{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:HV3KT34TQGTSZ5SMKHJA5CDW3M","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":"3d40adbb67c8511bab952f391b930fe21b5765c95407356b2b254fcd516082e0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-08-24T18:23:59Z","title_canon_sha256":"42eb041b1dc22aed1df79bb182fe8b2c98a4a2f8b4d3bb38eb244b30b7082708"},"schema_version":"1.0","source":{"id":"2308.13011","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.13011","created_at":"2026-07-05T06:45:38Z"},{"alias_kind":"arxiv_version","alias_value":"2308.13011v1","created_at":"2026-07-05T06:45:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.13011","created_at":"2026-07-05T06:45:38Z"},{"alias_kind":"pith_short_12","alias_value":"HV3KT34TQGTS","created_at":"2026-07-05T06:45:38Z"},{"alias_kind":"pith_short_16","alias_value":"HV3KT34TQGTSZ5SM","created_at":"2026-07-05T06:45:38Z"},{"alias_kind":"pith_short_8","alias_value":"HV3KT34T","created_at":"2026-07-05T06:45:38Z"}],"graph_snapshots":[{"event_id":"sha256:4d5086fec503f0cfdede0b4ea2537ab9035ba16696d0e9a58a9b6e5b63dfa61b","target":"graph","created_at":"2026-07-05T06:45:38Z","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/2308.13011/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Risk-sensitive reinforcement learning (RL) has garnered significant attention in recent years due to the growing interest in deploying RL agents in real-world scenarios. A critical aspect of risk awareness involves modeling highly rare risk events (rewards) that could potentially lead to catastrophic outcomes. These infrequent occurrences present a formidable challenge for data-driven methods aiming to capture such risky events accurately. While risk-aware RL techniques do exist, their level of risk aversion heavily relies on the precision of the state-action value function estimation when mod","authors_text":"Frank Liu, Jan Drgona, Karthik Somayaji NS, Mahantesh Halappanavar, Malachi Schram, Peng Li, Yu Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-08-24T18:23:59Z","title":"Extreme Risk Mitigation in Reinforcement Learning using Extreme Value Theory"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.13011","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":"sha256:4f597b19cc13d3008ed4c7c7112295902e30ba26172d7c42675dedb1914e17ad","target":"record","created_at":"2026-07-05T06:45:38Z","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":"3d40adbb67c8511bab952f391b930fe21b5765c95407356b2b254fcd516082e0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-08-24T18:23:59Z","title_canon_sha256":"42eb041b1dc22aed1df79bb182fe8b2c98a4a2f8b4d3bb38eb244b30b7082708"},"schema_version":"1.0","source":{"id":"2308.13011","kind":"arxiv","version":1}},"canonical_sha256":"3d76a9ef9381a72cf64c51d20e8876db3883bbdb69cbd839baa86ecf2444423a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3d76a9ef9381a72cf64c51d20e8876db3883bbdb69cbd839baa86ecf2444423a","first_computed_at":"2026-07-05T06:45:38.460621Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:45:38.460621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZO3gg+5meOhLvoed1i0aUE8OgnKGdce8AewUarRg4uP0A0Q+SGvu2IG3dJQSKrvaihWYirGBEvwPxvHDMBEjAg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:45:38.461037Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.13011","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4f597b19cc13d3008ed4c7c7112295902e30ba26172d7c42675dedb1914e17ad","sha256:4d5086fec503f0cfdede0b4ea2537ab9035ba16696d0e9a58a9b6e5b63dfa61b"],"state_sha256":"55d6b925bd4f7ec97ab8ee7216a8e7493a736191341e00bb8df8ce2a4ccb894b"}