{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:OWPBRGOVCT6T6G3H4WANXPQKSO","short_pith_number":"pith:OWPBRGOV","canonical_record":{"source":{"id":"2509.26100","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-09-30T11:20:41Z","cross_cats_sorted":[],"title_canon_sha256":"697e696b47ff6d12732393e39e764ae728b65d61c54d5fecd600de0c09d20ee1","abstract_canon_sha256":"0c282c1d2149cc5786d65f14f02efd5417148f3688bd08fcff6dd826f9caaf1a"},"schema_version":"1.0"},"canonical_sha256":"759e1899d514fd3f1b67e580dbbe0a93a917e025e5b1dd7ac7ec8327371b085e","source":{"kind":"arxiv","id":"2509.26100","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.26100","created_at":"2026-05-17T23:39:17Z"},{"alias_kind":"arxiv_version","alias_value":"2509.26100v2","created_at":"2026-05-17T23:39:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.26100","created_at":"2026-05-17T23:39:17Z"},{"alias_kind":"pith_short_12","alias_value":"OWPBRGOVCT6T","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"OWPBRGOVCT6T6G3H","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"OWPBRGOV","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:OWPBRGOVCT6T6G3H4WANXPQKSO","target":"record","payload":{"canonical_record":{"source":{"id":"2509.26100","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-09-30T11:20:41Z","cross_cats_sorted":[],"title_canon_sha256":"697e696b47ff6d12732393e39e764ae728b65d61c54d5fecd600de0c09d20ee1","abstract_canon_sha256":"0c282c1d2149cc5786d65f14f02efd5417148f3688bd08fcff6dd826f9caaf1a"},"schema_version":"1.0"},"canonical_sha256":"759e1899d514fd3f1b67e580dbbe0a93a917e025e5b1dd7ac7ec8327371b085e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:17.393468Z","signature_b64":"lG9P+EzFVOHMguHCtzDt/zJiqH6d8ezL1Y42gAxiGlYClvHMUCHh4ZVkzW6ykXgkLZdh25q401Rgn4yzN2vRDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"759e1899d514fd3f1b67e580dbbe0a93a917e025e5b1dd7ac7ec8327371b085e","last_reissued_at":"2026-05-17T23:39:17.392805Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:17.392805Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.26100","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":"2026-05-17T23:39:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E6wgwcyyQID1Q3Macre5e7ojauasX+0Tx34F/1uonS+eW+3RVGnumZ1uUMGFIUbuh3SwlG8GMHGzufmgtuiEAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T10:45:43.869452Z"},"content_sha256":"89094e827bf214a4e7018a6f1af954c1900c5a52dcf24e467090eef0657b88a3","schema_version":"1.0","event_id":"sha256:89094e827bf214a4e7018a6f1af954c1900c5a52dcf24e467090eef0657b88a3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:OWPBRGOVCT6T6G3H4WANXPQKSO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AgenticEval: Toward Agentic and Self-Evolving Safety Evaluation of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Xibang Yang, Xingjun Ma, Xin Wang, Xinyuan Li, Yang Yao, Yan Teng, Yingchun Wang, Yixu Wang","submitted_at":"2025-09-30T11:20:41Z","abstract_excerpt":"The rapid integration of Large Language Models (LLMs) into high-stakes domains necessitates reliable safety and compliance evaluation. However, existing static benchmarks are ill-equipped to address the dynamic nature of AI risks and evolving regulations, creating a critical safety gap. This paper introduces a new paradigm of agentic safety evaluation, reframing evaluation as a continuous and self-evolving process rather than a one-time audit. We then propose a novel multi-agent framework AgenticEval, which autonomously ingests unstructured policy documents to generate and perpetually evolve a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.26100","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"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":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FujvIK01QdprgTz22uJYBikkEjrOnb1khkTfbQz9E1jRXquJLwBKLYHqCs9sywi/E5mvNnlZL8QVXO4CihdhAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T10:45:43.869877Z"},"content_sha256":"dbd5cedc6efe999953cb3a38d8bdc47c79554f26f083331521f8d34768e81a3c","schema_version":"1.0","event_id":"sha256:dbd5cedc6efe999953cb3a38d8bdc47c79554f26f083331521f8d34768e81a3c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OWPBRGOVCT6T6G3H4WANXPQKSO/bundle.json","state_url":"https://pith.science/pith/OWPBRGOVCT6T6G3H4WANXPQKSO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OWPBRGOVCT6T6G3H4WANXPQKSO/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":"2026-05-26T10:45:43Z","links":{"resolver":"https://pith.science/pith/OWPBRGOVCT6T6G3H4WANXPQKSO","bundle":"https://pith.science/pith/OWPBRGOVCT6T6G3H4WANXPQKSO/bundle.json","state":"https://pith.science/pith/OWPBRGOVCT6T6G3H4WANXPQKSO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OWPBRGOVCT6T6G3H4WANXPQKSO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OWPBRGOVCT6T6G3H4WANXPQKSO","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":"0c282c1d2149cc5786d65f14f02efd5417148f3688bd08fcff6dd826f9caaf1a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-09-30T11:20:41Z","title_canon_sha256":"697e696b47ff6d12732393e39e764ae728b65d61c54d5fecd600de0c09d20ee1"},"schema_version":"1.0","source":{"id":"2509.26100","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.26100","created_at":"2026-05-17T23:39:17Z"},{"alias_kind":"arxiv_version","alias_value":"2509.26100v2","created_at":"2026-05-17T23:39:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.26100","created_at":"2026-05-17T23:39:17Z"},{"alias_kind":"pith_short_12","alias_value":"OWPBRGOVCT6T","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"OWPBRGOVCT6T6G3H","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"OWPBRGOV","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:dbd5cedc6efe999953cb3a38d8bdc47c79554f26f083331521f8d34768e81a3c","target":"graph","created_at":"2026-05-17T23:39:17Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"The rapid integration of Large Language Models (LLMs) into high-stakes domains necessitates reliable safety and compliance evaluation. However, existing static benchmarks are ill-equipped to address the dynamic nature of AI risks and evolving regulations, creating a critical safety gap. This paper introduces a new paradigm of agentic safety evaluation, reframing evaluation as a continuous and self-evolving process rather than a one-time audit. We then propose a novel multi-agent framework AgenticEval, which autonomously ingests unstructured policy documents to generate and perpetually evolve a","authors_text":"Xibang Yang, Xingjun Ma, Xin Wang, Xinyuan Li, Yang Yao, Yan Teng, Yingchun Wang, Yixu Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-09-30T11:20:41Z","title":"AgenticEval: Toward Agentic and Self-Evolving Safety Evaluation of Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.26100","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:89094e827bf214a4e7018a6f1af954c1900c5a52dcf24e467090eef0657b88a3","target":"record","created_at":"2026-05-17T23:39:17Z","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":"0c282c1d2149cc5786d65f14f02efd5417148f3688bd08fcff6dd826f9caaf1a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-09-30T11:20:41Z","title_canon_sha256":"697e696b47ff6d12732393e39e764ae728b65d61c54d5fecd600de0c09d20ee1"},"schema_version":"1.0","source":{"id":"2509.26100","kind":"arxiv","version":2}},"canonical_sha256":"759e1899d514fd3f1b67e580dbbe0a93a917e025e5b1dd7ac7ec8327371b085e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"759e1899d514fd3f1b67e580dbbe0a93a917e025e5b1dd7ac7ec8327371b085e","first_computed_at":"2026-05-17T23:39:17.392805Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:17.392805Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lG9P+EzFVOHMguHCtzDt/zJiqH6d8ezL1Y42gAxiGlYClvHMUCHh4ZVkzW6ykXgkLZdh25q401Rgn4yzN2vRDQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:17.393468Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.26100","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:89094e827bf214a4e7018a6f1af954c1900c5a52dcf24e467090eef0657b88a3","sha256:dbd5cedc6efe999953cb3a38d8bdc47c79554f26f083331521f8d34768e81a3c"],"state_sha256":"476d4c4642d27869f92dda0865dc45a16287cdffe2dd1e49c5bfbe30bf4c639e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ftjx8me8A383+V4kMnM27qtIfMwyxgkZuyXXrnUwmK5WY/mhYHj2D6GndDfOkSvUHkxvtHONCPgThCCVyUYuCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T10:45:43.873175Z","bundle_sha256":"e3424f20a43c997b5d1024a4dfbf11907989da059d45497e41461bcc25a3632d"}}