{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PKWRG7AW7NQDFX46QNSFRZZNLJ","short_pith_number":"pith:PKWRG7AW","schema_version":"1.0","canonical_sha256":"7aad137c16fb6032df9e836458e72d5a7cb02974eaf43150e9f956ce8924fb67","source":{"kind":"arxiv","id":"2508.20816","version":1},"attestation_state":"computed","paper":{"title":"Multi-Agent Penetration Testing AI for the Web","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Arthur Gervais, Isaac David","submitted_at":"2025-08-28T14:14:24Z","abstract_excerpt":"AI-powered development platforms are making software creation accessible to a broader audience, but this democratization has triggered a scalability crisis in security auditing. With studies showing that up to 40% of AI-generated code contains vulnerabilities, the pace of development now vastly outstrips the capacity for thorough security assessment.\n  We present MAPTA, a multi-agent system for autonomous web application security assessment that combines large language model orchestration with tool-grounded execution and end-to-end exploit validation. On the 104-challenge XBOW benchmark, MAPTA"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2508.20816","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2025-08-28T14:14:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a8d6a2e26f2f32931487cea5fead534ed8456fe6354e25ea8dcdf3f8c47c2e8b","abstract_canon_sha256":"53c7d9542ff168cd32e8da37330e132f437f38bf826f8864f6d65b6d55043b47"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:01:11.554549Z","signature_b64":"ax0bDY9LmtqndJhZRZs9FtohHL6G1VJRADDLq1c/UWuE6I6stPxFmTpAt/aDG7cRMpyYUHC8ONvU3P28CUlqDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7aad137c16fb6032df9e836458e72d5a7cb02974eaf43150e9f956ce8924fb67","last_reissued_at":"2026-07-05T12:01:11.554029Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:01:11.554029Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Agent Penetration Testing AI for the Web","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Arthur Gervais, Isaac David","submitted_at":"2025-08-28T14:14:24Z","abstract_excerpt":"AI-powered development platforms are making software creation accessible to a broader audience, but this democratization has triggered a scalability crisis in security auditing. With studies showing that up to 40% of AI-generated code contains vulnerabilities, the pace of development now vastly outstrips the capacity for thorough security assessment.\n  We present MAPTA, a multi-agent system for autonomous web application security assessment that combines large language model orchestration with tool-grounded execution and end-to-end exploit validation. On the 104-challenge XBOW benchmark, MAPTA"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.20816","kind":"arxiv","version":1},"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/2508.20816/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2508.20816","created_at":"2026-07-05T12:01:11.554088+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.20816v1","created_at":"2026-07-05T12:01:11.554088+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.20816","created_at":"2026-07-05T12:01:11.554088+00:00"},{"alias_kind":"pith_short_12","alias_value":"PKWRG7AW7NQD","created_at":"2026-07-05T12:01:11.554088+00:00"},{"alias_kind":"pith_short_16","alias_value":"PKWRG7AW7NQDFX46","created_at":"2026-07-05T12:01:11.554088+00:00"},{"alias_kind":"pith_short_8","alias_value":"PKWRG7AW","created_at":"2026-07-05T12:01:11.554088+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.29981","citing_title":"Hephaestus: Toward a Cybersecurity AI Scientist","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17416","citing_title":"Benchmarking Mythos-Linked Bug Rediscovery","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2603.09002","citing_title":"Security Considerations for Multi-agent Systems","ref_index":286,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10834","citing_title":"From Controlled to the Wild: Evaluation of Pentesting Agents for the Real-World","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10074","citing_title":"Agentic Fuzzing: Opportunities and Challenges","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10597","citing_title":"CrackMeBench: Binary Reverse Engineering for Agents","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06601","citing_title":"Patch2Vuln: Agentic Reconstruction of Vulnerabilities from Linux Distribution Binary Patches","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00081","citing_title":"Alignment Contracts for Agentic Security Systems","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18718","citing_title":"Towards Optimal Agentic Architectures for Offensive Security Tasks","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05719","citing_title":"Hackers or Hallucinators? A Comprehensive Analysis of LLM-Based Automated Penetration Testing","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PKWRG7AW7NQDFX46QNSFRZZNLJ","json":"https://pith.science/pith/PKWRG7AW7NQDFX46QNSFRZZNLJ.json","graph_json":"https://pith.science/api/pith-number/PKWRG7AW7NQDFX46QNSFRZZNLJ/graph.json","events_json":"https://pith.science/api/pith-number/PKWRG7AW7NQDFX46QNSFRZZNLJ/events.json","paper":"https://pith.science/paper/PKWRG7AW"},"agent_actions":{"view_html":"https://pith.science/pith/PKWRG7AW7NQDFX46QNSFRZZNLJ","download_json":"https://pith.science/pith/PKWRG7AW7NQDFX46QNSFRZZNLJ.json","view_paper":"https://pith.science/paper/PKWRG7AW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.20816&json=true","fetch_graph":"https://pith.science/api/pith-number/PKWRG7AW7NQDFX46QNSFRZZNLJ/graph.json","fetch_events":"https://pith.science/api/pith-number/PKWRG7AW7NQDFX46QNSFRZZNLJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PKWRG7AW7NQDFX46QNSFRZZNLJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PKWRG7AW7NQDFX46QNSFRZZNLJ/action/storage_attestation","attest_author":"https://pith.science/pith/PKWRG7AW7NQDFX46QNSFRZZNLJ/action/author_attestation","sign_citation":"https://pith.science/pith/PKWRG7AW7NQDFX46QNSFRZZNLJ/action/citation_signature","submit_replication":"https://pith.science/pith/PKWRG7AW7NQDFX46QNSFRZZNLJ/action/replication_record"}},"created_at":"2026-07-05T12:01:11.554088+00:00","updated_at":"2026-07-05T12:01:11.554088+00:00"}