{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:C47QFD7KVCD3TLW3CPFXDJGYGD","short_pith_number":"pith:C47QFD7K","canonical_record":{"source":{"id":"2605.13117","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-13T07:37:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"032fe1489f614d10816b631bb84ce1c71ab5cf1bce91251527798ee85836f210","abstract_canon_sha256":"7b14c3229a2a4d0b42685810621c4ddfc8d17a7ed244454bf84ef093db207672"},"schema_version":"1.0"},"canonical_sha256":"173f028feaa887b9aedb13cb71a4d830f7deb422adcff5471475ee59e0c6ec60","source":{"kind":"arxiv","id":"2605.13117","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13117","created_at":"2026-05-18T03:08:58Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13117v1","created_at":"2026-05-18T03:08:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13117","created_at":"2026-05-18T03:08:58Z"},{"alias_kind":"pith_short_12","alias_value":"C47QFD7KVCD3","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"C47QFD7KVCD3TLW3","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"C47QFD7K","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:C47QFD7KVCD3TLW3CPFXDJGYGD","target":"record","payload":{"canonical_record":{"source":{"id":"2605.13117","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-13T07:37:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"032fe1489f614d10816b631bb84ce1c71ab5cf1bce91251527798ee85836f210","abstract_canon_sha256":"7b14c3229a2a4d0b42685810621c4ddfc8d17a7ed244454bf84ef093db207672"},"schema_version":"1.0"},"canonical_sha256":"173f028feaa887b9aedb13cb71a4d830f7deb422adcff5471475ee59e0c6ec60","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:08:58.035662Z","signature_b64":"NGi5h1RdUu8BOC32zRtxkbPIbHemI6k1+tMn78KcL1iIn38m8RYP6GI7Rm9q0+r5PUSEkwmvAifGXv7KUQTUBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"173f028feaa887b9aedb13cb71a4d830f7deb422adcff5471475ee59e0c6ec60","last_reissued_at":"2026-05-18T03:08:58.034941Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:08:58.034941Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.13117","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":"2026-05-18T03:08:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f6Fcb/cTUXKkRln973c/Uy8cUp4G91UXYmG33xz9cFqUO7NTAIfwMqL1YSi1XprK4jn9FysxTGPK4g+h8McmAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T23:23:52.629744Z"},"content_sha256":"59d3a77d3b0c6bb8e29a0a35ca1ead850850785f6bc7b1c47be313d4a9de0beb","schema_version":"1.0","event_id":"sha256:59d3a77d3b0c6bb8e29a0a35ca1ead850850785f6bc7b1c47be313d4a9de0beb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:C47QFD7KVCD3TLW3CPFXDJGYGD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SECOND-Grasp: Semantic Contact-guided Dexterous Grasping","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"SECOND-Grasp derives dexterous grasp supervision from language-inferred contacts refined across views to reach 98 percent lifting success on seen objects.","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Han Yi Shin, Heeju Ko, Honglak Lee, Jaehyeok Lee, Jaewon Mun, Qixing Huang, Sangpil Kim, Sujin Jang, Sung June Kim","submitted_at":"2026-05-13T07:37:00Z","abstract_excerpt":"Achieving reliable robotic manipulation, such as dexterous grasping, requires a synergy between physically stable interactions and semantic task guidance, yet these objectives are often treated as separate, disjoint goals. In this paper, we investigate how to integrate dexterous grasping techniques, i.e., physically stable grasps for object lifting and language-guided grasp generation, to achieve both physical stability and semantic understanding. To this end, we propose SECOND-Grasp (SEmantic CONtact-guided Dexterous Grasping), a unified framework that enables robotic hands to dynamically adj"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Our approach, trained on DexGraspNet, consistently outperforms baselines in lifting success rate on both seen and unseen categories, achieving 98.2% and 97.7%, respectively, while also improving intent-aware grasping by 12.8% and 26.2%.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"Vision-language reasoning reliably infers appropriate contact regions from object properties and task language, and the Semantic-Geometric Consistency Refinement step produces accurate 3D contact maps without introducing systematic errors that would invalidate downstream inverse-kinematics supervision.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"SECOND-Grasp integrates semantic contact proposals from vision-language reasoning with geometric refinement to achieve 98%+ lifting success and improved intent-aware grasping on seen and unseen objects.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"SECOND-Grasp derives dexterous grasp supervision from language-inferred contacts refined across views to reach 98 percent lifting success on seen objects.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"15d360f1519642fcbdfa8309def60359662ca534a1a17c957dc7d1d2209e70fd"},"source":{"id":"2605.13117","kind":"arxiv","version":1},"verdict":{"id":"fdd92260-416a-4204-9ff2-e6ad2307055d","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T18:36:22.143017Z","strongest_claim":"Our approach, trained on DexGraspNet, consistently outperforms baselines in lifting success rate on both seen and unseen categories, achieving 98.2% and 97.7%, respectively, while also improving intent-aware grasping by 12.8% and 26.2%.","one_line_summary":"SECOND-Grasp integrates semantic contact proposals from vision-language reasoning with geometric refinement to achieve 98%+ lifting success and improved intent-aware grasping on seen and unseen objects.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"Vision-language reasoning reliably infers appropriate contact regions from object properties and task language, and the Semantic-Geometric Consistency Refinement step produces accurate 3D contact maps without introducing systematic errors that would invalidate downstream inverse-kinematics supervision.","pith_extraction_headline":"SECOND-Grasp derives dexterous grasp supervision from language-inferred contacts refined across views to reach 98 percent lifting success on seen objects."},"references":{"count":59,"sample":[{"doi":"","year":2025,"title":"Qwen3-VL Technical Report","work_id":"1fe243aa-e3c0-4da6-b391-4cbcfc88d5c0","ref_index":1,"cited_arxiv_id":"2511.21631","is_internal_anchor":true},{"doi":"","year":2004,"title":"S. Buss. Introduction to inverse kinematics with jacobian transpose, pseudoinverse and damped least squares methods. 2004","work_id":"6bd142fe-426f-49ae-ad5a-1db193bb18e1","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2015,"title":"B. Calli, A. Singh, A. Walsman, S. Srinivasa, P. Abbeel, and A. M. Dollar. The ycb object and model set: Towards common benchmarks for manipulation research. In2015 international conference on advance","work_id":"2a2921ce-cce8-47d1-8900-4343e6ffd01e","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"T. Chen, M. Tippur, S. Wu, V . Kumar, E. Adelson, and P. Agrawal. Visual dexterity: In-hand reorientation of novel and complex object shapes.Science Robotics, 8(84):eadc9244, 2023","work_id":"15c906fa-44c4-4568-9666-dddb1d9d68f6","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"S. Deng, X. Xu, C. Wu, K. Chen, and K. Jia. 3d affordancenet: A benchmark for visual object affordance understanding. Inproceedings of the IEEE/CVF conference on computer vision and pattern recognitio","work_id":"ccf39d99-5412-4b48-b60f-5b64e53c34db","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":59,"snapshot_sha256":"aa1323c57c7e1d25108123b973e6c6404c60e2507ce8db76b46bc781f3ddffb8","internal_anchors":4},"formal_canon":{"evidence_count":2,"snapshot_sha256":"1c733e9b1ad2511a37e89da4c3abe3b9eb0136bb539f079aa07f389cc689e98c"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"fdd92260-416a-4204-9ff2-e6ad2307055d"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:08:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jZYl0rcub/5Bcq6o53GYKvoYQGhTdcPP8IdeRNBBsM6ISqBUbIuuliDBDak0wZ5yvlQ3irBfTHQp6RdEHGvxCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T23:23:52.630929Z"},"content_sha256":"b2af8cd5839013f1446c409e3a2ff8cd676cd9e4d1e27cec5aca6b7381d5d7e0","schema_version":"1.0","event_id":"sha256:b2af8cd5839013f1446c409e3a2ff8cd676cd9e4d1e27cec5aca6b7381d5d7e0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/C47QFD7KVCD3TLW3CPFXDJGYGD/bundle.json","state_url":"https://pith.science/pith/C47QFD7KVCD3TLW3CPFXDJGYGD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/C47QFD7KVCD3TLW3CPFXDJGYGD/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":"2026-05-20T23:23:52Z","links":{"resolver":"https://pith.science/pith/C47QFD7KVCD3TLW3CPFXDJGYGD","bundle":"https://pith.science/pith/C47QFD7KVCD3TLW3CPFXDJGYGD/bundle.json","state":"https://pith.science/pith/C47QFD7KVCD3TLW3CPFXDJGYGD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/C47QFD7KVCD3TLW3CPFXDJGYGD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:C47QFD7KVCD3TLW3CPFXDJGYGD","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":"7b14c3229a2a4d0b42685810621c4ddfc8d17a7ed244454bf84ef093db207672","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-13T07:37:00Z","title_canon_sha256":"032fe1489f614d10816b631bb84ce1c71ab5cf1bce91251527798ee85836f210"},"schema_version":"1.0","source":{"id":"2605.13117","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13117","created_at":"2026-05-18T03:08:58Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13117v1","created_at":"2026-05-18T03:08:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13117","created_at":"2026-05-18T03:08:58Z"},{"alias_kind":"pith_short_12","alias_value":"C47QFD7KVCD3","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"C47QFD7KVCD3TLW3","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"C47QFD7K","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:b2af8cd5839013f1446c409e3a2ff8cd676cd9e4d1e27cec5aca6b7381d5d7e0","target":"graph","created_at":"2026-05-18T03:08:58Z","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":"Our approach, trained on DexGraspNet, consistently outperforms baselines in lifting success rate on both seen and unseen categories, achieving 98.2% and 97.7%, respectively, while also improving intent-aware grasping by 12.8% and 26.2%."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"Vision-language reasoning reliably infers appropriate contact regions from object properties and task language, and the Semantic-Geometric Consistency Refinement step produces accurate 3D contact maps without introducing systematic errors that would invalidate downstream inverse-kinematics supervision."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"SECOND-Grasp integrates semantic contact proposals from vision-language reasoning with geometric refinement to achieve 98%+ lifting success and improved intent-aware grasping on seen and unseen objects."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"SECOND-Grasp derives dexterous grasp supervision from language-inferred contacts refined across views to reach 98 percent lifting success on seen objects."}],"snapshot_sha256":"15d360f1519642fcbdfa8309def60359662ca534a1a17c957dc7d1d2209e70fd"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"1c733e9b1ad2511a37e89da4c3abe3b9eb0136bb539f079aa07f389cc689e98c"},"paper":{"abstract_excerpt":"Achieving reliable robotic manipulation, such as dexterous grasping, requires a synergy between physically stable interactions and semantic task guidance, yet these objectives are often treated as separate, disjoint goals. In this paper, we investigate how to integrate dexterous grasping techniques, i.e., physically stable grasps for object lifting and language-guided grasp generation, to achieve both physical stability and semantic understanding. To this end, we propose SECOND-Grasp (SEmantic CONtact-guided Dexterous Grasping), a unified framework that enables robotic hands to dynamically adj","authors_text":"Han Yi Shin, Heeju Ko, Honglak Lee, Jaehyeok Lee, Jaewon Mun, Qixing Huang, Sangpil Kim, Sujin Jang, Sung June Kim","cross_cats":["cs.AI"],"headline":"SECOND-Grasp derives dexterous grasp supervision from language-inferred contacts refined across views to reach 98 percent lifting success on seen objects.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-13T07:37:00Z","title":"SECOND-Grasp: Semantic Contact-guided Dexterous Grasping"},"references":{"count":59,"internal_anchors":4,"resolved_work":59,"sample":[{"cited_arxiv_id":"2511.21631","doi":"","is_internal_anchor":true,"ref_index":1,"title":"Qwen3-VL Technical Report","work_id":"1fe243aa-e3c0-4da6-b391-4cbcfc88d5c0","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"S. Buss. Introduction to inverse kinematics with jacobian transpose, pseudoinverse and damped least squares methods. 2004","work_id":"6bd142fe-426f-49ae-ad5a-1db193bb18e1","year":2004},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"B. Calli, A. Singh, A. Walsman, S. Srinivasa, P. Abbeel, and A. M. Dollar. The ycb object and model set: Towards common benchmarks for manipulation research. In2015 international conference on advance","work_id":"2a2921ce-cce8-47d1-8900-4343e6ffd01e","year":2015},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"T. Chen, M. Tippur, S. Wu, V . Kumar, E. Adelson, and P. Agrawal. Visual dexterity: In-hand reorientation of novel and complex object shapes.Science Robotics, 8(84):eadc9244, 2023","work_id":"15c906fa-44c4-4568-9666-dddb1d9d68f6","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"S. Deng, X. Xu, C. Wu, K. Chen, and K. Jia. 3d affordancenet: A benchmark for visual object affordance understanding. Inproceedings of the IEEE/CVF conference on computer vision and pattern recognitio","work_id":"ccf39d99-5412-4b48-b60f-5b64e53c34db","year":2021}],"snapshot_sha256":"aa1323c57c7e1d25108123b973e6c6404c60e2507ce8db76b46bc781f3ddffb8"},"source":{"id":"2605.13117","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T18:36:22.143017Z","id":"fdd92260-416a-4204-9ff2-e6ad2307055d","model_set":{"reader":"grok-4.3"},"one_line_summary":"SECOND-Grasp integrates semantic contact proposals from vision-language reasoning with geometric refinement to achieve 98%+ lifting success and improved intent-aware grasping on seen and unseen objects.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"SECOND-Grasp derives dexterous grasp supervision from language-inferred contacts refined across views to reach 98 percent lifting success on seen objects.","strongest_claim":"Our approach, trained on DexGraspNet, consistently outperforms baselines in lifting success rate on both seen and unseen categories, achieving 98.2% and 97.7%, respectively, while also improving intent-aware grasping by 12.8% and 26.2%.","weakest_assumption":"Vision-language reasoning reliably infers appropriate contact regions from object properties and task language, and the Semantic-Geometric Consistency Refinement step produces accurate 3D contact maps without introducing systematic errors that would invalidate downstream inverse-kinematics supervision."}},"verdict_id":"fdd92260-416a-4204-9ff2-e6ad2307055d"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:59d3a77d3b0c6bb8e29a0a35ca1ead850850785f6bc7b1c47be313d4a9de0beb","target":"record","created_at":"2026-05-18T03:08:58Z","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":"7b14c3229a2a4d0b42685810621c4ddfc8d17a7ed244454bf84ef093db207672","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-13T07:37:00Z","title_canon_sha256":"032fe1489f614d10816b631bb84ce1c71ab5cf1bce91251527798ee85836f210"},"schema_version":"1.0","source":{"id":"2605.13117","kind":"arxiv","version":1}},"canonical_sha256":"173f028feaa887b9aedb13cb71a4d830f7deb422adcff5471475ee59e0c6ec60","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"173f028feaa887b9aedb13cb71a4d830f7deb422adcff5471475ee59e0c6ec60","first_computed_at":"2026-05-18T03:08:58.034941Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:08:58.034941Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NGi5h1RdUu8BOC32zRtxkbPIbHemI6k1+tMn78KcL1iIn38m8RYP6GI7Rm9q0+r5PUSEkwmvAifGXv7KUQTUBA==","signature_status":"signed_v1","signed_at":"2026-05-18T03:08:58.035662Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.13117","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:59d3a77d3b0c6bb8e29a0a35ca1ead850850785f6bc7b1c47be313d4a9de0beb","sha256:b2af8cd5839013f1446c409e3a2ff8cd676cd9e4d1e27cec5aca6b7381d5d7e0"],"state_sha256":"1601e96f1917e542a2b59101377018c1c29ccb4649eba9f18a52cc525d52ee15"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iTQXTcl4oRrAcvZsmGI5kpLKOphYsFXbpG3UJYLeYAebKXkfpgrFx5VBo1pMAXuaY5h00BNITtKBeM2JBLIEAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-20T23:23:52.637401Z","bundle_sha256":"a096cd20cb8f6e6b2d3f9d20b9aac840e16e6bc02eed03ab938734cb20f6863f"}}