{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:JVDJDNU3SMYY6L3EMD54HS32WQ","short_pith_number":"pith:JVDJDNU3","schema_version":"1.0","canonical_sha256":"4d4691b69b93318f2f6460fbc3cb7ab41afaf848a5c982a6acb964541b591644","source":{"kind":"arxiv","id":"1402.0555","version":2},"attestation_state":"computed","paper":{"title":"Taming the Monster: A Fast and Simple Algorithm for Contextual Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alekh Agarwal, Daniel Hsu, John Langford, Lihong Li, Robert E. Schapire, Satyen Kale","submitted_at":"2014-02-04T00:48:29Z","abstract_excerpt":"We present a new algorithm for the contextual bandit learning problem, where the learner repeatedly takes one of $K$ actions in response to the observed context, and observes the reward only for that chosen action. Our method assumes access to an oracle for solving fully supervised cost-sensitive classification problems and achieves the statistically optimal regret guarantee with only $\\tilde{O}(\\sqrt{KT/\\log N})$ oracle calls across all $T$ rounds, where $N$ is the number of policies in the policy class we compete against. By doing so, we obtain the most practical contextual bandit learning a"},"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":"1402.0555","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-02-04T00:48:29Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"5cb3bbda6555e1ebd9c6b9af30470565ce07aec834c5f390e1c9443e9e13b3e9","abstract_canon_sha256":"1fba3f5b1a1a5276af99934322c542396f9e309ba7648f67df7305dc0e9e8dcf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:40:10.784089Z","signature_b64":"VV5mkFLojHY4KfWBSy0s1hbY848jny/ojFwL7oyOYTvdfPbHvdZejOIOqqZJrUhjz5ufp4MaH+0iWRRv+8zsCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d4691b69b93318f2f6460fbc3cb7ab41afaf848a5c982a6acb964541b591644","last_reissued_at":"2026-05-18T02:40:10.783437Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:40:10.783437Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Taming the Monster: A Fast and Simple Algorithm for Contextual Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alekh Agarwal, Daniel Hsu, John Langford, Lihong Li, Robert E. Schapire, Satyen Kale","submitted_at":"2014-02-04T00:48:29Z","abstract_excerpt":"We present a new algorithm for the contextual bandit learning problem, where the learner repeatedly takes one of $K$ actions in response to the observed context, and observes the reward only for that chosen action. Our method assumes access to an oracle for solving fully supervised cost-sensitive classification problems and achieves the statistically optimal regret guarantee with only $\\tilde{O}(\\sqrt{KT/\\log N})$ oracle calls across all $T$ rounds, where $N$ is the number of policies in the policy class we compete against. By doing so, we obtain the most practical contextual bandit learning a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1402.0555","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":"1402.0555","created_at":"2026-05-18T02:40:10.783510+00:00"},{"alias_kind":"arxiv_version","alias_value":"1402.0555v2","created_at":"2026-05-18T02:40:10.783510+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1402.0555","created_at":"2026-05-18T02:40:10.783510+00:00"},{"alias_kind":"pith_short_12","alias_value":"JVDJDNU3SMYY","created_at":"2026-05-18T12:28:35.611951+00:00"},{"alias_kind":"pith_short_16","alias_value":"JVDJDNU3SMYY6L3E","created_at":"2026-05-18T12:28:35.611951+00:00"},{"alias_kind":"pith_short_8","alias_value":"JVDJDNU3","created_at":"2026-05-18T12:28:35.611951+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/JVDJDNU3SMYY6L3EMD54HS32WQ","json":"https://pith.science/pith/JVDJDNU3SMYY6L3EMD54HS32WQ.json","graph_json":"https://pith.science/api/pith-number/JVDJDNU3SMYY6L3EMD54HS32WQ/graph.json","events_json":"https://pith.science/api/pith-number/JVDJDNU3SMYY6L3EMD54HS32WQ/events.json","paper":"https://pith.science/paper/JVDJDNU3"},"agent_actions":{"view_html":"https://pith.science/pith/JVDJDNU3SMYY6L3EMD54HS32WQ","download_json":"https://pith.science/pith/JVDJDNU3SMYY6L3EMD54HS32WQ.json","view_paper":"https://pith.science/paper/JVDJDNU3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1402.0555&json=true","fetch_graph":"https://pith.science/api/pith-number/JVDJDNU3SMYY6L3EMD54HS32WQ/graph.json","fetch_events":"https://pith.science/api/pith-number/JVDJDNU3SMYY6L3EMD54HS32WQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JVDJDNU3SMYY6L3EMD54HS32WQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JVDJDNU3SMYY6L3EMD54HS32WQ/action/storage_attestation","attest_author":"https://pith.science/pith/JVDJDNU3SMYY6L3EMD54HS32WQ/action/author_attestation","sign_citation":"https://pith.science/pith/JVDJDNU3SMYY6L3EMD54HS32WQ/action/citation_signature","submit_replication":"https://pith.science/pith/JVDJDNU3SMYY6L3EMD54HS32WQ/action/replication_record"}},"created_at":"2026-05-18T02:40:10.783510+00:00","updated_at":"2026-05-18T02:40:10.783510+00:00"}