{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:WKJS3I5OTUHUB5HKJ56ISVD66R","short_pith_number":"pith:WKJS3I5O","canonical_record":{"source":{"id":"2506.18088","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-06-22T16:26:53Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV","cs.MA"],"title_canon_sha256":"67b0caeefe8120b56da1470eead7dd090905cacac81ef89855b2cd40c3e1cdc2","abstract_canon_sha256":"4e604ee5317429d5c97333ac1a0ebe8bbdf34e0a381e305de1d9e359dc0899ad"},"schema_version":"1.0"},"canonical_sha256":"b2932da3ae9d0f40f4ea4f7c89547ef4427332a2bb5bafa1aa22b070cc34ea0c","source":{"kind":"arxiv","id":"2506.18088","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.18088","created_at":"2026-07-05T12:00:03Z"},{"alias_kind":"arxiv_version","alias_value":"2506.18088v2","created_at":"2026-07-05T12:00:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.18088","created_at":"2026-07-05T12:00:03Z"},{"alias_kind":"pith_short_12","alias_value":"WKJS3I5OTUHU","created_at":"2026-07-05T12:00:03Z"},{"alias_kind":"pith_short_16","alias_value":"WKJS3I5OTUHUB5HK","created_at":"2026-07-05T12:00:03Z"},{"alias_kind":"pith_short_8","alias_value":"WKJS3I5O","created_at":"2026-07-05T12:00:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:WKJS3I5OTUHUB5HKJ56ISVD66R","target":"record","payload":{"canonical_record":{"source":{"id":"2506.18088","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-06-22T16:26:53Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV","cs.MA"],"title_canon_sha256":"67b0caeefe8120b56da1470eead7dd090905cacac81ef89855b2cd40c3e1cdc2","abstract_canon_sha256":"4e604ee5317429d5c97333ac1a0ebe8bbdf34e0a381e305de1d9e359dc0899ad"},"schema_version":"1.0"},"canonical_sha256":"b2932da3ae9d0f40f4ea4f7c89547ef4427332a2bb5bafa1aa22b070cc34ea0c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:00:03.019499Z","signature_b64":"EzItoNFuo5EN+L9ynj1mgHm+NDCDhHRfUhe0HWXJ1y6eMM1wQ8htAACHiuPLGn5U6eTgg7Ym5hIZOj8aRRoxCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2932da3ae9d0f40f4ea4f7c89547ef4427332a2bb5bafa1aa22b070cc34ea0c","last_reissued_at":"2026-07-05T12:00:03.018955Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:00:03.018955Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.18088","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":"2026-07-05T12:00:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qeUSrhAjlm2AQ9HYhmspoRCf7JyHMIAVfxmFVEEqll1IeNQWl8UTeEVvrdmo5/GgSMSE87yh/idA8ZjUJLfFCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T19:59:34.457276Z"},"content_sha256":"f91a2dfb6d991f3d53bc0c506755efcd2d15e9d4249f9f067bfff79f611faf12","schema_version":"1.0","event_id":"sha256:f91a2dfb6d991f3d53bc0c506755efcd2d15e9d4249f9f067bfff79f611faf12"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:WKJS3I5OTUHUB5HKJ56ISVD66R","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Synthetic data from structured domain randomization lets bimanual robot policies reach 367 percent gains with only 10 real demonstrations.","cross_cats":["cs.AI","cs.CL","cs.CV","cs.MA"],"primary_cat":"cs.RO","authors_text":"Baijun Chen, Guodong Liu, Huan-ang Gao, Kailun Su, Kaixuan Wang, Mengkang Hu, Ping Luo, Qiangyu Chen, Qiwei Liang, Tianling Xu, Tian Nian, Tianxing Chen, Weiliang Deng, Xianliang Lin, Xiaokang Yang, Xuanbing Xie, Yao Mu, Yibin Liu, Yiheng Ge, Yubin Guo, Yusen Qin, Zanxin Chen, Zhenyu Gu, Zhixuan Liang, Zijian Cai, Zixuan Li","submitted_at":"2025-06-22T16:26:53Z","abstract_excerpt":"Simulation-based data synthesis has emerged as a powerful paradigm for advancing real-world robotic manipulation. Yet existing datasets remain insufficient for robust bimanual manipulation due to (1) the lack of scalable task generation methods and (2) oversimplified simulation environments. We present RoboTwin 2.0, a scalable framework for automated, large-scale generation of diverse and realistic data, together with unified evaluation protocols for dual-arm manipulation. At its core is RoboTwin-OD, an object library of 731 instances across 147 categories with semantic and manipulation-releva"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"For downstream policy learning, a VLA model trained with synthetic data plus only 10 real demonstrations achieves a 367% relative improvement over the 10-demo baseline, while zero-shot models trained solely on synthetic data obtain a 228% gain.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The domain randomization across clutter, lighting, background, tabletop height, and language, combined with the MLLM-generated tasks, produces data that generalizes effectively to real-world bimanual manipulation without significant sim-to-real gap.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"RoboTwin 2.0 automates diverse synthetic data creation for dual-arm robots via MLLMs and five-axis domain randomization, leading to 228-367% gains in manipulation success.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Synthetic data from structured domain randomization lets bimanual robot policies reach 367 percent gains with only 10 real demonstrations.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"b8698b9e55b3f8ba093f7919a96c0cdc6ac21dd9b2aa75a3eb4bc0a42df7c9d6"},"source":{"id":"2506.18088","kind":"arxiv","version":2},"verdict":{"id":"0a834250-489f-4d1c-92fd-c27a5ada5949","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-11T06:35:01.518695Z","strongest_claim":"For downstream policy learning, a VLA model trained with synthetic data plus only 10 real demonstrations achieves a 367% relative improvement over the 10-demo baseline, while zero-shot models trained solely on synthetic data obtain a 228% gain.","one_line_summary":"RoboTwin 2.0 automates diverse synthetic data creation for dual-arm robots via MLLMs and five-axis domain randomization, leading to 228-367% gains in manipulation success.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The domain randomization across clutter, lighting, background, tabletop height, and language, combined with the MLLM-generated tasks, produces data that generalizes effectively to real-world bimanual manipulation without significant sim-to-real gap.","pith_extraction_headline":"Synthetic data from structured domain randomization lets bimanual robot policies reach 367 percent gains with only 10 real demonstrations."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2506.18088/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":52,"sample":[{"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":1,"cited_arxiv_id":"2410.24164","is_internal_anchor":true},{"doi":"","year":2023,"title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","work_id":"ff438a8a-8003-4fae-9131-acd418b3597b","ref_index":2,"cited_arxiv_id":"2307.15818","is_internal_anchor":true},{"doi":"","year":2022,"title":"RT-1: Robotics Transformer for Real-World Control at Scale","work_id":"e11bda85-8531-46bc-a07f-d0ade3643ab1","ref_index":3,"cited_arxiv_id":"2212.06817","is_internal_anchor":true},{"doi":"","year":2025,"title":"AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems","work_id":"f797e9ec-510f-43a7-8a0c-18009ce332e5","ref_index":4,"cited_arxiv_id":"2503.06669","is_internal_anchor":true},{"doi":"","year":2019,"title":"Closing the sim-to-real loop: Adapting simulation randomization with real world experience","work_id":"a633c957-0891-4c83-8719-7a1e6cf30571","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":52,"snapshot_sha256":"d1fbbb86550fd0a52ffc568e7afbf017742b5117edeed44c828e70d24379cb24","internal_anchors":16},"formal_canon":{"evidence_count":2,"snapshot_sha256":"bf81e2da6aa4099aee98f4bb88ff70da953e338cf7136a198ef52f0b3aef3fd5"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"0a834250-489f-4d1c-92fd-c27a5ada5949"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:00:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qB/lJxUrM7MBcyvVJplRvF39qqrRZUA0IjTL8XyA7HWO+sQqzWlKrQUMjsko1V2g2lX25iG6MjvSl3ITxKkeDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T19:59:34.457833Z"},"content_sha256":"40e81c92e342af73fcbd701aed56c7c60f2333fd7f86b5c53e3229072c012757","schema_version":"1.0","event_id":"sha256:40e81c92e342af73fcbd701aed56c7c60f2333fd7f86b5c53e3229072c012757"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WKJS3I5OTUHUB5HKJ56ISVD66R/bundle.json","state_url":"https://pith.science/pith/WKJS3I5OTUHUB5HKJ56ISVD66R/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WKJS3I5OTUHUB5HKJ56ISVD66R/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":"2026-08-06T19:59:34Z","links":{"resolver":"https://pith.science/pith/WKJS3I5OTUHUB5HKJ56ISVD66R","bundle":"https://pith.science/pith/WKJS3I5OTUHUB5HKJ56ISVD66R/bundle.json","state":"https://pith.science/pith/WKJS3I5OTUHUB5HKJ56ISVD66R/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WKJS3I5OTUHUB5HKJ56ISVD66R/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WKJS3I5OTUHUB5HKJ56ISVD66R","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":"4e604ee5317429d5c97333ac1a0ebe8bbdf34e0a381e305de1d9e359dc0899ad","cross_cats_sorted":["cs.AI","cs.CL","cs.CV","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-06-22T16:26:53Z","title_canon_sha256":"67b0caeefe8120b56da1470eead7dd090905cacac81ef89855b2cd40c3e1cdc2"},"schema_version":"1.0","source":{"id":"2506.18088","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.18088","created_at":"2026-07-05T12:00:03Z"},{"alias_kind":"arxiv_version","alias_value":"2506.18088v2","created_at":"2026-07-05T12:00:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.18088","created_at":"2026-07-05T12:00:03Z"},{"alias_kind":"pith_short_12","alias_value":"WKJS3I5OTUHU","created_at":"2026-07-05T12:00:03Z"},{"alias_kind":"pith_short_16","alias_value":"WKJS3I5OTUHUB5HK","created_at":"2026-07-05T12:00:03Z"},{"alias_kind":"pith_short_8","alias_value":"WKJS3I5O","created_at":"2026-07-05T12:00:03Z"}],"graph_snapshots":[{"event_id":"sha256:40e81c92e342af73fcbd701aed56c7c60f2333fd7f86b5c53e3229072c012757","target":"graph","created_at":"2026-07-05T12:00:03Z","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":"For downstream policy learning, a VLA model trained with synthetic data plus only 10 real demonstrations achieves a 367% relative improvement over the 10-demo baseline, while zero-shot models trained solely on synthetic data obtain a 228% gain."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The domain randomization across clutter, lighting, background, tabletop height, and language, combined with the MLLM-generated tasks, produces data that generalizes effectively to real-world bimanual manipulation without significant sim-to-real gap."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"RoboTwin 2.0 automates diverse synthetic data creation for dual-arm robots via MLLMs and five-axis domain randomization, leading to 228-367% gains in manipulation success."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Synthetic data from structured domain randomization lets bimanual robot policies reach 367 percent gains with only 10 real demonstrations."}],"snapshot_sha256":"b8698b9e55b3f8ba093f7919a96c0cdc6ac21dd9b2aa75a3eb4bc0a42df7c9d6"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"bf81e2da6aa4099aee98f4bb88ff70da953e338cf7136a198ef52f0b3aef3fd5"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.18088/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Simulation-based data synthesis has emerged as a powerful paradigm for advancing real-world robotic manipulation. Yet existing datasets remain insufficient for robust bimanual manipulation due to (1) the lack of scalable task generation methods and (2) oversimplified simulation environments. We present RoboTwin 2.0, a scalable framework for automated, large-scale generation of diverse and realistic data, together with unified evaluation protocols for dual-arm manipulation. At its core is RoboTwin-OD, an object library of 731 instances across 147 categories with semantic and manipulation-releva","authors_text":"Baijun Chen, Guodong Liu, Huan-ang Gao, Kailun Su, Kaixuan Wang, Mengkang Hu, Ping Luo, Qiangyu Chen, Qiwei Liang, Tianling Xu, Tian Nian, Tianxing Chen, Weiliang Deng, Xianliang Lin, Xiaokang Yang, Xuanbing Xie, Yao Mu, Yibin Liu, Yiheng Ge, Yubin Guo, Yusen Qin, Zanxin Chen, Zhenyu Gu, Zhixuan Liang, Zijian Cai, Zixuan Li","cross_cats":["cs.AI","cs.CL","cs.CV","cs.MA"],"headline":"Synthetic data from structured domain randomization lets bimanual robot policies reach 367 percent gains with only 10 real demonstrations.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-06-22T16:26:53Z","title":"RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation"},"references":{"count":52,"internal_anchors":16,"resolved_work":52,"sample":[{"cited_arxiv_id":"2410.24164","doi":"","is_internal_anchor":true,"ref_index":1,"title":"$\\pi_0$: A Vision-Language-Action Flow Model for General Robot Control","work_id":"f790abdc-a796-482f-a40d-f8ee035ecfc2","year":2024},{"cited_arxiv_id":"2307.15818","doi":"","is_internal_anchor":true,"ref_index":2,"title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","work_id":"ff438a8a-8003-4fae-9131-acd418b3597b","year":2023},{"cited_arxiv_id":"2212.06817","doi":"","is_internal_anchor":true,"ref_index":3,"title":"RT-1: Robotics Transformer for Real-World Control at Scale","work_id":"e11bda85-8531-46bc-a07f-d0ade3643ab1","year":2022},{"cited_arxiv_id":"2503.06669","doi":"","is_internal_anchor":true,"ref_index":4,"title":"AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems","work_id":"f797e9ec-510f-43a7-8a0c-18009ce332e5","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Closing the sim-to-real loop: Adapting simulation randomization with real world experience","work_id":"a633c957-0891-4c83-8719-7a1e6cf30571","year":2019}],"snapshot_sha256":"d1fbbb86550fd0a52ffc568e7afbf017742b5117edeed44c828e70d24379cb24"},"source":{"id":"2506.18088","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-11T06:35:01.518695Z","id":"0a834250-489f-4d1c-92fd-c27a5ada5949","model_set":{"reader":"grok-4.3"},"one_line_summary":"RoboTwin 2.0 automates diverse synthetic data creation for dual-arm robots via MLLMs and five-axis domain randomization, leading to 228-367% gains in manipulation success.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Synthetic data from structured domain randomization lets bimanual robot policies reach 367 percent gains with only 10 real demonstrations.","strongest_claim":"For downstream policy learning, a VLA model trained with synthetic data plus only 10 real demonstrations achieves a 367% relative improvement over the 10-demo baseline, while zero-shot models trained solely on synthetic data obtain a 228% gain.","weakest_assumption":"The domain randomization across clutter, lighting, background, tabletop height, and language, combined with the MLLM-generated tasks, produces data that generalizes effectively to real-world bimanual manipulation without significant sim-to-real gap."}},"verdict_id":"0a834250-489f-4d1c-92fd-c27a5ada5949"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f91a2dfb6d991f3d53bc0c506755efcd2d15e9d4249f9f067bfff79f611faf12","target":"record","created_at":"2026-07-05T12:00:03Z","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":"4e604ee5317429d5c97333ac1a0ebe8bbdf34e0a381e305de1d9e359dc0899ad","cross_cats_sorted":["cs.AI","cs.CL","cs.CV","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-06-22T16:26:53Z","title_canon_sha256":"67b0caeefe8120b56da1470eead7dd090905cacac81ef89855b2cd40c3e1cdc2"},"schema_version":"1.0","source":{"id":"2506.18088","kind":"arxiv","version":2}},"canonical_sha256":"b2932da3ae9d0f40f4ea4f7c89547ef4427332a2bb5bafa1aa22b070cc34ea0c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b2932da3ae9d0f40f4ea4f7c89547ef4427332a2bb5bafa1aa22b070cc34ea0c","first_computed_at":"2026-07-05T12:00:03.018955Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:00:03.018955Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EzItoNFuo5EN+L9ynj1mgHm+NDCDhHRfUhe0HWXJ1y6eMM1wQ8htAACHiuPLGn5U6eTgg7Ym5hIZOj8aRRoxCg==","signature_status":"signed_v1","signed_at":"2026-07-05T12:00:03.019499Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.18088","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f91a2dfb6d991f3d53bc0c506755efcd2d15e9d4249f9f067bfff79f611faf12","sha256:40e81c92e342af73fcbd701aed56c7c60f2333fd7f86b5c53e3229072c012757"],"state_sha256":"651e51aeb47efcd1703eb66369d51f1a5605e4fabb6d8f68b517de63444559ae"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FrdsZ3wPCwk7ko+J2g8ly20EnHucskiq4x6QJJZ+fbW0TEL/yi8tPvapbmfc4+K+iDUZnw7/bAWnmcTYRxCACA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T19:59:34.461351Z","bundle_sha256":"fbcbd7a7b3dc64998adede6af43af3793cba7e499cd2f31be570c117e2d5824c"}}