{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2013:7I6CW6BUQV6GL3VHN7P3B2QMXU","short_pith_number":"pith:7I6CW6BU","schema_version":"1.0","canonical_sha256":"fa3c2b7834857c65eea76fdfb0ea0cbd18b8183376312d3e3d7db933aa51dca9","source":{"kind":"arxiv","id":"1302.3721","version":1},"attestation_state":"computed","paper":{"title":"Thompson Sampling in Switching Environments with Bayesian Online Change Point Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jonathan Shapiro, Joseph Mellor","submitted_at":"2013-02-15T10:48:57Z","abstract_excerpt":"Thompson Sampling has recently been shown to be optimal in the Bernoulli Multi-Armed Bandit setting[Kaufmann et al., 2012]. This bandit problem assumes stationary distributions for the rewards. It is often unrealistic to model the real world as a stationary distribution. In this paper we derive and evaluate algorithms using Thompson Sampling for a Switching Multi-Armed Bandit Problem. We propose a Thompson Sampling strategy equipped with a Bayesian change point mechanism to tackle this problem. We develop algorithms for a variety of cases with constant switching rate: when switching occurs all"},"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":"1302.3721","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-02-15T10:48:57Z","cross_cats_sorted":[],"title_canon_sha256":"70935c096f40997dc59f6adbeb716aa48e996c8ee30c802a9b0856f6796c4ba1","abstract_canon_sha256":"0148f319901bb2aba5054c36eef788f280432636103d273fd39a8eafbbe3610e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:33:35.991774Z","signature_b64":"n17o8zGcwTy54GO+nH+i+/zO8vaVRlfjStMJwzaYuFpYqghoaHp14uSKYgN/VEfVuqJN8Eh9KpA7c5T+H8AfDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa3c2b7834857c65eea76fdfb0ea0cbd18b8183376312d3e3d7db933aa51dca9","last_reissued_at":"2026-05-18T03:33:35.990918Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:33:35.990918Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Thompson Sampling in Switching Environments with Bayesian Online Change Point Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jonathan Shapiro, Joseph Mellor","submitted_at":"2013-02-15T10:48:57Z","abstract_excerpt":"Thompson Sampling has recently been shown to be optimal in the Bernoulli Multi-Armed Bandit setting[Kaufmann et al., 2012]. This bandit problem assumes stationary distributions for the rewards. It is often unrealistic to model the real world as a stationary distribution. In this paper we derive and evaluate algorithms using Thompson Sampling for a Switching Multi-Armed Bandit Problem. We propose a Thompson Sampling strategy equipped with a Bayesian change point mechanism to tackle this problem. We develop algorithms for a variety of cases with constant switching rate: when switching occurs all"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1302.3721","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":"1302.3721","created_at":"2026-05-18T03:33:35.991048+00:00"},{"alias_kind":"arxiv_version","alias_value":"1302.3721v1","created_at":"2026-05-18T03:33:35.991048+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1302.3721","created_at":"2026-05-18T03:33:35.991048+00:00"},{"alias_kind":"pith_short_12","alias_value":"7I6CW6BUQV6G","created_at":"2026-05-18T12:27:36.564083+00:00"},{"alias_kind":"pith_short_16","alias_value":"7I6CW6BUQV6GL3VH","created_at":"2026-05-18T12:27:36.564083+00:00"},{"alias_kind":"pith_short_8","alias_value":"7I6CW6BU","created_at":"2026-05-18T12:27:36.564083+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.19672","citing_title":"Budgeted Online Influence Maximization","ref_index":67,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7I6CW6BUQV6GL3VHN7P3B2QMXU","json":"https://pith.science/pith/7I6CW6BUQV6GL3VHN7P3B2QMXU.json","graph_json":"https://pith.science/api/pith-number/7I6CW6BUQV6GL3VHN7P3B2QMXU/graph.json","events_json":"https://pith.science/api/pith-number/7I6CW6BUQV6GL3VHN7P3B2QMXU/events.json","paper":"https://pith.science/paper/7I6CW6BU"},"agent_actions":{"view_html":"https://pith.science/pith/7I6CW6BUQV6GL3VHN7P3B2QMXU","download_json":"https://pith.science/pith/7I6CW6BUQV6GL3VHN7P3B2QMXU.json","view_paper":"https://pith.science/paper/7I6CW6BU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1302.3721&json=true","fetch_graph":"https://pith.science/api/pith-number/7I6CW6BUQV6GL3VHN7P3B2QMXU/graph.json","fetch_events":"https://pith.science/api/pith-number/7I6CW6BUQV6GL3VHN7P3B2QMXU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7I6CW6BUQV6GL3VHN7P3B2QMXU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7I6CW6BUQV6GL3VHN7P3B2QMXU/action/storage_attestation","attest_author":"https://pith.science/pith/7I6CW6BUQV6GL3VHN7P3B2QMXU/action/author_attestation","sign_citation":"https://pith.science/pith/7I6CW6BUQV6GL3VHN7P3B2QMXU/action/citation_signature","submit_replication":"https://pith.science/pith/7I6CW6BUQV6GL3VHN7P3B2QMXU/action/replication_record"}},"created_at":"2026-05-18T03:33:35.991048+00:00","updated_at":"2026-05-18T03:33:35.991048+00:00"}