{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2011:4PRQQDNLFSREWUQIDLVGL2RQYX","short_pith_number":"pith:4PRQQDNL","schema_version":"1.0","canonical_sha256":"e3e3080dab2ca24b52081aea65ea30c5e41c72dd9b63bf14f0ced8fd2289b496","source":{"kind":"arxiv","id":"1111.1797","version":3},"attestation_state":"computed","paper":{"title":"Analysis of Thompson Sampling for the multi-armed bandit problem","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS"],"primary_cat":"cs.LG","authors_text":"Navin Goyal, Shipra Agrawal","submitted_at":"2011-11-08T04:27:01Z","abstract_excerpt":"The multi-armed bandit problem is a popular model for studying exploration/exploitation trade-off in sequential decision problems. Many algorithms are now available for this well-studied problem. One of the earliest algorithms, given by W. R. Thompson, dates back to 1933. This algorithm, referred to as Thompson Sampling, is a natural Bayesian algorithm. The basic idea is to choose an arm to play according to its probability of being the best arm. Thompson Sampling algorithm has experimentally been shown to be close to optimal. In addition, it is efficient to implement and exhibits several desi"},"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":"1111.1797","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2011-11-08T04:27:01Z","cross_cats_sorted":["cs.DS"],"title_canon_sha256":"65971c3b604125890278d429800ace6255cdaaf1bc5dba6412f27979824c1b48","abstract_canon_sha256":"172697f5318053c330355dfac7b23709428fa9d73e9c55d7490798353dc8c762"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:58:24.478369Z","signature_b64":"OWbKEebfd3AMNwRAjBD2gVyfOswqG/dga7jR9BKtWnbJZL1vKAbh96TDE7uE5qsKYSuXWNMLdFSGpsUpz0nCBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e3e3080dab2ca24b52081aea65ea30c5e41c72dd9b63bf14f0ced8fd2289b496","last_reissued_at":"2026-05-18T03:58:24.477581Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:58:24.477581Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Analysis of Thompson Sampling for the multi-armed bandit problem","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS"],"primary_cat":"cs.LG","authors_text":"Navin Goyal, Shipra Agrawal","submitted_at":"2011-11-08T04:27:01Z","abstract_excerpt":"The multi-armed bandit problem is a popular model for studying exploration/exploitation trade-off in sequential decision problems. Many algorithms are now available for this well-studied problem. One of the earliest algorithms, given by W. R. Thompson, dates back to 1933. This algorithm, referred to as Thompson Sampling, is a natural Bayesian algorithm. The basic idea is to choose an arm to play according to its probability of being the best arm. Thompson Sampling algorithm has experimentally been shown to be close to optimal. In addition, it is efficient to implement and exhibits several desi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1111.1797","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":""},"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":"1111.1797","created_at":"2026-05-18T03:58:24.477688+00:00"},{"alias_kind":"arxiv_version","alias_value":"1111.1797v3","created_at":"2026-05-18T03:58:24.477688+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1111.1797","created_at":"2026-05-18T03:58:24.477688+00:00"},{"alias_kind":"pith_short_12","alias_value":"4PRQQDNLFSRE","created_at":"2026-05-18T12:26:20.644004+00:00"},{"alias_kind":"pith_short_16","alias_value":"4PRQQDNLFSREWUQI","created_at":"2026-05-18T12:26:20.644004+00:00"},{"alias_kind":"pith_short_8","alias_value":"4PRQQDNL","created_at":"2026-05-18T12:26:20.644004+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/4PRQQDNLFSREWUQIDLVGL2RQYX","json":"https://pith.science/pith/4PRQQDNLFSREWUQIDLVGL2RQYX.json","graph_json":"https://pith.science/api/pith-number/4PRQQDNLFSREWUQIDLVGL2RQYX/graph.json","events_json":"https://pith.science/api/pith-number/4PRQQDNLFSREWUQIDLVGL2RQYX/events.json","paper":"https://pith.science/paper/4PRQQDNL"},"agent_actions":{"view_html":"https://pith.science/pith/4PRQQDNLFSREWUQIDLVGL2RQYX","download_json":"https://pith.science/pith/4PRQQDNLFSREWUQIDLVGL2RQYX.json","view_paper":"https://pith.science/paper/4PRQQDNL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1111.1797&json=true","fetch_graph":"https://pith.science/api/pith-number/4PRQQDNLFSREWUQIDLVGL2RQYX/graph.json","fetch_events":"https://pith.science/api/pith-number/4PRQQDNLFSREWUQIDLVGL2RQYX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4PRQQDNLFSREWUQIDLVGL2RQYX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4PRQQDNLFSREWUQIDLVGL2RQYX/action/storage_attestation","attest_author":"https://pith.science/pith/4PRQQDNLFSREWUQIDLVGL2RQYX/action/author_attestation","sign_citation":"https://pith.science/pith/4PRQQDNLFSREWUQIDLVGL2RQYX/action/citation_signature","submit_replication":"https://pith.science/pith/4PRQQDNLFSREWUQIDLVGL2RQYX/action/replication_record"}},"created_at":"2026-05-18T03:58:24.477688+00:00","updated_at":"2026-05-18T03:58:24.477688+00:00"}