{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:HV3KT34TQGTSZ5SMKHJA5CDW3M","short_pith_number":"pith:HV3KT34T","schema_version":"1.0","canonical_sha256":"3d76a9ef9381a72cf64c51d20e8876db3883bbdb69cbd839baa86ecf2444423a","source":{"kind":"arxiv","id":"2308.13011","version":1},"attestation_state":"computed","paper":{"title":"Extreme Risk Mitigation in Reinforcement Learning using Extreme Value Theory","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Frank Liu, Jan Drgona, Karthik Somayaji NS, Mahantesh Halappanavar, Malachi Schram, Peng Li, Yu Wang","submitted_at":"2023-08-24T18:23:59Z","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"},"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":"2308.13011","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-08-24T18:23:59Z","cross_cats_sorted":[],"title_canon_sha256":"42eb041b1dc22aed1df79bb182fe8b2c98a4a2f8b4d3bb38eb244b30b7082708","abstract_canon_sha256":"3d40adbb67c8511bab952f391b930fe21b5765c95407356b2b254fcd516082e0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:45:38.461037Z","signature_b64":"ZO3gg+5meOhLvoed1i0aUE8OgnKGdce8AewUarRg4uP0A0Q+SGvu2IG3dJQSKrvaihWYirGBEvwPxvHDMBEjAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d76a9ef9381a72cf64c51d20e8876db3883bbdb69cbd839baa86ecf2444423a","last_reissued_at":"2026-07-05T06:45:38.460621Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:45:38.460621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Extreme Risk Mitigation in Reinforcement Learning using Extreme Value Theory","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Frank Liu, Jan Drgona, Karthik Somayaji NS, Mahantesh Halappanavar, Malachi Schram, Peng Li, Yu Wang","submitted_at":"2023-08-24T18:23:59Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.13011","kind":"arxiv","version":1},"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/2308.13011/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":"2308.13011","created_at":"2026-07-05T06:45:38.460679+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.13011v1","created_at":"2026-07-05T06:45:38.460679+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.13011","created_at":"2026-07-05T06:45:38.460679+00:00"},{"alias_kind":"pith_short_12","alias_value":"HV3KT34TQGTS","created_at":"2026-07-05T06:45:38.460679+00:00"},{"alias_kind":"pith_short_16","alias_value":"HV3KT34TQGTSZ5SM","created_at":"2026-07-05T06:45:38.460679+00:00"},{"alias_kind":"pith_short_8","alias_value":"HV3KT34T","created_at":"2026-07-05T06:45:38.460679+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HV3KT34TQGTSZ5SMKHJA5CDW3M","json":"https://pith.science/pith/HV3KT34TQGTSZ5SMKHJA5CDW3M.json","graph_json":"https://pith.science/api/pith-number/HV3KT34TQGTSZ5SMKHJA5CDW3M/graph.json","events_json":"https://pith.science/api/pith-number/HV3KT34TQGTSZ5SMKHJA5CDW3M/events.json","paper":"https://pith.science/paper/HV3KT34T"},"agent_actions":{"view_html":"https://pith.science/pith/HV3KT34TQGTSZ5SMKHJA5CDW3M","download_json":"https://pith.science/pith/HV3KT34TQGTSZ5SMKHJA5CDW3M.json","view_paper":"https://pith.science/paper/HV3KT34T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.13011&json=true","fetch_graph":"https://pith.science/api/pith-number/HV3KT34TQGTSZ5SMKHJA5CDW3M/graph.json","fetch_events":"https://pith.science/api/pith-number/HV3KT34TQGTSZ5SMKHJA5CDW3M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HV3KT34TQGTSZ5SMKHJA5CDW3M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HV3KT34TQGTSZ5SMKHJA5CDW3M/action/storage_attestation","attest_author":"https://pith.science/pith/HV3KT34TQGTSZ5SMKHJA5CDW3M/action/author_attestation","sign_citation":"https://pith.science/pith/HV3KT34TQGTSZ5SMKHJA5CDW3M/action/citation_signature","submit_replication":"https://pith.science/pith/HV3KT34TQGTSZ5SMKHJA5CDW3M/action/replication_record"}},"created_at":"2026-07-05T06:45:38.460679+00:00","updated_at":"2026-07-05T06:45:38.460679+00:00"}