{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YTMIQ7F5ZOFMTF3XQCUG476F4E","short_pith_number":"pith:YTMIQ7F5","schema_version":"1.0","canonical_sha256":"c4d8887cbdcb8ac9977780a86e7fc5e138c946179890977523a4494c3f81ee19","source":{"kind":"arxiv","id":"2506.02933","version":1},"attestation_state":"computed","paper":{"title":"From Theory to Practice with RAVEN-UCB: Addressing Non-Stationarity in Multi-Armed Bandits through Variance Adaptation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Chen Zhang, Junyi Fang, Yuxin Chen, Yuxun Chen","submitted_at":"2025-06-03T14:35:04Z","abstract_excerpt":"The Multi-Armed Bandit (MAB) problem is challenging in non-stationary environments where reward distributions evolve dynamically. We introduce RAVEN-UCB, a novel algorithm that combines theoretical rigor with practical efficiency via variance-aware adaptation. It achieves tighter regret bounds than UCB1 and UCB-V, with gap-dependent regret of order $K \\sigma_{\\max}^2 \\log T / \\Delta$ and gap-independent regret of order $\\sqrt{K T \\log T}$. RAVEN-UCB incorporates three innovations: (1) variance-driven exploration using $\\sqrt{\\hat{\\sigma}_k^2 / (N_k + 1)}$ in confidence bounds, (2) adaptive con"},"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":"2506.02933","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-03T14:35:04Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"70112c15258fc44450bc2fe4612116f1de5e095552dfa072ab733a90c79e3289","abstract_canon_sha256":"11823813f4a0bbe21952be8e634e7c4ddbaa10f15e7c6dab6d2a00dd338ab725"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:12.201622Z","signature_b64":"igpv1xfBvQxwRpaSbBHx6kMUS+QvDf78M4U4cg/wIAxTDn6scAGwCzXxbAX9x9jmXHu9KzX9uyyr6xV0VC7GBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c4d8887cbdcb8ac9977780a86e7fc5e138c946179890977523a4494c3f81ee19","last_reissued_at":"2026-07-05T11:15:12.201165Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:12.201165Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Theory to Practice with RAVEN-UCB: Addressing Non-Stationarity in Multi-Armed Bandits through Variance Adaptation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Chen Zhang, Junyi Fang, Yuxin Chen, Yuxun Chen","submitted_at":"2025-06-03T14:35:04Z","abstract_excerpt":"The Multi-Armed Bandit (MAB) problem is challenging in non-stationary environments where reward distributions evolve dynamically. We introduce RAVEN-UCB, a novel algorithm that combines theoretical rigor with practical efficiency via variance-aware adaptation. It achieves tighter regret bounds than UCB1 and UCB-V, with gap-dependent regret of order $K \\sigma_{\\max}^2 \\log T / \\Delta$ and gap-independent regret of order $\\sqrt{K T \\log T}$. RAVEN-UCB incorporates three innovations: (1) variance-driven exploration using $\\sqrt{\\hat{\\sigma}_k^2 / (N_k + 1)}$ in confidence bounds, (2) adaptive con"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02933","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/2506.02933/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":"2506.02933","created_at":"2026-07-05T11:15:12.201222+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.02933v1","created_at":"2026-07-05T11:15:12.201222+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02933","created_at":"2026-07-05T11:15:12.201222+00:00"},{"alias_kind":"pith_short_12","alias_value":"YTMIQ7F5ZOFM","created_at":"2026-07-05T11:15:12.201222+00:00"},{"alias_kind":"pith_short_16","alias_value":"YTMIQ7F5ZOFMTF3X","created_at":"2026-07-05T11:15:12.201222+00:00"},{"alias_kind":"pith_short_8","alias_value":"YTMIQ7F5","created_at":"2026-07-05T11:15:12.201222+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/YTMIQ7F5ZOFMTF3XQCUG476F4E","json":"https://pith.science/pith/YTMIQ7F5ZOFMTF3XQCUG476F4E.json","graph_json":"https://pith.science/api/pith-number/YTMIQ7F5ZOFMTF3XQCUG476F4E/graph.json","events_json":"https://pith.science/api/pith-number/YTMIQ7F5ZOFMTF3XQCUG476F4E/events.json","paper":"https://pith.science/paper/YTMIQ7F5"},"agent_actions":{"view_html":"https://pith.science/pith/YTMIQ7F5ZOFMTF3XQCUG476F4E","download_json":"https://pith.science/pith/YTMIQ7F5ZOFMTF3XQCUG476F4E.json","view_paper":"https://pith.science/paper/YTMIQ7F5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.02933&json=true","fetch_graph":"https://pith.science/api/pith-number/YTMIQ7F5ZOFMTF3XQCUG476F4E/graph.json","fetch_events":"https://pith.science/api/pith-number/YTMIQ7F5ZOFMTF3XQCUG476F4E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YTMIQ7F5ZOFMTF3XQCUG476F4E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YTMIQ7F5ZOFMTF3XQCUG476F4E/action/storage_attestation","attest_author":"https://pith.science/pith/YTMIQ7F5ZOFMTF3XQCUG476F4E/action/author_attestation","sign_citation":"https://pith.science/pith/YTMIQ7F5ZOFMTF3XQCUG476F4E/action/citation_signature","submit_replication":"https://pith.science/pith/YTMIQ7F5ZOFMTF3XQCUG476F4E/action/replication_record"}},"created_at":"2026-07-05T11:15:12.201222+00:00","updated_at":"2026-07-05T11:15:12.201222+00:00"}