{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:Q7CJZPVNLJWQKG3PZPO3M7IDYL","short_pith_number":"pith:Q7CJZPVN","schema_version":"1.0","canonical_sha256":"87c49cbead5a6d051b6fcbddb67d03c2f542ba7ab12a0521e2ad2a6fdb330d97","source":{"kind":"arxiv","id":"2606.09191","version":1},"attestation_state":"computed","paper":{"title":"Asymptotic Optimality of Thompson Sampling for Risk-Averse Bandits with Sub-Gaussian Rewards","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Joel Q. L. Chang","submitted_at":"2026-06-08T08:26:37Z","abstract_excerpt":"We prove that $\\rho\\text{-}\\mathrm{NPTS}_{\\mathrm{SG}}$, an anchor-free nonparametric Thompson Sampling algorithm for risk-averse bandits, achieves regret matching the instance-dependent lower bound to leading order in $\\log n$, establishing it as asymptotically optimal for any continuous risk functional $\\rho$ (CVaR, mean-variance, Sharpe ratio, distortion risk measures, and more) on the class of distributions with bounded density and sub-Gaussian tails, including Gaussian arms. Both this result and its bounded-support counterpart require only continuity of $\\rho$: strictly weaker than the do"},"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":"2606.09191","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-08T08:26:37Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"3796a9eedeeb21b819dc57e422434101e0265b7e21988add8547056a3206b875","abstract_canon_sha256":"e4829de5756dc16693976eb9be9164df93721544ff82a1ca76e1a07c12dd1a42"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:08:06.264295Z","signature_b64":"r7v2FSWq/WcqObPV1qB+YPS5MoxX2vVdX/Y/D8J/7kSeY4+Ke8mlf/sbYtt+GcWFOuZcrcwKRXGwRgxddos0Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"87c49cbead5a6d051b6fcbddb67d03c2f542ba7ab12a0521e2ad2a6fdb330d97","last_reissued_at":"2026-06-09T02:08:06.263326Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:08:06.263326Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Asymptotic Optimality of Thompson Sampling for Risk-Averse Bandits with Sub-Gaussian Rewards","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Joel Q. L. Chang","submitted_at":"2026-06-08T08:26:37Z","abstract_excerpt":"We prove that $\\rho\\text{-}\\mathrm{NPTS}_{\\mathrm{SG}}$, an anchor-free nonparametric Thompson Sampling algorithm for risk-averse bandits, achieves regret matching the instance-dependent lower bound to leading order in $\\log n$, establishing it as asymptotically optimal for any continuous risk functional $\\rho$ (CVaR, mean-variance, Sharpe ratio, distortion risk measures, and more) on the class of distributions with bounded density and sub-Gaussian tails, including Gaussian arms. Both this result and its bounded-support counterpart require only continuity of $\\rho$: strictly weaker than the do"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09191","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/2606.09191/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":"2606.09191","created_at":"2026-06-09T02:08:06.263514+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.09191v1","created_at":"2026-06-09T02:08:06.263514+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09191","created_at":"2026-06-09T02:08:06.263514+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q7CJZPVNLJWQ","created_at":"2026-06-09T02:08:06.263514+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q7CJZPVNLJWQKG3P","created_at":"2026-06-09T02:08:06.263514+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q7CJZPVN","created_at":"2026-06-09T02:08:06.263514+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/Q7CJZPVNLJWQKG3PZPO3M7IDYL","json":"https://pith.science/pith/Q7CJZPVNLJWQKG3PZPO3M7IDYL.json","graph_json":"https://pith.science/api/pith-number/Q7CJZPVNLJWQKG3PZPO3M7IDYL/graph.json","events_json":"https://pith.science/api/pith-number/Q7CJZPVNLJWQKG3PZPO3M7IDYL/events.json","paper":"https://pith.science/paper/Q7CJZPVN"},"agent_actions":{"view_html":"https://pith.science/pith/Q7CJZPVNLJWQKG3PZPO3M7IDYL","download_json":"https://pith.science/pith/Q7CJZPVNLJWQKG3PZPO3M7IDYL.json","view_paper":"https://pith.science/paper/Q7CJZPVN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.09191&json=true","fetch_graph":"https://pith.science/api/pith-number/Q7CJZPVNLJWQKG3PZPO3M7IDYL/graph.json","fetch_events":"https://pith.science/api/pith-number/Q7CJZPVNLJWQKG3PZPO3M7IDYL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q7CJZPVNLJWQKG3PZPO3M7IDYL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q7CJZPVNLJWQKG3PZPO3M7IDYL/action/storage_attestation","attest_author":"https://pith.science/pith/Q7CJZPVNLJWQKG3PZPO3M7IDYL/action/author_attestation","sign_citation":"https://pith.science/pith/Q7CJZPVNLJWQKG3PZPO3M7IDYL/action/citation_signature","submit_replication":"https://pith.science/pith/Q7CJZPVNLJWQKG3PZPO3M7IDYL/action/replication_record"}},"created_at":"2026-06-09T02:08:06.263514+00:00","updated_at":"2026-06-09T02:08:06.263514+00:00"}