{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:LCZRWHLVQOD7G6MAGDQKCR7PDO","short_pith_number":"pith:LCZRWHLV","canonical_record":{"source":{"id":"2503.01307","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-03T08:46:22Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5c72c80b98692a5792570317ad7d7dd3867bafe3f7650e1d3249552d881d6454","abstract_canon_sha256":"e80df4aaa9bea370f731c3395f6612069d2591cace4f314da6bfa0033140542e"},"schema_version":"1.0"},"canonical_sha256":"58b31b1d758387f3798030e0a147ef1b8ed31dea4ab980832468b55b95f50230","source":{"kind":"arxiv","id":"2503.01307","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.01307","created_at":"2026-05-17T23:38:14Z"},{"alias_kind":"arxiv_version","alias_value":"2503.01307v2","created_at":"2026-05-17T23:38:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.01307","created_at":"2026-05-17T23:38:14Z"},{"alias_kind":"pith_short_12","alias_value":"LCZRWHLVQOD7","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"LCZRWHLVQOD7G6MA","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"LCZRWHLV","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:LCZRWHLVQOD7G6MAGDQKCR7PDO","target":"record","payload":{"canonical_record":{"source":{"id":"2503.01307","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-03T08:46:22Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5c72c80b98692a5792570317ad7d7dd3867bafe3f7650e1d3249552d881d6454","abstract_canon_sha256":"e80df4aaa9bea370f731c3395f6612069d2591cace4f314da6bfa0033140542e"},"schema_version":"1.0"},"canonical_sha256":"58b31b1d758387f3798030e0a147ef1b8ed31dea4ab980832468b55b95f50230","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:14.216996Z","signature_b64":"ig+cVdH+98EHiy2FGhAiwRtc5ll2ngS/VYNi5Bkt6kFCiSf6bfWgQKP+mfntgktShEZ4zYJN+eF8Cr/VNhx+Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58b31b1d758387f3798030e0a147ef1b8ed31dea4ab980832468b55b95f50230","last_reissued_at":"2026-05-17T23:38:14.216463Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:14.216463Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.01307","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":"2026-05-17T23:38:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7M8MEhLGJwHDTEideeUMtsEy5QUFcuCkz2xG2q9CCpqlaCFyIVl/DrrNUW9dyoS/E8SdfSixx7Oi3SkLLvk+AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T13:54:31.783552Z"},"content_sha256":"5d264a706d9622be299faa274c0d21135e638a54bc80996f1417a1b412a3aeac","schema_version":"1.0","event_id":"sha256:5d264a706d9622be299faa274c0d21135e638a54bc80996f1417a1b412a3aeac"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:LCZRWHLVQOD7G6MAGDQKCR7PDO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Language models self-improve under RL when they already use reasoning behaviors like verification and backtracking, even if answers start wrong.","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Anikait Singh, Ayush Chakravarthy, Kanishk Gandhi, Nathan Lile, Noah D. Goodman","submitted_at":"2025-03-03T08:46:22Z","abstract_excerpt":"Test-time inference has emerged as a powerful paradigm for enabling language models to ``think'' longer and more carefully about complex challenges, much like skilled human experts. While reinforcement learning (RL) can drive self-improvement in language models on verifiable tasks, some models exhibit substantial gains while others quickly plateau. For instance, we find that Qwen-2.5-3B far exceeds Llama-3.2-3B under identical RL training for the game of Countdown. This discrepancy raises a critical question: what intrinsic properties enable effective self-improvement? We introduce a framework"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"the presence of reasoning behaviors, rather than correctness of answers, proves to be the critical factor -- models primed with incorrect solutions containing proper reasoning patterns achieve comparable performance to those trained on correct solutions.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the four identified cognitive behaviors are the primary causal drivers of self-improvement differences, and that the controlled priming experiments isolate their effect without confounding influences from model architecture, training history, or unmeasured variables.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Language models that naturally exhibit verification, backtracking, subgoal setting, and backward chaining improve substantially during RL on verifiable tasks, and these behaviors can be instilled via priming with reasoning-focused examples or filtered pretraining to enable self-improvement.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Language models self-improve under RL when they already use reasoning behaviors like verification and backtracking, even if answers start wrong.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"b3b7f7ed2aee6989940632b64d448131598ff90e729b43e131a4114ab3d29fe4"},"source":{"id":"2503.01307","kind":"arxiv","version":2},"verdict":{"id":"d32bc172-cd96-443c-8f1d-e4c9ed08c525","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-17T11:35:31.116346Z","strongest_claim":"the presence of reasoning behaviors, rather than correctness of answers, proves to be the critical factor -- models primed with incorrect solutions containing proper reasoning patterns achieve comparable performance to those trained on correct solutions.","one_line_summary":"Language models that naturally exhibit verification, backtracking, subgoal setting, and backward chaining improve substantially during RL on verifiable tasks, and these behaviors can be instilled via priming with reasoning-focused examples or filtered pretraining to enable self-improvement.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the four identified cognitive behaviors are the primary causal drivers of self-improvement differences, and that the controlled priming experiments isolate their effect without confounding influences from model architecture, training history, or unmeasured variables.","pith_extraction_headline":"Language models self-improve under RL when they already use reasoning behaviors like verification and backtracking, even if answers start wrong."},"references":{"count":13,"sample":[{"doi":"","year":2024,"title":"REINFORCE++: Stabilizing Critic-Free Policy Optimization with Global Advantage Normalization","work_id":"557f9e99-cb00-4dd2-92fd-67ddcddbb35d","ref_index":1,"cited_arxiv_id":"2501.03262","is_internal_anchor":true},{"doi":"10.1007/bf00992696","year":1971,"title":"Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters","work_id":"a8d50b24-bdf5-46ed-bc4f-2927dfd81f1d","ref_index":2,"cited_arxiv_id":"2408.03314","is_internal_anchor":true},{"doi":"","year":null,"title":"Backtracking Only: This dataset focuses exclusively on the backtracking strategy, where the model explores solution paths and retreats when encountering dead ends","work_id":"f16db8fe-855e-4c6c-a8fa-f1b9b2d94974","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Backtracking with Answer Verification: In addition to backtracking, this dataset incorporates answer verification, where the model checks its intermediate solutions with the target number","work_id":"21872aad-715f-42df-b5f6-c07cc9b3f044","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Backtracking with Subgoal Setting: This dataset combines backtracking with explicit subgoal setting, where the model breaks down complex problems into manageable intermediate steps","work_id":"6ed3f964-44b3-49d8-9995-34339ece07bc","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":13,"snapshot_sha256":"d2d6933031d2432c2eabe21412e254ed5ecfd3aff4e4e56a5ba08b58f7538823","internal_anchors":2},"formal_canon":{"evidence_count":2,"snapshot_sha256":"854cd3056e3b064c23e435fb4997486e49c6b91dacf8af2db1acc702d7ea385b"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"d32bc172-cd96-443c-8f1d-e4c9ed08c525"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"05rPIkM6i7oeLXBtWKjcSIkmjgoNoJFnO0Blwma/SF1IsFcXkDQk6xHb44i5bkuDwq2SsXqH9ZqkA16SsDdQAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T13:54:31.784084Z"},"content_sha256":"99e65cc261a38ff6eda8e5f705becb46fc733ce65e49fffcdcdf9c0afb6554a4","schema_version":"1.0","event_id":"sha256:99e65cc261a38ff6eda8e5f705becb46fc733ce65e49fffcdcdf9c0afb6554a4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LCZRWHLVQOD7G6MAGDQKCR7PDO/bundle.json","state_url":"https://pith.science/pith/LCZRWHLVQOD7G6MAGDQKCR7PDO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LCZRWHLVQOD7G6MAGDQKCR7PDO/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":"2026-05-28T13:54:31Z","links":{"resolver":"https://pith.science/pith/LCZRWHLVQOD7G6MAGDQKCR7PDO","bundle":"https://pith.science/pith/LCZRWHLVQOD7G6MAGDQKCR7PDO/bundle.json","state":"https://pith.science/pith/LCZRWHLVQOD7G6MAGDQKCR7PDO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LCZRWHLVQOD7G6MAGDQKCR7PDO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LCZRWHLVQOD7G6MAGDQKCR7PDO","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":"e80df4aaa9bea370f731c3395f6612069d2591cace4f314da6bfa0033140542e","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-03T08:46:22Z","title_canon_sha256":"5c72c80b98692a5792570317ad7d7dd3867bafe3f7650e1d3249552d881d6454"},"schema_version":"1.0","source":{"id":"2503.01307","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.01307","created_at":"2026-05-17T23:38:14Z"},{"alias_kind":"arxiv_version","alias_value":"2503.01307v2","created_at":"2026-05-17T23:38:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.01307","created_at":"2026-05-17T23:38:14Z"},{"alias_kind":"pith_short_12","alias_value":"LCZRWHLVQOD7","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"LCZRWHLVQOD7G6MA","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"LCZRWHLV","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:99e65cc261a38ff6eda8e5f705becb46fc733ce65e49fffcdcdf9c0afb6554a4","target":"graph","created_at":"2026-05-17T23:38:14Z","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":"the presence of reasoning behaviors, rather than correctness of answers, proves to be the critical factor -- models primed with incorrect solutions containing proper reasoning patterns achieve comparable performance to those trained on correct solutions."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the four identified cognitive behaviors are the primary causal drivers of self-improvement differences, and that the controlled priming experiments isolate their effect without confounding influences from model architecture, training history, or unmeasured variables."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Language models that naturally exhibit verification, backtracking, subgoal setting, and backward chaining improve substantially during RL on verifiable tasks, and these behaviors can be instilled via priming with reasoning-focused examples or filtered pretraining to enable self-improvement."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Language models self-improve under RL when they already use reasoning behaviors like verification and backtracking, even if answers start wrong."}],"snapshot_sha256":"b3b7f7ed2aee6989940632b64d448131598ff90e729b43e131a4114ab3d29fe4"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"854cd3056e3b064c23e435fb4997486e49c6b91dacf8af2db1acc702d7ea385b"},"paper":{"abstract_excerpt":"Test-time inference has emerged as a powerful paradigm for enabling language models to ``think'' longer and more carefully about complex challenges, much like skilled human experts. While reinforcement learning (RL) can drive self-improvement in language models on verifiable tasks, some models exhibit substantial gains while others quickly plateau. For instance, we find that Qwen-2.5-3B far exceeds Llama-3.2-3B under identical RL training for the game of Countdown. This discrepancy raises a critical question: what intrinsic properties enable effective self-improvement? We introduce a framework","authors_text":"Anikait Singh, Ayush Chakravarthy, Kanishk Gandhi, Nathan Lile, Noah D. Goodman","cross_cats":["cs.LG"],"headline":"Language models self-improve under RL when they already use reasoning behaviors like verification and backtracking, even if answers start wrong.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-03T08:46:22Z","title":"Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs"},"references":{"count":13,"internal_anchors":2,"resolved_work":13,"sample":[{"cited_arxiv_id":"2501.03262","doi":"","is_internal_anchor":true,"ref_index":1,"title":"REINFORCE++: Stabilizing Critic-Free Policy Optimization with Global Advantage Normalization","work_id":"557f9e99-cb00-4dd2-92fd-67ddcddbb35d","year":2024},{"cited_arxiv_id":"2408.03314","doi":"10.1007/bf00992696","is_internal_anchor":true,"ref_index":2,"title":"Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters","work_id":"a8d50b24-bdf5-46ed-bc4f-2927dfd81f1d","year":1971},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Backtracking Only: This dataset focuses exclusively on the backtracking strategy, where the model explores solution paths and retreats when encountering dead ends","work_id":"f16db8fe-855e-4c6c-a8fa-f1b9b2d94974","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Backtracking with Answer Verification: In addition to backtracking, this dataset incorporates answer verification, where the model checks its intermediate solutions with the target number","work_id":"21872aad-715f-42df-b5f6-c07cc9b3f044","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Backtracking with Subgoal Setting: This dataset combines backtracking with explicit subgoal setting, where the model breaks down complex problems into manageable intermediate steps","work_id":"6ed3f964-44b3-49d8-9995-34339ece07bc","year":null}],"snapshot_sha256":"d2d6933031d2432c2eabe21412e254ed5ecfd3aff4e4e56a5ba08b58f7538823"},"source":{"id":"2503.01307","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-17T11:35:31.116346Z","id":"d32bc172-cd96-443c-8f1d-e4c9ed08c525","model_set":{"reader":"grok-4.3"},"one_line_summary":"Language models that naturally exhibit verification, backtracking, subgoal setting, and backward chaining improve substantially during RL on verifiable tasks, and these behaviors can be instilled via priming with reasoning-focused examples or filtered pretraining to enable self-improvement.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Language models self-improve under RL when they already use reasoning behaviors like verification and backtracking, even if answers start wrong.","strongest_claim":"the presence of reasoning behaviors, rather than correctness of answers, proves to be the critical factor -- models primed with incorrect solutions containing proper reasoning patterns achieve comparable performance to those trained on correct solutions.","weakest_assumption":"That the four identified cognitive behaviors are the primary causal drivers of self-improvement differences, and that the controlled priming experiments isolate their effect without confounding influences from model architecture, training history, or unmeasured variables."}},"verdict_id":"d32bc172-cd96-443c-8f1d-e4c9ed08c525"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5d264a706d9622be299faa274c0d21135e638a54bc80996f1417a1b412a3aeac","target":"record","created_at":"2026-05-17T23:38:14Z","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":"e80df4aaa9bea370f731c3395f6612069d2591cace4f314da6bfa0033140542e","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-03T08:46:22Z","title_canon_sha256":"5c72c80b98692a5792570317ad7d7dd3867bafe3f7650e1d3249552d881d6454"},"schema_version":"1.0","source":{"id":"2503.01307","kind":"arxiv","version":2}},"canonical_sha256":"58b31b1d758387f3798030e0a147ef1b8ed31dea4ab980832468b55b95f50230","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"58b31b1d758387f3798030e0a147ef1b8ed31dea4ab980832468b55b95f50230","first_computed_at":"2026-05-17T23:38:14.216463Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:14.216463Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ig+cVdH+98EHiy2FGhAiwRtc5ll2ngS/VYNi5Bkt6kFCiSf6bfWgQKP+mfntgktShEZ4zYJN+eF8Cr/VNhx+Ag==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:14.216996Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.01307","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5d264a706d9622be299faa274c0d21135e638a54bc80996f1417a1b412a3aeac","sha256:99e65cc261a38ff6eda8e5f705becb46fc733ce65e49fffcdcdf9c0afb6554a4"],"state_sha256":"e32bd0b71a0cec471d67f7b8ef3cdbced4f46204cc9e5345b0392c3182d7698e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nMy1CZVHJTSbmJYXVmFf4M+u2LvYpJRiHBQr06qtjDjsw3DpwHpZTNDp+Qw1lsmIUtPW78eGRfe6npOZYJxnAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T13:54:31.786704Z","bundle_sha256":"588cf3bef4e3ed5bed0960824933d613e1b91cffcddcaeac88c701df4635d712"}}