{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:AMWLPIEKFB3FIZTTVIV2ZDNYH5","short_pith_number":"pith:AMWLPIEK","canonical_record":{"source":{"id":"2310.07745","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-11T16:24:14Z","cross_cats_sorted":[],"title_canon_sha256":"d9adfd2873aa1cf4ef797e0978417e96961f30b3b7cfbba56fb2efbd1b679c99","abstract_canon_sha256":"7cf7e57d3a721b3fe0cc63ea4bb17de7cd582f9b2452d118c5f25b4842aa920e"},"schema_version":"1.0"},"canonical_sha256":"032cb7a08a2876546673aa2bac8db83f588c95901468144bcc6cf0ae0f541653","source":{"kind":"arxiv","id":"2310.07745","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.07745","created_at":"2026-07-05T09:12:23Z"},{"alias_kind":"arxiv_version","alias_value":"2310.07745v3","created_at":"2026-07-05T09:12:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.07745","created_at":"2026-07-05T09:12:23Z"},{"alias_kind":"pith_short_12","alias_value":"AMWLPIEKFB3F","created_at":"2026-07-05T09:12:23Z"},{"alias_kind":"pith_short_16","alias_value":"AMWLPIEKFB3FIZTT","created_at":"2026-07-05T09:12:23Z"},{"alias_kind":"pith_short_8","alias_value":"AMWLPIEK","created_at":"2026-07-05T09:12:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:AMWLPIEKFB3FIZTTVIV2ZDNYH5","target":"record","payload":{"canonical_record":{"source":{"id":"2310.07745","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-11T16:24:14Z","cross_cats_sorted":[],"title_canon_sha256":"d9adfd2873aa1cf4ef797e0978417e96961f30b3b7cfbba56fb2efbd1b679c99","abstract_canon_sha256":"7cf7e57d3a721b3fe0cc63ea4bb17de7cd582f9b2452d118c5f25b4842aa920e"},"schema_version":"1.0"},"canonical_sha256":"032cb7a08a2876546673aa2bac8db83f588c95901468144bcc6cf0ae0f541653","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:12:23.614620Z","signature_b64":"H70OBgChFyToejRepNZMzErH2zOMAIXMLJC3IYrvr7NkaONqmlS7hcMrouhFHlL/9UP8BQiarBKk5LmzKCJeCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"032cb7a08a2876546673aa2bac8db83f588c95901468144bcc6cf0ae0f541653","last_reissued_at":"2026-07-05T09:12:23.614117Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:12:23.614117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.07745","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:12:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lM2ajjEfKVkBiP+I7zw/uG30mqCh/WR+7LtGr4eUjcReuRkIeG7RaEtLfJmxjzsFCVV5jvn+X968qdLpXZVJDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T20:38:31.362474Z"},"content_sha256":"b8d3581f7e1a844c2f54284651c22f4306cb330f01cf6ee5ecd0675bd61d834b","schema_version":"1.0","event_id":"sha256:b8d3581f7e1a844c2f54284651c22f4306cb330f01cf6ee5ecd0675bd61d834b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:AMWLPIEKFB3FIZTTVIV2ZDNYH5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Reinforcement Learning for Autonomous Cyber Defence: A Survey","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chris Parry, Chris Willis, Daniel J.B. Harrold, Gregory Palmer","submitted_at":"2023-10-11T16:24:14Z","abstract_excerpt":"The rapid increase in the number of cyber-attacks in recent years raises the need for principled methods for defending networks against malicious actors. Deep reinforcement learning (DRL) has emerged as a promising approach for mitigating these attacks. However, while DRL has shown much potential for cyber defence, numerous challenges must be overcome before DRL can be applied to the autonomous cyber defence (ACD) problem at scale. Principled methods are required for environments that confront learners with very high-dimensional state spaces, large multi-discrete action spaces, and adversarial"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.07745","kind":"arxiv","version":3},"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/2310.07745/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":"2026-07-05T09:12:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9p/bYbbQK6tlvRnX20f8/3Xeoh72y3OWWJRruKxKlpCuoAVYIRtSuPSl6OwUiuBUVzwoCYP2ANduQvcvHAy8Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T20:38:31.362800Z"},"content_sha256":"b0626ad3afd2fce84ecb5c44bf37c56e6c17390a49b548f574f6edce02b57f38","schema_version":"1.0","event_id":"sha256:b0626ad3afd2fce84ecb5c44bf37c56e6c17390a49b548f574f6edce02b57f38"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AMWLPIEKFB3FIZTTVIV2ZDNYH5/bundle.json","state_url":"https://pith.science/pith/AMWLPIEKFB3FIZTTVIV2ZDNYH5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AMWLPIEKFB3FIZTTVIV2ZDNYH5/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":"2026-07-31T20:38:31Z","links":{"resolver":"https://pith.science/pith/AMWLPIEKFB3FIZTTVIV2ZDNYH5","bundle":"https://pith.science/pith/AMWLPIEKFB3FIZTTVIV2ZDNYH5/bundle.json","state":"https://pith.science/pith/AMWLPIEKFB3FIZTTVIV2ZDNYH5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AMWLPIEKFB3FIZTTVIV2ZDNYH5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:AMWLPIEKFB3FIZTTVIV2ZDNYH5","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":"7cf7e57d3a721b3fe0cc63ea4bb17de7cd582f9b2452d118c5f25b4842aa920e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-11T16:24:14Z","title_canon_sha256":"d9adfd2873aa1cf4ef797e0978417e96961f30b3b7cfbba56fb2efbd1b679c99"},"schema_version":"1.0","source":{"id":"2310.07745","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.07745","created_at":"2026-07-05T09:12:23Z"},{"alias_kind":"arxiv_version","alias_value":"2310.07745v3","created_at":"2026-07-05T09:12:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.07745","created_at":"2026-07-05T09:12:23Z"},{"alias_kind":"pith_short_12","alias_value":"AMWLPIEKFB3F","created_at":"2026-07-05T09:12:23Z"},{"alias_kind":"pith_short_16","alias_value":"AMWLPIEKFB3FIZTT","created_at":"2026-07-05T09:12:23Z"},{"alias_kind":"pith_short_8","alias_value":"AMWLPIEK","created_at":"2026-07-05T09:12:23Z"}],"graph_snapshots":[{"event_id":"sha256:b0626ad3afd2fce84ecb5c44bf37c56e6c17390a49b548f574f6edce02b57f38","target":"graph","created_at":"2026-07-05T09:12:23Z","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/2310.07745/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The rapid increase in the number of cyber-attacks in recent years raises the need for principled methods for defending networks against malicious actors. Deep reinforcement learning (DRL) has emerged as a promising approach for mitigating these attacks. However, while DRL has shown much potential for cyber defence, numerous challenges must be overcome before DRL can be applied to the autonomous cyber defence (ACD) problem at scale. Principled methods are required for environments that confront learners with very high-dimensional state spaces, large multi-discrete action spaces, and adversarial","authors_text":"Chris Parry, Chris Willis, Daniel J.B. Harrold, Gregory Palmer","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-11T16:24:14Z","title":"Deep Reinforcement Learning for Autonomous Cyber Defence: A Survey"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.07745","kind":"arxiv","version":3},"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:b8d3581f7e1a844c2f54284651c22f4306cb330f01cf6ee5ecd0675bd61d834b","target":"record","created_at":"2026-07-05T09:12:23Z","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":"7cf7e57d3a721b3fe0cc63ea4bb17de7cd582f9b2452d118c5f25b4842aa920e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-11T16:24:14Z","title_canon_sha256":"d9adfd2873aa1cf4ef797e0978417e96961f30b3b7cfbba56fb2efbd1b679c99"},"schema_version":"1.0","source":{"id":"2310.07745","kind":"arxiv","version":3}},"canonical_sha256":"032cb7a08a2876546673aa2bac8db83f588c95901468144bcc6cf0ae0f541653","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"032cb7a08a2876546673aa2bac8db83f588c95901468144bcc6cf0ae0f541653","first_computed_at":"2026-07-05T09:12:23.614117Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:12:23.614117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"H70OBgChFyToejRepNZMzErH2zOMAIXMLJC3IYrvr7NkaONqmlS7hcMrouhFHlL/9UP8BQiarBKk5LmzKCJeCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:12:23.614620Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.07745","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b8d3581f7e1a844c2f54284651c22f4306cb330f01cf6ee5ecd0675bd61d834b","sha256:b0626ad3afd2fce84ecb5c44bf37c56e6c17390a49b548f574f6edce02b57f38"],"state_sha256":"20697ac577cec60acf71623ccc3825bec48ec222ec0fa0fe51aaef9a1cb85cc5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BhG1V2052goNfnFcN2ZP5ARrGWAWPrqi3wbPzdW3FHKjY8nZ9lWAs29t0+gisWkD/zbaBq/igPj52i31F0dfDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-31T20:38:31.365122Z","bundle_sha256":"119aed36a348ea2108f2c73c1a773de379cd5ce730b880bb863ac0aa6b6ed857"}}