{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:YAUJA2YT4QVGDMTAMGNBJXAJFU","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":"49fd22f9d63acf84b0c807b6bf56d7a800d7f4c7d12c032931a48b3a6c8a54a7","cross_cats_sorted":["math.OC"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"q-fin.PM","submitted_at":"2026-06-18T19:58:15Z","title_canon_sha256":"b710d733742a2d8d7d6a2e68f19bad9d5c08bf6ec72c3b0e373edb8f7813d357"},"schema_version":"1.0","source":{"id":"2606.20903","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.20903","created_at":"2026-06-23T01:12:21Z"},{"alias_kind":"arxiv_version","alias_value":"2606.20903v1","created_at":"2026-06-23T01:12:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.20903","created_at":"2026-06-23T01:12:21Z"},{"alias_kind":"pith_short_12","alias_value":"YAUJA2YT4QVG","created_at":"2026-06-23T01:12:21Z"},{"alias_kind":"pith_short_16","alias_value":"YAUJA2YT4QVGDMTA","created_at":"2026-06-23T01:12:21Z"},{"alias_kind":"pith_short_8","alias_value":"YAUJA2YT","created_at":"2026-06-23T01:12:21Z"}],"graph_snapshots":[{"event_id":"sha256:17e0d1aba0fa0ccaed1e575f30fb76d04e29f48ac8bbe812296516c0c5ecf4b2","target":"graph","created_at":"2026-06-23T01:12:21Z","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/2606.20903/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper develops a reinforcement-learning approach to continuous-time risk-sensitive benchmarked asset allocation in a partly model-based setting. The benchmarked problem does not directly fit the standard Markovian stochastic-control template: the state is uncontrolled, whereas the terminal reward contains a controlled It\\^o integral. We use free energy-entropy duality to reformulate the problem as a linear-quadratic-Gaussian stochastic differential game under an equivalent probability measure, yielding explicit finite- and infinite-horizon saddle-point solutions. This structure guides a c","authors_text":"Sebastien Lleo, Wolfgang Runggaldier","cross_cats":["math.OC"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"q-fin.PM","submitted_at":"2026-06-18T19:58:15Z","title":"Reinforcement Learning for Risk-Sensitive Investment Management: a Free Energy--Entropy Duality Approach"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.20903","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:fbbfb5de9f906ce937e4929c14c8fface03fb5a1fa63dcd5c499e7d630701ad2","target":"record","created_at":"2026-06-23T01:12:21Z","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":"49fd22f9d63acf84b0c807b6bf56d7a800d7f4c7d12c032931a48b3a6c8a54a7","cross_cats_sorted":["math.OC"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"q-fin.PM","submitted_at":"2026-06-18T19:58:15Z","title_canon_sha256":"b710d733742a2d8d7d6a2e68f19bad9d5c08bf6ec72c3b0e373edb8f7813d357"},"schema_version":"1.0","source":{"id":"2606.20903","kind":"arxiv","version":1}},"canonical_sha256":"c028906b13e42a61b260619a14dc092d14fd5140d0de1b098c8d65cb3be17c7e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c028906b13e42a61b260619a14dc092d14fd5140d0de1b098c8d65cb3be17c7e","first_computed_at":"2026-06-23T01:12:21.335934Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T01:12:21.335934Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jYjyCjUUMbYjRzMO58fHwjKdNDMnLLs2+gUsMGxjFS624gzqaiGLjxe+baTLjliIf7iZ0AD1PCnXFb0kL6MpAg==","signature_status":"signed_v1","signed_at":"2026-06-23T01:12:21.336433Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.20903","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fbbfb5de9f906ce937e4929c14c8fface03fb5a1fa63dcd5c499e7d630701ad2","sha256:17e0d1aba0fa0ccaed1e575f30fb76d04e29f48ac8bbe812296516c0c5ecf4b2"],"state_sha256":"bace671db9ea49a9cfd660144bc6bfe5e1991cce4f575a6ce80f7b3bd7d3f0aa"}