{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2010:O3WOWG4CAR2I2F5377DX2FZL4C","short_pith_number":"pith:O3WOWG4C","schema_version":"1.0","canonical_sha256":"76eceb1b8204748d17bbffc77d172be0b921d920721b2efd0e1e70080e932598","source":{"kind":"arxiv","id":"1002.4058","version":3},"attestation_state":"computed","paper":{"title":"Contextual Bandit Algorithms with Supervised Learning Guarantees","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alina Beygelzimer, John Langford, Lev Reyzin, Lihong Li, Robert E. Schapire","submitted_at":"2010-02-22T07:11:39Z","abstract_excerpt":"We address the problem of learning in an online, bandit setting where the learner must repeatedly select among $K$ actions, but only receives partial feedback based on its choices. We establish two new facts: First, using a new algorithm called Exp4.P, we show that it is possible to compete with the best in a set of $N$ experts with probability $1-\\delta$ while incurring regret at most $O(\\sqrt{KT\\ln(N/\\delta)})$ over $T$ time steps. The new algorithm is tested empirically in a large-scale, real-world dataset. Second, we give a new algorithm called VE that competes with a possibly infinite set"},"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":"1002.4058","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2010-02-22T07:11:39Z","cross_cats_sorted":[],"title_canon_sha256":"3ac7cd7797dac8e92c478aaa7d96083420ae798413a55ba37dd50ce9ee15622d","abstract_canon_sha256":"31be168c4ae84f87f6fed2599b1f4acfd2a300e95890cde0a40a832998d1c738"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T04:10:10.700751Z","signature_b64":"Sv1sYHLNqMDBCQzJ1ygxobVu47npcevVL/c/N3YhTRE2pX/hRgIyzxvKIUnNfSBHKBos9UdLu093YMeg/4jnCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"76eceb1b8204748d17bbffc77d172be0b921d920721b2efd0e1e70080e932598","last_reissued_at":"2026-05-18T04:10:10.699813Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T04:10:10.699813Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Contextual Bandit Algorithms with Supervised Learning Guarantees","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alina Beygelzimer, John Langford, Lev Reyzin, Lihong Li, Robert E. Schapire","submitted_at":"2010-02-22T07:11:39Z","abstract_excerpt":"We address the problem of learning in an online, bandit setting where the learner must repeatedly select among $K$ actions, but only receives partial feedback based on its choices. We establish two new facts: First, using a new algorithm called Exp4.P, we show that it is possible to compete with the best in a set of $N$ experts with probability $1-\\delta$ while incurring regret at most $O(\\sqrt{KT\\ln(N/\\delta)})$ over $T$ time steps. The new algorithm is tested empirically in a large-scale, real-world dataset. Second, we give a new algorithm called VE that competes with a possibly infinite set"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1002.4058","kind":"arxiv","version":3},"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":"1002.4058","created_at":"2026-05-18T04:10:10.699978+00:00"},{"alias_kind":"arxiv_version","alias_value":"1002.4058v3","created_at":"2026-05-18T04:10:10.699978+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1002.4058","created_at":"2026-05-18T04:10:10.699978+00:00"},{"alias_kind":"pith_short_12","alias_value":"O3WOWG4CAR2I","created_at":"2026-05-18T12:26:12.377268+00:00"},{"alias_kind":"pith_short_16","alias_value":"O3WOWG4CAR2I2F53","created_at":"2026-05-18T12:26:12.377268+00:00"},{"alias_kind":"pith_short_8","alias_value":"O3WOWG4C","created_at":"2026-05-18T12:26:12.377268+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/O3WOWG4CAR2I2F5377DX2FZL4C","json":"https://pith.science/pith/O3WOWG4CAR2I2F5377DX2FZL4C.json","graph_json":"https://pith.science/api/pith-number/O3WOWG4CAR2I2F5377DX2FZL4C/graph.json","events_json":"https://pith.science/api/pith-number/O3WOWG4CAR2I2F5377DX2FZL4C/events.json","paper":"https://pith.science/paper/O3WOWG4C"},"agent_actions":{"view_html":"https://pith.science/pith/O3WOWG4CAR2I2F5377DX2FZL4C","download_json":"https://pith.science/pith/O3WOWG4CAR2I2F5377DX2FZL4C.json","view_paper":"https://pith.science/paper/O3WOWG4C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1002.4058&json=true","fetch_graph":"https://pith.science/api/pith-number/O3WOWG4CAR2I2F5377DX2FZL4C/graph.json","fetch_events":"https://pith.science/api/pith-number/O3WOWG4CAR2I2F5377DX2FZL4C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O3WOWG4CAR2I2F5377DX2FZL4C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O3WOWG4CAR2I2F5377DX2FZL4C/action/storage_attestation","attest_author":"https://pith.science/pith/O3WOWG4CAR2I2F5377DX2FZL4C/action/author_attestation","sign_citation":"https://pith.science/pith/O3WOWG4CAR2I2F5377DX2FZL4C/action/citation_signature","submit_replication":"https://pith.science/pith/O3WOWG4CAR2I2F5377DX2FZL4C/action/replication_record"}},"created_at":"2026-05-18T04:10:10.699978+00:00","updated_at":"2026-05-18T04:10:10.699978+00:00"}