{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:3SDAE7UE2JHZ52A6DEDV6YA4O7","short_pith_number":"pith:3SDAE7UE","canonical_record":{"source":{"id":"2404.16130","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-24T18:38:11Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"b15117b27878331b6154a069ca0be97c7b337108a25e1180d57e849c505eccbd","abstract_canon_sha256":"b6d85dc86fd8bdc0435228e5fafdd41bfedcd4ba08156d23b30ed0e5e1c92e9d"},"schema_version":"1.0"},"canonical_sha256":"dc86027e84d24f9ee81e19075f601c77f8b6cf1b01676ea05043dce368a06f4d","source":{"kind":"arxiv","id":"2404.16130","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.16130","created_at":"2026-07-05T10:16:33Z"},{"alias_kind":"arxiv_version","alias_value":"2404.16130v2","created_at":"2026-07-05T10:16:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.16130","created_at":"2026-07-05T10:16:33Z"},{"alias_kind":"pith_short_12","alias_value":"3SDAE7UE2JHZ","created_at":"2026-07-05T10:16:33Z"},{"alias_kind":"pith_short_16","alias_value":"3SDAE7UE2JHZ52A6","created_at":"2026-07-05T10:16:33Z"},{"alias_kind":"pith_short_8","alias_value":"3SDAE7UE","created_at":"2026-07-05T10:16:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:3SDAE7UE2JHZ52A6DEDV6YA4O7","target":"record","payload":{"canonical_record":{"source":{"id":"2404.16130","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-24T18:38:11Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"b15117b27878331b6154a069ca0be97c7b337108a25e1180d57e849c505eccbd","abstract_canon_sha256":"b6d85dc86fd8bdc0435228e5fafdd41bfedcd4ba08156d23b30ed0e5e1c92e9d"},"schema_version":"1.0"},"canonical_sha256":"dc86027e84d24f9ee81e19075f601c77f8b6cf1b01676ea05043dce368a06f4d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:16:33.443334Z","signature_b64":"4+wxWZBX34kWhMOKBGVa/aJN+fXQeLdgN0i1iCEzs9hkUvxPZHCxlfxTcHM+tyzJhPCbge2Fb6FBsSLBqKgAAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc86027e84d24f9ee81e19075f601c77f8b6cf1b01676ea05043dce368a06f4d","last_reissued_at":"2026-07-05T10:16:33.442784Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:16:33.442784Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.16130","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":"2026-07-05T10:16:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2lJwJgO5HEGd/esToWPBB67WR1rqbRyn7SOE4AbEbMMYAQmHHi2efJJ91EbNrMGrzRLQzvajAnhFpwGjsGbsAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T06:15:47.714064Z"},"content_sha256":"aba6c46ea9aa05db9877a7be2ea4fda0d822dc9af750e46f13f420df5e8f3a6b","schema_version":"1.0","event_id":"sha256:aba6c46ea9aa05db9877a7be2ea4fda0d822dc9af750e46f13f420df5e8f3a6b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:3SDAE7UE2JHZ52A6DEDV6YA4O7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"From Local to Global: A Graph RAG Approach to Query-Focused Summarization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"GraphRAG builds entity knowledge graphs and community summaries to answer global questions over large private text collections more comprehensively than standard RAG.","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Alex Chao, Apurva Mody, Darren Edge, Dasha Metropolitansky, Ha Trinh, Jonathan Larson, Joshua Bradley, Newman Cheng, Robert Osazuwa Ness, Steven Truitt","submitted_at":"2024-04-24T18:38:11Z","abstract_excerpt":"The use of retrieval-augmented generation (RAG) to retrieve relevant information from an external knowledge source enables large language models (LLMs) to answer questions over private and/or previously unseen document collections. However, RAG fails on global questions directed at an entire text corpus, such as \"What are the main themes in the dataset?\", since this is inherently a query-focused summarization (QFS) task, rather than an explicit retrieval task. Prior QFS methods, meanwhile, do not scale to the quantities of text indexed by typical RAG systems. To combine the strengths of these "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"For a class of global sensemaking questions over datasets in the 1 million token range, we show that GraphRAG leads to substantial improvements over a conventional RAG baseline for both the comprehensiveness and diversity of generated answers.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That LLM-generated entity graphs and community summaries accurately and comprehensively capture the source material without introducing errors, omissions, or biases that would undermine the final combined responses for global questions.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"GraphRAG improves comprehensiveness and diversity of answers to global questions over million-token document sets by constructing entity graphs and hierarchical community summaries before combining partial responses.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"GraphRAG builds entity knowledge graphs and community summaries to answer global questions over large private text collections more comprehensively than standard RAG.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"b0646a2c0dbdaac7a3e293d67cd7f5ae4688f9c10a2efb21a90f4355683eea4c"},"source":{"id":"2404.16130","kind":"arxiv","version":2},"verdict":{"id":"ea83d1d8-208d-4c2d-9679-f2d4762583a6","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-11T05:07:17.015621Z","strongest_claim":"For a class of global sensemaking questions over datasets in the 1 million token range, we show that GraphRAG leads to substantial improvements over a conventional RAG baseline for both the comprehensiveness and diversity of generated answers.","one_line_summary":"GraphRAG improves comprehensiveness and diversity of answers to global questions over million-token document sets by constructing entity graphs and hierarchical community summaries before combining partial responses.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That LLM-generated entity graphs and community summaries accurately and comprehensively capture the source material without introducing errors, omissions, or biases that would undermine the final combined responses for global questions.","pith_extraction_headline":"GraphRAG builds entity knowledge graphs and community summaries to answer global questions over large private text collections more comprehensively than standard RAG."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2404.16130/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":79,"sample":[{"doi":"","year":2023,"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","ref_index":1,"cited_arxiv_id":"2303.08774","is_internal_anchor":true},{"doi":"","year":2023,"title":"Gemini: A Family of Highly Capable Multimodal Models","work_id":"83f7c85b-3f11-450f-ac0c-64d9745220b2","ref_index":2,"cited_arxiv_id":"2312.11805","is_internal_anchor":true},{"doi":"","year":2023,"title":"Knowledge-augmented language model prompting for zero-shot knowledge graph question answering","work_id":"2c7df13c-fbfe-4b89-b7c7-a1e8b2abdbe4","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Ban, T., Chen, L., Wang, X., and Chen, H. (2023). From query tools to causal architects: Harnessing large language models for advanced causal discovery from data","work_id":"34c5bdba-6b27-45dd-ba89-4640f59851ad","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"Barlaug, N. and Gulla, J. A. (2021). Neural networks for entity matching: A survey. ACM Transactions on Knowledge Discovery from Data (TKDD) , 15(3):1--37","work_id":"54da3606-6b77-4ebe-9090-48dd9e85a6d5","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":79,"snapshot_sha256":"783a345e9ad3fd8a32be203e5a9798f46a07c638df6cefb476a8750f4a46725b","internal_anchors":13},"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":"ea83d1d8-208d-4c2d-9679-f2d4762583a6"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:16:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WBCVhiCdZQPRJ35/XNHimF5BKX16KXlq7OQvZCnvOb8FPseP3Pxts27b9g83hcSH2hOtDjYQUdDm7gW0I7X8Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T06:15:47.715075Z"},"content_sha256":"8d333c18bc7eb296e0cdd08e5cb58f5f7542dcdc26f2e00b478a92d4fc09d6da","schema_version":"1.0","event_id":"sha256:8d333c18bc7eb296e0cdd08e5cb58f5f7542dcdc26f2e00b478a92d4fc09d6da"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3SDAE7UE2JHZ52A6DEDV6YA4O7/bundle.json","state_url":"https://pith.science/pith/3SDAE7UE2JHZ52A6DEDV6YA4O7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3SDAE7UE2JHZ52A6DEDV6YA4O7/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":"2026-08-07T06:15:47Z","links":{"resolver":"https://pith.science/pith/3SDAE7UE2JHZ52A6DEDV6YA4O7","bundle":"https://pith.science/pith/3SDAE7UE2JHZ52A6DEDV6YA4O7/bundle.json","state":"https://pith.science/pith/3SDAE7UE2JHZ52A6DEDV6YA4O7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3SDAE7UE2JHZ52A6DEDV6YA4O7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3SDAE7UE2JHZ52A6DEDV6YA4O7","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":"b6d85dc86fd8bdc0435228e5fafdd41bfedcd4ba08156d23b30ed0e5e1c92e9d","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-24T18:38:11Z","title_canon_sha256":"b15117b27878331b6154a069ca0be97c7b337108a25e1180d57e849c505eccbd"},"schema_version":"1.0","source":{"id":"2404.16130","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.16130","created_at":"2026-07-05T10:16:33Z"},{"alias_kind":"arxiv_version","alias_value":"2404.16130v2","created_at":"2026-07-05T10:16:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.16130","created_at":"2026-07-05T10:16:33Z"},{"alias_kind":"pith_short_12","alias_value":"3SDAE7UE2JHZ","created_at":"2026-07-05T10:16:33Z"},{"alias_kind":"pith_short_16","alias_value":"3SDAE7UE2JHZ52A6","created_at":"2026-07-05T10:16:33Z"},{"alias_kind":"pith_short_8","alias_value":"3SDAE7UE","created_at":"2026-07-05T10:16:33Z"}],"graph_snapshots":[{"event_id":"sha256:8d333c18bc7eb296e0cdd08e5cb58f5f7542dcdc26f2e00b478a92d4fc09d6da","target":"graph","created_at":"2026-07-05T10:16:33Z","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":"For a class of global sensemaking questions over datasets in the 1 million token range, we show that GraphRAG leads to substantial improvements over a conventional RAG baseline for both the comprehensiveness and diversity of generated answers."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That LLM-generated entity graphs and community summaries accurately and comprehensively capture the source material without introducing errors, omissions, or biases that would undermine the final combined responses for global questions."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"GraphRAG improves comprehensiveness and diversity of answers to global questions over million-token document sets by constructing entity graphs and hierarchical community summaries before combining partial responses."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"GraphRAG builds entity knowledge graphs and community summaries to answer global questions over large private text collections more comprehensively than standard RAG."}],"snapshot_sha256":"b0646a2c0dbdaac7a3e293d67cd7f5ae4688f9c10a2efb21a90f4355683eea4c"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2404.16130/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The use of retrieval-augmented generation (RAG) to retrieve relevant information from an external knowledge source enables large language models (LLMs) to answer questions over private and/or previously unseen document collections. However, RAG fails on global questions directed at an entire text corpus, such as \"What are the main themes in the dataset?\", since this is inherently a query-focused summarization (QFS) task, rather than an explicit retrieval task. Prior QFS methods, meanwhile, do not scale to the quantities of text indexed by typical RAG systems. To combine the strengths of these ","authors_text":"Alex Chao, Apurva Mody, Darren Edge, Dasha Metropolitansky, Ha Trinh, Jonathan Larson, Joshua Bradley, Newman Cheng, Robert Osazuwa Ness, Steven Truitt","cross_cats":["cs.AI","cs.IR"],"headline":"GraphRAG builds entity knowledge graphs and community summaries to answer global questions over large private text collections more comprehensively than standard RAG.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-24T18:38:11Z","title":"From Local to Global: A Graph RAG Approach to Query-Focused Summarization"},"references":{"count":79,"internal_anchors":13,"resolved_work":79,"sample":[{"cited_arxiv_id":"2303.08774","doi":"","is_internal_anchor":true,"ref_index":1,"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","year":2023},{"cited_arxiv_id":"2312.11805","doi":"","is_internal_anchor":true,"ref_index":2,"title":"Gemini: A Family of Highly Capable Multimodal Models","work_id":"83f7c85b-3f11-450f-ac0c-64d9745220b2","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Knowledge-augmented language model prompting for zero-shot knowledge graph question answering","work_id":"2c7df13c-fbfe-4b89-b7c7-a1e8b2abdbe4","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Ban, T., Chen, L., Wang, X., and Chen, H. (2023). From query tools to causal architects: Harnessing large language models for advanced causal discovery from data","work_id":"34c5bdba-6b27-45dd-ba89-4640f59851ad","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Barlaug, N. and Gulla, J. A. (2021). Neural networks for entity matching: A survey. ACM Transactions on Knowledge Discovery from Data (TKDD) , 15(3):1--37","work_id":"54da3606-6b77-4ebe-9090-48dd9e85a6d5","year":2021}],"snapshot_sha256":"783a345e9ad3fd8a32be203e5a9798f46a07c638df6cefb476a8750f4a46725b"},"source":{"id":"2404.16130","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-11T05:07:17.015621Z","id":"ea83d1d8-208d-4c2d-9679-f2d4762583a6","model_set":{"reader":"grok-4.3"},"one_line_summary":"GraphRAG improves comprehensiveness and diversity of answers to global questions over million-token document sets by constructing entity graphs and hierarchical community summaries before combining partial responses.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"GraphRAG builds entity knowledge graphs and community summaries to answer global questions over large private text collections more comprehensively than standard RAG.","strongest_claim":"For a class of global sensemaking questions over datasets in the 1 million token range, we show that GraphRAG leads to substantial improvements over a conventional RAG baseline for both the comprehensiveness and diversity of generated answers.","weakest_assumption":"That LLM-generated entity graphs and community summaries accurately and comprehensively capture the source material without introducing errors, omissions, or biases that would undermine the final combined responses for global questions."}},"verdict_id":"ea83d1d8-208d-4c2d-9679-f2d4762583a6"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:aba6c46ea9aa05db9877a7be2ea4fda0d822dc9af750e46f13f420df5e8f3a6b","target":"record","created_at":"2026-07-05T10:16:33Z","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":"b6d85dc86fd8bdc0435228e5fafdd41bfedcd4ba08156d23b30ed0e5e1c92e9d","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-24T18:38:11Z","title_canon_sha256":"b15117b27878331b6154a069ca0be97c7b337108a25e1180d57e849c505eccbd"},"schema_version":"1.0","source":{"id":"2404.16130","kind":"arxiv","version":2}},"canonical_sha256":"dc86027e84d24f9ee81e19075f601c77f8b6cf1b01676ea05043dce368a06f4d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dc86027e84d24f9ee81e19075f601c77f8b6cf1b01676ea05043dce368a06f4d","first_computed_at":"2026-07-05T10:16:33.442784Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:16:33.442784Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4+wxWZBX34kWhMOKBGVa/aJN+fXQeLdgN0i1iCEzs9hkUvxPZHCxlfxTcHM+tyzJhPCbge2Fb6FBsSLBqKgAAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:16:33.443334Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.16130","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aba6c46ea9aa05db9877a7be2ea4fda0d822dc9af750e46f13f420df5e8f3a6b","sha256:8d333c18bc7eb296e0cdd08e5cb58f5f7542dcdc26f2e00b478a92d4fc09d6da"],"state_sha256":"7904f9c60922548c9677fb3064e31d7ea59b53b0021f3b8799f51c901167d552"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AlH3W/TnV4NEbxrz0q4dNZK2sOTC2c8DMM+aJGKDmqdjfhb/Wf4Qq9PGTGJ359Bl2BIp8i6m6VIrk7JJ7I3JDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T06:15:47.720625Z","bundle_sha256":"8bb583ce50b3684a1504c6b12b4ab0142c6bc893a2952ddb4f55313ee55a09d6"}}