{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:G2VNPD6WTLMQZ6QE7G43FW7HSU","short_pith_number":"pith:G2VNPD6W","schema_version":"1.0","canonical_sha256":"36aad78fd69ad90cfa04f9b9b2dbe7953cd1dd780b2d4d9c6d286318cd21fc4f","source":{"kind":"arxiv","id":"1911.03959","version":4},"attestation_state":"computed","paper":{"title":"Multi-Armed Bandits with Correlated Arms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Gauri Joshi, Osman Ya\\u{g}an, Samarth Gupta, Shreyas Chaudhari","submitted_at":"2019-11-06T16:56:46Z","abstract_excerpt":"We consider a multi-armed bandit framework where the rewards obtained by pulling different arms are correlated. We develop a unified approach to leverage these reward correlations and present fundamental generalizations of classic bandit algorithms to the correlated setting. We present a unified proof technique to analyze the proposed algorithms. Rigorous analysis of C-UCB (the correlated bandit version of Upper-confidence-bound) reveals that the algorithm ends up pulling certain sub-optimal arms, termed as non-competitive, only O(1) times, as opposed to the O(log T) pulls required by classic "},"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":"1911.03959","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-11-06T16:56:46Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8721065fd44f1a57b018fc42208893bf4e40ef79b4749fcaf061816c6500e835","abstract_canon_sha256":"d79879ff7914421a67dc05843d06ddcef1225241aec313f643402b9d064be2fe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:12:59.593618Z","signature_b64":"D6ale+EglTlV/IgSRvOB0gQNwo5Icpj2G5TpQNXDm1ZBKyzwGC5PBgMROrYBLU9xt4PhDM72ZB164/DeJI3KDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36aad78fd69ad90cfa04f9b9b2dbe7953cd1dd780b2d4d9c6d286318cd21fc4f","last_reissued_at":"2026-07-05T03:12:59.593202Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:12:59.593202Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Armed Bandits with Correlated Arms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Gauri Joshi, Osman Ya\\u{g}an, Samarth Gupta, Shreyas Chaudhari","submitted_at":"2019-11-06T16:56:46Z","abstract_excerpt":"We consider a multi-armed bandit framework where the rewards obtained by pulling different arms are correlated. We develop a unified approach to leverage these reward correlations and present fundamental generalizations of classic bandit algorithms to the correlated setting. We present a unified proof technique to analyze the proposed algorithms. Rigorous analysis of C-UCB (the correlated bandit version of Upper-confidence-bound) reveals that the algorithm ends up pulling certain sub-optimal arms, termed as non-competitive, only O(1) times, as opposed to the O(log T) pulls required by classic "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.03959","kind":"arxiv","version":4},"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/1911.03959/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":"1911.03959","created_at":"2026-07-05T03:12:59.593266+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.03959v4","created_at":"2026-07-05T03:12:59.593266+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.03959","created_at":"2026-07-05T03:12:59.593266+00:00"},{"alias_kind":"pith_short_12","alias_value":"G2VNPD6WTLMQ","created_at":"2026-07-05T03:12:59.593266+00:00"},{"alias_kind":"pith_short_16","alias_value":"G2VNPD6WTLMQZ6QE","created_at":"2026-07-05T03:12:59.593266+00:00"},{"alias_kind":"pith_short_8","alias_value":"G2VNPD6W","created_at":"2026-07-05T03:12:59.593266+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/G2VNPD6WTLMQZ6QE7G43FW7HSU","json":"https://pith.science/pith/G2VNPD6WTLMQZ6QE7G43FW7HSU.json","graph_json":"https://pith.science/api/pith-number/G2VNPD6WTLMQZ6QE7G43FW7HSU/graph.json","events_json":"https://pith.science/api/pith-number/G2VNPD6WTLMQZ6QE7G43FW7HSU/events.json","paper":"https://pith.science/paper/G2VNPD6W"},"agent_actions":{"view_html":"https://pith.science/pith/G2VNPD6WTLMQZ6QE7G43FW7HSU","download_json":"https://pith.science/pith/G2VNPD6WTLMQZ6QE7G43FW7HSU.json","view_paper":"https://pith.science/paper/G2VNPD6W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.03959&json=true","fetch_graph":"https://pith.science/api/pith-number/G2VNPD6WTLMQZ6QE7G43FW7HSU/graph.json","fetch_events":"https://pith.science/api/pith-number/G2VNPD6WTLMQZ6QE7G43FW7HSU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G2VNPD6WTLMQZ6QE7G43FW7HSU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G2VNPD6WTLMQZ6QE7G43FW7HSU/action/storage_attestation","attest_author":"https://pith.science/pith/G2VNPD6WTLMQZ6QE7G43FW7HSU/action/author_attestation","sign_citation":"https://pith.science/pith/G2VNPD6WTLMQZ6QE7G43FW7HSU/action/citation_signature","submit_replication":"https://pith.science/pith/G2VNPD6WTLMQZ6QE7G43FW7HSU/action/replication_record"}},"created_at":"2026-07-05T03:12:59.593266+00:00","updated_at":"2026-07-05T03:12:59.593266+00:00"}