{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:SNVYB5TADMD3REEUIQ5KAAJNOK","short_pith_number":"pith:SNVYB5TA","schema_version":"1.0","canonical_sha256":"936b80f6601b07b89094443aa0012d729ae4a3a4742c8431ef655f032ce8730f","source":{"kind":"arxiv","id":"2106.15128","version":1},"attestation_state":"computed","paper":{"title":"Regularized OFU: an Efficient UCB Estimator forNon-linear Contextual Bandit","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Huishuai Zhang, Jun Zhu, Shihong Song, Tie-Yan Liu, Wei Chen, Yichi Zhou","submitted_at":"2021-06-29T07:28:15Z","abstract_excerpt":"Balancing exploration and exploitation (EE) is a fundamental problem in contex-tual bandit. One powerful principle for EE trade-off isOptimism in Face of Uncer-tainty(OFU), in which the agent takes the action according to an upper confidencebound (UCB) of reward. OFU has achieved (near-)optimal regret bound for lin-ear/kernel contextual bandits. However, it is in general unknown how to deriveefficient and effective EE trade-off methods for non-linearcomplex tasks, suchas contextual bandit with deep neural network as the reward function. In thispaper, we propose a novel OFU algorithm namedregul"},"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":"2106.15128","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-29T07:28:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"07a276ee43d2fa78333e2d4c7b86b332613935f60a285179dce7ad6d0be8008e","abstract_canon_sha256":"316e69236ad98208ebc2cd5d1d185867556932a38a5196dac68182ab5938e117"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:53:05.542600Z","signature_b64":"mv3CT2AF9EzRnXg5JiFsaRe2yH5tXlIT9tzIvroKsiLgtRORwdEQgf3s6p05hX7TWJdXFbIF7olIXMQH9gdsAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"936b80f6601b07b89094443aa0012d729ae4a3a4742c8431ef655f032ce8730f","last_reissued_at":"2026-07-05T02:53:05.542133Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:53:05.542133Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Regularized OFU: an Efficient UCB Estimator forNon-linear Contextual Bandit","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Huishuai Zhang, Jun Zhu, Shihong Song, Tie-Yan Liu, Wei Chen, Yichi Zhou","submitted_at":"2021-06-29T07:28:15Z","abstract_excerpt":"Balancing exploration and exploitation (EE) is a fundamental problem in contex-tual bandit. One powerful principle for EE trade-off isOptimism in Face of Uncer-tainty(OFU), in which the agent takes the action according to an upper confidencebound (UCB) of reward. OFU has achieved (near-)optimal regret bound for lin-ear/kernel contextual bandits. However, it is in general unknown how to deriveefficient and effective EE trade-off methods for non-linearcomplex tasks, suchas contextual bandit with deep neural network as the reward function. In thispaper, we propose a novel OFU algorithm namedregul"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.15128","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2106.15128/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":"2106.15128","created_at":"2026-07-05T02:53:05.542195+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.15128v1","created_at":"2026-07-05T02:53:05.542195+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.15128","created_at":"2026-07-05T02:53:05.542195+00:00"},{"alias_kind":"pith_short_12","alias_value":"SNVYB5TADMD3","created_at":"2026-07-05T02:53:05.542195+00:00"},{"alias_kind":"pith_short_16","alias_value":"SNVYB5TADMD3REEU","created_at":"2026-07-05T02:53:05.542195+00:00"},{"alias_kind":"pith_short_8","alias_value":"SNVYB5TA","created_at":"2026-07-05T02:53:05.542195+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/SNVYB5TADMD3REEUIQ5KAAJNOK","json":"https://pith.science/pith/SNVYB5TADMD3REEUIQ5KAAJNOK.json","graph_json":"https://pith.science/api/pith-number/SNVYB5TADMD3REEUIQ5KAAJNOK/graph.json","events_json":"https://pith.science/api/pith-number/SNVYB5TADMD3REEUIQ5KAAJNOK/events.json","paper":"https://pith.science/paper/SNVYB5TA"},"agent_actions":{"view_html":"https://pith.science/pith/SNVYB5TADMD3REEUIQ5KAAJNOK","download_json":"https://pith.science/pith/SNVYB5TADMD3REEUIQ5KAAJNOK.json","view_paper":"https://pith.science/paper/SNVYB5TA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.15128&json=true","fetch_graph":"https://pith.science/api/pith-number/SNVYB5TADMD3REEUIQ5KAAJNOK/graph.json","fetch_events":"https://pith.science/api/pith-number/SNVYB5TADMD3REEUIQ5KAAJNOK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SNVYB5TADMD3REEUIQ5KAAJNOK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SNVYB5TADMD3REEUIQ5KAAJNOK/action/storage_attestation","attest_author":"https://pith.science/pith/SNVYB5TADMD3REEUIQ5KAAJNOK/action/author_attestation","sign_citation":"https://pith.science/pith/SNVYB5TADMD3REEUIQ5KAAJNOK/action/citation_signature","submit_replication":"https://pith.science/pith/SNVYB5TADMD3REEUIQ5KAAJNOK/action/replication_record"}},"created_at":"2026-07-05T02:53:05.542195+00:00","updated_at":"2026-07-05T02:53:05.542195+00:00"}