{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OCB5I6H5SHWPKXGA3LJIWZIBP5","short_pith_number":"pith:OCB5I6H5","schema_version":"1.0","canonical_sha256":"7083d478fd91ecf55cc0dad28b65017f439643436023fa1e3549bbe1a140381b","source":{"kind":"arxiv","id":"2507.14658","version":1},"attestation_state":"computed","paper":{"title":"Learning to Communicate in Multi-Agent Reinforcement Learning for Autonomous Cyber Defence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.LG"],"primary_cat":"cs.MA","authors_text":"Faizan Contractor, Li Li, Ranwa Al Mallah","submitted_at":"2025-07-19T15:16:24Z","abstract_excerpt":"Popular methods in cooperative Multi-Agent Reinforcement Learning with partially observable environments typically allow agents to act independently during execution, which may limit the coordinated effect of the trained policies. However, by sharing information such as known or suspected ongoing threats, effective communication can lead to improved decision-making in the cyber battle space. We propose a game design where defender agents learn to communicate and defend against imminent cyber threats by playing training games in the Cyber Operations Research Gym, using the Differentiable Inter "},"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":"2507.14658","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2025-07-19T15:16:24Z","cross_cats_sorted":["cs.CR","cs.LG"],"title_canon_sha256":"9eef29ddf24f0c2cc8780946231d9be2c7a53cb9a928e8181d62ae96d18f548c","abstract_canon_sha256":"f61de29d7fed0cd1ef697d36b05f49bd88d608f24cee7a1f57b95461f3fc737a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:40:11.256399Z","signature_b64":"35OvP+9u1KgnLaxJPH+ifO8AU0oKMxXOiaxfQZ8bG/7YFt91d7MlLJhgnbmxIZ9cHM0UkNrDYqOiK2FjIPiPDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7083d478fd91ecf55cc0dad28b65017f439643436023fa1e3549bbe1a140381b","last_reissued_at":"2026-07-05T11:40:11.255801Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:40:11.255801Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Communicate in Multi-Agent Reinforcement Learning for Autonomous Cyber Defence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.LG"],"primary_cat":"cs.MA","authors_text":"Faizan Contractor, Li Li, Ranwa Al Mallah","submitted_at":"2025-07-19T15:16:24Z","abstract_excerpt":"Popular methods in cooperative Multi-Agent Reinforcement Learning with partially observable environments typically allow agents to act independently during execution, which may limit the coordinated effect of the trained policies. However, by sharing information such as known or suspected ongoing threats, effective communication can lead to improved decision-making in the cyber battle space. We propose a game design where defender agents learn to communicate and defend against imminent cyber threats by playing training games in the Cyber Operations Research Gym, using the Differentiable Inter "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.14658","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/2507.14658/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":"2507.14658","created_at":"2026-07-05T11:40:11.255876+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.14658v1","created_at":"2026-07-05T11:40:11.255876+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.14658","created_at":"2026-07-05T11:40:11.255876+00:00"},{"alias_kind":"pith_short_12","alias_value":"OCB5I6H5SHWP","created_at":"2026-07-05T11:40:11.255876+00:00"},{"alias_kind":"pith_short_16","alias_value":"OCB5I6H5SHWPKXGA","created_at":"2026-07-05T11:40:11.255876+00:00"},{"alias_kind":"pith_short_8","alias_value":"OCB5I6H5","created_at":"2026-07-05T11:40:11.255876+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/OCB5I6H5SHWPKXGA3LJIWZIBP5","json":"https://pith.science/pith/OCB5I6H5SHWPKXGA3LJIWZIBP5.json","graph_json":"https://pith.science/api/pith-number/OCB5I6H5SHWPKXGA3LJIWZIBP5/graph.json","events_json":"https://pith.science/api/pith-number/OCB5I6H5SHWPKXGA3LJIWZIBP5/events.json","paper":"https://pith.science/paper/OCB5I6H5"},"agent_actions":{"view_html":"https://pith.science/pith/OCB5I6H5SHWPKXGA3LJIWZIBP5","download_json":"https://pith.science/pith/OCB5I6H5SHWPKXGA3LJIWZIBP5.json","view_paper":"https://pith.science/paper/OCB5I6H5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.14658&json=true","fetch_graph":"https://pith.science/api/pith-number/OCB5I6H5SHWPKXGA3LJIWZIBP5/graph.json","fetch_events":"https://pith.science/api/pith-number/OCB5I6H5SHWPKXGA3LJIWZIBP5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OCB5I6H5SHWPKXGA3LJIWZIBP5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OCB5I6H5SHWPKXGA3LJIWZIBP5/action/storage_attestation","attest_author":"https://pith.science/pith/OCB5I6H5SHWPKXGA3LJIWZIBP5/action/author_attestation","sign_citation":"https://pith.science/pith/OCB5I6H5SHWPKXGA3LJIWZIBP5/action/citation_signature","submit_replication":"https://pith.science/pith/OCB5I6H5SHWPKXGA3LJIWZIBP5/action/replication_record"}},"created_at":"2026-07-05T11:40:11.255876+00:00","updated_at":"2026-07-05T11:40:11.255876+00:00"}