{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:SBPE66KTGWMTHF2VUZ37XHDTLX","short_pith_number":"pith:SBPE66KT","schema_version":"1.0","canonical_sha256":"905e4f79533599339755a677fb9c735deaded7bea32ab170b7767f06a2cadcbd","source":{"kind":"arxiv","id":"1906.05247","version":3},"attestation_state":"computed","paper":{"title":"Bootstrapping Upper Confidence Bound","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Botao Hao, Guang Cheng, Yasin Abbasi-Yadkori, Zheng Wen","submitted_at":"2019-06-12T17:11:41Z","abstract_excerpt":"Upper Confidence Bound (UCB) method is arguably the most celebrated one used in online decision making with partial information feedback. Existing techniques for constructing confidence bounds are typically built upon various concentration inequalities, which thus lead to over-exploration. In this paper, we propose a non-parametric and data-dependent UCB algorithm based on the multiplier bootstrap. To improve its finite sample performance, we further incorporate second-order correction into the above construction. In theory, we derive both problem-dependent and problem-independent regret bound"},"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":"1906.05247","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-06-12T17:11:41Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6f453b18c7c55708ab7d9306481c26c86d75a7a7ff5f9ced88c1cc1f54d0fced","abstract_canon_sha256":"59bbe5a55d42a650a1716a979bdba308e311b6df823f07656fa8b85c202f7f20"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:16:04.262085Z","signature_b64":"bDCphWd5u7ZDkngVXFNB3iJXffy46O3CszjM7tbf3IndlPUvmQ3EXU3qhDRy0sfQKzhuTQuil11jGhMZudGGDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"905e4f79533599339755a677fb9c735deaded7bea32ab170b7767f06a2cadcbd","last_reissued_at":"2026-07-05T00:16:04.261687Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:16:04.261687Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bootstrapping Upper Confidence Bound","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Botao Hao, Guang Cheng, Yasin Abbasi-Yadkori, Zheng Wen","submitted_at":"2019-06-12T17:11:41Z","abstract_excerpt":"Upper Confidence Bound (UCB) method is arguably the most celebrated one used in online decision making with partial information feedback. Existing techniques for constructing confidence bounds are typically built upon various concentration inequalities, which thus lead to over-exploration. In this paper, we propose a non-parametric and data-dependent UCB algorithm based on the multiplier bootstrap. To improve its finite sample performance, we further incorporate second-order correction into the above construction. In theory, we derive both problem-dependent and problem-independent regret bound"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.05247","kind":"arxiv","version":3},"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/1906.05247/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":"1906.05247","created_at":"2026-07-05T00:16:04.261740+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.05247v3","created_at":"2026-07-05T00:16:04.261740+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.05247","created_at":"2026-07-05T00:16:04.261740+00:00"},{"alias_kind":"pith_short_12","alias_value":"SBPE66KTGWMT","created_at":"2026-07-05T00:16:04.261740+00:00"},{"alias_kind":"pith_short_16","alias_value":"SBPE66KTGWMTHF2V","created_at":"2026-07-05T00:16:04.261740+00:00"},{"alias_kind":"pith_short_8","alias_value":"SBPE66KT","created_at":"2026-07-05T00:16:04.261740+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/SBPE66KTGWMTHF2VUZ37XHDTLX","json":"https://pith.science/pith/SBPE66KTGWMTHF2VUZ37XHDTLX.json","graph_json":"https://pith.science/api/pith-number/SBPE66KTGWMTHF2VUZ37XHDTLX/graph.json","events_json":"https://pith.science/api/pith-number/SBPE66KTGWMTHF2VUZ37XHDTLX/events.json","paper":"https://pith.science/paper/SBPE66KT"},"agent_actions":{"view_html":"https://pith.science/pith/SBPE66KTGWMTHF2VUZ37XHDTLX","download_json":"https://pith.science/pith/SBPE66KTGWMTHF2VUZ37XHDTLX.json","view_paper":"https://pith.science/paper/SBPE66KT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.05247&json=true","fetch_graph":"https://pith.science/api/pith-number/SBPE66KTGWMTHF2VUZ37XHDTLX/graph.json","fetch_events":"https://pith.science/api/pith-number/SBPE66KTGWMTHF2VUZ37XHDTLX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SBPE66KTGWMTHF2VUZ37XHDTLX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SBPE66KTGWMTHF2VUZ37XHDTLX/action/storage_attestation","attest_author":"https://pith.science/pith/SBPE66KTGWMTHF2VUZ37XHDTLX/action/author_attestation","sign_citation":"https://pith.science/pith/SBPE66KTGWMTHF2VUZ37XHDTLX/action/citation_signature","submit_replication":"https://pith.science/pith/SBPE66KTGWMTHF2VUZ37XHDTLX/action/replication_record"}},"created_at":"2026-07-05T00:16:04.261740+00:00","updated_at":"2026-07-05T00:16:04.261740+00:00"}