{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:WV2OW65AL2ZT7KUQVQ3C4KDC2C","short_pith_number":"pith:WV2OW65A","canonical_record":{"source":{"id":"2605.15153","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-14T17:50:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fbc61c28e0d7ad856aadcfdb063e0eb80407214c812b41febe2e76c06e74670d","abstract_canon_sha256":"1302cfeabe73feb2bf15a2c473d647c5a45cf2e070559a1f3b1945f1e6d588d5"},"schema_version":"1.0"},"canonical_sha256":"b574eb7ba05eb33faa90ac362e2862d084a56dab2b458c1a79efcfc14f10cedb","source":{"kind":"arxiv","id":"2605.15153","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15153","created_at":"2026-05-17T21:18:33Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15153v1","created_at":"2026-05-17T21:18:33Z"},{"alias_kind":"pith_short_12","alias_value":"WV2OW65AL2ZT","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"WV2OW65AL2ZT7KUQ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"WV2OW65A","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:WV2OW65AL2ZT7KUQVQ3C4KDC2C","target":"record","payload":{"canonical_record":{"source":{"id":"2605.15153","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-14T17:50:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fbc61c28e0d7ad856aadcfdb063e0eb80407214c812b41febe2e76c06e74670d","abstract_canon_sha256":"1302cfeabe73feb2bf15a2c473d647c5a45cf2e070559a1f3b1945f1e6d588d5"},"schema_version":"1.0"},"canonical_sha256":"b574eb7ba05eb33faa90ac362e2862d084a56dab2b458c1a79efcfc14f10cedb","receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.2","canonical_sha256":"b574eb7ba05eb33faa90ac362e2862d084a56dab2b458c1a79efcfc14f10cedb","last_reissued_at":"2026-05-17T21:57:18.779538Z","signature_status":"unsigned_v0","first_computed_at":"2026-05-17T21:40:25.459139Z"},"source_kind":"arxiv","source_id":"2605.15153","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":"2026-05-17T21:18:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zgSQkCVUJR7Ib2RlpJ9EYnGM+Ue78WI5+/bC+VqSQg3VFP3S13P3jOYkAtNtBSCq0tei7y/EdccARyhzigDnBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T19:09:36.721115Z"},"content_sha256":"61f32ec3aa099bf5381e27cbded1aa34ff58ce120022b2c3c484b48269a98732","schema_version":"1.0","event_id":"sha256:61f32ec3aa099bf5381e27cbded1aa34ff58ce120022b2c3c484b48269a98732"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:WV2OW65AL2ZT7KUQVQ3C4KDC2C","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Pelican-Unified 1.0: A Unified Embodied Intelligence Model for Understanding, Reasoning, Imagination and Action","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A single VLM-based model unifies understanding, reasoning, imagination, and action in one checkpoint without performance trade-offs.","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Che Liu, Haosong Sun, Haoyuan Shi, Jian Tang, Jiayu Hu, Jinpeng Lu, Jin Xu, Junwei Liao, Kuishu Wu, Nga Teng Chan, Renwen Cui, Senkang Hu, Shilong Zou, Wenhai Liu, Xiancong Ren, Xiaopeng Zhang, Xiaozhu Ju, Yang Xu, Yechen Wu, Yechi Liu, Yidong Wang, Yinda Chen, Yingji Zhang, Yi Zhang, Yong Dai, Zecong Tang, Zeyuan Ding","submitted_at":"2026-05-14T17:50:42Z","abstract_excerpt":"We present Pelican-Unified 1.0, the first embodied foundation model trained according to the principle of unification. Pelican-Unified 1.0 uses a single VLM as a unified understanding module, mapping scenes, instructions, visual contexts, and action histories into a shared semantic space. The same VLM also serves as a unified reasoning module, autoregressively producing task-, action-, and future-oriented chains of thought in a single forward pass and projecting the final hidden state into a dense latent variable. A Unified Future Generator (UFG) then conditions on this latent variable and joi"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"With a single checkpoint, Pelican-Unified 1.0 achieves strong performance across all three capabilities: 64.7 on eight VLM benchmarks, the best among comparable-scale models; 66.03 on WorldArena, ranking first; and 93.5 on RoboTwin, the second-best average among compared action methods.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That joint back-propagation of language, video, and action losses into a shared VLM representation produces a model whose performance on each capability matches or exceeds separately trained specialist systems without hidden trade-offs or benchmark-specific tuning.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Pelican-Unified 1.0 trains a single VLM plus Unified Future Generator to jointly optimize understanding, reasoning, future video prediction, and action generation, reporting top-tier scores on VLM, WorldArena, and RoboTwin benchmarks.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A single VLM-based model unifies understanding, reasoning, imagination, and action in one checkpoint without performance trade-offs.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"08393091868655406e54b8ed37d048bc664e2a9d817cccbfcfedfe36307d42f2"},"source":{"id":"2605.15153","kind":"arxiv","version":1},"verdict":{"id":"2310873e-7c3a-4f20-b060-90ec6526b74a","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T03:10:38.086442Z","strongest_claim":"With a single checkpoint, Pelican-Unified 1.0 achieves strong performance across all three capabilities: 64.7 on eight VLM benchmarks, the best among comparable-scale models; 66.03 on WorldArena, ranking first; and 93.5 on RoboTwin, the second-best average among compared action methods.","one_line_summary":"Pelican-Unified 1.0 trains a single VLM plus Unified Future Generator to jointly optimize understanding, reasoning, future video prediction, and action generation, reporting top-tier scores on VLM, WorldArena, and RoboTwin benchmarks.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That joint back-propagation of language, video, and action losses into a shared VLM representation produces a model whose performance on each capability matches or exceeds separately trained specialist systems without hidden trade-offs or benchmark-specific tuning.","pith_extraction_headline":"A single VLM-based model unifies understanding, reasoning, imagination, and action in one checkpoint without performance trade-offs."},"references":{"count":57,"sample":[{"doi":"","year":2025,"title":"N. Agarwal, A. Ali, M. Bala, Y. Balaji, E. Barker, T. Cai, P. Chattopadhyay, Y. Chen, Y. Cui, Y. Ding, et al. Cosmos world foundation model platform for physical ai, 2025","work_id":"6ce44985-849f-45f2-9801-2a454be55a7a","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"World Simulation with Video Foundation Models for Physical AI","work_id":"1dc393b8-98c3-43bd-8ab0-25d7c2a9705b","ref_index":2,"cited_arxiv_id":"2511.00062","is_internal_anchor":true},{"doi":"","year":2025,"title":"Qwen3-VL Technical Report","work_id":"1fe243aa-e3c0-4da6-b391-4cbcfc88d5c0","ref_index":3,"cited_arxiv_id":"2511.21631","is_internal_anchor":true},{"doi":"","year":2025,"title":"H. Bi, H. Tan, S. Xie, Z. Wang, S. Huang, H. Liu, R. Zhao, Y. Feng, C. Xiang, Y. Rong, H. Zhao, H. Liu, Z. Su, L. Ma, H. Su, and J. Zhu. Motus: A unified latent action world model, 2025","work_id":"7a5a2e7c-138a-4a61-884b-cb62b50e8896","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"$\\pi_0$: A Vision-Language-Action Flow Model for General Robot Control","work_id":"f790abdc-a796-482f-a40d-f8ee035ecfc2","ref_index":5,"cited_arxiv_id":"2410.24164","is_internal_anchor":true}],"resolved_work":57,"snapshot_sha256":"20fc06736a3fed7b22f3d8ccfba51dbd8672296b76562582feac93aad068abc0","internal_anchors":17},"formal_canon":{"evidence_count":2,"snapshot_sha256":"6c74bcd500acf58653d017673f79b0c0f3683637f54a81bf1978ba36819740b1"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"2310873e-7c3a-4f20-b060-90ec6526b74a"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T21:57:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x83XNS4EU0UzWzoZXDCETPXsJ5VumFLl0ryMiBed6GamtBpYYy4aOXw5CBHO9LPvAGXxpIpMiXUG/w09SgLhAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T19:09:36.721678Z"},"content_sha256":"bdefb65a54656ab9bd2c58cc43b48a4acc8c5adfc77a1ffc31fb2144cab03e19","schema_version":"1.0","event_id":"sha256:bdefb65a54656ab9bd2c58cc43b48a4acc8c5adfc77a1ffc31fb2144cab03e19"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WV2OW65AL2ZT7KUQVQ3C4KDC2C/bundle.json","state_url":"https://pith.science/pith/WV2OW65AL2ZT7KUQVQ3C4KDC2C/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WV2OW65AL2ZT7KUQVQ3C4KDC2C/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":"2026-05-31T19:09:36Z","links":{"resolver":"https://pith.science/pith/WV2OW65AL2ZT7KUQVQ3C4KDC2C","bundle":"https://pith.science/pith/WV2OW65AL2ZT7KUQVQ3C4KDC2C/bundle.json","state":"https://pith.science/pith/WV2OW65AL2ZT7KUQVQ3C4KDC2C/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WV2OW65AL2ZT7KUQVQ3C4KDC2C/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:WV2OW65AL2ZT7KUQVQ3C4KDC2C","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":"1302cfeabe73feb2bf15a2c473d647c5a45cf2e070559a1f3b1945f1e6d588d5","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-14T17:50:42Z","title_canon_sha256":"fbc61c28e0d7ad856aadcfdb063e0eb80407214c812b41febe2e76c06e74670d"},"schema_version":"1.0","source":{"id":"2605.15153","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15153","created_at":"2026-05-17T21:18:33Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15153v1","created_at":"2026-05-17T21:18:33Z"},{"alias_kind":"pith_short_12","alias_value":"WV2OW65AL2ZT","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"WV2OW65AL2ZT7KUQ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"WV2OW65A","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:bdefb65a54656ab9bd2c58cc43b48a4acc8c5adfc77a1ffc31fb2144cab03e19","target":"graph","created_at":"2026-05-17T21:57:18Z","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":"With a single checkpoint, Pelican-Unified 1.0 achieves strong performance across all three capabilities: 64.7 on eight VLM benchmarks, the best among comparable-scale models; 66.03 on WorldArena, ranking first; and 93.5 on RoboTwin, the second-best average among compared action methods."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That joint back-propagation of language, video, and action losses into a shared VLM representation produces a model whose performance on each capability matches or exceeds separately trained specialist systems without hidden trade-offs or benchmark-specific tuning."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Pelican-Unified 1.0 trains a single VLM plus Unified Future Generator to jointly optimize understanding, reasoning, future video prediction, and action generation, reporting top-tier scores on VLM, WorldArena, and RoboTwin benchmarks."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A single VLM-based model unifies understanding, reasoning, imagination, and action in one checkpoint without performance trade-offs."}],"snapshot_sha256":"08393091868655406e54b8ed37d048bc664e2a9d817cccbfcfedfe36307d42f2"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"6c74bcd500acf58653d017673f79b0c0f3683637f54a81bf1978ba36819740b1"},"paper":{"abstract_excerpt":"We present Pelican-Unified 1.0, the first embodied foundation model trained according to the principle of unification. Pelican-Unified 1.0 uses a single VLM as a unified understanding module, mapping scenes, instructions, visual contexts, and action histories into a shared semantic space. The same VLM also serves as a unified reasoning module, autoregressively producing task-, action-, and future-oriented chains of thought in a single forward pass and projecting the final hidden state into a dense latent variable. A Unified Future Generator (UFG) then conditions on this latent variable and joi","authors_text":"Che Liu, Haosong Sun, Haoyuan Shi, Jian Tang, Jiayu Hu, Jinpeng Lu, Jin Xu, Junwei Liao, Kuishu Wu, Nga Teng Chan, Renwen Cui, Senkang Hu, Shilong Zou, Wenhai Liu, Xiancong Ren, Xiaopeng Zhang, Xiaozhu Ju, Yang Xu, Yechen Wu, Yechi Liu, Yidong Wang, Yinda Chen, Yingji Zhang, Yi Zhang, Yong Dai, Zecong Tang, Zeyuan Ding","cross_cats":["cs.AI"],"headline":"A single VLM-based model unifies understanding, reasoning, imagination, and action in one checkpoint without performance trade-offs.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-14T17:50:42Z","title":"Pelican-Unified 1.0: A Unified Embodied Intelligence Model for Understanding, Reasoning, Imagination and Action"},"references":{"count":57,"internal_anchors":17,"resolved_work":57,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"N. Agarwal, A. Ali, M. Bala, Y. Balaji, E. Barker, T. Cai, P. Chattopadhyay, Y. Chen, Y. Cui, Y. Ding, et al. Cosmos world foundation model platform for physical ai, 2025","work_id":"6ce44985-849f-45f2-9801-2a454be55a7a","year":2025},{"cited_arxiv_id":"2511.00062","doi":"","is_internal_anchor":true,"ref_index":2,"title":"World Simulation with Video Foundation Models for Physical AI","work_id":"1dc393b8-98c3-43bd-8ab0-25d7c2a9705b","year":2025},{"cited_arxiv_id":"2511.21631","doi":"","is_internal_anchor":true,"ref_index":3,"title":"Qwen3-VL Technical Report","work_id":"1fe243aa-e3c0-4da6-b391-4cbcfc88d5c0","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"H. Bi, H. Tan, S. Xie, Z. Wang, S. Huang, H. Liu, R. Zhao, Y. Feng, C. Xiang, Y. Rong, H. Zhao, H. Liu, Z. Su, L. Ma, H. Su, and J. Zhu. Motus: A unified latent action world model, 2025","work_id":"7a5a2e7c-138a-4a61-884b-cb62b50e8896","year":2025},{"cited_arxiv_id":"2410.24164","doi":"","is_internal_anchor":true,"ref_index":5,"title":"$\\pi_0$: A Vision-Language-Action Flow Model for General Robot Control","work_id":"f790abdc-a796-482f-a40d-f8ee035ecfc2","year":2024}],"snapshot_sha256":"20fc06736a3fed7b22f3d8ccfba51dbd8672296b76562582feac93aad068abc0"},"source":{"id":"2605.15153","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-15T03:10:38.086442Z","id":"2310873e-7c3a-4f20-b060-90ec6526b74a","model_set":{"reader":"grok-4.3"},"one_line_summary":"Pelican-Unified 1.0 trains a single VLM plus Unified Future Generator to jointly optimize understanding, reasoning, future video prediction, and action generation, reporting top-tier scores on VLM, WorldArena, and RoboTwin benchmarks.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A single VLM-based model unifies understanding, reasoning, imagination, and action in one checkpoint without performance trade-offs.","strongest_claim":"With a single checkpoint, Pelican-Unified 1.0 achieves strong performance across all three capabilities: 64.7 on eight VLM benchmarks, the best among comparable-scale models; 66.03 on WorldArena, ranking first; and 93.5 on RoboTwin, the second-best average among compared action methods.","weakest_assumption":"That joint back-propagation of language, video, and action losses into a shared VLM representation produces a model whose performance on each capability matches or exceeds separately trained specialist systems without hidden trade-offs or benchmark-specific tuning."}},"verdict_id":"2310873e-7c3a-4f20-b060-90ec6526b74a"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:61f32ec3aa099bf5381e27cbded1aa34ff58ce120022b2c3c484b48269a98732","target":"record","created_at":"2026-05-17T21:18:33Z","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":"1302cfeabe73feb2bf15a2c473d647c5a45cf2e070559a1f3b1945f1e6d588d5","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-14T17:50:42Z","title_canon_sha256":"fbc61c28e0d7ad856aadcfdb063e0eb80407214c812b41febe2e76c06e74670d"},"schema_version":"1.0","source":{"id":"2605.15153","kind":"arxiv","version":1}},"canonical_sha256":"b574eb7ba05eb33faa90ac362e2862d084a56dab2b458c1a79efcfc14f10cedb","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b574eb7ba05eb33faa90ac362e2862d084a56dab2b458c1a79efcfc14f10cedb","first_computed_at":"2026-05-17T21:40:25.459139Z","kind":"pith_receipt","last_reissued_at":"2026-05-17T21:57:18.779538Z","receipt_version":"0.2","signature_status":"unsigned_v0"},"source_id":"2605.15153","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:61f32ec3aa099bf5381e27cbded1aa34ff58ce120022b2c3c484b48269a98732","sha256:bdefb65a54656ab9bd2c58cc43b48a4acc8c5adfc77a1ffc31fb2144cab03e19"],"state_sha256":"0915e83547ad22800bc46c631b43bb0bf225978f63c83e3d6b9c62fd63361876"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vJv+7uyB9kYptqyLHYiIjkraFgqNssuLHUUEmROpEZWw4GLlnE9m+uUmrB++vVwSBo27ih/0ANprHiyOciCyBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T19:09:36.724680Z","bundle_sha256":"26dcbf92cfad1babf5b18f57f05fa6d4f450158c025bfff0664b9624f3f74fd4"}}