{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:CZF6CG3DPWAB4AUK3A6S4TWMLX","short_pith_number":"pith:CZF6CG3D","schema_version":"1.0","canonical_sha256":"164be11b637d801e028ad83d2e4ecc5df0a676b65502f79a63ae1f038c4927fe","source":{"kind":"arxiv","id":"2109.06449","version":1},"attestation_state":"computed","paper":{"title":"Deep hierarchical reinforcement agents for automated penetration testing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.LG"],"primary_cat":"cs.AI","authors_text":"(2) Institution Two), Ashlesha Akella (1), Chin-Teng Lin (1) ((1) Institution One, David Bowman (2), Junae Kim (2), Khuong Tran (1), Maxwell Standen (2), Toby Richer (2)","submitted_at":"2021-09-14T05:28:22Z","abstract_excerpt":"Penetration testing the organised attack of a computer system in order to test existing defences has been used extensively to evaluate network security. This is a time consuming process and requires in-depth knowledge for the establishment of a strategy that resembles a real cyber-attack. This paper presents a novel deep reinforcement learning architecture with hierarchically structured agents called HA-DRL, which employs an algebraic action decomposition strategy to address the large discrete action space of an autonomous penetration testing simulator where the number of actions is exponentia"},"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":"2109.06449","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-09-14T05:28:22Z","cross_cats_sorted":["cs.CR","cs.LG"],"title_canon_sha256":"34ceb81703fd41789fd72f3ef47998c58cf7a34152a0245c3a5407180af09f79","abstract_canon_sha256":"918201de65438959fb4cc8f1fc14595806b658c946b2979f1d0cc399dbd3bccc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:13:54.543038Z","signature_b64":"rIvrjz2oRgR2VnUbdS2IxrZLjsAbjiSHTftDxM+lLJj5jVFyRBI4FKL3Fjnbt7Z3L4fIuMWlvy5yH//Z30BiCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"164be11b637d801e028ad83d2e4ecc5df0a676b65502f79a63ae1f038c4927fe","last_reissued_at":"2026-07-05T03:13:54.542528Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:13:54.542528Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep hierarchical reinforcement agents for automated penetration testing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.LG"],"primary_cat":"cs.AI","authors_text":"(2) Institution Two), Ashlesha Akella (1), Chin-Teng Lin (1) ((1) Institution One, David Bowman (2), Junae Kim (2), Khuong Tran (1), Maxwell Standen (2), Toby Richer (2)","submitted_at":"2021-09-14T05:28:22Z","abstract_excerpt":"Penetration testing the organised attack of a computer system in order to test existing defences has been used extensively to evaluate network security. This is a time consuming process and requires in-depth knowledge for the establishment of a strategy that resembles a real cyber-attack. This paper presents a novel deep reinforcement learning architecture with hierarchically structured agents called HA-DRL, which employs an algebraic action decomposition strategy to address the large discrete action space of an autonomous penetration testing simulator where the number of actions is exponentia"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.06449","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/2109.06449/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":"2109.06449","created_at":"2026-07-05T03:13:54.542586+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.06449v1","created_at":"2026-07-05T03:13:54.542586+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.06449","created_at":"2026-07-05T03:13:54.542586+00:00"},{"alias_kind":"pith_short_12","alias_value":"CZF6CG3DPWAB","created_at":"2026-07-05T03:13:54.542586+00:00"},{"alias_kind":"pith_short_16","alias_value":"CZF6CG3DPWAB4AUK","created_at":"2026-07-05T03:13:54.542586+00:00"},{"alias_kind":"pith_short_8","alias_value":"CZF6CG3D","created_at":"2026-07-05T03:13:54.542586+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.13021","citing_title":"xOffense: An Autonomous Multi-Agent Framework for Penetration Testing with Domain-Adapted Large Language Models","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CZF6CG3DPWAB4AUK3A6S4TWMLX","json":"https://pith.science/pith/CZF6CG3DPWAB4AUK3A6S4TWMLX.json","graph_json":"https://pith.science/api/pith-number/CZF6CG3DPWAB4AUK3A6S4TWMLX/graph.json","events_json":"https://pith.science/api/pith-number/CZF6CG3DPWAB4AUK3A6S4TWMLX/events.json","paper":"https://pith.science/paper/CZF6CG3D"},"agent_actions":{"view_html":"https://pith.science/pith/CZF6CG3DPWAB4AUK3A6S4TWMLX","download_json":"https://pith.science/pith/CZF6CG3DPWAB4AUK3A6S4TWMLX.json","view_paper":"https://pith.science/paper/CZF6CG3D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.06449&json=true","fetch_graph":"https://pith.science/api/pith-number/CZF6CG3DPWAB4AUK3A6S4TWMLX/graph.json","fetch_events":"https://pith.science/api/pith-number/CZF6CG3DPWAB4AUK3A6S4TWMLX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CZF6CG3DPWAB4AUK3A6S4TWMLX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CZF6CG3DPWAB4AUK3A6S4TWMLX/action/storage_attestation","attest_author":"https://pith.science/pith/CZF6CG3DPWAB4AUK3A6S4TWMLX/action/author_attestation","sign_citation":"https://pith.science/pith/CZF6CG3DPWAB4AUK3A6S4TWMLX/action/citation_signature","submit_replication":"https://pith.science/pith/CZF6CG3DPWAB4AUK3A6S4TWMLX/action/replication_record"}},"created_at":"2026-07-05T03:13:54.542586+00:00","updated_at":"2026-07-05T03:13:54.542586+00:00"}