{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QN6RQWWCPFWYV2HPMQC5OQNQQZ","short_pith_number":"pith:QN6RQWWC","schema_version":"1.0","canonical_sha256":"837d185ac2796d8ae8ef6405d741b08678beed1b9b38bf276c024a68ae744477","source":{"kind":"arxiv","id":"2505.22531","version":2},"attestation_state":"computed","paper":{"title":"Training RL Agents for Multi-Objective Network Defense Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.LG","authors_text":"Ahmad Ridley, Akash Trivedi, Andres Molina-Markham, Derek Tsui, Lauren Brandt, Luis Robaina, Nicholas Potteiger, Ransom Winder, Sean Steinle","submitted_at":"2025-05-28T16:18:21Z","abstract_excerpt":"Open-ended learning (OEL) -- which emphasizes training agents that achieve broad capability over narrow competency -- is emerging as a paradigm to develop artificial intelligence (AI) agents to achieve robustness and generalization. However, despite promising results that demonstrate the benefits of OEL, applying OEL to develop autonomous agents for real-world cybersecurity applications remains a challenge.\n  We propose a training approach, inspired by OEL, to develop autonomous network defenders. Our results demonstrate that like in other domains, OEL principles can translate into more robust"},"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":"2505.22531","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-28T16:18:21Z","cross_cats_sorted":["cs.AI","cs.CR"],"title_canon_sha256":"f4db310ddf10589d706d208bafef22e64bcdbd9bd80739594b0121fa45b6ecfa","abstract_canon_sha256":"be20dfe6da4442fc87f1b533f89c5650134769ac02fa8a8505d1b668536389a6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:20:54.557942Z","signature_b64":"uDrH/F44IAU6bmlbhK0jk5gobrTJeP9X1VXIYZD0REJ1ptMpehZbSplnke9tbtcXm0pC5Lehgz7eqFq97M8sDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"837d185ac2796d8ae8ef6405d741b08678beed1b9b38bf276c024a68ae744477","last_reissued_at":"2026-07-05T11:20:54.557451Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:20:54.557451Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Training RL Agents for Multi-Objective Network Defense Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.LG","authors_text":"Ahmad Ridley, Akash Trivedi, Andres Molina-Markham, Derek Tsui, Lauren Brandt, Luis Robaina, Nicholas Potteiger, Ransom Winder, Sean Steinle","submitted_at":"2025-05-28T16:18:21Z","abstract_excerpt":"Open-ended learning (OEL) -- which emphasizes training agents that achieve broad capability over narrow competency -- is emerging as a paradigm to develop artificial intelligence (AI) agents to achieve robustness and generalization. However, despite promising results that demonstrate the benefits of OEL, applying OEL to develop autonomous agents for real-world cybersecurity applications remains a challenge.\n  We propose a training approach, inspired by OEL, to develop autonomous network defenders. Our results demonstrate that like in other domains, OEL principles can translate into more robust"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22531","kind":"arxiv","version":2},"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/2505.22531/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":"2505.22531","created_at":"2026-07-05T11:20:54.557512+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.22531v2","created_at":"2026-07-05T11:20:54.557512+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22531","created_at":"2026-07-05T11:20:54.557512+00:00"},{"alias_kind":"pith_short_12","alias_value":"QN6RQWWCPFWY","created_at":"2026-07-05T11:20:54.557512+00:00"},{"alias_kind":"pith_short_16","alias_value":"QN6RQWWCPFWYV2HP","created_at":"2026-07-05T11:20:54.557512+00:00"},{"alias_kind":"pith_short_8","alias_value":"QN6RQWWC","created_at":"2026-07-05T11:20:54.557512+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.08805","citing_title":"Building Better Environments for Autonomous Cyber Defence","ref_index":53,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QN6RQWWCPFWYV2HPMQC5OQNQQZ","json":"https://pith.science/pith/QN6RQWWCPFWYV2HPMQC5OQNQQZ.json","graph_json":"https://pith.science/api/pith-number/QN6RQWWCPFWYV2HPMQC5OQNQQZ/graph.json","events_json":"https://pith.science/api/pith-number/QN6RQWWCPFWYV2HPMQC5OQNQQZ/events.json","paper":"https://pith.science/paper/QN6RQWWC"},"agent_actions":{"view_html":"https://pith.science/pith/QN6RQWWCPFWYV2HPMQC5OQNQQZ","download_json":"https://pith.science/pith/QN6RQWWCPFWYV2HPMQC5OQNQQZ.json","view_paper":"https://pith.science/paper/QN6RQWWC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.22531&json=true","fetch_graph":"https://pith.science/api/pith-number/QN6RQWWCPFWYV2HPMQC5OQNQQZ/graph.json","fetch_events":"https://pith.science/api/pith-number/QN6RQWWCPFWYV2HPMQC5OQNQQZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QN6RQWWCPFWYV2HPMQC5OQNQQZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QN6RQWWCPFWYV2HPMQC5OQNQQZ/action/storage_attestation","attest_author":"https://pith.science/pith/QN6RQWWCPFWYV2HPMQC5OQNQQZ/action/author_attestation","sign_citation":"https://pith.science/pith/QN6RQWWCPFWYV2HPMQC5OQNQQZ/action/citation_signature","submit_replication":"https://pith.science/pith/QN6RQWWCPFWYV2HPMQC5OQNQQZ/action/replication_record"}},"created_at":"2026-07-05T11:20:54.557512+00:00","updated_at":"2026-07-05T11:20:54.557512+00:00"}