{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:UJZQGCVY76UO2YERCCMIJ5KDJZ","short_pith_number":"pith:UJZQGCVY","canonical_record":{"source":{"id":"2412.13877","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-12-18T14:17:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e41524d351c8f6fb1edfb3e3cc66934c619045f0693e88813b6e2421fe6ccfe0","abstract_canon_sha256":"ee85b764b915c8a18ced5e4e44e65f1dc1cb20057358023cc558d160b23b0e93"},"schema_version":"1.0"},"canonical_sha256":"a273030ab8ffa8ed6091109884f5434e4b456ce207197e0eda640336fee9c895","source":{"kind":"arxiv","id":"2412.13877","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.13877","created_at":"2026-05-17T23:38:49Z"},{"alias_kind":"arxiv_version","alias_value":"2412.13877v3","created_at":"2026-05-17T23:38:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.13877","created_at":"2026-05-17T23:38:49Z"},{"alias_kind":"pith_short_12","alias_value":"UJZQGCVY76UO","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"UJZQGCVY76UO2YER","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"UJZQGCVY","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:UJZQGCVY76UO2YERCCMIJ5KDJZ","target":"record","payload":{"canonical_record":{"source":{"id":"2412.13877","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-12-18T14:17:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e41524d351c8f6fb1edfb3e3cc66934c619045f0693e88813b6e2421fe6ccfe0","abstract_canon_sha256":"ee85b764b915c8a18ced5e4e44e65f1dc1cb20057358023cc558d160b23b0e93"},"schema_version":"1.0"},"canonical_sha256":"a273030ab8ffa8ed6091109884f5434e4b456ce207197e0eda640336fee9c895","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:49.980466Z","signature_b64":"TGcPPsqlziYlIpA0TmemmQC6Mfn1OZJinFBmVgrTzFnt23cFnbfTy6rnTaqyH9/MPqG0rwdAhLcZraITzCBXBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a273030ab8ffa8ed6091109884f5434e4b456ce207197e0eda640336fee9c895","last_reissued_at":"2026-05-17T23:38:49.979445Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:49.979445Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.13877","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"InkZQYUxMKhSd9gwgU3VqkMB7EJFdVKjHzYEsW5s+tS+JtAfXsIaHCJlRHSCTZlmtGsxPuzopf5PxqFO1MseBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T22:57:57.937691Z"},"content_sha256":"3079940759978f8dbfb2c4751fa4fb096003ae5bcea71b1a032ad1883d2a8d3c","schema_version":"1.0","event_id":"sha256:3079940759978f8dbfb2c4751fa4fb096003ae5bcea71b1a032ad1883d2a8d3c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:UJZQGCVY76UO2YERCCMIJ5KDJZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RoboMIND: Benchmark on Multi-embodiment Intelligence Normative Data for Robot Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"RoboMIND supplies 107k teleoperated trajectories across four robot embodiments to train generalizable manipulation policies.","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Chengkai Hou, Chenxuan Li, Chenyang Gu, Di Wu, Fei Liao, Guang Yang, Guangyu Li, Jiaming Liu, Jian Tang, Jilei Mao, Jingyang He, Kun Wu, Lecheng Wang, Meng Li, Mengzhen Liu, Ning Liu, Pei Ren, Pengju An, Qiang Zhang, Shanghang Zhang, Shichao Fan, Sixiang Chen, Siyuan Qian, Xiaozhu Ju, Xingyu Wang, Xinhua Wang, Yankai Fu, Yaoxu Lyu, Yinuo Zhao, Yulin Luo, Zeyu Gao, Zhao Jin, Zhengping Che, Zhenyu Wang, Zhen Zhao, Zhiyuan Xu, Zhuqin Yang","submitted_at":"2024-12-18T14:17:16Z","abstract_excerpt":"In this paper, we introduce RoboMIND (Multi-embodiment Intelligence Normative Data for Robot Manipulation), a dataset containing 107k demonstration trajectories across 479 diverse tasks involving 96 object classes. RoboMIND is collected through human teleoperation and encompasses comprehensive robotic-related information, including multi-view observations, proprioceptive robot state information, and linguistic task descriptions. To ensure data consistency and reliability for imitation learning, RoboMIND is built on a unified data collection platform and a standardized protocol, covering four d"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"To the best of our knowledge, RoboMIND is the largest multi-embodiment teleoperation dataset collected on a unified platform, providing large-scale and high-quality robotic training data.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That demonstrations collected via human teleoperation on a single unified platform, together with the recorded failure cases, are sufficient in quality and coverage to train policies that generalize across embodiments and to unseen real-world conditions.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"RoboMIND is a large-scale multi-embodiment teleoperation dataset for robot manipulation containing 107k trajectories across four robots, with failure annotations and a digital twin simulator.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"RoboMIND supplies 107k teleoperated trajectories across four robot embodiments to train generalizable manipulation policies.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"02f5da766fef73f8c93c3887b97a33b3fdb699ffb3af15f633f35dfec638ba3d"},"source":{"id":"2412.13877","kind":"arxiv","version":3},"verdict":{"id":"0aeda771-c8d3-461d-ab6c-a4312d4b7c97","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T22:09:44.467479Z","strongest_claim":"To the best of our knowledge, RoboMIND is the largest multi-embodiment teleoperation dataset collected on a unified platform, providing large-scale and high-quality robotic training data.","one_line_summary":"RoboMIND is a large-scale multi-embodiment teleoperation dataset for robot manipulation containing 107k trajectories across four robots, with failure annotations and a digital twin simulator.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That demonstrations collected via human teleoperation on a single unified platform, together with the recorded failure cases, are sufficient in quality and coverage to train policies that generalize across embodiments and to unseen real-world conditions.","pith_extraction_headline":"RoboMIND supplies 107k teleoperated trajectories across four robot embodiments to train generalizable manipulation policies."},"references":{"count":118,"sample":[{"doi":"","year":2023,"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","ref_index":1,"cited_arxiv_id":"2303.08774","is_internal_anchor":true},{"doi":"","year":2023,"title":"Do as i can, not as i say: Grounding language in robotic affordances","work_id":"fc4809fb-0879-4ce4-9788-114e512e0cdd","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2020,"title":"Learning dexterous in-hand manipula- tion","work_id":"7401fffe-c123-4b9f-988f-4910ef644447","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models","work_id":"87bfa84a-e663-4165-806f-93ef439d88d0","ref_index":4,"cited_arxiv_id":"2308.01390","is_internal_anchor":true},{"doi":"","year":2023,"title":"Affordances from human videos as a versatile representation for robotics","work_id":"b304b1d8-62ac-4d6f-b661-13b44adf5b8c","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":118,"snapshot_sha256":"1c7c2a9ec48b66bf98f04a3888329bc0ea05d16559d200ee5c68f878ed85da5e","internal_anchors":9},"formal_canon":{"evidence_count":2,"snapshot_sha256":"93548622fb43281f8ae48f6f5b6cdf7bed9f2ecd4a5493091904b9be94bd22ab"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"0aeda771-c8d3-461d-ab6c-a4312d4b7c97"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RX7XqnpV4/7TxubCfzt9CMkrQ7VXlcR5FFVe+rDx0bFYl0+7LPGnEDuKh9jDvbFY1m1r9hsL8aK5RRU1xGd2DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T22:57:57.938714Z"},"content_sha256":"f4928979f4f3edf266d7dd72bae55d3076e447013c4681cbb3048668838069fb","schema_version":"1.0","event_id":"sha256:f4928979f4f3edf266d7dd72bae55d3076e447013c4681cbb3048668838069fb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UJZQGCVY76UO2YERCCMIJ5KDJZ/bundle.json","state_url":"https://pith.science/pith/UJZQGCVY76UO2YERCCMIJ5KDJZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UJZQGCVY76UO2YERCCMIJ5KDJZ/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":"2026-05-27T22:57:57Z","links":{"resolver":"https://pith.science/pith/UJZQGCVY76UO2YERCCMIJ5KDJZ","bundle":"https://pith.science/pith/UJZQGCVY76UO2YERCCMIJ5KDJZ/bundle.json","state":"https://pith.science/pith/UJZQGCVY76UO2YERCCMIJ5KDJZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UJZQGCVY76UO2YERCCMIJ5KDJZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UJZQGCVY76UO2YERCCMIJ5KDJZ","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":"ee85b764b915c8a18ced5e4e44e65f1dc1cb20057358023cc558d160b23b0e93","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-12-18T14:17:16Z","title_canon_sha256":"e41524d351c8f6fb1edfb3e3cc66934c619045f0693e88813b6e2421fe6ccfe0"},"schema_version":"1.0","source":{"id":"2412.13877","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.13877","created_at":"2026-05-17T23:38:49Z"},{"alias_kind":"arxiv_version","alias_value":"2412.13877v3","created_at":"2026-05-17T23:38:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.13877","created_at":"2026-05-17T23:38:49Z"},{"alias_kind":"pith_short_12","alias_value":"UJZQGCVY76UO","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"UJZQGCVY76UO2YER","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"UJZQGCVY","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:f4928979f4f3edf266d7dd72bae55d3076e447013c4681cbb3048668838069fb","target":"graph","created_at":"2026-05-17T23:38:49Z","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":"To the best of our knowledge, RoboMIND is the largest multi-embodiment teleoperation dataset collected on a unified platform, providing large-scale and high-quality robotic training data."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That demonstrations collected via human teleoperation on a single unified platform, together with the recorded failure cases, are sufficient in quality and coverage to train policies that generalize across embodiments and to unseen real-world conditions."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"RoboMIND is a large-scale multi-embodiment teleoperation dataset for robot manipulation containing 107k trajectories across four robots, with failure annotations and a digital twin simulator."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"RoboMIND supplies 107k teleoperated trajectories across four robot embodiments to train generalizable manipulation policies."}],"snapshot_sha256":"02f5da766fef73f8c93c3887b97a33b3fdb699ffb3af15f633f35dfec638ba3d"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"93548622fb43281f8ae48f6f5b6cdf7bed9f2ecd4a5493091904b9be94bd22ab"},"paper":{"abstract_excerpt":"In this paper, we introduce RoboMIND (Multi-embodiment Intelligence Normative Data for Robot Manipulation), a dataset containing 107k demonstration trajectories across 479 diverse tasks involving 96 object classes. RoboMIND is collected through human teleoperation and encompasses comprehensive robotic-related information, including multi-view observations, proprioceptive robot state information, and linguistic task descriptions. To ensure data consistency and reliability for imitation learning, RoboMIND is built on a unified data collection platform and a standardized protocol, covering four d","authors_text":"Chengkai Hou, Chenxuan Li, Chenyang Gu, Di Wu, Fei Liao, Guang Yang, Guangyu Li, Jiaming Liu, Jian Tang, Jilei Mao, Jingyang He, Kun Wu, Lecheng Wang, Meng Li, Mengzhen Liu, Ning Liu, Pei Ren, Pengju An, Qiang Zhang, Shanghang Zhang, Shichao Fan, Sixiang Chen, Siyuan Qian, Xiaozhu Ju, Xingyu Wang, Xinhua Wang, Yankai Fu, Yaoxu Lyu, Yinuo Zhao, Yulin Luo, Zeyu Gao, Zhao Jin, Zhengping Che, Zhenyu Wang, Zhen Zhao, Zhiyuan Xu, Zhuqin Yang","cross_cats":["cs.AI"],"headline":"RoboMIND supplies 107k teleoperated trajectories across four robot embodiments to train generalizable manipulation policies.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-12-18T14:17:16Z","title":"RoboMIND: Benchmark on Multi-embodiment Intelligence Normative Data for Robot Manipulation"},"references":{"count":118,"internal_anchors":9,"resolved_work":118,"sample":[{"cited_arxiv_id":"2303.08774","doi":"","is_internal_anchor":true,"ref_index":1,"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Do as i can, not as i say: Grounding language in robotic affordances","work_id":"fc4809fb-0879-4ce4-9788-114e512e0cdd","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Learning dexterous in-hand manipula- tion","work_id":"7401fffe-c123-4b9f-988f-4910ef644447","year":2020},{"cited_arxiv_id":"2308.01390","doi":"","is_internal_anchor":true,"ref_index":4,"title":"OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models","work_id":"87bfa84a-e663-4165-806f-93ef439d88d0","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Affordances from human videos as a versatile representation for robotics","work_id":"b304b1d8-62ac-4d6f-b661-13b44adf5b8c","year":2023}],"snapshot_sha256":"1c7c2a9ec48b66bf98f04a3888329bc0ea05d16559d200ee5c68f878ed85da5e"},"source":{"id":"2412.13877","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-15T22:09:44.467479Z","id":"0aeda771-c8d3-461d-ab6c-a4312d4b7c97","model_set":{"reader":"grok-4.3"},"one_line_summary":"RoboMIND is a large-scale multi-embodiment teleoperation dataset for robot manipulation containing 107k trajectories across four robots, with failure annotations and a digital twin simulator.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"RoboMIND supplies 107k teleoperated trajectories across four robot embodiments to train generalizable manipulation policies.","strongest_claim":"To the best of our knowledge, RoboMIND is the largest multi-embodiment teleoperation dataset collected on a unified platform, providing large-scale and high-quality robotic training data.","weakest_assumption":"That demonstrations collected via human teleoperation on a single unified platform, together with the recorded failure cases, are sufficient in quality and coverage to train policies that generalize across embodiments and to unseen real-world conditions."}},"verdict_id":"0aeda771-c8d3-461d-ab6c-a4312d4b7c97"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:3079940759978f8dbfb2c4751fa4fb096003ae5bcea71b1a032ad1883d2a8d3c","target":"record","created_at":"2026-05-17T23:38:49Z","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":"ee85b764b915c8a18ced5e4e44e65f1dc1cb20057358023cc558d160b23b0e93","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-12-18T14:17:16Z","title_canon_sha256":"e41524d351c8f6fb1edfb3e3cc66934c619045f0693e88813b6e2421fe6ccfe0"},"schema_version":"1.0","source":{"id":"2412.13877","kind":"arxiv","version":3}},"canonical_sha256":"a273030ab8ffa8ed6091109884f5434e4b456ce207197e0eda640336fee9c895","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a273030ab8ffa8ed6091109884f5434e4b456ce207197e0eda640336fee9c895","first_computed_at":"2026-05-17T23:38:49.979445Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:49.979445Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TGcPPsqlziYlIpA0TmemmQC6Mfn1OZJinFBmVgrTzFnt23cFnbfTy6rnTaqyH9/MPqG0rwdAhLcZraITzCBXBg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:49.980466Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.13877","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3079940759978f8dbfb2c4751fa4fb096003ae5bcea71b1a032ad1883d2a8d3c","sha256:f4928979f4f3edf266d7dd72bae55d3076e447013c4681cbb3048668838069fb"],"state_sha256":"b33343da2757f65382a83ada81f4ad875ff56817cb991e64df92f19cf247043c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fzRUlXkkvEZxVYD3YGd4HTsEIxZ7AkMjRVo2+XyPYFzAk2aLf4ebX52MRvqBYJtRCNxYk3bppBbr8IjRtsIHAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T22:57:57.942978Z","bundle_sha256":"86d168377be78b9b47f3f40bb96c3975effa09e5f29c08eb110028321ecaa53c"}}