{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GHSCRZWZZTF32TNFYSKILVMKYG","short_pith_number":"pith:GHSCRZWZ","schema_version":"1.0","canonical_sha256":"31e428e6d9cccbbd4da5c49485d58ac1920413e0397730f83c62cd8faedcc95b","source":{"kind":"arxiv","id":"2307.03026","version":1},"attestation_state":"computed","paper":{"title":"Exploratory mean-variance portfolio selection with Choquet regularizers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.PR"],"primary_cat":"math.OC","authors_text":"Hao Wang, Junyi Guo, Xia Han","submitted_at":"2023-07-06T14:43:03Z","abstract_excerpt":"In this paper, we study a continuous-time exploratory mean-variance (EMV) problem under the framework of reinforcement learning (RL), and the Choquet regularizers are used to measure the level of exploration. By applying the classical Bellman principle of optimality, the Hamilton-Jacobi-Bellman equation of the EMV problem is derived and solved explicitly via maximizing statically a mean-variance constrained Choquet regularizer. In particular, the optimal distributions form a location-scale family, whose shape depends on the choices of the Choquet regularizer. We further reformulate the continu"},"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":"2307.03026","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2023-07-06T14:43:03Z","cross_cats_sorted":["math.PR"],"title_canon_sha256":"5cde4d0bcfe49ca5c92e9caf924b85d89916706521dfb072ce002355d12b8e25","abstract_canon_sha256":"282a8d32781e5b4ffb4017dcbf6ca79f38fef22c3b91cf217500fce6593ff346"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:28:27.268112Z","signature_b64":"V629tWq40F/38//72dvc4UI/paiR9XFc0U6IMXuWfCGB5wDn5q+1pfqm5kPgeUpK3bAq6WtXKGmj/QcFbvtRCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31e428e6d9cccbbd4da5c49485d58ac1920413e0397730f83c62cd8faedcc95b","last_reissued_at":"2026-07-05T06:28:27.267676Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:28:27.267676Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploratory mean-variance portfolio selection with Choquet regularizers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.PR"],"primary_cat":"math.OC","authors_text":"Hao Wang, Junyi Guo, Xia Han","submitted_at":"2023-07-06T14:43:03Z","abstract_excerpt":"In this paper, we study a continuous-time exploratory mean-variance (EMV) problem under the framework of reinforcement learning (RL), and the Choquet regularizers are used to measure the level of exploration. By applying the classical Bellman principle of optimality, the Hamilton-Jacobi-Bellman equation of the EMV problem is derived and solved explicitly via maximizing statically a mean-variance constrained Choquet regularizer. In particular, the optimal distributions form a location-scale family, whose shape depends on the choices of the Choquet regularizer. We further reformulate the continu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.03026","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/2307.03026/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":"2307.03026","created_at":"2026-07-05T06:28:27.267737+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.03026v1","created_at":"2026-07-05T06:28:27.267737+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.03026","created_at":"2026-07-05T06:28:27.267737+00:00"},{"alias_kind":"pith_short_12","alias_value":"GHSCRZWZZTF3","created_at":"2026-07-05T06:28:27.267737+00:00"},{"alias_kind":"pith_short_16","alias_value":"GHSCRZWZZTF32TNF","created_at":"2026-07-05T06:28:27.267737+00:00"},{"alias_kind":"pith_short_8","alias_value":"GHSCRZWZ","created_at":"2026-07-05T06:28:27.267737+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.04788","citing_title":"A non-zero-sum game with reinforcement learning under mean-variance framework","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GHSCRZWZZTF32TNFYSKILVMKYG","json":"https://pith.science/pith/GHSCRZWZZTF32TNFYSKILVMKYG.json","graph_json":"https://pith.science/api/pith-number/GHSCRZWZZTF32TNFYSKILVMKYG/graph.json","events_json":"https://pith.science/api/pith-number/GHSCRZWZZTF32TNFYSKILVMKYG/events.json","paper":"https://pith.science/paper/GHSCRZWZ"},"agent_actions":{"view_html":"https://pith.science/pith/GHSCRZWZZTF32TNFYSKILVMKYG","download_json":"https://pith.science/pith/GHSCRZWZZTF32TNFYSKILVMKYG.json","view_paper":"https://pith.science/paper/GHSCRZWZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.03026&json=true","fetch_graph":"https://pith.science/api/pith-number/GHSCRZWZZTF32TNFYSKILVMKYG/graph.json","fetch_events":"https://pith.science/api/pith-number/GHSCRZWZZTF32TNFYSKILVMKYG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GHSCRZWZZTF32TNFYSKILVMKYG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GHSCRZWZZTF32TNFYSKILVMKYG/action/storage_attestation","attest_author":"https://pith.science/pith/GHSCRZWZZTF32TNFYSKILVMKYG/action/author_attestation","sign_citation":"https://pith.science/pith/GHSCRZWZZTF32TNFYSKILVMKYG/action/citation_signature","submit_replication":"https://pith.science/pith/GHSCRZWZZTF32TNFYSKILVMKYG/action/replication_record"}},"created_at":"2026-07-05T06:28:27.267737+00:00","updated_at":"2026-07-05T06:28:27.267737+00:00"}