{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YAUJA2YT4QVGDMTAMGNBJXAJFU","short_pith_number":"pith:YAUJA2YT","schema_version":"1.0","canonical_sha256":"c028906b13e42a61b260619a14dc092d14fd5140d0de1b098c8d65cb3be17c7e","source":{"kind":"arxiv","id":"2606.20903","version":1},"attestation_state":"computed","paper":{"title":"Reinforcement Learning for Risk-Sensitive Investment Management: a Free Energy--Entropy Duality Approach","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"q-fin.PM","authors_text":"Sebastien Lleo, Wolfgang Runggaldier","submitted_at":"2026-06-18T19:58:15Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.20903","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"q-fin.PM","submitted_at":"2026-06-18T19:58:15Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"b710d733742a2d8d7d6a2e68f19bad9d5c08bf6ec72c3b0e373edb8f7813d357","abstract_canon_sha256":"49fd22f9d63acf84b0c807b6bf56d7a800d7f4c7d12c032931a48b3a6c8a54a7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T01:12:21.336433Z","signature_b64":"jYjyCjUUMbYjRzMO58fHwjKdNDMnLLs2+gUsMGxjFS624gzqaiGLjxe+baTLjliIf7iZ0AD1PCnXFb0kL6MpAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c028906b13e42a61b260619a14dc092d14fd5140d0de1b098c8d65cb3be17c7e","last_reissued_at":"2026-06-23T01:12:21.335934Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T01:12:21.335934Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement Learning for Risk-Sensitive Investment Management: a Free Energy--Entropy Duality Approach","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"q-fin.PM","authors_text":"Sebastien Lleo, Wolfgang Runggaldier","submitted_at":"2026-06-18T19:58:15Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.20903","kind":"arxiv","version":1},"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/2606.20903/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.20903","created_at":"2026-06-23T01:12:21.336009+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.20903v1","created_at":"2026-06-23T01:12:21.336009+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.20903","created_at":"2026-06-23T01:12:21.336009+00:00"},{"alias_kind":"pith_short_12","alias_value":"YAUJA2YT4QVG","created_at":"2026-06-23T01:12:21.336009+00:00"},{"alias_kind":"pith_short_16","alias_value":"YAUJA2YT4QVGDMTA","created_at":"2026-06-23T01:12:21.336009+00:00"},{"alias_kind":"pith_short_8","alias_value":"YAUJA2YT","created_at":"2026-06-23T01:12:21.336009+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YAUJA2YT4QVGDMTAMGNBJXAJFU","json":"https://pith.science/pith/YAUJA2YT4QVGDMTAMGNBJXAJFU.json","graph_json":"https://pith.science/api/pith-number/YAUJA2YT4QVGDMTAMGNBJXAJFU/graph.json","events_json":"https://pith.science/api/pith-number/YAUJA2YT4QVGDMTAMGNBJXAJFU/events.json","paper":"https://pith.science/paper/YAUJA2YT"},"agent_actions":{"view_html":"https://pith.science/pith/YAUJA2YT4QVGDMTAMGNBJXAJFU","download_json":"https://pith.science/pith/YAUJA2YT4QVGDMTAMGNBJXAJFU.json","view_paper":"https://pith.science/paper/YAUJA2YT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.20903&json=true","fetch_graph":"https://pith.science/api/pith-number/YAUJA2YT4QVGDMTAMGNBJXAJFU/graph.json","fetch_events":"https://pith.science/api/pith-number/YAUJA2YT4QVGDMTAMGNBJXAJFU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YAUJA2YT4QVGDMTAMGNBJXAJFU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YAUJA2YT4QVGDMTAMGNBJXAJFU/action/storage_attestation","attest_author":"https://pith.science/pith/YAUJA2YT4QVGDMTAMGNBJXAJFU/action/author_attestation","sign_citation":"https://pith.science/pith/YAUJA2YT4QVGDMTAMGNBJXAJFU/action/citation_signature","submit_replication":"https://pith.science/pith/YAUJA2YT4QVGDMTAMGNBJXAJFU/action/replication_record"}},"created_at":"2026-06-23T01:12:21.336009+00:00","updated_at":"2026-06-23T01:12:21.336009+00:00"}