{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2012:R5W2MD3SJFTWUJ6OJD76UCNP47","short_pith_number":"pith:R5W2MD3S","schema_version":"1.0","canonical_sha256":"8f6da60f7249676a27ce48ffea09afe7fb738c7f78f3c3858b5b311518c0f3a2","source":{"kind":"arxiv","id":"1202.1334","version":2},"attestation_state":"computed","paper":{"title":"Contextual Bandit Learning with Predictable Rewards","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alekh Agarwal, John Langford, Miroslav Dud\\'ik, Robert E. Schapire, Satyen Kale","submitted_at":"2012-02-07T02:27:55Z","abstract_excerpt":"Contextual bandit learning is a reinforcement learning problem where the learner repeatedly receives a set of features (context), takes an action and receives a reward based on the action and context. We consider this problem under a realizability assumption: there exists a function in a (known) function class, always capable of predicting the expected reward, given the action and context. Under this assumption, we show three things. We present a new algorithm---Regressor Elimination--- with a regret similar to the agnostic setting (i.e. in the absence of realizability assumption). We prove 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":"1202.1334","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-02-07T02:27:55Z","cross_cats_sorted":[],"title_canon_sha256":"389d8945457550323f886e1bd287df8838bbd1b518f374117cc8ed8c4ca01599","abstract_canon_sha256":"868bbf5bf530cfbe5b2ed1b4526edd7f612bd26a91aa4a98caab67d94e665757"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T04:01:01.394268Z","signature_b64":"dI5baVb5mH3K/RTBoVs0dK1FgXGPH0yRiGTYLTZ3O/4KFl6X7fKzbyP86kkd2IrbvlBbIyvcIqhuoci58RhnDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f6da60f7249676a27ce48ffea09afe7fb738c7f78f3c3858b5b311518c0f3a2","last_reissued_at":"2026-05-18T04:01:01.393591Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T04:01:01.393591Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Contextual Bandit Learning with Predictable Rewards","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alekh Agarwal, John Langford, Miroslav Dud\\'ik, Robert E. Schapire, Satyen Kale","submitted_at":"2012-02-07T02:27:55Z","abstract_excerpt":"Contextual bandit learning is a reinforcement learning problem where the learner repeatedly receives a set of features (context), takes an action and receives a reward based on the action and context. We consider this problem under a realizability assumption: there exists a function in a (known) function class, always capable of predicting the expected reward, given the action and context. Under this assumption, we show three things. We present a new algorithm---Regressor Elimination--- with a regret similar to the agnostic setting (i.e. in the absence of realizability assumption). We prove a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1202.1334","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":"1202.1334","created_at":"2026-05-18T04:01:01.393704+00:00"},{"alias_kind":"arxiv_version","alias_value":"1202.1334v2","created_at":"2026-05-18T04:01:01.393704+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1202.1334","created_at":"2026-05-18T04:01:01.393704+00:00"},{"alias_kind":"pith_short_12","alias_value":"R5W2MD3SJFTW","created_at":"2026-05-18T12:27:20.899486+00:00"},{"alias_kind":"pith_short_16","alias_value":"R5W2MD3SJFTWUJ6O","created_at":"2026-05-18T12:27:20.899486+00:00"},{"alias_kind":"pith_short_8","alias_value":"R5W2MD3S","created_at":"2026-05-18T12:27:20.899486+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/R5W2MD3SJFTWUJ6OJD76UCNP47","json":"https://pith.science/pith/R5W2MD3SJFTWUJ6OJD76UCNP47.json","graph_json":"https://pith.science/api/pith-number/R5W2MD3SJFTWUJ6OJD76UCNP47/graph.json","events_json":"https://pith.science/api/pith-number/R5W2MD3SJFTWUJ6OJD76UCNP47/events.json","paper":"https://pith.science/paper/R5W2MD3S"},"agent_actions":{"view_html":"https://pith.science/pith/R5W2MD3SJFTWUJ6OJD76UCNP47","download_json":"https://pith.science/pith/R5W2MD3SJFTWUJ6OJD76UCNP47.json","view_paper":"https://pith.science/paper/R5W2MD3S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1202.1334&json=true","fetch_graph":"https://pith.science/api/pith-number/R5W2MD3SJFTWUJ6OJD76UCNP47/graph.json","fetch_events":"https://pith.science/api/pith-number/R5W2MD3SJFTWUJ6OJD76UCNP47/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R5W2MD3SJFTWUJ6OJD76UCNP47/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R5W2MD3SJFTWUJ6OJD76UCNP47/action/storage_attestation","attest_author":"https://pith.science/pith/R5W2MD3SJFTWUJ6OJD76UCNP47/action/author_attestation","sign_citation":"https://pith.science/pith/R5W2MD3SJFTWUJ6OJD76UCNP47/action/citation_signature","submit_replication":"https://pith.science/pith/R5W2MD3SJFTWUJ6OJD76UCNP47/action/replication_record"}},"created_at":"2026-05-18T04:01:01.393704+00:00","updated_at":"2026-05-18T04:01:01.393704+00:00"}