{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LNJZU6PPLW5ZM67S22ACXXSPFB","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":"a72f19adc1a2595f7393e9d17516f084328e5ee62ccf4f2c4ae2b8c2b82a6c22","cross_cats_sorted":["cs.AI","cs.CR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-05T07:53:39Z","title_canon_sha256":"60684b04d6839ab80ea734827128fe30b3d7cf987f2d48759efc0859b2619f2c"},"schema_version":"1.0","source":{"id":"2503.03245","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.03245","created_at":"2026-07-05T10:27:27Z"},{"alias_kind":"arxiv_version","alias_value":"2503.03245v2","created_at":"2026-07-05T10:27:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.03245","created_at":"2026-07-05T10:27:27Z"},{"alias_kind":"pith_short_12","alias_value":"LNJZU6PPLW5Z","created_at":"2026-07-05T10:27:27Z"},{"alias_kind":"pith_short_16","alias_value":"LNJZU6PPLW5ZM67S","created_at":"2026-07-05T10:27:27Z"},{"alias_kind":"pith_short_8","alias_value":"LNJZU6PP","created_at":"2026-07-05T10:27:27Z"}],"graph_snapshots":[{"event_id":"sha256:999d842c4d708697f4c5fd2b00872f29e2d4e3b2935034b3912f63b48fdc04c9","target":"graph","created_at":"2026-07-05T10:27:27Z","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/2503.03245/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chris Hicks, Elizabeth Bates, Vasilios Mavroudis","cross_cats":["cs.AI","cs.CR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-05T07:53:39Z","title":"Less is more? Rewards in RL for Cyber Defence"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.03245","kind":"arxiv","version":2},"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":"sha256:8c2a9f00563ffd5f1ced31df92f901272694407f04966e05ff7edd5ccf8feccc","target":"record","created_at":"2026-07-05T10:27:27Z","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":"a72f19adc1a2595f7393e9d17516f084328e5ee62ccf4f2c4ae2b8c2b82a6c22","cross_cats_sorted":["cs.AI","cs.CR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-05T07:53:39Z","title_canon_sha256":"60684b04d6839ab80ea734827128fe30b3d7cf987f2d48759efc0859b2619f2c"},"schema_version":"1.0","source":{"id":"2503.03245","kind":"arxiv","version":2}},"canonical_sha256":"5b539a79ef5dbb967bf2d6802bde4f285f02fa3876736cfb5c3dfed2dbbfa29d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5b539a79ef5dbb967bf2d6802bde4f285f02fa3876736cfb5c3dfed2dbbfa29d","first_computed_at":"2026-07-05T10:27:27.457476Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:27:27.457476Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GhyN9T09piVTuY3TEFXVxKza0VPA4EEb0ZQDU1kW5HV29onM0LiqDuYQozVqq61zhNGVyyswdGI7dtT1vFo0CA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:27:27.458004Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.03245","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8c2a9f00563ffd5f1ced31df92f901272694407f04966e05ff7edd5ccf8feccc","sha256:999d842c4d708697f4c5fd2b00872f29e2d4e3b2935034b3912f63b48fdc04c9"],"state_sha256":"fdb1e22d633d579abef5a99c13238e866481767b47687ffc3d8ccc48411bacff"}