{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:KN5Y4FSOEAPVREUJZCK4KUFB3A","short_pith_number":"pith:KN5Y4FSO","canonical_record":{"source":{"id":"2304.03442","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2023-04-07T01:55:19Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"f3770ec6de1fcbcb88b2c89175ea29cd6caef1189e993e684d226ab41afbcce6","abstract_canon_sha256":"0930470f0f1222fc63f8ad33e69b562c61312fd5385aa11667230a05634db314"},"schema_version":"1.0"},"canonical_sha256":"537b8e164e201f589289c895c550a1d810eb388d40dba6d882f871b50b400e7f","source":{"kind":"arxiv","id":"2304.03442","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.03442","created_at":"2026-07-05T06:37:57Z"},{"alias_kind":"arxiv_version","alias_value":"2304.03442v2","created_at":"2026-07-05T06:37:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.03442","created_at":"2026-07-05T06:37:57Z"},{"alias_kind":"pith_short_12","alias_value":"KN5Y4FSOEAPV","created_at":"2026-07-05T06:37:57Z"},{"alias_kind":"pith_short_16","alias_value":"KN5Y4FSOEAPVREUJ","created_at":"2026-07-05T06:37:57Z"},{"alias_kind":"pith_short_8","alias_value":"KN5Y4FSO","created_at":"2026-07-05T06:37:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:KN5Y4FSOEAPVREUJZCK4KUFB3A","target":"record","payload":{"canonical_record":{"source":{"id":"2304.03442","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2023-04-07T01:55:19Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"f3770ec6de1fcbcb88b2c89175ea29cd6caef1189e993e684d226ab41afbcce6","abstract_canon_sha256":"0930470f0f1222fc63f8ad33e69b562c61312fd5385aa11667230a05634db314"},"schema_version":"1.0"},"canonical_sha256":"537b8e164e201f589289c895c550a1d810eb388d40dba6d882f871b50b400e7f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:37:57.785997Z","signature_b64":"E8DCSs5NWhWZSOxSFdRCAbEiDYqQSAMabylNrKGJOIDct2A0GHD6DpsWaIODCee+6EL4u9eBlTgOQVtIbEDoBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"537b8e164e201f589289c895c550a1d810eb388d40dba6d882f871b50b400e7f","last_reissued_at":"2026-07-05T06:37:57.785324Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:37:57.785324Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.03442","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":"2026-07-05T06:37:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HmITLBAm+BiMHV3OOmZJAt8/7rND7RsG+J9+3cMpr2ocTI9HRgbuk8x+TJga0nrlMncpuC3yx+AllWokKyetBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T15:41:08.996164Z"},"content_sha256":"81cf8784598b8c596b3c7d6b5752f2a169c1389b72c713991efa8c4e59f02981","schema_version":"1.0","event_id":"sha256:81cf8784598b8c596b3c7d6b5752f2a169c1389b72c713991efa8c4e59f02981"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:KN5Y4FSOEAPVREUJZCK4KUFB3A","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Generative Agents: Interactive Simulacra of Human Behavior","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Generative agents extend large language models with memory, reflection, and planning to produce believable individual and social behaviors in a simulated town.","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.HC","authors_text":"Carrie J. Cai, Joon Sung Park, Joseph C. O'Brien, Meredith Ringel Morris, Michael S. Bernstein, Percy Liang","submitted_at":"2023-04-07T01:55:19Z","abstract_excerpt":"Believable proxies of human behavior can empower interactive applications ranging from immersive environments to rehearsal spaces for interpersonal communication to prototyping tools. In this paper, we introduce generative agents--computational software agents that simulate believable human behavior. Generative agents wake up, cook breakfast, and head to work; artists paint, while authors write; they form opinions, notice each other, and initiate conversations; they remember and reflect on days past as they plan the next day. To enable generative agents, we describe an architecture that extend"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Generative agents produce believable individual and emergent social behaviors: for example, starting with only a single user-specified notion that one agent wants to throw a Valentine's Day party, the agents autonomously spread invitations to the party over the next two days, make new acquaintances, ask each other out on dates to the party, and coordinate to show up for the party together at the right time.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That large language models will reliably generate coherent, non-contradictory actions, reflections, and dialogues that remain consistent with an agent's accumulating memory and personality across multi-day interactions without external correction.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Generative agents with memory streams, reflection, and planning using LLMs exhibit believable individual and emergent social behaviors in a simulated town.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Generative agents extend large language models with memory, reflection, and planning to produce believable individual and social behaviors in a simulated town.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"204d17c7840d641a80f7a68befc7817f95d36348a27c07626503027e05d7299e"},"source":{"id":"2304.03442","kind":"arxiv","version":2},"verdict":{"id":"15e1f64c-5533-4b9b-8ee7-f3ffda1af5bd","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-11T18:58:57.161389Z","strongest_claim":"Generative agents produce believable individual and emergent social behaviors: for example, starting with only a single user-specified notion that one agent wants to throw a Valentine's Day party, the agents autonomously spread invitations to the party over the next two days, make new acquaintances, ask each other out on dates to the party, and coordinate to show up for the party together at the right time.","one_line_summary":"Generative agents with memory streams, reflection, and planning using LLMs exhibit believable individual and emergent social behaviors in a simulated town.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That large language models will reliably generate coherent, non-contradictory actions, reflections, and dialogues that remain consistent with an agent's accumulating memory and personality across multi-day interactions without external correction.","pith_extraction_headline":"Generative agents extend large language models with memory, reflection, and planning to produce believable individual and social behaviors in a simulated town."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2304.03442/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":117,"sample":[{"doi":"","year":2023,"title":"Mirages: On anthropomorphism in dialogue systems","work_id":"c5c79c15-3cc0-46d5-b042-f1891ead877f","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2013,"title":"Robert Ackland, Jamsheed Shorish, Paul Thomas, and Lexing Xie. 2013. How dense is a network? http://users.cecs.anu.edu.au/~xlx/teaching/css2013/ network-density.html","work_id":"03c530a3-0468-4826-a317-265e350ce755","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1145/2642918.2647395","year":2014,"title":"Eytan Adar, Mira Dontcheva, and Gierad Laput. 2014. CommandSpace: Modeling the Relationships between Tasks, Descriptions and Features. In Proceedings of the 27th Annual ACM Symposium on User Interface","work_id":"304ceb61-9a68-4fc1-b7b9-1854f9b098d8","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Saleema Amershi, Maya Cakmak, William Bradley Knox, and Todd Kulesza","work_id":"f245c964-ceec-4918-ab6b-165a4fd54663","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2014,"title":"AI Magazine 35, 4 (2014), 105–120","work_id":"35635553-bceb-4871-af5e-c58de235efa3","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":117,"snapshot_sha256":"c38cac86814cdb4477401a6ec8d92ad5757f2059246b1a777cca52e6f62c19b5","internal_anchors":8},"formal_canon":{"evidence_count":3,"snapshot_sha256":"c339237fdaf799c8b7c470af961c5aa90a91554f4cd02d71210dbd01be8e5c79"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"15e1f64c-5533-4b9b-8ee7-f3ffda1af5bd"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:37:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V6Pp4g+4kzOjsoM1QE3m47J8qHX2bU0ciV3xuxgNyvitW2Lsh1p4DEwP4vBJGo0DI/tWsEExBnomXsUU+vYXAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T15:41:08.997030Z"},"content_sha256":"f52cbef07af7ee01e40987c265f5e0ac4dd3b404181178490b653b1a248b7fdc","schema_version":"1.0","event_id":"sha256:f52cbef07af7ee01e40987c265f5e0ac4dd3b404181178490b653b1a248b7fdc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KN5Y4FSOEAPVREUJZCK4KUFB3A/bundle.json","state_url":"https://pith.science/pith/KN5Y4FSOEAPVREUJZCK4KUFB3A/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KN5Y4FSOEAPVREUJZCK4KUFB3A/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":"2026-08-03T15:41:08Z","links":{"resolver":"https://pith.science/pith/KN5Y4FSOEAPVREUJZCK4KUFB3A","bundle":"https://pith.science/pith/KN5Y4FSOEAPVREUJZCK4KUFB3A/bundle.json","state":"https://pith.science/pith/KN5Y4FSOEAPVREUJZCK4KUFB3A/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KN5Y4FSOEAPVREUJZCK4KUFB3A/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:KN5Y4FSOEAPVREUJZCK4KUFB3A","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":"0930470f0f1222fc63f8ad33e69b562c61312fd5385aa11667230a05634db314","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2023-04-07T01:55:19Z","title_canon_sha256":"f3770ec6de1fcbcb88b2c89175ea29cd6caef1189e993e684d226ab41afbcce6"},"schema_version":"1.0","source":{"id":"2304.03442","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.03442","created_at":"2026-07-05T06:37:57Z"},{"alias_kind":"arxiv_version","alias_value":"2304.03442v2","created_at":"2026-07-05T06:37:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.03442","created_at":"2026-07-05T06:37:57Z"},{"alias_kind":"pith_short_12","alias_value":"KN5Y4FSOEAPV","created_at":"2026-07-05T06:37:57Z"},{"alias_kind":"pith_short_16","alias_value":"KN5Y4FSOEAPVREUJ","created_at":"2026-07-05T06:37:57Z"},{"alias_kind":"pith_short_8","alias_value":"KN5Y4FSO","created_at":"2026-07-05T06:37:57Z"}],"graph_snapshots":[{"event_id":"sha256:f52cbef07af7ee01e40987c265f5e0ac4dd3b404181178490b653b1a248b7fdc","target":"graph","created_at":"2026-07-05T06:37:57Z","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":"Generative agents produce believable individual and emergent social behaviors: for example, starting with only a single user-specified notion that one agent wants to throw a Valentine's Day party, the agents autonomously spread invitations to the party over the next two days, make new acquaintances, ask each other out on dates to the party, and coordinate to show up for the party together at the right time."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That large language models will reliably generate coherent, non-contradictory actions, reflections, and dialogues that remain consistent with an agent's accumulating memory and personality across multi-day interactions without external correction."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Generative agents with memory streams, reflection, and planning using LLMs exhibit believable individual and emergent social behaviors in a simulated town."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Generative agents extend large language models with memory, reflection, and planning to produce believable individual and social behaviors in a simulated town."}],"snapshot_sha256":"204d17c7840d641a80f7a68befc7817f95d36348a27c07626503027e05d7299e"},"formal_canon":{"evidence_count":3,"snapshot_sha256":"c339237fdaf799c8b7c470af961c5aa90a91554f4cd02d71210dbd01be8e5c79"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2304.03442/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Believable proxies of human behavior can empower interactive applications ranging from immersive environments to rehearsal spaces for interpersonal communication to prototyping tools. In this paper, we introduce generative agents--computational software agents that simulate believable human behavior. Generative agents wake up, cook breakfast, and head to work; artists paint, while authors write; they form opinions, notice each other, and initiate conversations; they remember and reflect on days past as they plan the next day. To enable generative agents, we describe an architecture that extend","authors_text":"Carrie J. Cai, Joon Sung Park, Joseph C. O'Brien, Meredith Ringel Morris, Michael S. Bernstein, Percy Liang","cross_cats":["cs.AI","cs.LG"],"headline":"Generative agents extend large language models with memory, reflection, and planning to produce believable individual and social behaviors in a simulated town.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2023-04-07T01:55:19Z","title":"Generative Agents: Interactive Simulacra of Human Behavior"},"references":{"count":117,"internal_anchors":8,"resolved_work":117,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Mirages: On anthropomorphism in dialogue systems","work_id":"c5c79c15-3cc0-46d5-b042-f1891ead877f","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Robert Ackland, Jamsheed Shorish, Paul Thomas, and Lexing Xie. 2013. How dense is a network? http://users.cecs.anu.edu.au/~xlx/teaching/css2013/ network-density.html","work_id":"03c530a3-0468-4826-a317-265e350ce755","year":2013},{"cited_arxiv_id":"","doi":"10.1145/2642918.2647395","is_internal_anchor":false,"ref_index":3,"title":"Eytan Adar, Mira Dontcheva, and Gierad Laput. 2014. CommandSpace: Modeling the Relationships between Tasks, Descriptions and Features. In Proceedings of the 27th Annual ACM Symposium on User Interface","work_id":"304ceb61-9a68-4fc1-b7b9-1854f9b098d8","year":2014},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Saleema Amershi, Maya Cakmak, William Bradley Knox, and Todd Kulesza","work_id":"f245c964-ceec-4918-ab6b-165a4fd54663","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"AI Magazine 35, 4 (2014), 105–120","work_id":"35635553-bceb-4871-af5e-c58de235efa3","year":2014}],"snapshot_sha256":"c38cac86814cdb4477401a6ec8d92ad5757f2059246b1a777cca52e6f62c19b5"},"source":{"id":"2304.03442","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-11T18:58:57.161389Z","id":"15e1f64c-5533-4b9b-8ee7-f3ffda1af5bd","model_set":{"reader":"grok-4.3"},"one_line_summary":"Generative agents with memory streams, reflection, and planning using LLMs exhibit believable individual and emergent social behaviors in a simulated town.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Generative agents extend large language models with memory, reflection, and planning to produce believable individual and social behaviors in a simulated town.","strongest_claim":"Generative agents produce believable individual and emergent social behaviors: for example, starting with only a single user-specified notion that one agent wants to throw a Valentine's Day party, the agents autonomously spread invitations to the party over the next two days, make new acquaintances, ask each other out on dates to the party, and coordinate to show up for the party together at the right time.","weakest_assumption":"That large language models will reliably generate coherent, non-contradictory actions, reflections, and dialogues that remain consistent with an agent's accumulating memory and personality across multi-day interactions without external correction."}},"verdict_id":"15e1f64c-5533-4b9b-8ee7-f3ffda1af5bd"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:81cf8784598b8c596b3c7d6b5752f2a169c1389b72c713991efa8c4e59f02981","target":"record","created_at":"2026-07-05T06:37:57Z","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":"0930470f0f1222fc63f8ad33e69b562c61312fd5385aa11667230a05634db314","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2023-04-07T01:55:19Z","title_canon_sha256":"f3770ec6de1fcbcb88b2c89175ea29cd6caef1189e993e684d226ab41afbcce6"},"schema_version":"1.0","source":{"id":"2304.03442","kind":"arxiv","version":2}},"canonical_sha256":"537b8e164e201f589289c895c550a1d810eb388d40dba6d882f871b50b400e7f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"537b8e164e201f589289c895c550a1d810eb388d40dba6d882f871b50b400e7f","first_computed_at":"2026-07-05T06:37:57.785324Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:37:57.785324Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"E8DCSs5NWhWZSOxSFdRCAbEiDYqQSAMabylNrKGJOIDct2A0GHD6DpsWaIODCee+6EL4u9eBlTgOQVtIbEDoBg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:37:57.785997Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.03442","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:81cf8784598b8c596b3c7d6b5752f2a169c1389b72c713991efa8c4e59f02981","sha256:f52cbef07af7ee01e40987c265f5e0ac4dd3b404181178490b653b1a248b7fdc"],"state_sha256":"75599012b390aba461c98095af42f9e4f98eac44079dcf111eadf4fb6371ecd1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4GlNS5tYZG2dC/Ad4USjYVNl2taPCgPK0rXs7FiuW+lf85gmeO7FCgqeSnb7gf1sewZglNfT8XOluJbq92qLBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T15:41:09.001867Z","bundle_sha256":"ea4f302c28f9e54e165d07c54e61619d46b9fdd1788294d0824cefb088fa6074"}}