{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FOS6J2TGILZ5UVHB2QHBLFBMYZ","short_pith_number":"pith:FOS6J2TG","schema_version":"1.0","canonical_sha256":"2ba5e4ea6642f3da54e1d40e15942cc6438d882a92672a10b19956468eb04409","source":{"kind":"arxiv","id":"2401.10149","version":1},"attestation_state":"computed","paper":{"title":"Multi-Agent Reinforcement Learning for Maritime Operational Technology Cyber Security","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR","cs.MA"],"primary_cat":"cs.LG","authors_text":"Alec Wilson, David Foster, Esin Turkbeyler, Lisa Gralewski, Marco Casassa Mont, Neela Morarji, Ryan Menzies","submitted_at":"2024-01-18T17:22:22Z","abstract_excerpt":"This paper demonstrates the potential for autonomous cyber defence to be applied on industrial control systems and provides a baseline environment to further explore Multi-Agent Reinforcement Learning's (MARL) application to this problem domain. It introduces a simulation environment, IPMSRL, of a generic Integrated Platform Management System (IPMS) and explores the use of MARL for autonomous cyber defence decision-making on generic maritime based IPMS Operational Technology (OT). OT cyber defensive actions are less mature than they are for Enterprise IT. This is due to the relatively brittle "},"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":"2401.10149","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-01-18T17:22:22Z","cross_cats_sorted":["cs.CR","cs.MA"],"title_canon_sha256":"a2702fb99a67015113e0d1cd3e07ad9a0e4a3174fefe47c2a920a2c8fb4e1331","abstract_canon_sha256":"5ebed4b25f652de4537f586fe40640cd3bb116841f2fa1e8be0ea3c4a77b0a06"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:31:10.818117Z","signature_b64":"Y/SnduWQMuWzJm4F4dF8qemYtFkXsEcpYzt703H1QcvREFW+piWHZVYUk7C4NRl7buL5eXfXSLxymK2gwIpkAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ba5e4ea6642f3da54e1d40e15942cc6438d882a92672a10b19956468eb04409","last_reissued_at":"2026-07-05T08:31:10.817616Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:31:10.817616Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Agent Reinforcement Learning for Maritime Operational Technology Cyber Security","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR","cs.MA"],"primary_cat":"cs.LG","authors_text":"Alec Wilson, David Foster, Esin Turkbeyler, Lisa Gralewski, Marco Casassa Mont, Neela Morarji, Ryan Menzies","submitted_at":"2024-01-18T17:22:22Z","abstract_excerpt":"This paper demonstrates the potential for autonomous cyber defence to be applied on industrial control systems and provides a baseline environment to further explore Multi-Agent Reinforcement Learning's (MARL) application to this problem domain. It introduces a simulation environment, IPMSRL, of a generic Integrated Platform Management System (IPMS) and explores the use of MARL for autonomous cyber defence decision-making on generic maritime based IPMS Operational Technology (OT). OT cyber defensive actions are less mature than they are for Enterprise IT. This is due to the relatively brittle "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.10149","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/2401.10149/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":"2401.10149","created_at":"2026-07-05T08:31:10.817679+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.10149v1","created_at":"2026-07-05T08:31:10.817679+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.10149","created_at":"2026-07-05T08:31:10.817679+00:00"},{"alias_kind":"pith_short_12","alias_value":"FOS6J2TGILZ5","created_at":"2026-07-05T08:31:10.817679+00:00"},{"alias_kind":"pith_short_16","alias_value":"FOS6J2TGILZ5UVHB","created_at":"2026-07-05T08:31:10.817679+00:00"},{"alias_kind":"pith_short_8","alias_value":"FOS6J2TG","created_at":"2026-07-05T08:31:10.817679+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.09792","citing_title":"Operationalizing Cybersecurity Governance for Mitigation Planning with Attack-Path Modeling and Reinforcement Learning","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FOS6J2TGILZ5UVHB2QHBLFBMYZ","json":"https://pith.science/pith/FOS6J2TGILZ5UVHB2QHBLFBMYZ.json","graph_json":"https://pith.science/api/pith-number/FOS6J2TGILZ5UVHB2QHBLFBMYZ/graph.json","events_json":"https://pith.science/api/pith-number/FOS6J2TGILZ5UVHB2QHBLFBMYZ/events.json","paper":"https://pith.science/paper/FOS6J2TG"},"agent_actions":{"view_html":"https://pith.science/pith/FOS6J2TGILZ5UVHB2QHBLFBMYZ","download_json":"https://pith.science/pith/FOS6J2TGILZ5UVHB2QHBLFBMYZ.json","view_paper":"https://pith.science/paper/FOS6J2TG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.10149&json=true","fetch_graph":"https://pith.science/api/pith-number/FOS6J2TGILZ5UVHB2QHBLFBMYZ/graph.json","fetch_events":"https://pith.science/api/pith-number/FOS6J2TGILZ5UVHB2QHBLFBMYZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FOS6J2TGILZ5UVHB2QHBLFBMYZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FOS6J2TGILZ5UVHB2QHBLFBMYZ/action/storage_attestation","attest_author":"https://pith.science/pith/FOS6J2TGILZ5UVHB2QHBLFBMYZ/action/author_attestation","sign_citation":"https://pith.science/pith/FOS6J2TGILZ5UVHB2QHBLFBMYZ/action/citation_signature","submit_replication":"https://pith.science/pith/FOS6J2TGILZ5UVHB2QHBLFBMYZ/action/replication_record"}},"created_at":"2026-07-05T08:31:10.817679+00:00","updated_at":"2026-07-05T08:31:10.817679+00:00"}