{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:SRNDI2E5CLIAYMW2EYTOGRR4CY","short_pith_number":"pith:SRNDI2E5","schema_version":"1.0","canonical_sha256":"945a34689d12d00c32da2626e3463c161324c542d363f411477e2b6f07449963","source":{"kind":"arxiv","id":"1903.07839","version":2},"attestation_state":"computed","paper":{"title":"A Note on KL-UCB+ Policy for the Stochastic Bandit","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Junya Honda","submitted_at":"2019-03-19T05:16:43Z","abstract_excerpt":"A classic setting of the stochastic K-armed bandit problem is considered in this note. In this problem it has been known that KL-UCB policy achieves the asymptotically optimal regret bound and KL-UCB+ policy empirically performs better than the KL-UCB policy although the regret bound for the original form of the KL-UCB+ policy has been unknown. This note demonstrates that a simple proof of the asymptotic optimality of the KL-UCB+ policy can be given by the same technique as those used for analyses of other known policies."},"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":"1903.07839","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-19T05:16:43Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"87a6d1af337e137c93cf77feba680c9932b5052df0ad6a4908f176970b81d46e","abstract_canon_sha256":"79c88fca26c40a9e9ba62dac88486cc6419d418d44120c4c92de898a89fe0879"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:50:48.428953Z","signature_b64":"axSx1YOZIpPGB3YzTe2BFuGrshFAJaUyCJSV1cPUffUzfto8g6bokCT3rfGx/ZsIuuzikJeHO/3AEReRRjyhAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"945a34689d12d00c32da2626e3463c161324c542d363f411477e2b6f07449963","last_reissued_at":"2026-05-17T23:50:48.428287Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:50:48.428287Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Note on KL-UCB+ Policy for the Stochastic Bandit","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Junya Honda","submitted_at":"2019-03-19T05:16:43Z","abstract_excerpt":"A classic setting of the stochastic K-armed bandit problem is considered in this note. In this problem it has been known that KL-UCB policy achieves the asymptotically optimal regret bound and KL-UCB+ policy empirically performs better than the KL-UCB policy although the regret bound for the original form of the KL-UCB+ policy has been unknown. This note demonstrates that a simple proof of the asymptotic optimality of the KL-UCB+ policy can be given by the same technique as those used for analyses of other known policies."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.07839","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1903.07839","created_at":"2026-05-17T23:50:48.428405+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.07839v2","created_at":"2026-05-17T23:50:48.428405+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.07839","created_at":"2026-05-17T23:50:48.428405+00:00"},{"alias_kind":"pith_short_12","alias_value":"SRNDI2E5CLIA","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_16","alias_value":"SRNDI2E5CLIAYMW2","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_8","alias_value":"SRNDI2E5","created_at":"2026-05-18T12:33:27.125529+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.05613","citing_title":"Optimal Regret of Bernoulli Bandits under Global Differential Privacy","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SRNDI2E5CLIAYMW2EYTOGRR4CY","json":"https://pith.science/pith/SRNDI2E5CLIAYMW2EYTOGRR4CY.json","graph_json":"https://pith.science/api/pith-number/SRNDI2E5CLIAYMW2EYTOGRR4CY/graph.json","events_json":"https://pith.science/api/pith-number/SRNDI2E5CLIAYMW2EYTOGRR4CY/events.json","paper":"https://pith.science/paper/SRNDI2E5"},"agent_actions":{"view_html":"https://pith.science/pith/SRNDI2E5CLIAYMW2EYTOGRR4CY","download_json":"https://pith.science/pith/SRNDI2E5CLIAYMW2EYTOGRR4CY.json","view_paper":"https://pith.science/paper/SRNDI2E5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.07839&json=true","fetch_graph":"https://pith.science/api/pith-number/SRNDI2E5CLIAYMW2EYTOGRR4CY/graph.json","fetch_events":"https://pith.science/api/pith-number/SRNDI2E5CLIAYMW2EYTOGRR4CY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SRNDI2E5CLIAYMW2EYTOGRR4CY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SRNDI2E5CLIAYMW2EYTOGRR4CY/action/storage_attestation","attest_author":"https://pith.science/pith/SRNDI2E5CLIAYMW2EYTOGRR4CY/action/author_attestation","sign_citation":"https://pith.science/pith/SRNDI2E5CLIAYMW2EYTOGRR4CY/action/citation_signature","submit_replication":"https://pith.science/pith/SRNDI2E5CLIAYMW2EYTOGRR4CY/action/replication_record"}},"created_at":"2026-05-17T23:50:48.428405+00:00","updated_at":"2026-05-17T23:50:48.428405+00:00"}