{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WYOTKIOPPW4YXZHORGZRIVC75D","short_pith_number":"pith:WYOTKIOP","schema_version":"1.0","canonical_sha256":"b61d3521cf7db98be4ee89b314545fe8d7ebfa99649d22414f4a7b6e7e4ed668","source":{"kind":"arxiv","id":"2606.18223","version":1},"attestation_state":"computed","paper":{"title":"Learning Red Agent Policy from Observations for Neurosymbolic Autonomous Cyber Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SY","eess.SY"],"primary_cat":"cs.CR","authors_text":"Ankita Samaddar, Daniel Balasubramanian, Sandeep Neema, Xenofon Koutsoukos","submitted_at":"2026-06-16T17:50:41Z","abstract_excerpt":"With sophisticated cyber-attacks becoming increasingly prevalent, modern networks require intelligent autonomous cyber-defense agents trained via Reinforcement Learning (RL). These agents employ neurosymbolic approaches such as behavior trees with learning-enabled components (LECs) to learn, reason, adapt, and implement security rules while maintaining critical operations. However, these autonomous networks are partially observable systems, i.e., the cyber-attacker's (red agent's) actions are not observable, making it difficult for the defender to predict red actions, learn red policies, or as"},"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":"2606.18223","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-06-16T17:50:41Z","cross_cats_sorted":["cs.AI","cs.LG","cs.SY","eess.SY"],"title_canon_sha256":"521ecfee32c5f0c561d9e2e5b523f1edb79d1d2df9f8af95f1cfcd536aee17b9","abstract_canon_sha256":"575da32d9ae09c1dd00e5ce11c137d8d6824bbc883e9e69b4a4717ab1eacf51b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:10:51.482111Z","signature_b64":"bBSLFvtU62fAAMPtbMeJzP72KiOfYNvJKywZRa1SSwCwNVva0nCnYdBsxcIDbeoB6nFDqEciBXl7+yI4LEymCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b61d3521cf7db98be4ee89b314545fe8d7ebfa99649d22414f4a7b6e7e4ed668","last_reissued_at":"2026-06-19T16:10:51.481770Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:10:51.481770Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Red Agent Policy from Observations for Neurosymbolic Autonomous Cyber Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SY","eess.SY"],"primary_cat":"cs.CR","authors_text":"Ankita Samaddar, Daniel Balasubramanian, Sandeep Neema, Xenofon Koutsoukos","submitted_at":"2026-06-16T17:50:41Z","abstract_excerpt":"With sophisticated cyber-attacks becoming increasingly prevalent, modern networks require intelligent autonomous cyber-defense agents trained via Reinforcement Learning (RL). These agents employ neurosymbolic approaches such as behavior trees with learning-enabled components (LECs) to learn, reason, adapt, and implement security rules while maintaining critical operations. However, these autonomous networks are partially observable systems, i.e., the cyber-attacker's (red agent's) actions are not observable, making it difficult for the defender to predict red actions, learn red policies, or as"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.18223","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/2606.18223/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":"2606.18223","created_at":"2026-06-19T16:10:51.481831+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.18223v1","created_at":"2026-06-19T16:10:51.481831+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.18223","created_at":"2026-06-19T16:10:51.481831+00:00"},{"alias_kind":"pith_short_12","alias_value":"WYOTKIOPPW4Y","created_at":"2026-06-19T16:10:51.481831+00:00"},{"alias_kind":"pith_short_16","alias_value":"WYOTKIOPPW4YXZHO","created_at":"2026-06-19T16:10:51.481831+00:00"},{"alias_kind":"pith_short_8","alias_value":"WYOTKIOP","created_at":"2026-06-19T16:10:51.481831+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WYOTKIOPPW4YXZHORGZRIVC75D","json":"https://pith.science/pith/WYOTKIOPPW4YXZHORGZRIVC75D.json","graph_json":"https://pith.science/api/pith-number/WYOTKIOPPW4YXZHORGZRIVC75D/graph.json","events_json":"https://pith.science/api/pith-number/WYOTKIOPPW4YXZHORGZRIVC75D/events.json","paper":"https://pith.science/paper/WYOTKIOP"},"agent_actions":{"view_html":"https://pith.science/pith/WYOTKIOPPW4YXZHORGZRIVC75D","download_json":"https://pith.science/pith/WYOTKIOPPW4YXZHORGZRIVC75D.json","view_paper":"https://pith.science/paper/WYOTKIOP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.18223&json=true","fetch_graph":"https://pith.science/api/pith-number/WYOTKIOPPW4YXZHORGZRIVC75D/graph.json","fetch_events":"https://pith.science/api/pith-number/WYOTKIOPPW4YXZHORGZRIVC75D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WYOTKIOPPW4YXZHORGZRIVC75D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WYOTKIOPPW4YXZHORGZRIVC75D/action/storage_attestation","attest_author":"https://pith.science/pith/WYOTKIOPPW4YXZHORGZRIVC75D/action/author_attestation","sign_citation":"https://pith.science/pith/WYOTKIOPPW4YXZHORGZRIVC75D/action/citation_signature","submit_replication":"https://pith.science/pith/WYOTKIOPPW4YXZHORGZRIVC75D/action/replication_record"}},"created_at":"2026-06-19T16:10:51.481831+00:00","updated_at":"2026-06-19T16:10:51.481831+00:00"}