{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:JLK4YQWGKHXUZRDJCSILALA5OT","short_pith_number":"pith:JLK4YQWG","canonical_record":{"source":{"id":"2503.17332","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2025-03-21T17:32:32Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"75333c9ac78d0bd6e2dcbcfcd1135fbbf6218be6d535c112c598c112170963fc","abstract_canon_sha256":"84a1c1f36e789035a99988a367b7fda9f3af4a54ba1d78b164e9ba91942992aa"},"schema_version":"1.0"},"canonical_sha256":"4ad5cc42c651ef4cc4691490b02c1d74c57f6ac28309705e95eee5422ffc1fc4","source":{"kind":"arxiv","id":"2503.17332","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.17332","created_at":"2026-07-05T11:26:03Z"},{"alias_kind":"arxiv_version","alias_value":"2503.17332v4","created_at":"2026-07-05T11:26:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.17332","created_at":"2026-07-05T11:26:03Z"},{"alias_kind":"pith_short_12","alias_value":"JLK4YQWGKHXU","created_at":"2026-07-05T11:26:03Z"},{"alias_kind":"pith_short_16","alias_value":"JLK4YQWGKHXUZRDJ","created_at":"2026-07-05T11:26:03Z"},{"alias_kind":"pith_short_8","alias_value":"JLK4YQWG","created_at":"2026-07-05T11:26:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:JLK4YQWGKHXUZRDJCSILALA5OT","target":"record","payload":{"canonical_record":{"source":{"id":"2503.17332","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2025-03-21T17:32:32Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"75333c9ac78d0bd6e2dcbcfcd1135fbbf6218be6d535c112c598c112170963fc","abstract_canon_sha256":"84a1c1f36e789035a99988a367b7fda9f3af4a54ba1d78b164e9ba91942992aa"},"schema_version":"1.0"},"canonical_sha256":"4ad5cc42c651ef4cc4691490b02c1d74c57f6ac28309705e95eee5422ffc1fc4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:26:03.586521Z","signature_b64":"yWT7wax2sqY5NOIU/fc3IlFBw+q1f/bL0ghJ91TsgKmIUIm46X2+LqnobYvS5MaKN7a//ZjXcLIRFaEaILkcBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ad5cc42c651ef4cc4691490b02c1d74c57f6ac28309705e95eee5422ffc1fc4","last_reissued_at":"2026-07-05T11:26:03.586023Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:26:03.586023Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.17332","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:26:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mMcCL8vhYnsmJ5Zobzv5SJPwc6TnW0+Pecr5urmnbvBCek10miF/LN0swgYshHgZdG2FumueeRwa6IFzOTYOAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:52:51.493598Z"},"content_sha256":"50c8cbcb874b23cf665e257f59f8c9d5ff9f28d3c48ab64bd1651c0cf19c74aa","schema_version":"1.0","event_id":"sha256:50c8cbcb874b23cf665e257f59f8c9d5ff9f28d3c48ab64bd1651c0cf19c74aa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:JLK4YQWGKHXUZRDJCSILALA5OT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CVE-Bench: A Benchmark for AI Agents' Ability to Exploit Real-World Web Application Vulnerabilities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Adarsh Danda, Akul Gupta, Antony Kellermann, Avi Dhir, Conner Jensen, Daniel Kang, Dylan Bowman, Eric Ihli, Jason Benn, Jet Geronimo, Kaicheng Yu, Philip Li, Richard Fang, Sudhit Rao, Twm Stone, Yuxuan Zhu","submitted_at":"2025-03-21T17:32:32Z","abstract_excerpt":"Large language model (LLM) agents are increasingly capable of autonomously conducting cyberattacks, posing significant threats to existing applications. This growing risk highlights the urgent need for a real-world benchmark to evaluate the ability of LLM agents to exploit web application vulnerabilities. However, existing benchmarks fall short as they are limited to abstracted Capture the Flag competitions or lack comprehensive coverage. Building a benchmark for real-world vulnerabilities involves both specialized expertise to reproduce exploits and a systematic approach to evaluating unpredi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.17332","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2503.17332/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T11:26:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uXqyp/70V8pAWdT5sCh7C7hHgIILlawkNB2JMLvdO45hi6NuCTQXi+medfySZuUS0QZDm0JI7AA6kCBaNm3XDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:52:51.494486Z"},"content_sha256":"c1cb5cb2d504d20d7a94aa5bd36afcf4a7c46ef3b45726943703fa458b50350b","schema_version":"1.0","event_id":"sha256:c1cb5cb2d504d20d7a94aa5bd36afcf4a7c46ef3b45726943703fa458b50350b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JLK4YQWGKHXUZRDJCSILALA5OT/bundle.json","state_url":"https://pith.science/pith/JLK4YQWGKHXUZRDJCSILALA5OT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JLK4YQWGKHXUZRDJCSILALA5OT/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":"2026-08-03T19:52:51Z","links":{"resolver":"https://pith.science/pith/JLK4YQWGKHXUZRDJCSILALA5OT","bundle":"https://pith.science/pith/JLK4YQWGKHXUZRDJCSILALA5OT/bundle.json","state":"https://pith.science/pith/JLK4YQWGKHXUZRDJCSILALA5OT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JLK4YQWGKHXUZRDJCSILALA5OT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JLK4YQWGKHXUZRDJCSILALA5OT","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":"84a1c1f36e789035a99988a367b7fda9f3af4a54ba1d78b164e9ba91942992aa","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2025-03-21T17:32:32Z","title_canon_sha256":"75333c9ac78d0bd6e2dcbcfcd1135fbbf6218be6d535c112c598c112170963fc"},"schema_version":"1.0","source":{"id":"2503.17332","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.17332","created_at":"2026-07-05T11:26:03Z"},{"alias_kind":"arxiv_version","alias_value":"2503.17332v4","created_at":"2026-07-05T11:26:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.17332","created_at":"2026-07-05T11:26:03Z"},{"alias_kind":"pith_short_12","alias_value":"JLK4YQWGKHXU","created_at":"2026-07-05T11:26:03Z"},{"alias_kind":"pith_short_16","alias_value":"JLK4YQWGKHXUZRDJ","created_at":"2026-07-05T11:26:03Z"},{"alias_kind":"pith_short_8","alias_value":"JLK4YQWG","created_at":"2026-07-05T11:26:03Z"}],"graph_snapshots":[{"event_id":"sha256:c1cb5cb2d504d20d7a94aa5bd36afcf4a7c46ef3b45726943703fa458b50350b","target":"graph","created_at":"2026-07-05T11:26:03Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2503.17332/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language model (LLM) agents are increasingly capable of autonomously conducting cyberattacks, posing significant threats to existing applications. This growing risk highlights the urgent need for a real-world benchmark to evaluate the ability of LLM agents to exploit web application vulnerabilities. However, existing benchmarks fall short as they are limited to abstracted Capture the Flag competitions or lack comprehensive coverage. Building a benchmark for real-world vulnerabilities involves both specialized expertise to reproduce exploits and a systematic approach to evaluating unpredi","authors_text":"Adarsh Danda, Akul Gupta, Antony Kellermann, Avi Dhir, Conner Jensen, Daniel Kang, Dylan Bowman, Eric Ihli, Jason Benn, Jet Geronimo, Kaicheng Yu, Philip Li, Richard Fang, Sudhit Rao, Twm Stone, Yuxuan Zhu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2025-03-21T17:32:32Z","title":"CVE-Bench: A Benchmark for AI Agents' Ability to Exploit Real-World Web Application Vulnerabilities"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.17332","kind":"arxiv","version":4},"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":"sha256:50c8cbcb874b23cf665e257f59f8c9d5ff9f28d3c48ab64bd1651c0cf19c74aa","target":"record","created_at":"2026-07-05T11:26:03Z","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":"84a1c1f36e789035a99988a367b7fda9f3af4a54ba1d78b164e9ba91942992aa","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2025-03-21T17:32:32Z","title_canon_sha256":"75333c9ac78d0bd6e2dcbcfcd1135fbbf6218be6d535c112c598c112170963fc"},"schema_version":"1.0","source":{"id":"2503.17332","kind":"arxiv","version":4}},"canonical_sha256":"4ad5cc42c651ef4cc4691490b02c1d74c57f6ac28309705e95eee5422ffc1fc4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4ad5cc42c651ef4cc4691490b02c1d74c57f6ac28309705e95eee5422ffc1fc4","first_computed_at":"2026-07-05T11:26:03.586023Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:26:03.586023Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yWT7wax2sqY5NOIU/fc3IlFBw+q1f/bL0ghJ91TsgKmIUIm46X2+LqnobYvS5MaKN7a//ZjXcLIRFaEaILkcBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:26:03.586521Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.17332","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:50c8cbcb874b23cf665e257f59f8c9d5ff9f28d3c48ab64bd1651c0cf19c74aa","sha256:c1cb5cb2d504d20d7a94aa5bd36afcf4a7c46ef3b45726943703fa458b50350b"],"state_sha256":"397254f70da6b4895e9eac13922ce82afad6ed21e6e07c7348b0101a1262e6a9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uj3zc8OWjVUsrVA1Grvjam1xkGvooYxJFf5+/7OLkprr9kez4Vc+9XX9eztRSITRdf+2x94f8StvNXUSXreyDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T19:52:51.501003Z","bundle_sha256":"fe26795b053154c5f6b9b2f5a7d691a52931c468e334cd3382a3390c88021bdb"}}