{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:K4UE4HSJLCKMVEFKQ2OYGQ2DD2","short_pith_number":"pith:K4UE4HSJ","canonical_record":{"source":{"id":"2509.00678","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2025-08-31T03:18:02Z","cross_cats_sorted":["cs.GT"],"title_canon_sha256":"8dffec6d4ddd59eab4001813f20ead359801f0c40e12c37c2838f4eaafcdcfc3","abstract_canon_sha256":"c1fc635f9a9b154fa1ec633652369356a5ecb78d6f9f02572a701eac14b2fe6e"},"schema_version":"1.0"},"canonical_sha256":"57284e1e495894ca90aa869d8343431eb9b616732994508d99c2527841b374ec","source":{"kind":"arxiv","id":"2509.00678","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.00678","created_at":"2026-07-05T12:02:20Z"},{"alias_kind":"arxiv_version","alias_value":"2509.00678v1","created_at":"2026-07-05T12:02:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.00678","created_at":"2026-07-05T12:02:20Z"},{"alias_kind":"pith_short_12","alias_value":"K4UE4HSJLCKM","created_at":"2026-07-05T12:02:20Z"},{"alias_kind":"pith_short_16","alias_value":"K4UE4HSJLCKMVEFK","created_at":"2026-07-05T12:02:20Z"},{"alias_kind":"pith_short_8","alias_value":"K4UE4HSJ","created_at":"2026-07-05T12:02:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:K4UE4HSJLCKMVEFKQ2OYGQ2DD2","target":"record","payload":{"canonical_record":{"source":{"id":"2509.00678","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2025-08-31T03:18:02Z","cross_cats_sorted":["cs.GT"],"title_canon_sha256":"8dffec6d4ddd59eab4001813f20ead359801f0c40e12c37c2838f4eaafcdcfc3","abstract_canon_sha256":"c1fc635f9a9b154fa1ec633652369356a5ecb78d6f9f02572a701eac14b2fe6e"},"schema_version":"1.0"},"canonical_sha256":"57284e1e495894ca90aa869d8343431eb9b616732994508d99c2527841b374ec","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:02:20.950774Z","signature_b64":"faY5HFMCwgWOXXYZTgYPBJCG1wLjW3ZTGR9TlkLrPnI65xbFK3zrrxdfhhP3I3JbprHMQUqJj/i9JTOGbTciBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"57284e1e495894ca90aa869d8343431eb9b616732994508d99c2527841b374ec","last_reissued_at":"2026-07-05T12:02:20.950254Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:02:20.950254Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.00678","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:02:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qc8g2Meh0rOCH1HqdiN/r1BxPDI85mOSoWewjls/j4gMFSW7Ylo0lmDymU1DBwDkqbMoRG20w9hlJRHA+p8bDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T04:53:29.354168Z"},"content_sha256":"6df8990a5c7f674d414cd725b0f77524414a17cd10d67599fa4c3f04ec3ce42c","schema_version":"1.0","event_id":"sha256:6df8990a5c7f674d414cd725b0f77524414a17cd10d67599fa4c3f04ec3ce42c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:K4UE4HSJLCKMVEFKQ2OYGQ2DD2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Nash Q-Network for Multi-Agent Cybersecurity Simulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GT"],"primary_cat":"cs.MA","authors_text":"Edward Koh, Peter Chin, Qintong Xie, Xavier Cadet","submitted_at":"2025-08-31T03:18:02Z","abstract_excerpt":"Cybersecurity defense involves interactions between adversarial parties (namely defenders and hackers), making multi-agent reinforcement learning (MARL) an ideal approach for modeling and learning strategies for these scenarios. This paper addresses one of the key challenges to MARL, the complexity of simultaneous training of agents in nontrivial environments, and presents a novel policy-based Nash Q-learning to directly converge onto a steady equilibrium. We demonstrate the successful implementation of this algorithm in a notable complex cyber defense simulation treated as a two-player zero-s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.00678","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/2509.00678/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:02:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QVS1hjGQMTWLc4T/awTDDNNCpVNr2tpKPqfcG0/xHPtf8Hq03a8MTKfntjj0WjSHTEWuyvZ5jRC5JexbGuEhBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T04:53:29.355143Z"},"content_sha256":"1f970dd25690c6f7d45b5fe01b390540cc05b4ec02ee677218522e6f69a9b57c","schema_version":"1.0","event_id":"sha256:1f970dd25690c6f7d45b5fe01b390540cc05b4ec02ee677218522e6f69a9b57c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/K4UE4HSJLCKMVEFKQ2OYGQ2DD2/bundle.json","state_url":"https://pith.science/pith/K4UE4HSJLCKMVEFKQ2OYGQ2DD2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/K4UE4HSJLCKMVEFKQ2OYGQ2DD2/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T04:53:29Z","links":{"resolver":"https://pith.science/pith/K4UE4HSJLCKMVEFKQ2OYGQ2DD2","bundle":"https://pith.science/pith/K4UE4HSJLCKMVEFKQ2OYGQ2DD2/bundle.json","state":"https://pith.science/pith/K4UE4HSJLCKMVEFKQ2OYGQ2DD2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/K4UE4HSJLCKMVEFKQ2OYGQ2DD2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:K4UE4HSJLCKMVEFKQ2OYGQ2DD2","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c1fc635f9a9b154fa1ec633652369356a5ecb78d6f9f02572a701eac14b2fe6e","cross_cats_sorted":["cs.GT"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2025-08-31T03:18:02Z","title_canon_sha256":"8dffec6d4ddd59eab4001813f20ead359801f0c40e12c37c2838f4eaafcdcfc3"},"schema_version":"1.0","source":{"id":"2509.00678","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.00678","created_at":"2026-07-05T12:02:20Z"},{"alias_kind":"arxiv_version","alias_value":"2509.00678v1","created_at":"2026-07-05T12:02:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.00678","created_at":"2026-07-05T12:02:20Z"},{"alias_kind":"pith_short_12","alias_value":"K4UE4HSJLCKM","created_at":"2026-07-05T12:02:20Z"},{"alias_kind":"pith_short_16","alias_value":"K4UE4HSJLCKMVEFK","created_at":"2026-07-05T12:02:20Z"},{"alias_kind":"pith_short_8","alias_value":"K4UE4HSJ","created_at":"2026-07-05T12:02:20Z"}],"graph_snapshots":[{"event_id":"sha256:1f970dd25690c6f7d45b5fe01b390540cc05b4ec02ee677218522e6f69a9b57c","target":"graph","created_at":"2026-07-05T12:02:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2509.00678/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Cybersecurity defense involves interactions between adversarial parties (namely defenders and hackers), making multi-agent reinforcement learning (MARL) an ideal approach for modeling and learning strategies for these scenarios. This paper addresses one of the key challenges to MARL, the complexity of simultaneous training of agents in nontrivial environments, and presents a novel policy-based Nash Q-learning to directly converge onto a steady equilibrium. We demonstrate the successful implementation of this algorithm in a notable complex cyber defense simulation treated as a two-player zero-s","authors_text":"Edward Koh, Peter Chin, Qintong Xie, Xavier Cadet","cross_cats":["cs.GT"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2025-08-31T03:18:02Z","title":"Nash Q-Network for Multi-Agent Cybersecurity Simulation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.00678","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:6df8990a5c7f674d414cd725b0f77524414a17cd10d67599fa4c3f04ec3ce42c","target":"record","created_at":"2026-07-05T12:02:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"c1fc635f9a9b154fa1ec633652369356a5ecb78d6f9f02572a701eac14b2fe6e","cross_cats_sorted":["cs.GT"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2025-08-31T03:18:02Z","title_canon_sha256":"8dffec6d4ddd59eab4001813f20ead359801f0c40e12c37c2838f4eaafcdcfc3"},"schema_version":"1.0","source":{"id":"2509.00678","kind":"arxiv","version":1}},"canonical_sha256":"57284e1e495894ca90aa869d8343431eb9b616732994508d99c2527841b374ec","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"57284e1e495894ca90aa869d8343431eb9b616732994508d99c2527841b374ec","first_computed_at":"2026-07-05T12:02:20.950254Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:02:20.950254Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"faY5HFMCwgWOXXYZTgYPBJCG1wLjW3ZTGR9TlkLrPnI65xbFK3zrrxdfhhP3I3JbprHMQUqJj/i9JTOGbTciBw==","signature_status":"signed_v1","signed_at":"2026-07-05T12:02:20.950774Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.00678","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6df8990a5c7f674d414cd725b0f77524414a17cd10d67599fa4c3f04ec3ce42c","sha256:1f970dd25690c6f7d45b5fe01b390540cc05b4ec02ee677218522e6f69a9b57c"],"state_sha256":"7e3846b03831b58f9b367cbd9baaa6a6a974a10be6c94c5b7013142bd8b208c8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0BN8nG4zSq8Ap8flYs9kDLQQXmc3RNeRnxIJPtSTCxopUhoU68TOVGbK/qUVKfCxURTo89bT0Ccsi7KiF0TyAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T04:53:29.362635Z","bundle_sha256":"ff73e47eddbfe4ae77b4a1a4be1b4ced22d1e4b014eb3e7439b64729edf2b451"}}