{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:SNVYB5TADMD3REEUIQ5KAAJNOK","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"316e69236ad98208ebc2cd5d1d185867556932a38a5196dac68182ab5938e117","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-29T07:28:15Z","title_canon_sha256":"07a276ee43d2fa78333e2d4c7b86b332613935f60a285179dce7ad6d0be8008e"},"schema_version":"1.0","source":{"id":"2106.15128","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.15128","created_at":"2026-07-05T02:53:05Z"},{"alias_kind":"arxiv_version","alias_value":"2106.15128v1","created_at":"2026-07-05T02:53:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.15128","created_at":"2026-07-05T02:53:05Z"},{"alias_kind":"pith_short_12","alias_value":"SNVYB5TADMD3","created_at":"2026-07-05T02:53:05Z"},{"alias_kind":"pith_short_16","alias_value":"SNVYB5TADMD3REEU","created_at":"2026-07-05T02:53:05Z"},{"alias_kind":"pith_short_8","alias_value":"SNVYB5TA","created_at":"2026-07-05T02:53:05Z"}],"graph_snapshots":[{"event_id":"sha256:3c38c9fdb3fe241b587d4c7fdd2da3887c0d26327c19af65cc196686c2e3f874","target":"graph","created_at":"2026-07-05T02:53:05Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2106.15128/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Huishuai Zhang, Jun Zhu, Shihong Song, Tie-Yan Liu, Wei Chen, Yichi Zhou","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-29T07:28:15Z","title":"Regularized OFU: an Efficient UCB Estimator forNon-linear Contextual Bandit"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.15128","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:eb68e507b7ea105919e150edde42a98202d79182791045eafece9180ea6dafbd","target":"record","created_at":"2026-07-05T02:53:05Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"316e69236ad98208ebc2cd5d1d185867556932a38a5196dac68182ab5938e117","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-29T07:28:15Z","title_canon_sha256":"07a276ee43d2fa78333e2d4c7b86b332613935f60a285179dce7ad6d0be8008e"},"schema_version":"1.0","source":{"id":"2106.15128","kind":"arxiv","version":1}},"canonical_sha256":"936b80f6601b07b89094443aa0012d729ae4a3a4742c8431ef655f032ce8730f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"936b80f6601b07b89094443aa0012d729ae4a3a4742c8431ef655f032ce8730f","first_computed_at":"2026-07-05T02:53:05.542133Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:53:05.542133Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mv3CT2AF9EzRnXg5JiFsaRe2yH5tXlIT9tzIvroKsiLgtRORwdEQgf3s6p05hX7TWJdXFbIF7olIXMQH9gdsAg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:53:05.542600Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.15128","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eb68e507b7ea105919e150edde42a98202d79182791045eafece9180ea6dafbd","sha256:3c38c9fdb3fe241b587d4c7fdd2da3887c0d26327c19af65cc196686c2e3f874"],"state_sha256":"b57d87e2929421e9c51156a96cc7b2852f7fcf7ae35ac7e8fa43ef431b461747"}