{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:K6I5NPVUHXMOTLGGRIVLXGYLYX","short_pith_number":"pith:K6I5NPVU","schema_version":"1.0","canonical_sha256":"5791d6beb43dd8e9acc68a2abb9b0bc5df6ee4f0c29c23ca552252ac405d83b9","source":{"kind":"arxiv","id":"2304.11052","version":1},"attestation_state":"computed","paper":{"title":"A Multiagent CyberBattleSim for RL Cyber Operation Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CR","authors_text":"Christian Fisher, Christopher Nguyen, James La Novara-Gsell, Li Li, Thomas Kunz","submitted_at":"2023-04-03T20:43:19Z","abstract_excerpt":"Hardening cyber physical assets is both crucial and labor-intensive. Recently, Machine Learning (ML) in general and Reinforcement Learning RL) more specifically has shown great promise to automate tasks that otherwise would require significant human insight/intelligence. The development of autonomous RL agents requires a suitable training environment that allows us to quickly evaluate various alternatives, in particular how to arrange training scenarios that pit attackers and defenders against each other. CyberBattleSim is a training environment that supports the training of red agents, i.e., "},"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":"2304.11052","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2023-04-03T20:43:19Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"1f661cb6d5b901515cb5b954fb289fe26e4a2b0ac7a1df421ebfc4fe621a66ff","abstract_canon_sha256":"8ef50efa93b5718c6bd3906b4f1d32c49e422bd750a6163369d6886bc6da65a8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:03:18.475227Z","signature_b64":"peF/7np8Q38xLsls2qGRYoTQOleSsqG6C0zDLjqG2KmEYjVLmUzDuqf6FYAQmpKMzHqnOkQUpBNtRevat2YzCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5791d6beb43dd8e9acc68a2abb9b0bc5df6ee4f0c29c23ca552252ac405d83b9","last_reissued_at":"2026-07-05T06:03:18.474797Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:03:18.474797Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Multiagent CyberBattleSim for RL Cyber Operation Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CR","authors_text":"Christian Fisher, Christopher Nguyen, James La Novara-Gsell, Li Li, Thomas Kunz","submitted_at":"2023-04-03T20:43:19Z","abstract_excerpt":"Hardening cyber physical assets is both crucial and labor-intensive. Recently, Machine Learning (ML) in general and Reinforcement Learning RL) more specifically has shown great promise to automate tasks that otherwise would require significant human insight/intelligence. The development of autonomous RL agents requires a suitable training environment that allows us to quickly evaluate various alternatives, in particular how to arrange training scenarios that pit attackers and defenders against each other. CyberBattleSim is a training environment that supports the training of red agents, i.e., "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.11052","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/2304.11052/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":"2304.11052","created_at":"2026-07-05T06:03:18.474854+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.11052v1","created_at":"2026-07-05T06:03:18.474854+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.11052","created_at":"2026-07-05T06:03:18.474854+00:00"},{"alias_kind":"pith_short_12","alias_value":"K6I5NPVUHXMO","created_at":"2026-07-05T06:03:18.474854+00:00"},{"alias_kind":"pith_short_16","alias_value":"K6I5NPVUHXMOTLGG","created_at":"2026-07-05T06:03:18.474854+00:00"},{"alias_kind":"pith_short_8","alias_value":"K6I5NPVU","created_at":"2026-07-05T06:03:18.474854+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.19837","citing_title":"Multi-Agent Reinforcement Learning in Cybersecurity: From Fundamentals to Applications","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K6I5NPVUHXMOTLGGRIVLXGYLYX","json":"https://pith.science/pith/K6I5NPVUHXMOTLGGRIVLXGYLYX.json","graph_json":"https://pith.science/api/pith-number/K6I5NPVUHXMOTLGGRIVLXGYLYX/graph.json","events_json":"https://pith.science/api/pith-number/K6I5NPVUHXMOTLGGRIVLXGYLYX/events.json","paper":"https://pith.science/paper/K6I5NPVU"},"agent_actions":{"view_html":"https://pith.science/pith/K6I5NPVUHXMOTLGGRIVLXGYLYX","download_json":"https://pith.science/pith/K6I5NPVUHXMOTLGGRIVLXGYLYX.json","view_paper":"https://pith.science/paper/K6I5NPVU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.11052&json=true","fetch_graph":"https://pith.science/api/pith-number/K6I5NPVUHXMOTLGGRIVLXGYLYX/graph.json","fetch_events":"https://pith.science/api/pith-number/K6I5NPVUHXMOTLGGRIVLXGYLYX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K6I5NPVUHXMOTLGGRIVLXGYLYX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K6I5NPVUHXMOTLGGRIVLXGYLYX/action/storage_attestation","attest_author":"https://pith.science/pith/K6I5NPVUHXMOTLGGRIVLXGYLYX/action/author_attestation","sign_citation":"https://pith.science/pith/K6I5NPVUHXMOTLGGRIVLXGYLYX/action/citation_signature","submit_replication":"https://pith.science/pith/K6I5NPVUHXMOTLGGRIVLXGYLYX/action/replication_record"}},"created_at":"2026-07-05T06:03:18.474854+00:00","updated_at":"2026-07-05T06:03:18.474854+00:00"}