{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:WYMNCCIPSKUKDYYGT64DIUVDM6","short_pith_number":"pith:WYMNCCIP","schema_version":"1.0","canonical_sha256":"b618d1090f92a8a1e3069fb83452a367aaf12742dcdee7d41c1d13f94933dcf4","source":{"kind":"arxiv","id":"1507.00300","version":1},"attestation_state":"computed","paper":{"title":"Bootstrapped Thompson Sampling and Deep Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Benjamin Van Roy, Ian Osband","submitted_at":"2015-07-01T17:47:01Z","abstract_excerpt":"This technical note presents a new approach to carrying out the kind of exploration achieved by Thompson sampling, but without explicitly maintaining or sampling from posterior distributions. The approach is based on a bootstrap technique that uses a combination of observed and artificially generated data. The latter serves to induce a prior distribution which, as we will demonstrate, is critical to effective exploration. We explain how the approach can be applied to multi-armed bandit and reinforcement learning problems and how it relates to Thompson sampling. The approach is particularly wel"},"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":"1507.00300","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-07-01T17:47:01Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"fe111e50cdaff96ccf53d5071e4ee12de2c0299eac3bd09c8a65baa0cfaf636d","abstract_canon_sha256":"3825c75d3a370c95dc1bceec5020e6b8ae79a3caa1a39c006862c8f66c370c08"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:37:29.268293Z","signature_b64":"yhWhB0QIvwGttGE3lGerZHzDGm3rOE8pYSFFQk3fwvjCegHIRuATgKeeveu5zUj98vG8xKKtLj9Yy2XdIH53AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b618d1090f92a8a1e3069fb83452a367aaf12742dcdee7d41c1d13f94933dcf4","last_reissued_at":"2026-05-18T01:37:29.267582Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:37:29.267582Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bootstrapped Thompson Sampling and Deep Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Benjamin Van Roy, Ian Osband","submitted_at":"2015-07-01T17:47:01Z","abstract_excerpt":"This technical note presents a new approach to carrying out the kind of exploration achieved by Thompson sampling, but without explicitly maintaining or sampling from posterior distributions. The approach is based on a bootstrap technique that uses a combination of observed and artificially generated data. The latter serves to induce a prior distribution which, as we will demonstrate, is critical to effective exploration. We explain how the approach can be applied to multi-armed bandit and reinforcement learning problems and how it relates to Thompson sampling. The approach is particularly wel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1507.00300","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":""},"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":"1507.00300","created_at":"2026-05-18T01:37:29.267698+00:00"},{"alias_kind":"arxiv_version","alias_value":"1507.00300v1","created_at":"2026-05-18T01:37:29.267698+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1507.00300","created_at":"2026-05-18T01:37:29.267698+00:00"},{"alias_kind":"pith_short_12","alias_value":"WYMNCCIPSKUK","created_at":"2026-05-18T12:29:47.479230+00:00"},{"alias_kind":"pith_short_16","alias_value":"WYMNCCIPSKUKDYYG","created_at":"2026-05-18T12:29:47.479230+00:00"},{"alias_kind":"pith_short_8","alias_value":"WYMNCCIP","created_at":"2026-05-18T12:29:47.479230+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2105.09232","citing_title":"Diffusion Approximations for Thompson Sampling in the Small Gap Regime","ref_index":40,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WYMNCCIPSKUKDYYGT64DIUVDM6","json":"https://pith.science/pith/WYMNCCIPSKUKDYYGT64DIUVDM6.json","graph_json":"https://pith.science/api/pith-number/WYMNCCIPSKUKDYYGT64DIUVDM6/graph.json","events_json":"https://pith.science/api/pith-number/WYMNCCIPSKUKDYYGT64DIUVDM6/events.json","paper":"https://pith.science/paper/WYMNCCIP"},"agent_actions":{"view_html":"https://pith.science/pith/WYMNCCIPSKUKDYYGT64DIUVDM6","download_json":"https://pith.science/pith/WYMNCCIPSKUKDYYGT64DIUVDM6.json","view_paper":"https://pith.science/paper/WYMNCCIP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1507.00300&json=true","fetch_graph":"https://pith.science/api/pith-number/WYMNCCIPSKUKDYYGT64DIUVDM6/graph.json","fetch_events":"https://pith.science/api/pith-number/WYMNCCIPSKUKDYYGT64DIUVDM6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WYMNCCIPSKUKDYYGT64DIUVDM6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WYMNCCIPSKUKDYYGT64DIUVDM6/action/storage_attestation","attest_author":"https://pith.science/pith/WYMNCCIPSKUKDYYGT64DIUVDM6/action/author_attestation","sign_citation":"https://pith.science/pith/WYMNCCIPSKUKDYYGT64DIUVDM6/action/citation_signature","submit_replication":"https://pith.science/pith/WYMNCCIPSKUKDYYGT64DIUVDM6/action/replication_record"}},"created_at":"2026-05-18T01:37:29.267698+00:00","updated_at":"2026-05-18T01:37:29.267698+00:00"}