{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GJY3DGIEWTMINUOY2YSHWGK4WK","short_pith_number":"pith:GJY3DGIE","schema_version":"1.0","canonical_sha256":"3271b19904b4d886d1d8d6247b195cb2a2bde62a93fbdb08a4b9d8139bd9330d","source":{"kind":"arxiv","id":"2602.16862","version":3},"attestation_state":"computed","paper":{"title":"Entropy Regularization under Bayesian Drift Uncertainty","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"Gaussian policies remain optimal for entropy-regularized mean-variance optimization under Bayesian drift uncertainty, yielding closed-form belief-dependent solutions.","cross_cats":["q-fin.PM"],"primary_cat":"math.OC","authors_text":"Andy Au","submitted_at":"2026-02-18T20:42:32Z","abstract_excerpt":"We solve the entropy-regularized mean-variance portfolio problem under Bayesian drift uncertainty. Combining continuous-time Bayesian filtering with stochastic policy optimization, the main finding is negative: the two mechanisms are orthogonal. Posterior dynamics are policy independent, so entropy regularization cannot accelerate learning about the unknown drift. The mean control is identical to the deterministic Bayesian Markowitz feedback, and entropy enters only through policy variance. On the technical side, the optimal policy is Gaussian, the value function is quadratic in wealth, and th"},"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":true},"canonical_record":{"source":{"id":"2602.16862","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"math.OC","submitted_at":"2026-02-18T20:42:32Z","cross_cats_sorted":["q-fin.PM"],"title_canon_sha256":"4e3967aea91b86bd0f8d7e0753273ab7b79f55616896a035de83cb207d8f29ca","abstract_canon_sha256":"c704e25e98fc7d239be9d202cec5528ac1c5a5dea01aaf73e1af7d5356f077ef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:07:21.657096Z","signature_b64":"b+4QadWR3m3eqyddeiUERLWNbgbnKYs/pDaImRXHwnJvvOmqpD9TqwMAoq4DP0EhK1htLYFEOc3midOBXx0oAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3271b19904b4d886d1d8d6247b195cb2a2bde62a93fbdb08a4b9d8139bd9330d","last_reissued_at":"2026-06-09T02:07:21.656068Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:07:21.656068Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Entropy Regularization under Bayesian Drift Uncertainty","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"Gaussian policies remain optimal for entropy-regularized mean-variance optimization under Bayesian drift uncertainty, yielding closed-form belief-dependent solutions.","cross_cats":["q-fin.PM"],"primary_cat":"math.OC","authors_text":"Andy Au","submitted_at":"2026-02-18T20:42:32Z","abstract_excerpt":"We solve the entropy-regularized mean-variance portfolio problem under Bayesian drift uncertainty. Combining continuous-time Bayesian filtering with stochastic policy optimization, the main finding is negative: the two mechanisms are orthogonal. Posterior dynamics are policy independent, so entropy regularization cannot accelerate learning about the unknown drift. The mean control is identical to the deterministic Bayesian Markowitz feedback, and entropy enters only through policy variance. On the technical side, the optimal policy is Gaussian, the value function is quadratic in wealth, and th"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Gaussian policies remain optimal under partial information, the value function is quadratic in wealth, and belief-dependent coefficients admit closed-form solutions. The mean control is identical to deterministic Bayesian Markowitz feedback; entropy regularization affects only the policy variance. Notably, optimal policy variance increases with posterior conviction |m_t|.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The model permits closed-form solutions under the combination of linear-Gaussian dynamics, quadratic costs, and Bayesian updating of the drift, which may not generalize if the uncertainty structure or cost functions deviate from these standard forms.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Under Bayesian drift uncertainty, entropy regularization leaves mean control identical to deterministic Bayesian Markowitz while making optimal policy variance increase with posterior conviction |m_t| for added robustness without affecting information gain.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Gaussian policies remain optimal for entropy-regularized mean-variance optimization under Bayesian drift uncertainty, yielding closed-form belief-dependent solutions.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"656213859b0da62ecc1dea2d5a2600e0663f9d9d2953308497421fdf2b9380bc"},"source":{"id":"2602.16862","kind":"arxiv","version":3},"verdict":{"id":"01b31870-e971-400b-ab37-fec893683ad2","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T20:58:11.334372Z","strongest_claim":"Gaussian policies remain optimal under partial information, the value function is quadratic in wealth, and belief-dependent coefficients admit closed-form solutions. The mean control is identical to deterministic Bayesian Markowitz feedback; entropy regularization affects only the policy variance. Notably, optimal policy variance increases with posterior conviction |m_t|.","one_line_summary":"Under Bayesian drift uncertainty, entropy regularization leaves mean control identical to deterministic Bayesian Markowitz while making optimal policy variance increase with posterior conviction |m_t| for added robustness without affecting information gain.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The model permits closed-form solutions under the combination of linear-Gaussian dynamics, quadratic costs, and Bayesian updating of the drift, which may not generalize if the uncertainty structure or cost functions deviate from these standard forms.","pith_extraction_headline":"Gaussian policies remain optimal for entropy-regularized mean-variance optimization under Bayesian drift uncertainty, yielding closed-form belief-dependent solutions."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2602.16862/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":3,"snapshot_sha256":"a29e86027415740e8ce700d329d5b843bf47bb75cc86beeeddd24a8d63031184"},"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":"2602.16862","created_at":"2026-06-09T02:07:21.656191+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.16862v3","created_at":"2026-06-09T02:07:21.656191+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.16862","created_at":"2026-06-09T02:07:21.656191+00:00"},{"alias_kind":"pith_short_12","alias_value":"GJY3DGIEWTMI","created_at":"2026-06-09T02:07:21.656191+00:00"},{"alias_kind":"pith_short_16","alias_value":"GJY3DGIEWTMINUOY","created_at":"2026-06-09T02:07:21.656191+00:00"},{"alias_kind":"pith_short_8","alias_value":"GJY3DGIE","created_at":"2026-06-09T02:07:21.656191+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":3,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GJY3DGIEWTMINUOY2YSHWGK4WK","json":"https://pith.science/pith/GJY3DGIEWTMINUOY2YSHWGK4WK.json","graph_json":"https://pith.science/api/pith-number/GJY3DGIEWTMINUOY2YSHWGK4WK/graph.json","events_json":"https://pith.science/api/pith-number/GJY3DGIEWTMINUOY2YSHWGK4WK/events.json","paper":"https://pith.science/paper/GJY3DGIE"},"agent_actions":{"view_html":"https://pith.science/pith/GJY3DGIEWTMINUOY2YSHWGK4WK","download_json":"https://pith.science/pith/GJY3DGIEWTMINUOY2YSHWGK4WK.json","view_paper":"https://pith.science/paper/GJY3DGIE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.16862&json=true","fetch_graph":"https://pith.science/api/pith-number/GJY3DGIEWTMINUOY2YSHWGK4WK/graph.json","fetch_events":"https://pith.science/api/pith-number/GJY3DGIEWTMINUOY2YSHWGK4WK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GJY3DGIEWTMINUOY2YSHWGK4WK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GJY3DGIEWTMINUOY2YSHWGK4WK/action/storage_attestation","attest_author":"https://pith.science/pith/GJY3DGIEWTMINUOY2YSHWGK4WK/action/author_attestation","sign_citation":"https://pith.science/pith/GJY3DGIEWTMINUOY2YSHWGK4WK/action/citation_signature","submit_replication":"https://pith.science/pith/GJY3DGIEWTMINUOY2YSHWGK4WK/action/replication_record"}},"created_at":"2026-06-09T02:07:21.656191+00:00","updated_at":"2026-06-09T02:07:21.656191+00:00"}