{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7TOOUNCGGLRGIKUEFNKBECBQAZ","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":"f0dd8c89c875e52ec114aab20b0d933701051f3be195332c37fd2c108f7ad608","cross_cats_sorted":["cs.AI","q-fin.RM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-fin.MF","submitted_at":"2025-05-07T16:31:42Z","title_canon_sha256":"9b7362a45fac4010395a850a9aee886f21da44102020596fa73093e223dc238a"},"schema_version":"1.0","source":{"id":"2505.04553","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.04553","created_at":"2026-07-05T11:03:24Z"},{"alias_kind":"arxiv_version","alias_value":"2505.04553v2","created_at":"2026-07-05T11:03:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.04553","created_at":"2026-07-05T11:03:24Z"},{"alias_kind":"pith_short_12","alias_value":"7TOOUNCGGLRG","created_at":"2026-07-05T11:03:24Z"},{"alias_kind":"pith_short_16","alias_value":"7TOOUNCGGLRGIKUE","created_at":"2026-07-05T11:03:24Z"},{"alias_kind":"pith_short_8","alias_value":"7TOOUNCG","created_at":"2026-07-05T11:03:24Z"}],"graph_snapshots":[{"event_id":"sha256:9b12902053808d7bafcca4d3676a1a55a253f40671b75ef91106e4202d97adc1","target":"graph","created_at":"2026-07-05T11:03:24Z","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/2505.04553/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a reinforcement learning (RL) framework under a broad class of risk objectives, characterized by convex scoring functions. This class covers many common risk measures, such as variance, Expected Shortfall, entropic Value-at-Risk, and mean-risk utility. To resolve the time-inconsistency issue, we consider an augmented state space and an auxiliary variable and recast the problem as a two-state optimization problem. We propose a customized Actor-Critic algorithm and establish some theoretical approximation guarantees. A key theoretical contribution is that our results do not require th","authors_text":"Shanyu Han, Xiang Yu, Yang Liu","cross_cats":["cs.AI","q-fin.RM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-fin.MF","submitted_at":"2025-05-07T16:31:42Z","title":"Risk-sensitive Reinforcement Learning Based on Convex Scoring Functions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.04553","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":"sha256:6a5737d9a21d9bbbac704c54f1889ced389b2d5fd2f0737764b393e04c2fb176","target":"record","created_at":"2026-07-05T11:03:24Z","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":"f0dd8c89c875e52ec114aab20b0d933701051f3be195332c37fd2c108f7ad608","cross_cats_sorted":["cs.AI","q-fin.RM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-fin.MF","submitted_at":"2025-05-07T16:31:42Z","title_canon_sha256":"9b7362a45fac4010395a850a9aee886f21da44102020596fa73093e223dc238a"},"schema_version":"1.0","source":{"id":"2505.04553","kind":"arxiv","version":2}},"canonical_sha256":"fcdcea344632e2642a842b54120830066b76b3966da8625ae597d4e6946489c2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fcdcea344632e2642a842b54120830066b76b3966da8625ae597d4e6946489c2","first_computed_at":"2026-07-05T11:03:24.158293Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:03:24.158293Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DD1liQY+6sJjqMvrLwtnH9UpONIxPL3UI6ARZOkmhxEJq2JU/Vr4oyKemkyvZ8wlK4wJYgJN056X8gcSQYu7Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:03:24.158796Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.04553","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6a5737d9a21d9bbbac704c54f1889ced389b2d5fd2f0737764b393e04c2fb176","sha256:9b12902053808d7bafcca4d3676a1a55a253f40671b75ef91106e4202d97adc1"],"state_sha256":"4b2e4d4d229c0d169ac453b3bee7b68db3a351f2cc1efbbde97ca67b41999b24"}