{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:OWBQ25XVLBKMRKUIV3EFPAYXGI","short_pith_number":"pith:OWBQ25XV","canonical_record":{"source":{"id":"2605.13751","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-13T16:33:07Z","cross_cats_sorted":["cs.SE","cs.SY","eess.SY"],"title_canon_sha256":"d1c3ea195b967f53710d854698b1b367cd99129be38d70700dd46b793b7fb0a4","abstract_canon_sha256":"efd81b6aa4d60de71c7e2c6ee0228d05bb4205395ba82504f1daea8603f37a35"},"schema_version":"1.0"},"canonical_sha256":"75830d76f55854c8aa88aec8578317320c3ce3bc2b47473936837d10007f01a1","source":{"kind":"arxiv","id":"2605.13751","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13751","created_at":"2026-05-18T02:44:16Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13751v1","created_at":"2026-05-18T02:44:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13751","created_at":"2026-05-18T02:44:16Z"},{"alias_kind":"pith_short_12","alias_value":"OWBQ25XVLBKM","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"OWBQ25XVLBKMRKUI","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"OWBQ25XV","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:OWBQ25XVLBKMRKUIV3EFPAYXGI","target":"record","payload":{"canonical_record":{"source":{"id":"2605.13751","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-13T16:33:07Z","cross_cats_sorted":["cs.SE","cs.SY","eess.SY"],"title_canon_sha256":"d1c3ea195b967f53710d854698b1b367cd99129be38d70700dd46b793b7fb0a4","abstract_canon_sha256":"efd81b6aa4d60de71c7e2c6ee0228d05bb4205395ba82504f1daea8603f37a35"},"schema_version":"1.0"},"canonical_sha256":"75830d76f55854c8aa88aec8578317320c3ce3bc2b47473936837d10007f01a1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:44:16.374610Z","signature_b64":"YsGhr8s/93+sYL+EnB1DhYLjPBhgYe8vXDdkA+L1BsyotdsP2b/bzx5nalM8HWE0cJbfriY4EgnAgUiFtGKeBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"75830d76f55854c8aa88aec8578317320c3ce3bc2b47473936837d10007f01a1","last_reissued_at":"2026-05-18T02:44:16.374176Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:44:16.374176Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.13751","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":"2026-05-18T02:44:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GheMSLa3ezNSE5aFYtggXO7lWXDdlM3Dyt8JGmpf41srwVY+j6YjgFuFFS/9gYvrHweLyGo7cSiLl5gjiHJ+BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T19:30:42.909022Z"},"content_sha256":"80a5bbdfca39bd439b71c77b9ce14a775b9e59393e60d46c84a1884bc42a9c37","schema_version":"1.0","event_id":"sha256:80a5bbdfca39bd439b71c77b9ce14a775b9e59393e60d46c84a1884bc42a9c37"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:OWBQ25XVLBKMRKUIV3EFPAYXGI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Responsibility-Attributed Adversarial Scenarios for Testing Autonomous Vehicles","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"CARS framework generates collision scenarios for autonomous vehicle tests that carry clear responsibility attributions under standard driver models.","cross_cats":["cs.SE","cs.SY","eess.SY"],"primary_cat":"cs.RO","authors_text":"Cheng Wang, Haotian Yan, Mustafa Suphi Erden, Xintao Yan, Ying Wang, Yizhuo Xiao, Yuxin Zhang, Zhongpan Zhu","submitted_at":"2026-05-13T16:33:07Z","abstract_excerpt":"Establishing trustworthy safety assurance for autonomous driving systems (ADSs) requires evidence that failures arise from avoidable system deficiencies rather than unavoidable traffic conflicts. Current adversarial simulation methods can efficiently expose collisions, but generally lack mechanisms to distinguish these fundamentally different failure modes. Here we present CARS (Context-Aware, Responsibility-attributed Scenario generation), a framework that integrates responsibility attribution directly into adversarial scenario generation. CARS combines context-aware adversary selection with "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Across benchmark datasets spanning heterogeneous national traffic environments, CARS consistently discovers feasible collision scenarios with high attribution rates under multiple regulation-prescribed careful and competent driver models.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That responsibility attribution under the chosen driver models remains diagnostically meaningful and stable when the scenarios are generated adversarially in closed-loop simulation, without the optimization process itself biasing the attribution outcome.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"CARS integrates responsibility attribution into adversarial scenario generation to produce physically feasible collisions with high attribution rates under regulation-prescribed driver models for autonomous vehicle testing.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"CARS framework generates collision scenarios for autonomous vehicle tests that carry clear responsibility attributions under standard driver models.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"d1467f2a34a1680da3038ef19f341cc08fe38ff0204ba5fb6963a404d438ebf7"},"source":{"id":"2605.13751","kind":"arxiv","version":1},"verdict":{"id":"fedcd648-f2ba-4cf7-8244-9f523cf32fcd","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T19:23:49.230357Z","strongest_claim":"Across benchmark datasets spanning heterogeneous national traffic environments, CARS consistently discovers feasible collision scenarios with high attribution rates under multiple regulation-prescribed careful and competent driver models.","one_line_summary":"CARS integrates responsibility attribution into adversarial scenario generation to produce physically feasible collisions with high attribution rates under regulation-prescribed driver models for autonomous vehicle testing.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That responsibility attribution under the chosen driver models remains diagnostically meaningful and stable when the scenarios are generated adversarially in closed-loop simulation, without the optimization process itself biasing the attribution outcome.","pith_extraction_headline":"CARS framework generates collision scenarios for autonomous vehicle tests that carry clear responsibility attributions under standard driver models."},"references":{"count":38,"sample":[{"doi":"","year":2026,"title":"Qian, C., Xu, J., Xing, X. & Guo, F. Test case sampling optimization for safety validation of automated driving systems.Nat. Commun.17, 3114 (2026)","work_id":"e979b7e1-5a97-424c-9ab3-708015e48031","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2016,"title":"Kalra, N. & Paddock, S. M. Driving to safety: How many miles of driving would it take to demonstrate autonomous vehicle reliability?Transp. Res. Part A Policy Pract.94, 182–193 (2016)","work_id":"b512d974-7e2a-4dfc-85d4-0fa78ab2dbed","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Feng, S.et al.Dense reinforcement learning for safety validation of autonomous vehicles.Nature 615, 620–627 (2023). 12","work_id":"179eae2b-6231-4432-a417-c0697d91f7ac","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Liu, H. X. & Feng, S. Curse of rarity for autonomous vehicles.Nat. Commun.15, 4808 (2024)","work_id":"c3ef2622-f648-4064-a6fa-1b5d3ed864d4","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"Feng, S., Yan, X., Sun, H., Feng, Y . & Liu, H. X. Intelligent driving intelligence test for autonomous vehicles with naturalistic and adversarial environment.Nat. Commun.12, 748 (2021)","work_id":"fb08ef49-0381-4130-acbc-b3dd13f2f676","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":38,"snapshot_sha256":"829199414f968f3495be5d5889fe46ca2b896ea129b02347c2969623be37f495","internal_anchors":2},"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":"fedcd648-f2ba-4cf7-8244-9f523cf32fcd"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:44:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RCtqV2iI8+4Tm02XN3G58RW1euPB13eqtMThpN6s7jSI3bqxXwulrI9AoMjg3aCLmgF2lsIYAUIqapDam9VpCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T19:30:42.909721Z"},"content_sha256":"c88dd3a48faa102de907633b00537aa7d438af227bd1454202e80107108f111d","schema_version":"1.0","event_id":"sha256:c88dd3a48faa102de907633b00537aa7d438af227bd1454202e80107108f111d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OWBQ25XVLBKMRKUIV3EFPAYXGI/bundle.json","state_url":"https://pith.science/pith/OWBQ25XVLBKMRKUIV3EFPAYXGI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OWBQ25XVLBKMRKUIV3EFPAYXGI/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":"2026-05-26T19:30:42Z","links":{"resolver":"https://pith.science/pith/OWBQ25XVLBKMRKUIV3EFPAYXGI","bundle":"https://pith.science/pith/OWBQ25XVLBKMRKUIV3EFPAYXGI/bundle.json","state":"https://pith.science/pith/OWBQ25XVLBKMRKUIV3EFPAYXGI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OWBQ25XVLBKMRKUIV3EFPAYXGI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OWBQ25XVLBKMRKUIV3EFPAYXGI","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":"efd81b6aa4d60de71c7e2c6ee0228d05bb4205395ba82504f1daea8603f37a35","cross_cats_sorted":["cs.SE","cs.SY","eess.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-13T16:33:07Z","title_canon_sha256":"d1c3ea195b967f53710d854698b1b367cd99129be38d70700dd46b793b7fb0a4"},"schema_version":"1.0","source":{"id":"2605.13751","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13751","created_at":"2026-05-18T02:44:16Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13751v1","created_at":"2026-05-18T02:44:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13751","created_at":"2026-05-18T02:44:16Z"},{"alias_kind":"pith_short_12","alias_value":"OWBQ25XVLBKM","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"OWBQ25XVLBKMRKUI","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"OWBQ25XV","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:c88dd3a48faa102de907633b00537aa7d438af227bd1454202e80107108f111d","target":"graph","created_at":"2026-05-18T02:44:16Z","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":"Across benchmark datasets spanning heterogeneous national traffic environments, CARS consistently discovers feasible collision scenarios with high attribution rates under multiple regulation-prescribed careful and competent driver models."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That responsibility attribution under the chosen driver models remains diagnostically meaningful and stable when the scenarios are generated adversarially in closed-loop simulation, without the optimization process itself biasing the attribution outcome."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"CARS integrates responsibility attribution into adversarial scenario generation to produce physically feasible collisions with high attribution rates under regulation-prescribed driver models for autonomous vehicle testing."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"CARS framework generates collision scenarios for autonomous vehicle tests that carry clear responsibility attributions under standard driver models."}],"snapshot_sha256":"d1467f2a34a1680da3038ef19f341cc08fe38ff0204ba5fb6963a404d438ebf7"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Establishing trustworthy safety assurance for autonomous driving systems (ADSs) requires evidence that failures arise from avoidable system deficiencies rather than unavoidable traffic conflicts. Current adversarial simulation methods can efficiently expose collisions, but generally lack mechanisms to distinguish these fundamentally different failure modes. Here we present CARS (Context-Aware, Responsibility-attributed Scenario generation), a framework that integrates responsibility attribution directly into adversarial scenario generation. CARS combines context-aware adversary selection with ","authors_text":"Cheng Wang, Haotian Yan, Mustafa Suphi Erden, Xintao Yan, Ying Wang, Yizhuo Xiao, Yuxin Zhang, Zhongpan Zhu","cross_cats":["cs.SE","cs.SY","eess.SY"],"headline":"CARS framework generates collision scenarios for autonomous vehicle tests that carry clear responsibility attributions under standard driver models.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-13T16:33:07Z","title":"Learning Responsibility-Attributed Adversarial Scenarios for Testing Autonomous Vehicles"},"references":{"count":38,"internal_anchors":2,"resolved_work":38,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Qian, C., Xu, J., Xing, X. & Guo, F. Test case sampling optimization for safety validation of automated driving systems.Nat. Commun.17, 3114 (2026)","work_id":"e979b7e1-5a97-424c-9ab3-708015e48031","year":2026},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Kalra, N. & Paddock, S. M. Driving to safety: How many miles of driving would it take to demonstrate autonomous vehicle reliability?Transp. Res. Part A Policy Pract.94, 182–193 (2016)","work_id":"b512d974-7e2a-4dfc-85d4-0fa78ab2dbed","year":2016},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Feng, S.et al.Dense reinforcement learning for safety validation of autonomous vehicles.Nature 615, 620–627 (2023). 12","work_id":"179eae2b-6231-4432-a417-c0697d91f7ac","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Liu, H. X. & Feng, S. Curse of rarity for autonomous vehicles.Nat. Commun.15, 4808 (2024)","work_id":"c3ef2622-f648-4064-a6fa-1b5d3ed864d4","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Feng, S., Yan, X., Sun, H., Feng, Y . & Liu, H. X. Intelligent driving intelligence test for autonomous vehicles with naturalistic and adversarial environment.Nat. Commun.12, 748 (2021)","work_id":"fb08ef49-0381-4130-acbc-b3dd13f2f676","year":2021}],"snapshot_sha256":"829199414f968f3495be5d5889fe46ca2b896ea129b02347c2969623be37f495"},"source":{"id":"2605.13751","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T19:23:49.230357Z","id":"fedcd648-f2ba-4cf7-8244-9f523cf32fcd","model_set":{"reader":"grok-4.3"},"one_line_summary":"CARS integrates responsibility attribution into adversarial scenario generation to produce physically feasible collisions with high attribution rates under regulation-prescribed driver models for autonomous vehicle testing.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"CARS framework generates collision scenarios for autonomous vehicle tests that carry clear responsibility attributions under standard driver models.","strongest_claim":"Across benchmark datasets spanning heterogeneous national traffic environments, CARS consistently discovers feasible collision scenarios with high attribution rates under multiple regulation-prescribed careful and competent driver models.","weakest_assumption":"That responsibility attribution under the chosen driver models remains diagnostically meaningful and stable when the scenarios are generated adversarially in closed-loop simulation, without the optimization process itself biasing the attribution outcome."}},"verdict_id":"fedcd648-f2ba-4cf7-8244-9f523cf32fcd"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:80a5bbdfca39bd439b71c77b9ce14a775b9e59393e60d46c84a1884bc42a9c37","target":"record","created_at":"2026-05-18T02:44:16Z","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":"efd81b6aa4d60de71c7e2c6ee0228d05bb4205395ba82504f1daea8603f37a35","cross_cats_sorted":["cs.SE","cs.SY","eess.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-13T16:33:07Z","title_canon_sha256":"d1c3ea195b967f53710d854698b1b367cd99129be38d70700dd46b793b7fb0a4"},"schema_version":"1.0","source":{"id":"2605.13751","kind":"arxiv","version":1}},"canonical_sha256":"75830d76f55854c8aa88aec8578317320c3ce3bc2b47473936837d10007f01a1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"75830d76f55854c8aa88aec8578317320c3ce3bc2b47473936837d10007f01a1","first_computed_at":"2026-05-18T02:44:16.374176Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:44:16.374176Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YsGhr8s/93+sYL+EnB1DhYLjPBhgYe8vXDdkA+L1BsyotdsP2b/bzx5nalM8HWE0cJbfriY4EgnAgUiFtGKeBw==","signature_status":"signed_v1","signed_at":"2026-05-18T02:44:16.374610Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.13751","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:80a5bbdfca39bd439b71c77b9ce14a775b9e59393e60d46c84a1884bc42a9c37","sha256:c88dd3a48faa102de907633b00537aa7d438af227bd1454202e80107108f111d"],"state_sha256":"a5c21f80520fa0b611683e31283fc2b4c96dcdd03a1181ba1485b37d6507b31c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nOMt6txJKRlNhmZoyIxX9IvPqOqHM0hTTFS76QbfTJo2POoMhKnjHz98rsm0UC9Ho60NhgXfD/KmqU2rnFrwAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T19:30:42.912805Z","bundle_sha256":"e36847f067002390107ef0187597b0f72ddb9e2b1878f7d801a42c6d7f9e2391"}}