{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:3M5TZ6XQBCGSRALKAKZTKSS72K","short_pith_number":"pith:3M5TZ6XQ","schema_version":"1.0","canonical_sha256":"db3b3cfaf0088d28816a02b3354a5fd29f9d75b3a71dc4ad09a314a98a25edb7","source":{"kind":"arxiv","id":"2306.09048","version":1},"attestation_state":"computed","paper":{"title":"Optimal Best-Arm Identification in Bandits with Access to Offline Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Arun Sai Suggala, Karthikeyan Shanmugam, Sandeep Juneja, Shubhada Agrawal","submitted_at":"2023-06-15T11:12:35Z","abstract_excerpt":"Learning paradigms based purely on offline data as well as those based solely on sequential online learning have been well-studied in the literature. In this paper, we consider combining offline data with online learning, an area less studied but of obvious practical importance. We consider the stochastic $K$-armed bandit problem, where our goal is to identify the arm with the highest mean in the presence of relevant offline data, with confidence $1-\\delta$. We conduct a lower bound analysis on policies that provide such $1-\\delta$ probabilistic correctness guarantees. We develop algorithms th"},"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":"2306.09048","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-15T11:12:35Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"4e6654665a36de91a5ceb6a83acfe97428d107b309d28fbfa0aa09cf26a0cca9","abstract_canon_sha256":"06e44366aee2b0ab947d285549fc89f4a69be67e532bf48ca65ceff1684cbee7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:21:07.952524Z","signature_b64":"xFtk8N1T04nb0sZFKiKmaVPcec+xVxKH5PtFKG0Tc+O6VXdcvhxnzXuzjZZL5/vB39wcVe4zu3y7FZAgEnI/Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db3b3cfaf0088d28816a02b3354a5fd29f9d75b3a71dc4ad09a314a98a25edb7","last_reissued_at":"2026-07-05T06:21:07.952001Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:21:07.952001Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimal Best-Arm Identification in Bandits with Access to Offline Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Arun Sai Suggala, Karthikeyan Shanmugam, Sandeep Juneja, Shubhada Agrawal","submitted_at":"2023-06-15T11:12:35Z","abstract_excerpt":"Learning paradigms based purely on offline data as well as those based solely on sequential online learning have been well-studied in the literature. In this paper, we consider combining offline data with online learning, an area less studied but of obvious practical importance. We consider the stochastic $K$-armed bandit problem, where our goal is to identify the arm with the highest mean in the presence of relevant offline data, with confidence $1-\\delta$. We conduct a lower bound analysis on policies that provide such $1-\\delta$ probabilistic correctness guarantees. We develop algorithms th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.09048","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/2306.09048/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":"2306.09048","created_at":"2026-07-05T06:21:07.952057+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.09048v1","created_at":"2026-07-05T06:21:07.952057+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.09048","created_at":"2026-07-05T06:21:07.952057+00:00"},{"alias_kind":"pith_short_12","alias_value":"3M5TZ6XQBCGS","created_at":"2026-07-05T06:21:07.952057+00:00"},{"alias_kind":"pith_short_16","alias_value":"3M5TZ6XQBCGSRALK","created_at":"2026-07-05T06:21:07.952057+00:00"},{"alias_kind":"pith_short_8","alias_value":"3M5TZ6XQ","created_at":"2026-07-05T06:21:07.952057+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.08413","citing_title":"Decentralized Relaxed Smooth Optimization with Gradient Descent Methods","ref_index":2012,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3M5TZ6XQBCGSRALKAKZTKSS72K","json":"https://pith.science/pith/3M5TZ6XQBCGSRALKAKZTKSS72K.json","graph_json":"https://pith.science/api/pith-number/3M5TZ6XQBCGSRALKAKZTKSS72K/graph.json","events_json":"https://pith.science/api/pith-number/3M5TZ6XQBCGSRALKAKZTKSS72K/events.json","paper":"https://pith.science/paper/3M5TZ6XQ"},"agent_actions":{"view_html":"https://pith.science/pith/3M5TZ6XQBCGSRALKAKZTKSS72K","download_json":"https://pith.science/pith/3M5TZ6XQBCGSRALKAKZTKSS72K.json","view_paper":"https://pith.science/paper/3M5TZ6XQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.09048&json=true","fetch_graph":"https://pith.science/api/pith-number/3M5TZ6XQBCGSRALKAKZTKSS72K/graph.json","fetch_events":"https://pith.science/api/pith-number/3M5TZ6XQBCGSRALKAKZTKSS72K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3M5TZ6XQBCGSRALKAKZTKSS72K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3M5TZ6XQBCGSRALKAKZTKSS72K/action/storage_attestation","attest_author":"https://pith.science/pith/3M5TZ6XQBCGSRALKAKZTKSS72K/action/author_attestation","sign_citation":"https://pith.science/pith/3M5TZ6XQBCGSRALKAKZTKSS72K/action/citation_signature","submit_replication":"https://pith.science/pith/3M5TZ6XQBCGSRALKAKZTKSS72K/action/replication_record"}},"created_at":"2026-07-05T06:21:07.952057+00:00","updated_at":"2026-07-05T06:21:07.952057+00:00"}