{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VG2OCWO4EKLV7MGGTNJDDYQE6Q","short_pith_number":"pith:VG2OCWO4","schema_version":"1.0","canonical_sha256":"a9b4e159dc22975fb0c69b5231e204f40506b6c3806d2bfffa15f340b70b96b0","source":{"kind":"arxiv","id":"2501.16659","version":1},"attestation_state":"computed","paper":{"title":"Exploratory Mean-Variance Portfolio Optimization with Regime-Switching Market Dynamics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["q-fin.MF","q-fin.ST","stat.ML"],"primary_cat":"q-fin.PM","authors_text":"Bin Li, David Saunders, Yuling Max Chen","submitted_at":"2025-01-28T02:48:41Z","abstract_excerpt":"Considering the continuous-time Mean-Variance (MV) portfolio optimization problem, we study a regime-switching market setting and apply reinforcement learning (RL) techniques to assist informed exploration within the control space. We introduce and solve the Exploratory Mean Variance with Regime Switching (EMVRS) problem. We also present a Policy Improvement Theorem. Further, we recognize that the widely applied Temporal Difference (TD) learning is not adequate for the EMVRS context, hence we consider Orthogonality Condition (OC) learning, leveraging the martingale property of the induced opti"},"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":"2501.16659","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-fin.PM","submitted_at":"2025-01-28T02:48:41Z","cross_cats_sorted":["q-fin.MF","q-fin.ST","stat.ML"],"title_canon_sha256":"7e1bbfabfc1a9929c1aa9138ff16098a26f0dd614da4c2dc77d4f2ce006691e3","abstract_canon_sha256":"791c28ba829fd98f09d3b0dbfddeea434932926d2faf5f5ddf095c6b20c03e7e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:06:16.535564Z","signature_b64":"YW9+uqc5OEkbxqLWv5TEDs2RVfBBGpbW7bOQsyVgNWiSIi/rilUbycyg2qoBzuPfnWlZEy0oQ1DicL1k8CV+Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a9b4e159dc22975fb0c69b5231e204f40506b6c3806d2bfffa15f340b70b96b0","last_reissued_at":"2026-07-05T10:06:16.535109Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:06:16.535109Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploratory Mean-Variance Portfolio Optimization with Regime-Switching Market Dynamics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["q-fin.MF","q-fin.ST","stat.ML"],"primary_cat":"q-fin.PM","authors_text":"Bin Li, David Saunders, Yuling Max Chen","submitted_at":"2025-01-28T02:48:41Z","abstract_excerpt":"Considering the continuous-time Mean-Variance (MV) portfolio optimization problem, we study a regime-switching market setting and apply reinforcement learning (RL) techniques to assist informed exploration within the control space. We introduce and solve the Exploratory Mean Variance with Regime Switching (EMVRS) problem. We also present a Policy Improvement Theorem. Further, we recognize that the widely applied Temporal Difference (TD) learning is not adequate for the EMVRS context, hence we consider Orthogonality Condition (OC) learning, leveraging the martingale property of the induced opti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.16659","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/2501.16659/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":"2501.16659","created_at":"2026-07-05T10:06:16.535166+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.16659v1","created_at":"2026-07-05T10:06:16.535166+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.16659","created_at":"2026-07-05T10:06:16.535166+00:00"},{"alias_kind":"pith_short_12","alias_value":"VG2OCWO4EKLV","created_at":"2026-07-05T10:06:16.535166+00:00"},{"alias_kind":"pith_short_16","alias_value":"VG2OCWO4EKLV7MGG","created_at":"2026-07-05T10:06:16.535166+00:00"},{"alias_kind":"pith_short_8","alias_value":"VG2OCWO4","created_at":"2026-07-05T10:06:16.535166+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/VG2OCWO4EKLV7MGGTNJDDYQE6Q","json":"https://pith.science/pith/VG2OCWO4EKLV7MGGTNJDDYQE6Q.json","graph_json":"https://pith.science/api/pith-number/VG2OCWO4EKLV7MGGTNJDDYQE6Q/graph.json","events_json":"https://pith.science/api/pith-number/VG2OCWO4EKLV7MGGTNJDDYQE6Q/events.json","paper":"https://pith.science/paper/VG2OCWO4"},"agent_actions":{"view_html":"https://pith.science/pith/VG2OCWO4EKLV7MGGTNJDDYQE6Q","download_json":"https://pith.science/pith/VG2OCWO4EKLV7MGGTNJDDYQE6Q.json","view_paper":"https://pith.science/paper/VG2OCWO4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.16659&json=true","fetch_graph":"https://pith.science/api/pith-number/VG2OCWO4EKLV7MGGTNJDDYQE6Q/graph.json","fetch_events":"https://pith.science/api/pith-number/VG2OCWO4EKLV7MGGTNJDDYQE6Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VG2OCWO4EKLV7MGGTNJDDYQE6Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VG2OCWO4EKLV7MGGTNJDDYQE6Q/action/storage_attestation","attest_author":"https://pith.science/pith/VG2OCWO4EKLV7MGGTNJDDYQE6Q/action/author_attestation","sign_citation":"https://pith.science/pith/VG2OCWO4EKLV7MGGTNJDDYQE6Q/action/citation_signature","submit_replication":"https://pith.science/pith/VG2OCWO4EKLV7MGGTNJDDYQE6Q/action/replication_record"}},"created_at":"2026-07-05T10:06:16.535166+00:00","updated_at":"2026-07-05T10:06:16.535166+00:00"}