{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:RPQXP7PKWQP7ODEW6OOPAC52NR","short_pith_number":"pith:RPQXP7PK","schema_version":"1.0","canonical_sha256":"8be177fdeab41ff70c96f39cf00bba6c7eb0812980c5dec9c94238c8080e78e3","source":{"kind":"arxiv","id":"2109.03331","version":1},"attestation_state":"computed","paper":{"title":"CyGIL: A Cyber Gym for Training Autonomous Agents over Emulated Network Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CR","authors_text":"Adrian Taylor, Li Li, Raed Fayad","submitted_at":"2021-09-07T20:52:44Z","abstract_excerpt":"Given the success of reinforcement learning (RL) in various domains, it is promising to explore the application of its methods to the development of intelligent and autonomous cyber agents. Enabling this development requires a representative RL training environment. To that end, this work presents CyGIL: an experimental testbed of an emulated RL training environment for network cyber operations. CyGIL uses a stateless environment architecture and incorporates the MITRE ATT&CK framework to establish a high fidelity training environment, while presenting a sufficiently abstracted interface to en"},"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":"2109.03331","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2021-09-07T20:52:44Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"3b642fa36aab2da01bf938cfc3c9173e06493a90a123b5f7f67959daf390094d","abstract_canon_sha256":"ad000b98d48bcbab9cf5d55d5a85d74705a9a5f0f679d4a6f16f0ba9d3dff61e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:12:29.856830Z","signature_b64":"Cjcto3luymNLL22aCDiBrGPzC10cMa0qPmLOtFnySugzUaKsqQnjjl4A5PnjK+l5kQlzmp1NNamfzQl48qGLDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8be177fdeab41ff70c96f39cf00bba6c7eb0812980c5dec9c94238c8080e78e3","last_reissued_at":"2026-07-05T03:12:29.856487Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:12:29.856487Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CyGIL: A Cyber Gym for Training Autonomous Agents over Emulated Network Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CR","authors_text":"Adrian Taylor, Li Li, Raed Fayad","submitted_at":"2021-09-07T20:52:44Z","abstract_excerpt":"Given the success of reinforcement learning (RL) in various domains, it is promising to explore the application of its methods to the development of intelligent and autonomous cyber agents. Enabling this development requires a representative RL training environment. To that end, this work presents CyGIL: an experimental testbed of an emulated RL training environment for network cyber operations. CyGIL uses a stateless environment architecture and incorporates the MITRE ATT&CK framework to establish a high fidelity training environment, while presenting a sufficiently abstracted interface to en"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.03331","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/2109.03331/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":"2109.03331","created_at":"2026-07-05T03:12:29.856542+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.03331v1","created_at":"2026-07-05T03:12:29.856542+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.03331","created_at":"2026-07-05T03:12:29.856542+00:00"},{"alias_kind":"pith_short_12","alias_value":"RPQXP7PKWQP7","created_at":"2026-07-05T03:12:29.856542+00:00"},{"alias_kind":"pith_short_16","alias_value":"RPQXP7PKWQP7ODEW","created_at":"2026-07-05T03:12:29.856542+00:00"},{"alias_kind":"pith_short_8","alias_value":"RPQXP7PK","created_at":"2026-07-05T03:12:29.856542+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30479","citing_title":"COHORT: Collaborative Orchestration for Hardening via Offensive Replay on Emulated Topologies","ref_index":73,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24184","citing_title":"Dynamic Cyber Ranges","ref_index":42,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RPQXP7PKWQP7ODEW6OOPAC52NR","json":"https://pith.science/pith/RPQXP7PKWQP7ODEW6OOPAC52NR.json","graph_json":"https://pith.science/api/pith-number/RPQXP7PKWQP7ODEW6OOPAC52NR/graph.json","events_json":"https://pith.science/api/pith-number/RPQXP7PKWQP7ODEW6OOPAC52NR/events.json","paper":"https://pith.science/paper/RPQXP7PK"},"agent_actions":{"view_html":"https://pith.science/pith/RPQXP7PKWQP7ODEW6OOPAC52NR","download_json":"https://pith.science/pith/RPQXP7PKWQP7ODEW6OOPAC52NR.json","view_paper":"https://pith.science/paper/RPQXP7PK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.03331&json=true","fetch_graph":"https://pith.science/api/pith-number/RPQXP7PKWQP7ODEW6OOPAC52NR/graph.json","fetch_events":"https://pith.science/api/pith-number/RPQXP7PKWQP7ODEW6OOPAC52NR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RPQXP7PKWQP7ODEW6OOPAC52NR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RPQXP7PKWQP7ODEW6OOPAC52NR/action/storage_attestation","attest_author":"https://pith.science/pith/RPQXP7PKWQP7ODEW6OOPAC52NR/action/author_attestation","sign_citation":"https://pith.science/pith/RPQXP7PKWQP7ODEW6OOPAC52NR/action/citation_signature","submit_replication":"https://pith.science/pith/RPQXP7PKWQP7ODEW6OOPAC52NR/action/replication_record"}},"created_at":"2026-07-05T03:12:29.856542+00:00","updated_at":"2026-07-05T03:12:29.856542+00:00"}