{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:24ZH7CZOHOCKQI5UBKEGORMGTF","short_pith_number":"pith:24ZH7CZO","canonical_record":{"source":{"id":"2605.13641","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T15:05:18Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"25c79d2d6d192456412abfcc88c8bcbce2ae575bf3285c8a57a47d72c4c76ca3","abstract_canon_sha256":"89ad6306ebae2e291fe2e899775f6b3612ffad186d089f93b57cdd1eaf0ce81c"},"schema_version":"1.0"},"canonical_sha256":"d7327f8b2e3b84a823b40a88674586996f0819a993e2e14038a9405da7ba7edf","source":{"kind":"arxiv","id":"2605.13641","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13641","created_at":"2026-05-18T02:44:17Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13641v1","created_at":"2026-05-18T02:44:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13641","created_at":"2026-05-18T02:44:17Z"},{"alias_kind":"pith_short_12","alias_value":"24ZH7CZOHOCK","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"24ZH7CZOHOCKQI5U","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"24ZH7CZO","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:24ZH7CZOHOCKQI5UBKEGORMGTF","target":"record","payload":{"canonical_record":{"source":{"id":"2605.13641","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T15:05:18Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"25c79d2d6d192456412abfcc88c8bcbce2ae575bf3285c8a57a47d72c4c76ca3","abstract_canon_sha256":"89ad6306ebae2e291fe2e899775f6b3612ffad186d089f93b57cdd1eaf0ce81c"},"schema_version":"1.0"},"canonical_sha256":"d7327f8b2e3b84a823b40a88674586996f0819a993e2e14038a9405da7ba7edf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:44:17.604038Z","signature_b64":"ezvoGmnOaWucUxs5maX02qkCX6LWkdPdWQm+/qtpyUafdnTVUzBDTtHZGdW+s0t9tgH7GzENJYcs85beLfDrBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d7327f8b2e3b84a823b40a88674586996f0819a993e2e14038a9405da7ba7edf","last_reissued_at":"2026-05-18T02:44:17.603486Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:44:17.603486Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.13641","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":"2026-05-18T02:44:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HU+9nBpAPMwMtmmms3rTnBFU7FdRWSLO3GIEWhv8rxzq7cMmpqf/rQuRnz4RGwZYkx56Kgq0TG2wW+CM12beDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T12:26:46.868110Z"},"content_sha256":"cd547f852bcdad3bcaf67cb737b8244945c0e3b3d136ce9d4717ddeec5aaccae","schema_version":"1.0","event_id":"sha256:cd547f852bcdad3bcaf67cb737b8244945c0e3b3d136ce9d4717ddeec5aaccae"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:24ZH7CZOHOCKQI5UBKEGORMGTF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-Objective and Mixed-Reward Reinforcement Learning via Reward-Decorrelated Policy Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"RDPO stabilizes advantages in mixed-reward reinforcement learning by normalizing magnitudes and removing correlations before aggregation.","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Jiahong Zhou, Jingang Wang, Kaiyuan Liu, Rongxiang Weng, Xin Chen, Xunliang Cai, Yang Bai, Ziyuan Zhuang","submitted_at":"2026-05-13T15:05:18Z","abstract_excerpt":"Complex reinforcement learning environments frequently employ multi-task and mixed-reward formulations. In these settings, heterogeneous reward distributions and correlated reward dimensions often destabilize the construction of scalar advantages. To address these challenges, we propose Reward-Decorrelated Policy Optimization (RDPO), a reward-processing method designed to explicitly target both failure modes. RDPO first utilizes Magnitude-Aware Quantile normalization to stabilize prompt-level advantage allocation across binary, fractional, and continuous rewards. It then applies Mahalanobis wh"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"When applied during the post-training of LongCat-Flash, RDPO enhances instruction following, writing quality, and robustness to hard prompts while remaining broadly competitive on reasoning and coding evaluations.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That magnitude-aware quantile normalization and Mahalanobis whitening will stabilize advantages across heterogeneous rewards without discarding critical signal or introducing new biases in the specific reward distributions of the LongCat-Flash training setup.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"RDPO applies magnitude-aware quantile normalization and Mahalanobis whitening to decorrelate heterogeneous rewards in multi-objective RL, improving instruction following and writing quality on LongCat-Flash post-training while staying competitive on reasoning and coding.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"RDPO stabilizes advantages in mixed-reward reinforcement learning by normalizing magnitudes and removing correlations before aggregation.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"972ae1a76c20a2b7956de84521d7621a62b7068bf1f85c8e45fa9f265b7730a4"},"source":{"id":"2605.13641","kind":"arxiv","version":1},"verdict":{"id":"31a9043e-c6f2-4445-b53d-1950b87a7d90","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T19:20:34.498141Z","strongest_claim":"When applied during the post-training of LongCat-Flash, RDPO enhances instruction following, writing quality, and robustness to hard prompts while remaining broadly competitive on reasoning and coding evaluations.","one_line_summary":"RDPO applies magnitude-aware quantile normalization and Mahalanobis whitening to decorrelate heterogeneous rewards in multi-objective RL, improving instruction following and writing quality on LongCat-Flash post-training while staying competitive on reasoning and coding.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That magnitude-aware quantile normalization and Mahalanobis whitening will stabilize advantages across heterogeneous rewards without discarding critical signal or introducing new biases in the specific reward distributions of the LongCat-Flash training setup.","pith_extraction_headline":"RDPO stabilizes advantages in mixed-reward reinforcement learning by normalizing magnitudes and removing correlations before aggregation."},"references":{"count":17,"sample":[{"doi":"","year":null,"title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","work_id":"c5006563-f3ec-438a-9e35-b7b484f34828","ref_index":1,"cited_arxiv_id":"2402.03300","is_internal_anchor":true},{"doi":"10.48550/arxiv.2402.03300","year":null,"title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","work_id":"c5006563-f3ec-438a-9e35-b7b484f34828","ref_index":2,"cited_arxiv_id":"2402.03300","is_internal_anchor":true},{"doi":"10.48550/arxiv.2601.05242","year":null,"title":"GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization","work_id":"e60e0bf8-33b8-47c6-8d66-7975f5c121d4","ref_index":3,"cited_arxiv_id":"2601.05242","is_internal_anchor":true},{"doi":"10.48550/arxiv.2501.12599","year":null,"title":"Kimi k1.5: Scaling Reinforcement Learning with LLMs","work_id":"bff96ab1-bd6a-4585-be23-74fdb51969c7","ref_index":4,"cited_arxiv_id":"2501.12599","is_internal_anchor":true},{"doi":"10.48550/arxiv.2503.04697","year":null,"title":"L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning","work_id":"ad7236fb-3752-48a9-b782-a384899c45a0","ref_index":5,"cited_arxiv_id":"2503.04697","is_internal_anchor":true}],"resolved_work":17,"snapshot_sha256":"1e5b013d5cda89c960531d62204d94226a0666c2a6d5024d24bb00b4b409fcbf","internal_anchors":9},"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":"31a9043e-c6f2-4445-b53d-1950b87a7d90"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:44:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t5woVNl2z5wCdQVMytKlSCa9X35zNWnZA8Nu17f0VdCQa5IJCzdd8NJmXCos++lS4UZDyQfxLZe2CuwzPtnNBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T12:26:46.869164Z"},"content_sha256":"d1f818d386fbf81586f884aa702dc978959ad96797b4662b30890459bbbf255c","schema_version":"1.0","event_id":"sha256:d1f818d386fbf81586f884aa702dc978959ad96797b4662b30890459bbbf255c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/24ZH7CZOHOCKQI5UBKEGORMGTF/bundle.json","state_url":"https://pith.science/pith/24ZH7CZOHOCKQI5UBKEGORMGTF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/24ZH7CZOHOCKQI5UBKEGORMGTF/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":"2026-05-30T12:26:46Z","links":{"resolver":"https://pith.science/pith/24ZH7CZOHOCKQI5UBKEGORMGTF","bundle":"https://pith.science/pith/24ZH7CZOHOCKQI5UBKEGORMGTF/bundle.json","state":"https://pith.science/pith/24ZH7CZOHOCKQI5UBKEGORMGTF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/24ZH7CZOHOCKQI5UBKEGORMGTF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:24ZH7CZOHOCKQI5UBKEGORMGTF","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":"89ad6306ebae2e291fe2e899775f6b3612ffad186d089f93b57cdd1eaf0ce81c","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T15:05:18Z","title_canon_sha256":"25c79d2d6d192456412abfcc88c8bcbce2ae575bf3285c8a57a47d72c4c76ca3"},"schema_version":"1.0","source":{"id":"2605.13641","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13641","created_at":"2026-05-18T02:44:17Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13641v1","created_at":"2026-05-18T02:44:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13641","created_at":"2026-05-18T02:44:17Z"},{"alias_kind":"pith_short_12","alias_value":"24ZH7CZOHOCK","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"24ZH7CZOHOCKQI5U","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"24ZH7CZO","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:d1f818d386fbf81586f884aa702dc978959ad96797b4662b30890459bbbf255c","target":"graph","created_at":"2026-05-18T02:44:17Z","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":"When applied during the post-training of LongCat-Flash, RDPO enhances instruction following, writing quality, and robustness to hard prompts while remaining broadly competitive on reasoning and coding evaluations."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That magnitude-aware quantile normalization and Mahalanobis whitening will stabilize advantages across heterogeneous rewards without discarding critical signal or introducing new biases in the specific reward distributions of the LongCat-Flash training setup."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"RDPO applies magnitude-aware quantile normalization and Mahalanobis whitening to decorrelate heterogeneous rewards in multi-objective RL, improving instruction following and writing quality on LongCat-Flash post-training while staying competitive on reasoning and coding."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"RDPO stabilizes advantages in mixed-reward reinforcement learning by normalizing magnitudes and removing correlations before aggregation."}],"snapshot_sha256":"972ae1a76c20a2b7956de84521d7621a62b7068bf1f85c8e45fa9f265b7730a4"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Complex reinforcement learning environments frequently employ multi-task and mixed-reward formulations. In these settings, heterogeneous reward distributions and correlated reward dimensions often destabilize the construction of scalar advantages. To address these challenges, we propose Reward-Decorrelated Policy Optimization (RDPO), a reward-processing method designed to explicitly target both failure modes. RDPO first utilizes Magnitude-Aware Quantile normalization to stabilize prompt-level advantage allocation across binary, fractional, and continuous rewards. It then applies Mahalanobis wh","authors_text":"Jiahong Zhou, Jingang Wang, Kaiyuan Liu, Rongxiang Weng, Xin Chen, Xunliang Cai, Yang Bai, Ziyuan Zhuang","cross_cats":["cs.CL"],"headline":"RDPO stabilizes advantages in mixed-reward reinforcement learning by normalizing magnitudes and removing correlations before aggregation.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T15:05:18Z","title":"Multi-Objective and Mixed-Reward Reinforcement Learning via Reward-Decorrelated Policy Optimization"},"references":{"count":17,"internal_anchors":9,"resolved_work":17,"sample":[{"cited_arxiv_id":"2402.03300","doi":"","is_internal_anchor":true,"ref_index":1,"title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","work_id":"c5006563-f3ec-438a-9e35-b7b484f34828","year":null},{"cited_arxiv_id":"2402.03300","doi":"10.48550/arxiv.2402.03300","is_internal_anchor":true,"ref_index":2,"title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","work_id":"c5006563-f3ec-438a-9e35-b7b484f34828","year":null},{"cited_arxiv_id":"2601.05242","doi":"10.48550/arxiv.2601.05242","is_internal_anchor":true,"ref_index":3,"title":"GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization","work_id":"e60e0bf8-33b8-47c6-8d66-7975f5c121d4","year":null},{"cited_arxiv_id":"2501.12599","doi":"10.48550/arxiv.2501.12599","is_internal_anchor":true,"ref_index":4,"title":"Kimi k1.5: Scaling Reinforcement Learning with LLMs","work_id":"bff96ab1-bd6a-4585-be23-74fdb51969c7","year":null},{"cited_arxiv_id":"2503.04697","doi":"10.48550/arxiv.2503.04697","is_internal_anchor":true,"ref_index":5,"title":"L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning","work_id":"ad7236fb-3752-48a9-b782-a384899c45a0","year":null}],"snapshot_sha256":"1e5b013d5cda89c960531d62204d94226a0666c2a6d5024d24bb00b4b409fcbf"},"source":{"id":"2605.13641","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T19:20:34.498141Z","id":"31a9043e-c6f2-4445-b53d-1950b87a7d90","model_set":{"reader":"grok-4.3"},"one_line_summary":"RDPO applies magnitude-aware quantile normalization and Mahalanobis whitening to decorrelate heterogeneous rewards in multi-objective RL, improving instruction following and writing quality on LongCat-Flash post-training while staying competitive on reasoning and coding.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"RDPO stabilizes advantages in mixed-reward reinforcement learning by normalizing magnitudes and removing correlations before aggregation.","strongest_claim":"When applied during the post-training of LongCat-Flash, RDPO enhances instruction following, writing quality, and robustness to hard prompts while remaining broadly competitive on reasoning and coding evaluations.","weakest_assumption":"That magnitude-aware quantile normalization and Mahalanobis whitening will stabilize advantages across heterogeneous rewards without discarding critical signal or introducing new biases in the specific reward distributions of the LongCat-Flash training setup."}},"verdict_id":"31a9043e-c6f2-4445-b53d-1950b87a7d90"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:cd547f852bcdad3bcaf67cb737b8244945c0e3b3d136ce9d4717ddeec5aaccae","target":"record","created_at":"2026-05-18T02:44:17Z","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":"89ad6306ebae2e291fe2e899775f6b3612ffad186d089f93b57cdd1eaf0ce81c","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T15:05:18Z","title_canon_sha256":"25c79d2d6d192456412abfcc88c8bcbce2ae575bf3285c8a57a47d72c4c76ca3"},"schema_version":"1.0","source":{"id":"2605.13641","kind":"arxiv","version":1}},"canonical_sha256":"d7327f8b2e3b84a823b40a88674586996f0819a993e2e14038a9405da7ba7edf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d7327f8b2e3b84a823b40a88674586996f0819a993e2e14038a9405da7ba7edf","first_computed_at":"2026-05-18T02:44:17.603486Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:44:17.603486Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ezvoGmnOaWucUxs5maX02qkCX6LWkdPdWQm+/qtpyUafdnTVUzBDTtHZGdW+s0t9tgH7GzENJYcs85beLfDrBg==","signature_status":"signed_v1","signed_at":"2026-05-18T02:44:17.604038Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.13641","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cd547f852bcdad3bcaf67cb737b8244945c0e3b3d136ce9d4717ddeec5aaccae","sha256:d1f818d386fbf81586f884aa702dc978959ad96797b4662b30890459bbbf255c"],"state_sha256":"d5f4a43c46e555e86555b76de7ac9ef0cb176a57bf72d67ef7610f10180df4af"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o48C7gfW7mFSgi4WSleahkABPOZYQotUOZg6RqdzQXzxlrfgAy8cVVdMbt0tQ209pRHf2kLJ9rDcLUckAnOQCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T12:26:46.872982Z","bundle_sha256":"eac60ab5209144a47a4766bd5bf71ae526d5540fe019890534c55523d4aca807"}}