{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:SX5DPZYTHYL2YXMXHHTNYDNI7S","short_pith_number":"pith:SX5DPZYT","canonical_record":{"source":{"id":"2411.19650","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-11-29T12:06:03Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV","cs.LG"],"title_canon_sha256":"ce7cb2f834156a0f4243b049044d988ac34ec78292ebb89deea947a83e82d6c9","abstract_canon_sha256":"1e3504dd5200f00b97d0cf8a95095f01ba2f89bac0b4937b8af98aebf524144e"},"schema_version":"1.0"},"canonical_sha256":"95fa37e7133e17ac5d9739e6dc0da8fc9566c978181e0927f35d866bc48e47a2","source":{"kind":"arxiv","id":"2411.19650","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.19650","created_at":"2026-07-05T09:42:05Z"},{"alias_kind":"arxiv_version","alias_value":"2411.19650v1","created_at":"2026-07-05T09:42:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.19650","created_at":"2026-07-05T09:42:05Z"},{"alias_kind":"pith_short_12","alias_value":"SX5DPZYTHYL2","created_at":"2026-07-05T09:42:05Z"},{"alias_kind":"pith_short_16","alias_value":"SX5DPZYTHYL2YXMX","created_at":"2026-07-05T09:42:05Z"},{"alias_kind":"pith_short_8","alias_value":"SX5DPZYT","created_at":"2026-07-05T09:42:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:SX5DPZYTHYL2YXMXHHTNYDNI7S","target":"record","payload":{"canonical_record":{"source":{"id":"2411.19650","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-11-29T12:06:03Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV","cs.LG"],"title_canon_sha256":"ce7cb2f834156a0f4243b049044d988ac34ec78292ebb89deea947a83e82d6c9","abstract_canon_sha256":"1e3504dd5200f00b97d0cf8a95095f01ba2f89bac0b4937b8af98aebf524144e"},"schema_version":"1.0"},"canonical_sha256":"95fa37e7133e17ac5d9739e6dc0da8fc9566c978181e0927f35d866bc48e47a2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:42:05.868848Z","signature_b64":"bhAZxCv2dhNcSyCMbv5hiyfC5Nkv4nIUcD7vAEVl+PWkikvwsLV6DQu+S6oT5g6aJExDUmA+LaAhBT2NCAeUBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"95fa37e7133e17ac5d9739e6dc0da8fc9566c978181e0927f35d866bc48e47a2","last_reissued_at":"2026-07-05T09:42:05.868405Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:42:05.868405Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.19650","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":"2026-07-05T09:42:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ebhYWVYV/lv4tUVhQASnOzmRopPn4xAqAELLt0KG+LDaZb9kvbQ39gdIXy2pQ5fQQC+uPqfdrImbLpFl6rnqBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T21:29:19.712454Z"},"content_sha256":"75f5e2273718d74dc957d982078a4a8e4dc4a138e3a3925aaac79c8eec73ee15","schema_version":"1.0","event_id":"sha256:75f5e2273718d74dc957d982078a4a8e4dc4a138e3a3925aaac79c8eec73ee15"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:SX5DPZYTHYL2YXMXHHTNYDNI7S","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A componentized vision-language-action model with a diffusion action module achieves higher success rates in robotic manipulation tasks.","cross_cats":["cs.AI","cs.CL","cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Baining Guo, Bei Liu, Dong Chen, Fangyun Wei, Jianlong Fu, Jianmin Bao, Jiaolong Yang, Lin Luo, Mozheng Liao, Qixiu Li, Sicheng Xu, Xiaofan Wang, Xi Chen, Yaobo Liang, Yizhong Zhang, Yuanchun Shi, Yu Deng, Zeyu Wang","submitted_at":"2024-11-29T12:06:03Z","abstract_excerpt":"The advancement of large Vision-Language-Action (VLA) models has significantly improved robotic manipulation in terms of language-guided task execution and generalization to unseen scenarios. While existing VLAs adapted from pretrained large Vision-Language-Models (VLM) have demonstrated promising generalizability, their task performance is still unsatisfactory as indicated by the low tasks success rates in different environments. In this paper, we present a new advanced VLA architecture derived from VLM. Unlike previous works that directly repurpose VLM for action prediction by simple action "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"It exceeds the average success rates of OpenVLA which has similar model size (7B) with ours by over 35% in simulated evaluation and 55% in real robot experiments. It also outperforms the large RT-2-X model (55B) by 18% absolute success rates in simulation.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The performance improvements are attributable to the componentized architecture and diffusion action module rather than differences in training data volume, fine-tuning recipes, or evaluation protocols across compared models.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"CogACT is a new VLA model that uses a conditioned diffusion action transformer to achieve over 35% higher average success rates than OpenVLA in simulation and 55% in real-robot experiments while generalizing to new robots and objects.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A componentized vision-language-action model with a diffusion action module achieves higher success rates in robotic manipulation tasks.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"a4450084b3621d625739a1308a20aac00b774308c87736512870dae6bad40156"},"source":{"id":"2411.19650","kind":"arxiv","version":1},"verdict":{"id":"14a4ca1f-21c4-49fa-8826-481caf0104e5","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-12T07:27:30.041349Z","strongest_claim":"It exceeds the average success rates of OpenVLA which has similar model size (7B) with ours by over 35% in simulated evaluation and 55% in real robot experiments. It also outperforms the large RT-2-X model (55B) by 18% absolute success rates in simulation.","one_line_summary":"CogACT is a new VLA model that uses a conditioned diffusion action transformer to achieve over 35% higher average success rates than OpenVLA in simulation and 55% in real-robot experiments while generalizing to new robots and objects.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The performance improvements are attributable to the componentized architecture and diffusion action module rather than differences in training data volume, fine-tuning recipes, or evaluation protocols across compared models.","pith_extraction_headline":"A componentized vision-language-action model with a diffusion action module achieves higher success rates in robotic manipulation tasks."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2411.19650/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":78,"sample":[{"doi":"","year":2024,"title":"Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone","work_id":"feef9556-a016-493c-abd2-0c97a23a7ebf","ref_index":1,"cited_arxiv_id":"2404.14219","is_internal_anchor":true},{"doi":"","year":null,"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","ref_index":2,"cited_arxiv_id":"2303.08774","is_internal_anchor":true},{"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":3,"cited_arxiv_id":"2308.01390","is_internal_anchor":true},{"doi":"","year":2023,"title":"Hydra: Hybrid robot actions for imitation learning","work_id":"7e49d833-d5ff-42c2-b6d5-51cc33a82f35","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Gen2Act: Human Video Generation in Novel Scenarios enables Generalizable Robot Manipulation","work_id":"a3bde288-aace-40db-8067-3ae6656f9509","ref_index":5,"cited_arxiv_id":"2409.16283","is_internal_anchor":true}],"resolved_work":78,"snapshot_sha256":"2ea1a1277d8f89d85a67f5759c05452ad73167d721a82c6aa3fec587196ebcfa","internal_anchors":26},"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":"14a4ca1f-21c4-49fa-8826-481caf0104e5"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:42:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"csrxQiFQUH3pjkAw4j0DBdlTOA8EupMbm1xsEYuHTF6S+xCLM9WHLq+WnE4mCs2/OH85pkAbOfcgfVnbAAiyAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T21:29:19.713054Z"},"content_sha256":"9fa725c8fad17f83f99df309dba5ca17bbae6a7403d135bd7ff5200c8cc5ae47","schema_version":"1.0","event_id":"sha256:9fa725c8fad17f83f99df309dba5ca17bbae6a7403d135bd7ff5200c8cc5ae47"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SX5DPZYTHYL2YXMXHHTNYDNI7S/bundle.json","state_url":"https://pith.science/pith/SX5DPZYTHYL2YXMXHHTNYDNI7S/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SX5DPZYTHYL2YXMXHHTNYDNI7S/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":"2026-08-04T21:29:19Z","links":{"resolver":"https://pith.science/pith/SX5DPZYTHYL2YXMXHHTNYDNI7S","bundle":"https://pith.science/pith/SX5DPZYTHYL2YXMXHHTNYDNI7S/bundle.json","state":"https://pith.science/pith/SX5DPZYTHYL2YXMXHHTNYDNI7S/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SX5DPZYTHYL2YXMXHHTNYDNI7S/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SX5DPZYTHYL2YXMXHHTNYDNI7S","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":"1e3504dd5200f00b97d0cf8a95095f01ba2f89bac0b4937b8af98aebf524144e","cross_cats_sorted":["cs.AI","cs.CL","cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-11-29T12:06:03Z","title_canon_sha256":"ce7cb2f834156a0f4243b049044d988ac34ec78292ebb89deea947a83e82d6c9"},"schema_version":"1.0","source":{"id":"2411.19650","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.19650","created_at":"2026-07-05T09:42:05Z"},{"alias_kind":"arxiv_version","alias_value":"2411.19650v1","created_at":"2026-07-05T09:42:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.19650","created_at":"2026-07-05T09:42:05Z"},{"alias_kind":"pith_short_12","alias_value":"SX5DPZYTHYL2","created_at":"2026-07-05T09:42:05Z"},{"alias_kind":"pith_short_16","alias_value":"SX5DPZYTHYL2YXMX","created_at":"2026-07-05T09:42:05Z"},{"alias_kind":"pith_short_8","alias_value":"SX5DPZYT","created_at":"2026-07-05T09:42:05Z"}],"graph_snapshots":[{"event_id":"sha256:9fa725c8fad17f83f99df309dba5ca17bbae6a7403d135bd7ff5200c8cc5ae47","target":"graph","created_at":"2026-07-05T09:42:05Z","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":"It exceeds the average success rates of OpenVLA which has similar model size (7B) with ours by over 35% in simulated evaluation and 55% in real robot experiments. It also outperforms the large RT-2-X model (55B) by 18% absolute success rates in simulation."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The performance improvements are attributable to the componentized architecture and diffusion action module rather than differences in training data volume, fine-tuning recipes, or evaluation protocols across compared models."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"CogACT is a new VLA model that uses a conditioned diffusion action transformer to achieve over 35% higher average success rates than OpenVLA in simulation and 55% in real-robot experiments while generalizing to new robots and objects."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A componentized vision-language-action model with a diffusion action module achieves higher success rates in robotic manipulation tasks."}],"snapshot_sha256":"a4450084b3621d625739a1308a20aac00b774308c87736512870dae6bad40156"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2411.19650/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The advancement of large Vision-Language-Action (VLA) models has significantly improved robotic manipulation in terms of language-guided task execution and generalization to unseen scenarios. While existing VLAs adapted from pretrained large Vision-Language-Models (VLM) have demonstrated promising generalizability, their task performance is still unsatisfactory as indicated by the low tasks success rates in different environments. In this paper, we present a new advanced VLA architecture derived from VLM. Unlike previous works that directly repurpose VLM for action prediction by simple action ","authors_text":"Baining Guo, Bei Liu, Dong Chen, Fangyun Wei, Jianlong Fu, Jianmin Bao, Jiaolong Yang, Lin Luo, Mozheng Liao, Qixiu Li, Sicheng Xu, Xiaofan Wang, Xi Chen, Yaobo Liang, Yizhong Zhang, Yuanchun Shi, Yu Deng, Zeyu Wang","cross_cats":["cs.AI","cs.CL","cs.CV","cs.LG"],"headline":"A componentized vision-language-action model with a diffusion action module achieves higher success rates in robotic manipulation tasks.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-11-29T12:06:03Z","title":"CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation"},"references":{"count":78,"internal_anchors":26,"resolved_work":78,"sample":[{"cited_arxiv_id":"2404.14219","doi":"","is_internal_anchor":true,"ref_index":1,"title":"Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone","work_id":"feef9556-a016-493c-abd2-0c97a23a7ebf","year":2024},{"cited_arxiv_id":"2303.08774","doi":"","is_internal_anchor":true,"ref_index":2,"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","year":null},{"cited_arxiv_id":"2308.01390","doi":"","is_internal_anchor":true,"ref_index":3,"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":4,"title":"Hydra: Hybrid robot actions for imitation learning","work_id":"7e49d833-d5ff-42c2-b6d5-51cc33a82f35","year":2023},{"cited_arxiv_id":"2409.16283","doi":"","is_internal_anchor":true,"ref_index":5,"title":"Gen2Act: Human Video Generation in Novel Scenarios enables Generalizable Robot Manipulation","work_id":"a3bde288-aace-40db-8067-3ae6656f9509","year":null}],"snapshot_sha256":"2ea1a1277d8f89d85a67f5759c05452ad73167d721a82c6aa3fec587196ebcfa"},"source":{"id":"2411.19650","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-12T07:27:30.041349Z","id":"14a4ca1f-21c4-49fa-8826-481caf0104e5","model_set":{"reader":"grok-4.3"},"one_line_summary":"CogACT is a new VLA model that uses a conditioned diffusion action transformer to achieve over 35% higher average success rates than OpenVLA in simulation and 55% in real-robot experiments while generalizing to new robots and objects.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A componentized vision-language-action model with a diffusion action module achieves higher success rates in robotic manipulation tasks.","strongest_claim":"It exceeds the average success rates of OpenVLA which has similar model size (7B) with ours by over 35% in simulated evaluation and 55% in real robot experiments. It also outperforms the large RT-2-X model (55B) by 18% absolute success rates in simulation.","weakest_assumption":"The performance improvements are attributable to the componentized architecture and diffusion action module rather than differences in training data volume, fine-tuning recipes, or evaluation protocols across compared models."}},"verdict_id":"14a4ca1f-21c4-49fa-8826-481caf0104e5"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:75f5e2273718d74dc957d982078a4a8e4dc4a138e3a3925aaac79c8eec73ee15","target":"record","created_at":"2026-07-05T09:42:05Z","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":"1e3504dd5200f00b97d0cf8a95095f01ba2f89bac0b4937b8af98aebf524144e","cross_cats_sorted":["cs.AI","cs.CL","cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-11-29T12:06:03Z","title_canon_sha256":"ce7cb2f834156a0f4243b049044d988ac34ec78292ebb89deea947a83e82d6c9"},"schema_version":"1.0","source":{"id":"2411.19650","kind":"arxiv","version":1}},"canonical_sha256":"95fa37e7133e17ac5d9739e6dc0da8fc9566c978181e0927f35d866bc48e47a2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"95fa37e7133e17ac5d9739e6dc0da8fc9566c978181e0927f35d866bc48e47a2","first_computed_at":"2026-07-05T09:42:05.868405Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:42:05.868405Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bhAZxCv2dhNcSyCMbv5hiyfC5Nkv4nIUcD7vAEVl+PWkikvwsLV6DQu+S6oT5g6aJExDUmA+LaAhBT2NCAeUBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:42:05.868848Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.19650","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:75f5e2273718d74dc957d982078a4a8e4dc4a138e3a3925aaac79c8eec73ee15","sha256:9fa725c8fad17f83f99df309dba5ca17bbae6a7403d135bd7ff5200c8cc5ae47"],"state_sha256":"1b098b42b3e908bf5e65aeff597b7f5b51cb2f3a99b71c883999427a4bac051d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FO5B/3qMNzbqcGU4NMsyjyPH/6vsTbHXTSjyPp92IFPrUF/WIi36QKGgqipWO9BAE0vFgHkQzbfOTrc/wqNSCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T21:29:19.716378Z","bundle_sha256":"abbbe0f8674e3b4dd68861c9ed7ce83bc41cf1af8f5f299796c0730573418502"}}