{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LNJZU6PPLW5ZM67S22ACXXSPFB","short_pith_number":"pith:LNJZU6PP","schema_version":"1.0","canonical_sha256":"5b539a79ef5dbb967bf2d6802bde4f285f02fa3876736cfb5c3dfed2dbbfa29d","source":{"kind":"arxiv","id":"2503.03245","version":2},"attestation_state":"computed","paper":{"title":"Less is more? Rewards in RL for Cyber Defence","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.LG","authors_text":"Chris Hicks, Elizabeth Bates, Vasilios Mavroudis","submitted_at":"2025-03-05T07:53:39Z","abstract_excerpt":"The last few years have seen an explosion of interest in autonomous cyber defence agents based on deep reinforcement learning. Such agents are typically trained in a cyber gym environment, also known as a cyber simulator, at least 32 of which have already been built. Most, if not all cyber gyms provide dense \"scaffolded\" reward functions which combine many penalties or incentives for a range of (un)desirable states and costly actions. Whilst dense rewards help alleviate the challenge of exploring complex environments, yielding seemingly effective strategies from relatively few environment step"},"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":"2503.03245","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-05T07:53:39Z","cross_cats_sorted":["cs.AI","cs.CR"],"title_canon_sha256":"60684b04d6839ab80ea734827128fe30b3d7cf987f2d48759efc0859b2619f2c","abstract_canon_sha256":"a72f19adc1a2595f7393e9d17516f084328e5ee62ccf4f2c4ae2b8c2b82a6c22"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:27:27.458004Z","signature_b64":"GhyN9T09piVTuY3TEFXVxKza0VPA4EEb0ZQDU1kW5HV29onM0LiqDuYQozVqq61zhNGVyyswdGI7dtT1vFo0CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b539a79ef5dbb967bf2d6802bde4f285f02fa3876736cfb5c3dfed2dbbfa29d","last_reissued_at":"2026-07-05T10:27:27.457476Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:27:27.457476Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Less is more? Rewards in RL for Cyber Defence","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.LG","authors_text":"Chris Hicks, Elizabeth Bates, Vasilios Mavroudis","submitted_at":"2025-03-05T07:53:39Z","abstract_excerpt":"The last few years have seen an explosion of interest in autonomous cyber defence agents based on deep reinforcement learning. Such agents are typically trained in a cyber gym environment, also known as a cyber simulator, at least 32 of which have already been built. Most, if not all cyber gyms provide dense \"scaffolded\" reward functions which combine many penalties or incentives for a range of (un)desirable states and costly actions. Whilst dense rewards help alleviate the challenge of exploring complex environments, yielding seemingly effective strategies from relatively few environment step"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.03245","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/2503.03245/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":"2503.03245","created_at":"2026-07-05T10:27:27.457539+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.03245v2","created_at":"2026-07-05T10:27:27.457539+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.03245","created_at":"2026-07-05T10:27:27.457539+00:00"},{"alias_kind":"pith_short_12","alias_value":"LNJZU6PPLW5Z","created_at":"2026-07-05T10:27:27.457539+00:00"},{"alias_kind":"pith_short_16","alias_value":"LNJZU6PPLW5ZM67S","created_at":"2026-07-05T10:27:27.457539+00:00"},{"alias_kind":"pith_short_8","alias_value":"LNJZU6PP","created_at":"2026-07-05T10:27:27.457539+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":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LNJZU6PPLW5ZM67S22ACXXSPFB","json":"https://pith.science/pith/LNJZU6PPLW5ZM67S22ACXXSPFB.json","graph_json":"https://pith.science/api/pith-number/LNJZU6PPLW5ZM67S22ACXXSPFB/graph.json","events_json":"https://pith.science/api/pith-number/LNJZU6PPLW5ZM67S22ACXXSPFB/events.json","paper":"https://pith.science/paper/LNJZU6PP"},"agent_actions":{"view_html":"https://pith.science/pith/LNJZU6PPLW5ZM67S22ACXXSPFB","download_json":"https://pith.science/pith/LNJZU6PPLW5ZM67S22ACXXSPFB.json","view_paper":"https://pith.science/paper/LNJZU6PP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.03245&json=true","fetch_graph":"https://pith.science/api/pith-number/LNJZU6PPLW5ZM67S22ACXXSPFB/graph.json","fetch_events":"https://pith.science/api/pith-number/LNJZU6PPLW5ZM67S22ACXXSPFB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LNJZU6PPLW5ZM67S22ACXXSPFB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LNJZU6PPLW5ZM67S22ACXXSPFB/action/storage_attestation","attest_author":"https://pith.science/pith/LNJZU6PPLW5ZM67S22ACXXSPFB/action/author_attestation","sign_citation":"https://pith.science/pith/LNJZU6PPLW5ZM67S22ACXXSPFB/action/citation_signature","submit_replication":"https://pith.science/pith/LNJZU6PPLW5ZM67S22ACXXSPFB/action/replication_record"}},"created_at":"2026-07-05T10:27:27.457539+00:00","updated_at":"2026-07-05T10:27:27.457539+00:00"}