{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:TA3P55K2BR2AGCUQM7XSORBN6Y","short_pith_number":"pith:TA3P55K2","canonical_record":{"source":{"id":"2311.13589","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-22T18:50:06Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"370e5c82d306b2afbce202faf724a5198f78e04490c872e3a8667de929ebacdc","abstract_canon_sha256":"81289e4105eafbb0290e59503d7abd2962833a5237764a661af895034190c1ce"},"schema_version":"1.0"},"canonical_sha256":"9836fef55a0c74030a9067ef27442df607d39c29a10131043a29ba4bf682f43e","source":{"kind":"arxiv","id":"2311.13589","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:TA3P55K2BR2AGCUQM7XSORBN6Y","target":"record","payload":{"canonical_record":{"source":{"id":"2311.13589","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-22T18:50:06Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"370e5c82d306b2afbce202faf724a5198f78e04490c872e3a8667de929ebacdc","abstract_canon_sha256":"81289e4105eafbb0290e59503d7abd2962833a5237764a661af895034190c1ce"},"schema_version":"1.0"},"canonical_sha256":"9836fef55a0c74030a9067ef27442df607d39c29a10131043a29ba4bf682f43e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:52:37.299642Z","signature_b64":"YxwCN3vP5FpZtO7kRVE6Nu0pb+9d091xr5FpJ9rJHxkY+ZVCEG2zrAFgEdGfOQV68RT5va7Vvj1ZzZlC4ae6DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9836fef55a0c74030a9067ef27442df607d39c29a10131043a29ba4bf682f43e","last_reissued_at":"2026-07-05T09:52:37.299172Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:52:37.299172Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.13589","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:52:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"swudNwAm//TCoeESXN7o3+0dw2eny9xPiMAtd5vV79JVQZ9A2rmyiGNz0hDeRvNsUCjjkyVJHEwywooePn5LBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T13:54:10.143243Z"},"content_sha256":"2f54d5e78440c7bc40e9b674ca1dd5a357a7a4de57e30fce214f8e1732f4d447","schema_version":"1.0","event_id":"sha256:2f54d5e78440c7bc40e9b674ca1dd5a357a7a4de57e30fce214f8e1732f4d447"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:TA3P55K2BR2AGCUQM7XSORBN6Y","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Risk-sensitive Markov Decision Process and Learning under General Utility Functions","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Renyuan Xu, Zhengqi Wu","submitted_at":"2023-11-22T18:50:06Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.13589","kind":"arxiv","version":2},"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/2311.13589/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:52:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"abgDj4UU3I1QzqaNqLHBYb8AxGqUkYVr2K+p7ek40VQPa0rgsFxH2BrQA/0UMe1rkW701QeDIc4p+hq2I+vQAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T13:54:10.143631Z"},"content_sha256":"f2d98a3f52f4092b3a630c283cc041a870578e6b24338c616c907cd29eb531c0","schema_version":"1.0","event_id":"sha256:f2d98a3f52f4092b3a630c283cc041a870578e6b24338c616c907cd29eb531c0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TA3P55K2BR2AGCUQM7XSORBN6Y/bundle.json","state_url":"https://pith.science/pith/TA3P55K2BR2AGCUQM7XSORBN6Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TA3P55K2BR2AGCUQM7XSORBN6Y/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-17T13:54:10Z","links":{"resolver":"https://pith.science/pith/TA3P55K2BR2AGCUQM7XSORBN6Y","bundle":"https://pith.science/pith/TA3P55K2BR2AGCUQM7XSORBN6Y/bundle.json","state":"https://pith.science/pith/TA3P55K2BR2AGCUQM7XSORBN6Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TA3P55K2BR2AGCUQM7XSORBN6Y/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+opgIDIC+l/M48CweIjyfuIKRAjdiKVxBIwnDsCbSMBg/CrIoS2TXsz4rHcsIiPNU2pqpg0MPCRWCszve1/pDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T13:54:10.146195Z","bundle_sha256":"8ccf63b651a67825efdc1cb510d231eb60aba79b246975a198851826ea9fdf70"}}