{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:YLVMLQCGH4CXTYJQVOVYBNMYU2","short_pith_number":"pith:YLVMLQCG","canonical_record":{"source":{"id":"2307.04964","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-11T01:55:24Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c69253843ad7e306e4dbfca11d0095e5519020508eb9d9fb7ea4417a398f3e42","abstract_canon_sha256":"4759771176e5a57db34b180d670038182053f6e0e0813f34e57d3db6cda5879b"},"schema_version":"1.0"},"canonical_sha256":"c2eac5c0463f0579e130abab80b598a6b92b3e4612bc811c174a2165e07240e4","source":{"kind":"arxiv","id":"2307.04964","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.04964","created_at":"2026-05-17T23:38:13Z"},{"alias_kind":"arxiv_version","alias_value":"2307.04964v2","created_at":"2026-05-17T23:38:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.04964","created_at":"2026-05-17T23:38:13Z"},{"alias_kind":"pith_short_12","alias_value":"YLVMLQCGH4CX","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"YLVMLQCGH4CXTYJQ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"YLVMLQCG","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:YLVMLQCGH4CXTYJQVOVYBNMYU2","target":"record","payload":{"canonical_record":{"source":{"id":"2307.04964","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-11T01:55:24Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c69253843ad7e306e4dbfca11d0095e5519020508eb9d9fb7ea4417a398f3e42","abstract_canon_sha256":"4759771176e5a57db34b180d670038182053f6e0e0813f34e57d3db6cda5879b"},"schema_version":"1.0"},"canonical_sha256":"c2eac5c0463f0579e130abab80b598a6b92b3e4612bc811c174a2165e07240e4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:13.977278Z","signature_b64":"RE6AUkvv45GrXXI53azq+xAHyCkrY/52/UYX9w3JfB30s2V8hImnYlhg9ScQSH9pIu/dioNT/GkpA3tw95TFCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c2eac5c0463f0579e130abab80b598a6b92b3e4612bc811c174a2165e07240e4","last_reissued_at":"2026-05-17T23:38:13.976773Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:13.976773Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.04964","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":"2026-05-17T23:38:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xa95B7YQLANF9u+U5oLK5bwVNx9rJi+xwXu1UrDfV8ie+CwUHjmB8nGGlr9011A8TAHELNEGc3xRMMxWAzgKAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T21:22:16.422125Z"},"content_sha256":"a27e31ccbd6d2516426574424e54af3d1bc74cbcc6d2e37a7d55ff70dac066c5","schema_version":"1.0","event_id":"sha256:a27e31ccbd6d2516426574424e54af3d1bc74cbcc6d2e37a7d55ff70dac066c5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:YLVMLQCGH4CXTYJQVOVYBNMYU2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Secrets of RLHF in Large Language Models Part I: PPO","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Policy constraints are the key factor for effective PPO implementation in RLHF for large language models.","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Binghai Wang, Cheng Chang, Hang Yan, Haoran Huang, Limao Xiong, Lu Chen, Minghao Zhu, Nuo Xu, Qin Liu, Qi Zhang, Rongxiang Weng, Rui Zheng, Senjie Jin, Shihan Dou, Songyang Gao, Tao Gui, Tianxiang Sun, Wei Shen, Wenbin Lai, Wensen Cheng, Xipeng Qiu, Xuanjing Huang, Yan Liu, Yuan Hua, Yuhao Zhou, Zhangyue Yin, Zhiheng Xi","submitted_at":"2023-07-11T01:55:24Z","abstract_excerpt":"Large language models (LLMs) have formulated a blueprint for the advancement of artificial general intelligence. Its primary objective is to function as a human-centric (helpful, honest, and harmless) assistant. Alignment with humans assumes paramount significance, and reinforcement learning with human feedback (RLHF) emerges as the pivotal technological paradigm underpinning this pursuit. Current technical routes usually include \\textbf{reward models} to measure human preferences, \\textbf{Proximal Policy Optimization} (PPO) to optimize policy model outputs, and \\textbf{process supervision} to"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We identify policy constraints being the key factor for the effective implementation of the PPO algorithm. Therefore, we explore the PPO-max, an advanced version of PPO algorithm, to efficiently improve the training stability of the policy model.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the observed training instability in RLHF stems primarily from policy constraint mechanics in PPO rather than from reward model quality, data selection, or other unexamined components of the full pipeline.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Policy constraints are the critical factor for stable PPO training in RLHF, and the proposed PPO-max variant improves stability for large language model alignment.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Policy constraints are the key factor for effective PPO implementation in RLHF for large language models.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"fc08c09b1a2dc6f204bef33dbfb6cc9735cb28f8a47714ad1df63fba32bb48e1"},"source":{"id":"2307.04964","kind":"arxiv","version":2},"verdict":{"id":"ba43b342-14b3-4d38-a4cf-8265131077c1","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-17T13:11:43.566728Z","strongest_claim":"We identify policy constraints being the key factor for the effective implementation of the PPO algorithm. Therefore, we explore the PPO-max, an advanced version of PPO algorithm, to efficiently improve the training stability of the policy model.","one_line_summary":"Policy constraints are the critical factor for stable PPO training in RLHF, and the proposed PPO-max variant improves stability for large language model alignment.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the observed training instability in RLHF stems primarily from policy constraint mechanics in PPO rather than from reward model quality, data selection, or other unexamined components of the full pipeline.","pith_extraction_headline":"Policy constraints are the key factor for effective PPO implementation in RLHF for large language models."},"references":{"count":60,"sample":[{"doi":"","year":2023,"title":"LLaMA: Open and Efficient Foundation Language Models","work_id":"c018fc23-6f3f-4035-9d02-28a2173b2b9d","ref_index":1,"cited_arxiv_id":"2302.13971","is_internal_anchor":true},{"doi":"","year":2023,"title":"Chiang, W.-L., Z. Li, Z. Lin, et al. Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality. See https://vicuna. lmsys. org (accessed 14 April 2023) , 2023","work_id":"17fc14bb-5dff-4a72-af61-425c91b07479","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Gpt-4 technical report","work_id":"388f534c-855a-4366-b933-f07bf3e2db5f","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"A Survey of Large Language Models","work_id":"de1b42b5-4a0a-4b1f-8c78-1f7fe21be6c9","ref_index":4,"cited_arxiv_id":"2303.18223","is_internal_anchor":true},{"doi":"","year":1901,"title":"Brown, T., B. Mann, N. Ryder, et al. Language models are few-shot learners. Advances in neural information processing systems, 33:1877–1901, 2020","work_id":"9010afde-4504-4219-a609-1afdc37b81a3","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":60,"snapshot_sha256":"b5b055ecd0e7677ffb9ff2da154f836e84baaecdab77551ebf5395099677c30a","internal_anchors":14},"formal_canon":{"evidence_count":1,"snapshot_sha256":"ca570a855e77390e73535f3b9034a90c5e946dd6731ebfdc3aa7af6b218dfab5"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"ba43b342-14b3-4d38-a4cf-8265131077c1"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9z5SBKDc4zLeiSVj1Jq/U+KlCHsr74reJkyRjmKbfc1WLpJiOr7j/Dwjwz0mhHxBf386tJhS6btmSz6dYi6pAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T21:22:16.423407Z"},"content_sha256":"59fdd82161f390338eaa406e8efab18d7ddda0313b3edb45a8e8be0d8f7e122b","schema_version":"1.0","event_id":"sha256:59fdd82161f390338eaa406e8efab18d7ddda0313b3edb45a8e8be0d8f7e122b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YLVMLQCGH4CXTYJQVOVYBNMYU2/bundle.json","state_url":"https://pith.science/pith/YLVMLQCGH4CXTYJQVOVYBNMYU2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YLVMLQCGH4CXTYJQVOVYBNMYU2/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":"2026-05-29T21:22:16Z","links":{"resolver":"https://pith.science/pith/YLVMLQCGH4CXTYJQVOVYBNMYU2","bundle":"https://pith.science/pith/YLVMLQCGH4CXTYJQVOVYBNMYU2/bundle.json","state":"https://pith.science/pith/YLVMLQCGH4CXTYJQVOVYBNMYU2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YLVMLQCGH4CXTYJQVOVYBNMYU2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:YLVMLQCGH4CXTYJQVOVYBNMYU2","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":"4759771176e5a57db34b180d670038182053f6e0e0813f34e57d3db6cda5879b","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-11T01:55:24Z","title_canon_sha256":"c69253843ad7e306e4dbfca11d0095e5519020508eb9d9fb7ea4417a398f3e42"},"schema_version":"1.0","source":{"id":"2307.04964","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.04964","created_at":"2026-05-17T23:38:13Z"},{"alias_kind":"arxiv_version","alias_value":"2307.04964v2","created_at":"2026-05-17T23:38:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.04964","created_at":"2026-05-17T23:38:13Z"},{"alias_kind":"pith_short_12","alias_value":"YLVMLQCGH4CX","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"YLVMLQCGH4CXTYJQ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"YLVMLQCG","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:59fdd82161f390338eaa406e8efab18d7ddda0313b3edb45a8e8be0d8f7e122b","target":"graph","created_at":"2026-05-17T23:38:13Z","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":"We identify policy constraints being the key factor for the effective implementation of the PPO algorithm. Therefore, we explore the PPO-max, an advanced version of PPO algorithm, to efficiently improve the training stability of the policy model."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the observed training instability in RLHF stems primarily from policy constraint mechanics in PPO rather than from reward model quality, data selection, or other unexamined components of the full pipeline."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Policy constraints are the critical factor for stable PPO training in RLHF, and the proposed PPO-max variant improves stability for large language model alignment."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Policy constraints are the key factor for effective PPO implementation in RLHF for large language models."}],"snapshot_sha256":"fc08c09b1a2dc6f204bef33dbfb6cc9735cb28f8a47714ad1df63fba32bb48e1"},"formal_canon":{"evidence_count":1,"snapshot_sha256":"ca570a855e77390e73535f3b9034a90c5e946dd6731ebfdc3aa7af6b218dfab5"},"paper":{"abstract_excerpt":"Large language models (LLMs) have formulated a blueprint for the advancement of artificial general intelligence. Its primary objective is to function as a human-centric (helpful, honest, and harmless) assistant. Alignment with humans assumes paramount significance, and reinforcement learning with human feedback (RLHF) emerges as the pivotal technological paradigm underpinning this pursuit. Current technical routes usually include \\textbf{reward models} to measure human preferences, \\textbf{Proximal Policy Optimization} (PPO) to optimize policy model outputs, and \\textbf{process supervision} to","authors_text":"Binghai Wang, Cheng Chang, Hang Yan, Haoran Huang, Limao Xiong, Lu Chen, Minghao Zhu, Nuo Xu, Qin Liu, Qi Zhang, Rongxiang Weng, Rui Zheng, Senjie Jin, Shihan Dou, Songyang Gao, Tao Gui, Tianxiang Sun, Wei Shen, Wenbin Lai, Wensen Cheng, Xipeng Qiu, Xuanjing Huang, Yan Liu, Yuan Hua, Yuhao Zhou, Zhangyue Yin, Zhiheng Xi","cross_cats":["cs.AI","cs.LG"],"headline":"Policy constraints are the key factor for effective PPO implementation in RLHF for large language models.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-11T01:55:24Z","title":"Secrets of RLHF in Large Language Models Part I: PPO"},"references":{"count":60,"internal_anchors":14,"resolved_work":60,"sample":[{"cited_arxiv_id":"2302.13971","doi":"","is_internal_anchor":true,"ref_index":1,"title":"LLaMA: Open and Efficient Foundation Language Models","work_id":"c018fc23-6f3f-4035-9d02-28a2173b2b9d","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Chiang, W.-L., Z. Li, Z. Lin, et al. Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality. See https://vicuna. lmsys. org (accessed 14 April 2023) , 2023","work_id":"17fc14bb-5dff-4a72-af61-425c91b07479","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Gpt-4 technical report","work_id":"388f534c-855a-4366-b933-f07bf3e2db5f","year":2023},{"cited_arxiv_id":"2303.18223","doi":"","is_internal_anchor":true,"ref_index":4,"title":"A Survey of Large Language Models","work_id":"de1b42b5-4a0a-4b1f-8c78-1f7fe21be6c9","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Brown, T., B. Mann, N. Ryder, et al. Language models are few-shot learners. Advances in neural information processing systems, 33:1877–1901, 2020","work_id":"9010afde-4504-4219-a609-1afdc37b81a3","year":1901}],"snapshot_sha256":"b5b055ecd0e7677ffb9ff2da154f836e84baaecdab77551ebf5395099677c30a"},"source":{"id":"2307.04964","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-17T13:11:43.566728Z","id":"ba43b342-14b3-4d38-a4cf-8265131077c1","model_set":{"reader":"grok-4.3"},"one_line_summary":"Policy constraints are the critical factor for stable PPO training in RLHF, and the proposed PPO-max variant improves stability for large language model alignment.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Policy constraints are the key factor for effective PPO implementation in RLHF for large language models.","strongest_claim":"We identify policy constraints being the key factor for the effective implementation of the PPO algorithm. Therefore, we explore the PPO-max, an advanced version of PPO algorithm, to efficiently improve the training stability of the policy model.","weakest_assumption":"That the observed training instability in RLHF stems primarily from policy constraint mechanics in PPO rather than from reward model quality, data selection, or other unexamined components of the full pipeline."}},"verdict_id":"ba43b342-14b3-4d38-a4cf-8265131077c1"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a27e31ccbd6d2516426574424e54af3d1bc74cbcc6d2e37a7d55ff70dac066c5","target":"record","created_at":"2026-05-17T23:38:13Z","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":"4759771176e5a57db34b180d670038182053f6e0e0813f34e57d3db6cda5879b","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-11T01:55:24Z","title_canon_sha256":"c69253843ad7e306e4dbfca11d0095e5519020508eb9d9fb7ea4417a398f3e42"},"schema_version":"1.0","source":{"id":"2307.04964","kind":"arxiv","version":2}},"canonical_sha256":"c2eac5c0463f0579e130abab80b598a6b92b3e4612bc811c174a2165e07240e4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c2eac5c0463f0579e130abab80b598a6b92b3e4612bc811c174a2165e07240e4","first_computed_at":"2026-05-17T23:38:13.976773Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:13.976773Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RE6AUkvv45GrXXI53azq+xAHyCkrY/52/UYX9w3JfB30s2V8hImnYlhg9ScQSH9pIu/dioNT/GkpA3tw95TFCQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:13.977278Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.04964","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a27e31ccbd6d2516426574424e54af3d1bc74cbcc6d2e37a7d55ff70dac066c5","sha256:59fdd82161f390338eaa406e8efab18d7ddda0313b3edb45a8e8be0d8f7e122b"],"state_sha256":"5c7f0e65477df409906a024fd96782bd618bc52bdb2d111885b1cc8268ea377b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"61yuJ8nIliabF7aG52FeGslLJzKKy09Tco3VJfNG2dnrdkgrvJbpJbZ2/R2n6nUaJCUzMVaxpjw5I1X8ioy/AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-29T21:22:16.428679Z","bundle_sha256":"3fac612ffb94c3e8d04238f0ac6582acc89066dc7a5afb823e73ca4b5811c1f5"}}