{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UAPDLFDL4QCR4EXNCYC3CF4NUL","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":"56b79cdfa0be4add40f3fd7866573db00aa1c8962c7c1d132252550327ad1770","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-07T11:22:46Z","title_canon_sha256":"84d09a0bdbd8484d9c1c6fe800673a9dc9992a2b9684449c41cd6ee8eb5805ed"},"schema_version":"1.0","source":{"id":"2411.04625","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.04625","created_at":"2026-07-05T10:12:23Z"},{"alias_kind":"arxiv_version","alias_value":"2411.04625v2","created_at":"2026-07-05T10:12:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.04625","created_at":"2026-07-05T10:12:23Z"},{"alias_kind":"pith_short_12","alias_value":"UAPDLFDL4QCR","created_at":"2026-07-05T10:12:23Z"},{"alias_kind":"pith_short_16","alias_value":"UAPDLFDL4QCR4EXN","created_at":"2026-07-05T10:12:23Z"},{"alias_kind":"pith_short_8","alias_value":"UAPDLFDL","created_at":"2026-07-05T10:12:23Z"}],"graph_snapshots":[{"event_id":"sha256:dc11afbc0616fa26df4bf95c3071fe6758cb3dc0f1c8be9da0327310944d006e","target":"graph","created_at":"2026-07-05T10:12:23Z","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/2411.04625/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reverse-Kullback-Leibler (KL) regularization has emerged to be a predominant technique used to enhance policy optimization in reinforcement learning (RL) and reinforcement learning from human feedback (RLHF), which forces the learned policy to stay close to a reference policy. While the effectiveness and necessity of KL-regularization have been empirically demonstrated in various practical scenarios, current theoretical analysis of KL-regularized RLHF still obtains the same $\\mathcal{O}(1 / \\epsilon^2)$ sample complexity as problems without KL-regularization. To understand the fundamental dist","authors_text":"Chenlu Ye, Heyang Zhao, Quanquan Gu, Tong Zhang","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-07T11:22:46Z","title":"Sharp Analysis for KL-Regularized Contextual Bandits and RLHF"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.04625","kind":"arxiv","version":2},"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":"sha256:705792924cec37b07c20ca238cd3b17c200e12911299818b8e12468dff7ceecb","target":"record","created_at":"2026-07-05T10:12:23Z","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":"56b79cdfa0be4add40f3fd7866573db00aa1c8962c7c1d132252550327ad1770","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-07T11:22:46Z","title_canon_sha256":"84d09a0bdbd8484d9c1c6fe800673a9dc9992a2b9684449c41cd6ee8eb5805ed"},"schema_version":"1.0","source":{"id":"2411.04625","kind":"arxiv","version":2}},"canonical_sha256":"a01e35946be4051e12ed1605b1178da2ee3cee02db8073a1a12212493406f621","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a01e35946be4051e12ed1605b1178da2ee3cee02db8073a1a12212493406f621","first_computed_at":"2026-07-05T10:12:23.227785Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:12:23.227785Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XCwkm158Oll7Avuudmk77DY+C+F9o/pH6XhO+Lf6Hj+j8V5i/rcnphDexU0DUX0aLoQoUlZ/Mtv5qF+b88ITAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:12:23.228267Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.04625","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:705792924cec37b07c20ca238cd3b17c200e12911299818b8e12468dff7ceecb","sha256:dc11afbc0616fa26df4bf95c3071fe6758cb3dc0f1c8be9da0327310944d006e"],"state_sha256":"2a78dbe378069fde20d0f6e06e06ffaddaf78067225ac9fe5a32c60057fb00ed"}