{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:TA3P55K2BR2AGCUQM7XSORBN6Y","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":"81289e4105eafbb0290e59503d7abd2962833a5237764a661af895034190c1ce","cross_cats_sorted":["math.OC"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-22T18:50:06Z","title_canon_sha256":"370e5c82d306b2afbce202faf724a5198f78e04490c872e3a8667de929ebacdc"},"schema_version":"1.0","source":{"id":"2311.13589","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.13589","created_at":"2026-07-05T09:52:37Z"},{"alias_kind":"arxiv_version","alias_value":"2311.13589v2","created_at":"2026-07-05T09:52:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.13589","created_at":"2026-07-05T09:52:37Z"},{"alias_kind":"pith_short_12","alias_value":"TA3P55K2BR2A","created_at":"2026-07-05T09:52:37Z"},{"alias_kind":"pith_short_16","alias_value":"TA3P55K2BR2AGCUQ","created_at":"2026-07-05T09:52:37Z"},{"alias_kind":"pith_short_8","alias_value":"TA3P55K2","created_at":"2026-07-05T09:52:37Z"}],"graph_snapshots":[{"event_id":"sha256:f2d98a3f52f4092b3a630c283cc041a870578e6b24338c616c907cd29eb531c0","target":"graph","created_at":"2026-07-05T09:52:37Z","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/2311.13589/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning (RL) has gained substantial attention across diverse application domains and theoretical investigations. Existing literature on RL theory largely focuses on risk-neutral settings where the decision-maker learns to maximize the expected cumulative reward. However, in practical scenarios such as portfolio management and e-commerce recommendations, decision-makers often persist in heterogeneous risk preferences subject to outcome uncertainties, which can not be well-captured by the risk-neural framework. Incorporating these preferences can be approached through utility theo","authors_text":"Renyuan Xu, Zhengqi Wu","cross_cats":["math.OC"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-22T18:50:06Z","title":"Risk-sensitive Markov Decision Process and Learning under General Utility Functions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.13589","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":"sha256:2f54d5e78440c7bc40e9b674ca1dd5a357a7a4de57e30fce214f8e1732f4d447","target":"record","created_at":"2026-07-05T09:52:37Z","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":"81289e4105eafbb0290e59503d7abd2962833a5237764a661af895034190c1ce","cross_cats_sorted":["math.OC"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-22T18:50:06Z","title_canon_sha256":"370e5c82d306b2afbce202faf724a5198f78e04490c872e3a8667de929ebacdc"},"schema_version":"1.0","source":{"id":"2311.13589","kind":"arxiv","version":2}},"canonical_sha256":"9836fef55a0c74030a9067ef27442df607d39c29a10131043a29ba4bf682f43e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9836fef55a0c74030a9067ef27442df607d39c29a10131043a29ba4bf682f43e","first_computed_at":"2026-07-05T09:52:37.299172Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:52:37.299172Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YxwCN3vP5FpZtO7kRVE6Nu0pb+9d091xr5FpJ9rJHxkY+ZVCEG2zrAFgEdGfOQV68RT5va7Vvj1ZzZlC4ae6DA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:52:37.299642Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.13589","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2f54d5e78440c7bc40e9b674ca1dd5a357a7a4de57e30fce214f8e1732f4d447","sha256:f2d98a3f52f4092b3a630c283cc041a870578e6b24338c616c907cd29eb531c0"],"state_sha256":"34f68b4bcfb75a90f1c6f40b8eddf63427f37f3e906b267754427191a3609ce1"}