{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JKZLZLNBHO6SB6EW3IJFSIB2PH","short_pith_number":"pith:JKZLZLNB","schema_version":"1.0","canonical_sha256":"4ab2bcada13bbd20f896da1259203a79d1ae64992e534a2674992f0460173564","source":{"kind":"arxiv","id":"2505.06913","version":1},"attestation_state":"computed","paper":{"title":"RedTeamLLM: an Agentic AI framework for offensive security","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CY"],"primary_cat":"cs.CR","authors_text":"Brian Challita, Pierre Parrend","submitted_at":"2025-05-11T09:19:10Z","abstract_excerpt":"From automated intrusion testing to discovery of zero-day attacks before software launch, agentic AI calls for great promises in security engineering. This strong capability is bound with a similar threat: the security and research community must build up its models before the approach is leveraged by malicious actors for cybercrime. We therefore propose and evaluate RedTeamLLM, an integrated architecture with a comprehensive security model for automatization of pentest tasks. RedTeamLLM follows three key steps: summarizing, reasoning and act, which embed its operational capacity. This novel f"},"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":"2505.06913","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2025-05-11T09:19:10Z","cross_cats_sorted":["cs.AI","cs.CY"],"title_canon_sha256":"9d95c2496ace0502981d6cf32f35bedbdf84decdd4f16037d37cbc79b15aee4b","abstract_canon_sha256":"c761a46d82282110e3f9f089f0d7702b2060dcd0308d3a00748ab3109f94d3e4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:01:39.165116Z","signature_b64":"OS61AkSpRnu26j5nx4wVRWMqYPPzz4VcsXzpePfx9bkwLVyRZWgLdP0wqNuw6NSEJNhs5tccHxmbztsoVzUACQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ab2bcada13bbd20f896da1259203a79d1ae64992e534a2674992f0460173564","last_reissued_at":"2026-07-05T11:01:39.164639Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:01:39.164639Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RedTeamLLM: an Agentic AI framework for offensive security","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CY"],"primary_cat":"cs.CR","authors_text":"Brian Challita, Pierre Parrend","submitted_at":"2025-05-11T09:19:10Z","abstract_excerpt":"From automated intrusion testing to discovery of zero-day attacks before software launch, agentic AI calls for great promises in security engineering. This strong capability is bound with a similar threat: the security and research community must build up its models before the approach is leveraged by malicious actors for cybercrime. We therefore propose and evaluate RedTeamLLM, an integrated architecture with a comprehensive security model for automatization of pentest tasks. RedTeamLLM follows three key steps: summarizing, reasoning and act, which embed its operational capacity. This novel f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.06913","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/2505.06913/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":"2505.06913","created_at":"2026-07-05T11:01:39.164697+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.06913v1","created_at":"2026-07-05T11:01:39.164697+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.06913","created_at":"2026-07-05T11:01:39.164697+00:00"},{"alias_kind":"pith_short_12","alias_value":"JKZLZLNBHO6S","created_at":"2026-07-05T11:01:39.164697+00:00"},{"alias_kind":"pith_short_16","alias_value":"JKZLZLNBHO6SB6EW","created_at":"2026-07-05T11:01:39.164697+00:00"},{"alias_kind":"pith_short_8","alias_value":"JKZLZLNB","created_at":"2026-07-05T11:01:39.164697+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.28334","citing_title":"Towards Cybersecurity SuperIntelligence (CSI): What's the best harness for cybersecurity?","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01892","citing_title":"CyberAId: AI-Driven Cybersecurity for Financial Service Providers","ref_index":25,"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":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JKZLZLNBHO6SB6EW3IJFSIB2PH","json":"https://pith.science/pith/JKZLZLNBHO6SB6EW3IJFSIB2PH.json","graph_json":"https://pith.science/api/pith-number/JKZLZLNBHO6SB6EW3IJFSIB2PH/graph.json","events_json":"https://pith.science/api/pith-number/JKZLZLNBHO6SB6EW3IJFSIB2PH/events.json","paper":"https://pith.science/paper/JKZLZLNB"},"agent_actions":{"view_html":"https://pith.science/pith/JKZLZLNBHO6SB6EW3IJFSIB2PH","download_json":"https://pith.science/pith/JKZLZLNBHO6SB6EW3IJFSIB2PH.json","view_paper":"https://pith.science/paper/JKZLZLNB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.06913&json=true","fetch_graph":"https://pith.science/api/pith-number/JKZLZLNBHO6SB6EW3IJFSIB2PH/graph.json","fetch_events":"https://pith.science/api/pith-number/JKZLZLNBHO6SB6EW3IJFSIB2PH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JKZLZLNBHO6SB6EW3IJFSIB2PH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JKZLZLNBHO6SB6EW3IJFSIB2PH/action/storage_attestation","attest_author":"https://pith.science/pith/JKZLZLNBHO6SB6EW3IJFSIB2PH/action/author_attestation","sign_citation":"https://pith.science/pith/JKZLZLNBHO6SB6EW3IJFSIB2PH/action/citation_signature","submit_replication":"https://pith.science/pith/JKZLZLNBHO6SB6EW3IJFSIB2PH/action/replication_record"}},"created_at":"2026-07-05T11:01:39.164697+00:00","updated_at":"2026-07-05T11:01:39.164697+00:00"}