{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2012:IAJLR7JEFYG36EVR5CK6B33WRD","short_pith_number":"pith:IAJLR7JE","schema_version":"1.0","canonical_sha256":"4012b8fd242e0dbf12b1e895e0ef7688cd1501b39bc9e4fe22ce54a2746da821","source":{"kind":"arxiv","id":"1205.4217","version":2},"attestation_state":"computed","paper":{"title":"Thompson Sampling: An Asymptotically Optimal Finite Time Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Emilie Kaufmann, Nathaniel Korda, R\\'emi Munos","submitted_at":"2012-05-18T19:00:51Z","abstract_excerpt":"The question of the optimality of Thompson Sampling for solving the stochastic multi-armed bandit problem had been open since 1933. In this paper we answer it positively for the case of Bernoulli rewards by providing the first finite-time analysis that matches the asymptotic rate given in the Lai and Robbins lower bound for the cumulative regret. The proof is accompanied by a numerical comparison with other optimal policies, experiments that have been lacking in the literature until now for the Bernoulli case."},"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":"1205.4217","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2012-05-18T19:00:51Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4315d78b7d418f278920b818db7beb94f88394b3d951b09fb62f2943f2a8f1a2","abstract_canon_sha256":"469fc41c1b8b3294b36332a83b3e11a7f0e3151544ed85d3848bccc883c8419b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:50:37.095022Z","signature_b64":"Sz8G22Y6AOvpsXjWrWaE+TMIPrcUQgsuD34DpzeZv+EoRNV+rtYjTVkC6hSXXvOqmxQ+siUsey6A5P0zp6jyDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4012b8fd242e0dbf12b1e895e0ef7688cd1501b39bc9e4fe22ce54a2746da821","last_reissued_at":"2026-05-18T03:50:37.094375Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:50:37.094375Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Thompson Sampling: An Asymptotically Optimal Finite Time Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Emilie Kaufmann, Nathaniel Korda, R\\'emi Munos","submitted_at":"2012-05-18T19:00:51Z","abstract_excerpt":"The question of the optimality of Thompson Sampling for solving the stochastic multi-armed bandit problem had been open since 1933. In this paper we answer it positively for the case of Bernoulli rewards by providing the first finite-time analysis that matches the asymptotic rate given in the Lai and Robbins lower bound for the cumulative regret. The proof is accompanied by a numerical comparison with other optimal policies, experiments that have been lacking in the literature until now for the Bernoulli case."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1205.4217","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":"1205.4217","created_at":"2026-05-18T03:50:37.094502+00:00"},{"alias_kind":"arxiv_version","alias_value":"1205.4217v2","created_at":"2026-05-18T03:50:37.094502+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1205.4217","created_at":"2026-05-18T03:50:37.094502+00:00"},{"alias_kind":"pith_short_12","alias_value":"IAJLR7JEFYG3","created_at":"2026-05-18T12:27:09.501522+00:00"},{"alias_kind":"pith_short_16","alias_value":"IAJLR7JEFYG36EVR","created_at":"2026-05-18T12:27:09.501522+00:00"},{"alias_kind":"pith_short_8","alias_value":"IAJLR7JE","created_at":"2026-05-18T12:27:09.501522+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.25272","citing_title":"Spectral bandits","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19672","citing_title":"Budgeted Online Influence Maximization","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13738","citing_title":"Covariance-adapting algorithm for semi-bandits with application to sparse rewards","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IAJLR7JEFYG36EVR5CK6B33WRD","json":"https://pith.science/pith/IAJLR7JEFYG36EVR5CK6B33WRD.json","graph_json":"https://pith.science/api/pith-number/IAJLR7JEFYG36EVR5CK6B33WRD/graph.json","events_json":"https://pith.science/api/pith-number/IAJLR7JEFYG36EVR5CK6B33WRD/events.json","paper":"https://pith.science/paper/IAJLR7JE"},"agent_actions":{"view_html":"https://pith.science/pith/IAJLR7JEFYG36EVR5CK6B33WRD","download_json":"https://pith.science/pith/IAJLR7JEFYG36EVR5CK6B33WRD.json","view_paper":"https://pith.science/paper/IAJLR7JE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1205.4217&json=true","fetch_graph":"https://pith.science/api/pith-number/IAJLR7JEFYG36EVR5CK6B33WRD/graph.json","fetch_events":"https://pith.science/api/pith-number/IAJLR7JEFYG36EVR5CK6B33WRD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IAJLR7JEFYG36EVR5CK6B33WRD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IAJLR7JEFYG36EVR5CK6B33WRD/action/storage_attestation","attest_author":"https://pith.science/pith/IAJLR7JEFYG36EVR5CK6B33WRD/action/author_attestation","sign_citation":"https://pith.science/pith/IAJLR7JEFYG36EVR5CK6B33WRD/action/citation_signature","submit_replication":"https://pith.science/pith/IAJLR7JEFYG36EVR5CK6B33WRD/action/replication_record"}},"created_at":"2026-05-18T03:50:37.094502+00:00","updated_at":"2026-05-18T03:50:37.094502+00:00"}