{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WF5CC4IKM6WLUKSTMI5K7QZY4T","short_pith_number":"pith:WF5CC4IK","schema_version":"1.0","canonical_sha256":"b17a21710a67acba2a53623aafc338e4ef2fd2cf830448299e0d65885ed4c235","source":{"kind":"arxiv","id":"2310.19821","version":1},"attestation_state":"computed","paper":{"title":"A Risk-Averse Framework for Non-Stationary Stochastic Multi-Armed Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Mastane Achab, Mohammed Mahfoud, Reda Alami","submitted_at":"2023-10-24T19:29:13Z","abstract_excerpt":"In a typical stochastic multi-armed bandit problem, the objective is often to maximize the expected sum of rewards over some time horizon $T$. While the choice of a strategy that accomplishes that is optimal with no additional information, it is no longer the case when provided additional environment-specific knowledge. In particular, in areas of high volatility like healthcare or finance, a naive reward maximization approach often does not accurately capture the complexity of the learning problem and results in unreliable solutions. To tackle problems of this nature, we propose a framework of"},"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":"2310.19821","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-24T19:29:13Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"fd921216932cb5b9e685b07d8f11a5198793b3c0f8c42e7de4313748709d7359","abstract_canon_sha256":"4c2801bdce50645a2deec98de86d4757ab779c67269b52c1ac7cd744f887cd6c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:07:19.782401Z","signature_b64":"p76YgWs0Ho1xTinBaAARkhygw0lA+Xt1glpWMsnKYsYzszngytDS6+PQYoqLDVU9Vvm6ROeR6PsYLGwVn/bRCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b17a21710a67acba2a53623aafc338e4ef2fd2cf830448299e0d65885ed4c235","last_reissued_at":"2026-07-05T07:07:19.781647Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:07:19.781647Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Risk-Averse Framework for Non-Stationary Stochastic Multi-Armed Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Mastane Achab, Mohammed Mahfoud, Reda Alami","submitted_at":"2023-10-24T19:29:13Z","abstract_excerpt":"In a typical stochastic multi-armed bandit problem, the objective is often to maximize the expected sum of rewards over some time horizon $T$. While the choice of a strategy that accomplishes that is optimal with no additional information, it is no longer the case when provided additional environment-specific knowledge. In particular, in areas of high volatility like healthcare or finance, a naive reward maximization approach often does not accurately capture the complexity of the learning problem and results in unreliable solutions. To tackle problems of this nature, we propose a framework of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.19821","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/2310.19821/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":"2310.19821","created_at":"2026-07-05T07:07:19.781882+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.19821v1","created_at":"2026-07-05T07:07:19.781882+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.19821","created_at":"2026-07-05T07:07:19.781882+00:00"},{"alias_kind":"pith_short_12","alias_value":"WF5CC4IKM6WL","created_at":"2026-07-05T07:07:19.781882+00:00"},{"alias_kind":"pith_short_16","alias_value":"WF5CC4IKM6WLUKST","created_at":"2026-07-05T07:07:19.781882+00:00"},{"alias_kind":"pith_short_8","alias_value":"WF5CC4IK","created_at":"2026-07-05T07:07:19.781882+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/WF5CC4IKM6WLUKSTMI5K7QZY4T","json":"https://pith.science/pith/WF5CC4IKM6WLUKSTMI5K7QZY4T.json","graph_json":"https://pith.science/api/pith-number/WF5CC4IKM6WLUKSTMI5K7QZY4T/graph.json","events_json":"https://pith.science/api/pith-number/WF5CC4IKM6WLUKSTMI5K7QZY4T/events.json","paper":"https://pith.science/paper/WF5CC4IK"},"agent_actions":{"view_html":"https://pith.science/pith/WF5CC4IKM6WLUKSTMI5K7QZY4T","download_json":"https://pith.science/pith/WF5CC4IKM6WLUKSTMI5K7QZY4T.json","view_paper":"https://pith.science/paper/WF5CC4IK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.19821&json=true","fetch_graph":"https://pith.science/api/pith-number/WF5CC4IKM6WLUKSTMI5K7QZY4T/graph.json","fetch_events":"https://pith.science/api/pith-number/WF5CC4IKM6WLUKSTMI5K7QZY4T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WF5CC4IKM6WLUKSTMI5K7QZY4T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WF5CC4IKM6WLUKSTMI5K7QZY4T/action/storage_attestation","attest_author":"https://pith.science/pith/WF5CC4IKM6WLUKSTMI5K7QZY4T/action/author_attestation","sign_citation":"https://pith.science/pith/WF5CC4IKM6WLUKSTMI5K7QZY4T/action/citation_signature","submit_replication":"https://pith.science/pith/WF5CC4IKM6WLUKSTMI5K7QZY4T/action/replication_record"}},"created_at":"2026-07-05T07:07:19.781882+00:00","updated_at":"2026-07-05T07:07:19.781882+00:00"}