{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:NZT4L5TY3IJHLG2Y4XCOYWGPR4","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":"f310ccd6683905f76b0589e8f65c21536529a6aaf2aae54aeb9884743ae71d62","cross_cats_sorted":["cs.SY","eess.SY","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T21:53:51Z","title_canon_sha256":"c52fb7720f60c8a6feb4050324b1ed02d1c4b88eade0dd8d7a2e99d84b915dde"},"schema_version":"1.0","source":{"id":"2605.21763","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.21763","created_at":"2026-05-22T01:03:30Z"},{"alias_kind":"arxiv_version","alias_value":"2605.21763v1","created_at":"2026-05-22T01:03:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21763","created_at":"2026-05-22T01:03:30Z"},{"alias_kind":"pith_short_12","alias_value":"NZT4L5TY3IJH","created_at":"2026-05-22T01:03:30Z"},{"alias_kind":"pith_short_16","alias_value":"NZT4L5TY3IJHLG2Y","created_at":"2026-05-22T01:03:30Z"},{"alias_kind":"pith_short_8","alias_value":"NZT4L5TY","created_at":"2026-05-22T01:03:30Z"}],"graph_snapshots":[{"event_id":"sha256:6ac42391cfe5e82b590a18bcc5dc0077782d9f1a7f3adf561f54583e99f421df","target":"graph","created_at":"2026-05-22T01:03:30Z","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/2605.21763/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study risk-sensitive reinforcement learning in finite discounted MDPs, where a generative model of the MDP is assumed to be available. We consider a family or risk measures called the optimized certainty equivalent (OCE), which includes important risk measures such as entropic risk, CVaR, and mean-variance. Our focus is on the sample complexities of learning the optimal state-action value function (value learning) and an optimal policy (policy learning) under recursive OCE. We provide an exact characterization of utility functions $u$ for which the corresponding OCE defines an objective tha","authors_text":"Mohammad Sadegh Talebi, Oliver Mortensen","cross_cats":["cs.SY","eess.SY","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T21:53:51Z","title":"On the Sample Complexity of Discounted Reinforcement Learning with Optimized Certainty Equivalents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21763","kind":"arxiv","version":1},"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":"sha256:3aa30cf465f2bea7a0dd926a92969f6a1da97a8f0a7143b96c24a9ddcb1b0e49","target":"record","created_at":"2026-05-22T01:03:30Z","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":"f310ccd6683905f76b0589e8f65c21536529a6aaf2aae54aeb9884743ae71d62","cross_cats_sorted":["cs.SY","eess.SY","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T21:53:51Z","title_canon_sha256":"c52fb7720f60c8a6feb4050324b1ed02d1c4b88eade0dd8d7a2e99d84b915dde"},"schema_version":"1.0","source":{"id":"2605.21763","kind":"arxiv","version":1}},"canonical_sha256":"6e67c5f678da12759b58e5c4ec58cf8f08f93b4d27bae15863e54a022dc41ed0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6e67c5f678da12759b58e5c4ec58cf8f08f93b4d27bae15863e54a022dc41ed0","first_computed_at":"2026-05-22T01:03:30.934039Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T01:03:30.934039Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OgsZQzz7Gz5w0WHypWGpnz4gLrsO0Q3/JcIFIh2ovQhyCna8NyARLcuTNV2VMJijULyefY1NvdyySyirHTItAw==","signature_status":"signed_v1","signed_at":"2026-05-22T01:03:30.934743Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.21763","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3aa30cf465f2bea7a0dd926a92969f6a1da97a8f0a7143b96c24a9ddcb1b0e49","sha256:6ac42391cfe5e82b590a18bcc5dc0077782d9f1a7f3adf561f54583e99f421df"],"state_sha256":"9dc8a315094773613069c39a5edd3c7dd4b32b9b9abaa37abbf5951b3de97af6"}