{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:HS4AIKW7PT6JOUBAB3YKRS2IOU","short_pith_number":"pith:HS4AIKW7","schema_version":"1.0","canonical_sha256":"3cb8042adf7cfc9750200ef0a8cb4875060468f979640321f12fa12882201c79","source":{"kind":"arxiv","id":"2005.12632","version":2},"attestation_state":"computed","paper":{"title":"Modeling Penetration Testing with Reinforcement Learning Using Capture-the-Flag Challenges: Trade-offs between Model-free Learning and A Priori Knowledge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CR","authors_text":"Fabio Massimo Zennaro, Laszlo Erdodi","submitted_at":"2020-05-26T11:23:10Z","abstract_excerpt":"Penetration testing is a security exercise aimed at assessing the security of a system by simulating attacks against it. So far, penetration testing has been carried out mainly by trained human attackers and its success critically depended on the available expertise. Automating this practice constitutes a non-trivial problem, as the range of actions that a human expert may attempts against a system and the range of knowledge she relies on to take her decisions are hard to capture. In this paper, we focus our attention on simplified penetration testing problems expressed in the form of capture "},"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":"2005.12632","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2020-05-26T11:23:10Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"ed3f04542f03c7f676f71d6495497654873ddd29c3458f56c008332db22fe3ed","abstract_canon_sha256":"67547b4d2dd6874da27d5cc22712798a790ef02f6d186b5ce21281402f727cdf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:42:12.960350Z","signature_b64":"YMiV+HWIjiAMnKL60nJFIaFPkGznrGA5S+/sXfJ/PBwoUi0kZLvqVFP9dGfvI99E9qMPijza2jyZU3ecEIJ4Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3cb8042adf7cfc9750200ef0a8cb4875060468f979640321f12fa12882201c79","last_reissued_at":"2026-07-05T02:42:12.959890Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:42:12.959890Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Modeling Penetration Testing with Reinforcement Learning Using Capture-the-Flag Challenges: Trade-offs between Model-free Learning and A Priori Knowledge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CR","authors_text":"Fabio Massimo Zennaro, Laszlo Erdodi","submitted_at":"2020-05-26T11:23:10Z","abstract_excerpt":"Penetration testing is a security exercise aimed at assessing the security of a system by simulating attacks against it. So far, penetration testing has been carried out mainly by trained human attackers and its success critically depended on the available expertise. Automating this practice constitutes a non-trivial problem, as the range of actions that a human expert may attempts against a system and the range of knowledge she relies on to take her decisions are hard to capture. In this paper, we focus our attention on simplified penetration testing problems expressed in the form of capture "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.12632","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2005.12632/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":"2005.12632","created_at":"2026-07-05T02:42:12.959950+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.12632v2","created_at":"2026-07-05T02:42:12.959950+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.12632","created_at":"2026-07-05T02:42:12.959950+00:00"},{"alias_kind":"pith_short_12","alias_value":"HS4AIKW7PT6J","created_at":"2026-07-05T02:42:12.959950+00:00"},{"alias_kind":"pith_short_16","alias_value":"HS4AIKW7PT6JOUBA","created_at":"2026-07-05T02:42:12.959950+00:00"},{"alias_kind":"pith_short_8","alias_value":"HS4AIKW7","created_at":"2026-07-05T02:42:12.959950+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.04078","citing_title":"Mind the Gap: Towards Generalizable Autonomous Penetration Testing via Domain Randomization and Meta-Reinforcement Learning","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HS4AIKW7PT6JOUBAB3YKRS2IOU","json":"https://pith.science/pith/HS4AIKW7PT6JOUBAB3YKRS2IOU.json","graph_json":"https://pith.science/api/pith-number/HS4AIKW7PT6JOUBAB3YKRS2IOU/graph.json","events_json":"https://pith.science/api/pith-number/HS4AIKW7PT6JOUBAB3YKRS2IOU/events.json","paper":"https://pith.science/paper/HS4AIKW7"},"agent_actions":{"view_html":"https://pith.science/pith/HS4AIKW7PT6JOUBAB3YKRS2IOU","download_json":"https://pith.science/pith/HS4AIKW7PT6JOUBAB3YKRS2IOU.json","view_paper":"https://pith.science/paper/HS4AIKW7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.12632&json=true","fetch_graph":"https://pith.science/api/pith-number/HS4AIKW7PT6JOUBAB3YKRS2IOU/graph.json","fetch_events":"https://pith.science/api/pith-number/HS4AIKW7PT6JOUBAB3YKRS2IOU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HS4AIKW7PT6JOUBAB3YKRS2IOU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HS4AIKW7PT6JOUBAB3YKRS2IOU/action/storage_attestation","attest_author":"https://pith.science/pith/HS4AIKW7PT6JOUBAB3YKRS2IOU/action/author_attestation","sign_citation":"https://pith.science/pith/HS4AIKW7PT6JOUBAB3YKRS2IOU/action/citation_signature","submit_replication":"https://pith.science/pith/HS4AIKW7PT6JOUBAB3YKRS2IOU/action/replication_record"}},"created_at":"2026-07-05T02:42:12.959950+00:00","updated_at":"2026-07-05T02:42:12.959950+00:00"}