{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:LVPWXSGYEVADWFCGDBQYX7ZL5L","short_pith_number":"pith:LVPWXSGY","canonical_record":{"source":{"id":"2602.07458","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-02-07T09:23:34Z","cross_cats_sorted":[],"title_canon_sha256":"1b5d4237dc6f688e08f86957fa5d701d53ea0fa79ea55d2fde65d83d45a38ce0","abstract_canon_sha256":"858e2f5a747c75d8bd75320f8f48e4fc3f0a7e5cdc6e2a6ef6e7b75004144ea8"},"schema_version":"1.0"},"canonical_sha256":"5d5f6bc8d825403b144618618bff2bead30ec8155b6065932ba15832e9e355a8","source":{"kind":"arxiv","id":"2602.07458","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.07458","created_at":"2026-05-18T02:44:31Z"},{"alias_kind":"arxiv_version","alias_value":"2602.07458v4","created_at":"2026-05-18T02:44:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.07458","created_at":"2026-05-18T02:44:31Z"},{"alias_kind":"pith_short_12","alias_value":"LVPWXSGYEVAD","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"LVPWXSGYEVADWFCG","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"LVPWXSGY","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:LVPWXSGYEVADWFCGDBQYX7ZL5L","target":"record","payload":{"canonical_record":{"source":{"id":"2602.07458","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-02-07T09:23:34Z","cross_cats_sorted":[],"title_canon_sha256":"1b5d4237dc6f688e08f86957fa5d701d53ea0fa79ea55d2fde65d83d45a38ce0","abstract_canon_sha256":"858e2f5a747c75d8bd75320f8f48e4fc3f0a7e5cdc6e2a6ef6e7b75004144ea8"},"schema_version":"1.0"},"canonical_sha256":"5d5f6bc8d825403b144618618bff2bead30ec8155b6065932ba15832e9e355a8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:44:31.313550Z","signature_b64":"2b8or8nPl1VbxndHxGzi7gjFSX3UMo0+/oFE/PigAOyv+DT1X8uhXev3UTfyyj2nFDRvdNODu/zVlQagbloPCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d5f6bc8d825403b144618618bff2bead30ec8155b6065932ba15832e9e355a8","last_reissued_at":"2026-05-18T02:44:31.312988Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:44:31.312988Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2602.07458","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:44:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rnXjkFs0GN6cbMO7PqiJhSdOLiraB+CGwALrYfcslL/dsbChXXIMXxllKnnJPgEvH9wASsiphEJNjziRy8+aCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T00:34:45.876909Z"},"content_sha256":"a7e388a149be56f7cdd155ed54ed540b9b95b06ecee744c19ac7e7015665c093","schema_version":"1.0","event_id":"sha256:a7e388a149be56f7cdd155ed54ed540b9b95b06ecee744c19ac7e7015665c093"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:LVPWXSGYEVADWFCGDBQYX7ZL5L","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SpatialReward: Bridging the Perception Gap in Online RL for Image Editing via Explicit Spatial Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Anchoring rewards to predicted edit regions closes the perception gap in image editing RL","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Wen, Changyi Liu, Fan Yang, Han Li, Haonan Fan, Hongyang Wei, Jiankang Chen, Kaiyu Jiang, Kaiyu Tang, Shuo Yang, Tianke Zhang, Tingting Gao, Wei Chen, Yancheng Long, Yankai Yang","submitted_at":"2026-02-07T09:23:34Z","abstract_excerpt":"Online Reinforcement Learning (RL) offers a promising avenue for complex image editing but is currently constrained by the scarcity of reliable and fine-grained reward signals. Existing evaluators frequently struggle with a critical perception gap we term \"Attention Collapse,\" where models neglect cross-image comparisons and fail to capture fine-grained details, resulting in inaccurate perception and miscalibrated scores. To address these limitations, we propose SpatialReward, a reward model that enforces precise verification via explicit spatial reasoning. By anchoring reasoning to predicted "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"SpatialReward serves as a robust signal in online RL, boosting OmniGen2 by +0.90 on GEdit-Bench--surpassing the leading discriminative model and doubling the gain of GPT-4.1 (+0.45).","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That predicting edit regions and anchoring reasoning to them reliably grounds semantic judgments in pixel-level evidence without the prediction step introducing new errors that offset the gains.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"SpatialReward is a new reward model that grounds image edit evaluations in pixel-level spatial reasoning on predicted regions, achieving SOTA on benchmarks and doubling RL gains for OmniGen2.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Anchoring rewards to predicted edit regions closes the perception gap in image editing RL","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"c37e0bce4c6925394fa2bfaffdedf6bf090594c13379ef373ccad3e0141bc907"},"source":{"id":"2602.07458","kind":"arxiv","version":4},"verdict":{"id":"b41b4442-63f5-4b9e-b539-5dc62b07270e","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T06:30:28.074324Z","strongest_claim":"SpatialReward serves as a robust signal in online RL, boosting OmniGen2 by +0.90 on GEdit-Bench--surpassing the leading discriminative model and doubling the gain of GPT-4.1 (+0.45).","one_line_summary":"SpatialReward is a new reward model that grounds image edit evaluations in pixel-level spatial reasoning on predicted regions, achieving SOTA on benchmarks and doubling RL gains for OmniGen2.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That predicting edit regions and anchoring reasoning to them reliably grounds semantic judgments in pixel-level evidence without the prediction step introducing new errors that offset the gains.","pith_extraction_headline":"Anchoring rewards to predicted edit regions closes the perception gap in image editing RL"},"references":{"count":29,"sample":[{"doi":"","year":null,"title":"• Good: All edit operations in the instruction are perfectly executed","work_id":"5aa17261-390f-4938-a28d-cef6dfb44857","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"•Good: High fidelity, no visible artifacts","work_id":"bacec80f-ceaf-47cb-8122-ca37b79da335","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2017,"title":"Overall AestheticsA holistic assessment of the image’s visual appeal and harmony. annotators are instructed to judge solely based on the visual outcome: •Good: Visually pleasing, professional-looking ","work_id":"1626f568-15b7-4dd0-b7f8-0dce40250ee2","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Reward Model Interpretation(Section C.1): We analyze the internal attention mechanisms of SpatialReward to verify its reasoning logic and explain the metrics used for quantitative diagnosis","work_id":"339aea62-cb1a-4a16-ab1b-f02f812da550","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Policy Generation Results(Section C.2): We showcase additional qualitative comparisons of the downstream policy model (OmniGen2) trained via Online RL, demonstrating the effectiveness of our reward si","work_id":"638b3958-8a3c-4ec9-ad34-8fa2ace54285","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":29,"snapshot_sha256":"e392cd577fc150b4a5b1c8001342c906a09c3ebf0d7e37c97d5f8535a4ebb7c8","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"7fcad0284b9586149212dd74cd856be83c26e01c97febcea75a9cd92901d98e7"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"b41b4442-63f5-4b9e-b539-5dc62b07270e"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:44:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lWmMd/hZxGBKUwO1ZPo+iWtcZ4ZgwcHhn/2hgBmBdZKMW7ALJouxRIfibHuPkzb15PnNEjJqCdrQPPK/+qRPDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T00:34:45.877536Z"},"content_sha256":"01eb437db5635947242de2ec29b514caeacdd6fe84616adf1fd1854d115bbe81","schema_version":"1.0","event_id":"sha256:01eb437db5635947242de2ec29b514caeacdd6fe84616adf1fd1854d115bbe81"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LVPWXSGYEVADWFCGDBQYX7ZL5L/bundle.json","state_url":"https://pith.science/pith/LVPWXSGYEVADWFCGDBQYX7ZL5L/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LVPWXSGYEVADWFCGDBQYX7ZL5L/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":"2026-05-28T00:34:45Z","links":{"resolver":"https://pith.science/pith/LVPWXSGYEVADWFCGDBQYX7ZL5L","bundle":"https://pith.science/pith/LVPWXSGYEVADWFCGDBQYX7ZL5L/bundle.json","state":"https://pith.science/pith/LVPWXSGYEVADWFCGDBQYX7ZL5L/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LVPWXSGYEVADWFCGDBQYX7ZL5L/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:LVPWXSGYEVADWFCGDBQYX7ZL5L","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":"858e2f5a747c75d8bd75320f8f48e4fc3f0a7e5cdc6e2a6ef6e7b75004144ea8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-02-07T09:23:34Z","title_canon_sha256":"1b5d4237dc6f688e08f86957fa5d701d53ea0fa79ea55d2fde65d83d45a38ce0"},"schema_version":"1.0","source":{"id":"2602.07458","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.07458","created_at":"2026-05-18T02:44:31Z"},{"alias_kind":"arxiv_version","alias_value":"2602.07458v4","created_at":"2026-05-18T02:44:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.07458","created_at":"2026-05-18T02:44:31Z"},{"alias_kind":"pith_short_12","alias_value":"LVPWXSGYEVAD","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"LVPWXSGYEVADWFCG","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"LVPWXSGY","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:01eb437db5635947242de2ec29b514caeacdd6fe84616adf1fd1854d115bbe81","target":"graph","created_at":"2026-05-18T02:44:31Z","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":"SpatialReward serves as a robust signal in online RL, boosting OmniGen2 by +0.90 on GEdit-Bench--surpassing the leading discriminative model and doubling the gain of GPT-4.1 (+0.45)."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That predicting edit regions and anchoring reasoning to them reliably grounds semantic judgments in pixel-level evidence without the prediction step introducing new errors that offset the gains."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"SpatialReward is a new reward model that grounds image edit evaluations in pixel-level spatial reasoning on predicted regions, achieving SOTA on benchmarks and doubling RL gains for OmniGen2."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Anchoring rewards to predicted edit regions closes the perception gap in image editing RL"}],"snapshot_sha256":"c37e0bce4c6925394fa2bfaffdedf6bf090594c13379ef373ccad3e0141bc907"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"7fcad0284b9586149212dd74cd856be83c26e01c97febcea75a9cd92901d98e7"},"paper":{"abstract_excerpt":"Online Reinforcement Learning (RL) offers a promising avenue for complex image editing but is currently constrained by the scarcity of reliable and fine-grained reward signals. Existing evaluators frequently struggle with a critical perception gap we term \"Attention Collapse,\" where models neglect cross-image comparisons and fail to capture fine-grained details, resulting in inaccurate perception and miscalibrated scores. To address these limitations, we propose SpatialReward, a reward model that enforces precise verification via explicit spatial reasoning. By anchoring reasoning to predicted ","authors_text":"Bin Wen, Changyi Liu, Fan Yang, Han Li, Haonan Fan, Hongyang Wei, Jiankang Chen, Kaiyu Jiang, Kaiyu Tang, Shuo Yang, Tianke Zhang, Tingting Gao, Wei Chen, Yancheng Long, Yankai Yang","cross_cats":[],"headline":"Anchoring rewards to predicted edit regions closes the perception gap in image editing RL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-02-07T09:23:34Z","title":"SpatialReward: Bridging the Perception Gap in Online RL for Image Editing via Explicit Spatial Reasoning"},"references":{"count":29,"internal_anchors":0,"resolved_work":29,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"• Good: All edit operations in the instruction are perfectly executed","work_id":"5aa17261-390f-4938-a28d-cef6dfb44857","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"•Good: High fidelity, no visible artifacts","work_id":"bacec80f-ceaf-47cb-8122-ca37b79da335","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Overall AestheticsA holistic assessment of the image’s visual appeal and harmony. annotators are instructed to judge solely based on the visual outcome: •Good: Visually pleasing, professional-looking ","work_id":"1626f568-15b7-4dd0-b7f8-0dce40250ee2","year":2017},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Reward Model Interpretation(Section C.1): We analyze the internal attention mechanisms of SpatialReward to verify its reasoning logic and explain the metrics used for quantitative diagnosis","work_id":"339aea62-cb1a-4a16-ab1b-f02f812da550","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Policy Generation Results(Section C.2): We showcase additional qualitative comparisons of the downstream policy model (OmniGen2) trained via Online RL, demonstrating the effectiveness of our reward si","work_id":"638b3958-8a3c-4ec9-ad34-8fa2ace54285","year":null}],"snapshot_sha256":"e392cd577fc150b4a5b1c8001342c906a09c3ebf0d7e37c97d5f8535a4ebb7c8"},"source":{"id":"2602.07458","kind":"arxiv","version":4},"verdict":{"created_at":"2026-05-16T06:30:28.074324Z","id":"b41b4442-63f5-4b9e-b539-5dc62b07270e","model_set":{"reader":"grok-4.3"},"one_line_summary":"SpatialReward is a new reward model that grounds image edit evaluations in pixel-level spatial reasoning on predicted regions, achieving SOTA on benchmarks and doubling RL gains for OmniGen2.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Anchoring rewards to predicted edit regions closes the perception gap in image editing RL","strongest_claim":"SpatialReward serves as a robust signal in online RL, boosting OmniGen2 by +0.90 on GEdit-Bench--surpassing the leading discriminative model and doubling the gain of GPT-4.1 (+0.45).","weakest_assumption":"That predicting edit regions and anchoring reasoning to them reliably grounds semantic judgments in pixel-level evidence without the prediction step introducing new errors that offset the gains."}},"verdict_id":"b41b4442-63f5-4b9e-b539-5dc62b07270e"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a7e388a149be56f7cdd155ed54ed540b9b95b06ecee744c19ac7e7015665c093","target":"record","created_at":"2026-05-18T02:44:31Z","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":"858e2f5a747c75d8bd75320f8f48e4fc3f0a7e5cdc6e2a6ef6e7b75004144ea8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-02-07T09:23:34Z","title_canon_sha256":"1b5d4237dc6f688e08f86957fa5d701d53ea0fa79ea55d2fde65d83d45a38ce0"},"schema_version":"1.0","source":{"id":"2602.07458","kind":"arxiv","version":4}},"canonical_sha256":"5d5f6bc8d825403b144618618bff2bead30ec8155b6065932ba15832e9e355a8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5d5f6bc8d825403b144618618bff2bead30ec8155b6065932ba15832e9e355a8","first_computed_at":"2026-05-18T02:44:31.312988Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:44:31.312988Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2b8or8nPl1VbxndHxGzi7gjFSX3UMo0+/oFE/PigAOyv+DT1X8uhXev3UTfyyj2nFDRvdNODu/zVlQagbloPCg==","signature_status":"signed_v1","signed_at":"2026-05-18T02:44:31.313550Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.07458","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a7e388a149be56f7cdd155ed54ed540b9b95b06ecee744c19ac7e7015665c093","sha256:01eb437db5635947242de2ec29b514caeacdd6fe84616adf1fd1854d115bbe81"],"state_sha256":"ec34737a59f2a54112d37bb18a5c730e13842eb63f5d139300fe8ffea1f9c1dd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wHdF45apPfcXNKnURmTUPFSwtEXdA9GAPBnJlzVEOZbgxdklti07ZzgUd9nV9KSuo8fjCJB2iDp+oLfIO1hJCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T00:34:45.880174Z","bundle_sha256":"4e5744bfb0d8a081a69466b4cf55cccb401d944de141e190f3b0244664aca4be"}}