{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:BQET4DP4CGLGSH5HBGVPZA77ST","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":"85361b663ee384041e6f38b7e2c80fc94433016cbbe8941f245c54c005db6526","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2022-11-23T15:33:19Z","title_canon_sha256":"14245cb4acae416124bbef7058522e6d2533e3d1c4e843fb8f7b204a0b295d5b"},"schema_version":"1.0","source":{"id":"2211.13032","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.13032","created_at":"2026-07-05T05:22:31Z"},{"alias_kind":"arxiv_version","alias_value":"2211.13032v2","created_at":"2026-07-05T05:22:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.13032","created_at":"2026-07-05T05:22:31Z"},{"alias_kind":"pith_short_12","alias_value":"BQET4DP4CGLG","created_at":"2026-07-05T05:22:31Z"},{"alias_kind":"pith_short_16","alias_value":"BQET4DP4CGLGSH5H","created_at":"2026-07-05T05:22:31Z"},{"alias_kind":"pith_short_8","alias_value":"BQET4DP4","created_at":"2026-07-05T05:22:31Z"}],"graph_snapshots":[{"event_id":"sha256:247803f58acbd0dbca8d9de77999fdfcb30f976c4e624c7eb67d615000f8b669","target":"graph","created_at":"2026-07-05T05:22:31Z","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/2211.13032/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In many risk-aware and multi-objective reinforcement learning settings, the utility of the user is derived from a single execution of a policy. In these settings, making decisions based on the average future returns is not suitable. For example, in a medical setting a patient may only have one opportunity to treat their illness. Making decisions using just the expected future returns -- known in reinforcement learning as the value -- cannot account for the potential range of adverse or positive outcomes a decision may have. Therefore, we should use the distribution over expected future returns","authors_text":"Conor F. Hayes, Diederik M. Roijers, Enda Howley, Mathieu Reymond, Patrick Mannion","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2022-11-23T15:33:19Z","title":"Monte Carlo Tree Search Algorithms for Risk-Aware and Multi-Objective Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.13032","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":"sha256:9bcf9bed3d37e319e0399199e6db0ed2aa86c664a986cdbf33520b10d0527bd6","target":"record","created_at":"2026-07-05T05:22:31Z","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":"85361b663ee384041e6f38b7e2c80fc94433016cbbe8941f245c54c005db6526","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2022-11-23T15:33:19Z","title_canon_sha256":"14245cb4acae416124bbef7058522e6d2533e3d1c4e843fb8f7b204a0b295d5b"},"schema_version":"1.0","source":{"id":"2211.13032","kind":"arxiv","version":2}},"canonical_sha256":"0c093e0dfc1196691fa709aafc83ff94f1a00399547a4c2f5eded4ebecd39007","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0c093e0dfc1196691fa709aafc83ff94f1a00399547a4c2f5eded4ebecd39007","first_computed_at":"2026-07-05T05:22:31.076970Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:22:31.076970Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZDCbub31aThG0NaJLZ7mPXH4C584sSQ23fSksG6sei14WNTi0p4wOOvK5dYPaHkfMyj7eyCnRoSyjCWMns60BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:22:31.077372Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.13032","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9bcf9bed3d37e319e0399199e6db0ed2aa86c664a986cdbf33520b10d0527bd6","sha256:247803f58acbd0dbca8d9de77999fdfcb30f976c4e624c7eb67d615000f8b669"],"state_sha256":"09bd138272063587acc2db19c057164a75ca16ed3cc14340495a1f01509fc380"}