf368e-802b-4a1b-9c71-c31818bf4ff9","year":2002},{"cited_arxiv_id":"","doi":"10.18653/v1/2024.acl-long.77","is_internal_anchor":false,"ref_index":3,"title":"Mitigating catastrophic forgetting in large language models with self-synthesized rehearsal","work_id":"0a00fc04-f30a-45f4-8121-b456df382bab","year":2023},{"cited_arxiv_id":"2308.03281","doi":"10.18653/v1/2024","is_internal_anchor":true,"ref_index":4,"title":"Towards General Text Embeddings with Multi-stage Contrastive Learning","work_id":"861a61de-66fe-49d1-b1ab-11f8b082a4cc","year":2024},{"cited_arxiv_id":"","doi":"10.18653/v1/2022.emnlp-main","is_internal_anchor":false,"ref_index":5,"title":"Red Teaming Language Models with Language Models.Proceedings of EMNLP 2022, pp","work_id":"3601bd7c-4994-45a6-8587-7fc9c9aa1540","year":2022}],"snapshot_sha256":"31aefd0bc4e5d9bb6fc4ae5921657b7c00f95b91b30e921261900cc16a8ecc67"},"source":{"id":"2502.14802","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-17T01:30:40.665831Z","id":"41a68707-565c-42db-a3a7-6d945d3fdc3f","model_set":{"reader":"grok-4.3"},"one_line_summary":"HippoRAG 2 improves on standard RAG and prior HippoRAG by adding deeper passage integration and more effective LLM use in Personalized PageRank, delivering superior performance on factual, sense-making, and associative memory tasks including a 7% gain in associative memory over state-of-the-art.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"HippoRAG 2 enhances Personalized PageRank with deeper passage integration and online LLM use to outperform standard RAG on factual, sense-making, and associative memory tasks.","strongest_claim":"HippoRAG 2 ... achieving a 7% improvement in associative memory tasks over the state-of-the-art embedding model while also exhibiting superior factual knowledge and sense-making memory capabilities.","weakest_assumption":"That the specific enhancements to passage integration depth and online LLM usage in the Personalized PageRank process are what drive the reported gains and that the chosen memory-task benchmarks accurately reflect the dynamic, interconnected nature of human long-term memory."}},"verdict_id":"41a68707-565c-42db-a3a7-6d945d3fdc3f"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:fd79be56269fdd626bfcdb790c243c47213d6199858f1d0dc673c550bbad47bb","target":"record","created_at":"2026-05-17T23:38:45Z","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":"f654d7b685b2fe89159830b4af05295abf0236d8455be59c85157462e84296a5","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-20T18:26:02Z","title_canon_sha256":"328069aa3c1ce500a395303508bcebfdd7e0f9d727dec094984ce4c47707d8eb"},"schema_version":"1.0","source":{"id":"2502.14802","kind":"arxiv","version":2}},"canonical_sha256":"9f6603df618d410311f586f59584f000182d65814519a5232ba48889ea3049bf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9f6603df618d410311f586f59584f000182d65814519a5232ba48889ea3049bf","first_computed_at":"2026-05-17T23:38:45.966151Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:45.966151Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fhyqW5UPODucyI4g0pq3bCvYsNb2L29ZGLLIxiDVa2EJ7fjn+dRDIa+qEj0jOZmirQGgXL8OG9OzV/ZXpdEnBQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:45.966818Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.14802","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fd79be56269fdd626bfcdb790c243c47213d6199858f1d0dc673c550bbad47bb","sha256:0e6f575138f2bfb95407fd9ee50fe76c9ab0fe1cbc8ec74b0d03bb8a536d3ebc"],"state_sha256":"2758bc1d2ef58a0d5ce17fb1f9e0320b3b40e7c9641025dcd1e086a1ff9388b7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vYP7N7LQtw3JTsKcUSSOYk2a6UEdffropADol5U1KL2xqXBFcX2gxI0TV0BEmPM9dZlAcu5iab687w3rj/g0Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T17:26:26.528074Z","bundle_sha256":"43b4ce60f1e63d914aefc8ddd0f157594c42243c4f67b3aa52c52f5114365674"}}