{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZG3PB2WWP3WQCSD57TMYPLXB27","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":"d3c50aed247563754a0d03e4b3e7804edab177502ce3f82a4f11b5ecfe548785","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-15T22:11:18Z","title_canon_sha256":"2d4818253cdc937f683b3b3d7fd5b1a654b6d79bf601a9761f6c20f826ef2ddc"},"schema_version":"1.0","source":{"id":"2402.10342","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.10342","created_at":"2026-07-05T08:43:53Z"},{"alias_kind":"arxiv_version","alias_value":"2402.10342v2","created_at":"2026-07-05T08:43:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.10342","created_at":"2026-07-05T08:43:53Z"},{"alias_kind":"pith_short_12","alias_value":"ZG3PB2WWP3WQ","created_at":"2026-07-05T08:43:53Z"},{"alias_kind":"pith_short_16","alias_value":"ZG3PB2WWP3WQCSD5","created_at":"2026-07-05T08:43:53Z"},{"alias_kind":"pith_short_8","alias_value":"ZG3PB2WW","created_at":"2026-07-05T08:43:53Z"}],"graph_snapshots":[{"event_id":"sha256:1e8aebcc0bfd3a7c6468145884cc65b9750b20bb5392a200d92e69fdc327a280","target":"graph","created_at":"2026-07-05T08:43:53Z","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/2402.10342/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning from Human Feedback (RLHF) has achieved impressive empirical successes while relying on a small amount of human feedback. However, there is limited theoretical justification for this phenomenon. Additionally, most recent studies focus on value-based algorithms despite the recent empirical successes of policy-based algorithms. In this work, we consider an RLHF algorithm based on policy optimization (PO-RLHF). The algorithm is based on the popular Policy Cover-Policy Gradient (PC-PG) algorithm, which assumes knowledge of the reward function. In PO-RLHF, knowledge of the re","authors_text":"Anna Winnicki, Gal Dalal, R. Srikant, Shie Mannor, Yihan Du","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-15T22:11:18Z","title":"Exploration-Driven Policy Optimization in RLHF: Theoretical Insights on Efficient Data Utilization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.10342","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":"sha256:657dce4a67e04329f252fc406c8c784668c999e4ec4a74aca8747bb2bed54b03","target":"record","created_at":"2026-07-05T08:43:53Z","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":"d3c50aed247563754a0d03e4b3e7804edab177502ce3f82a4f11b5ecfe548785","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-15T22:11:18Z","title_canon_sha256":"2d4818253cdc937f683b3b3d7fd5b1a654b6d79bf601a9761f6c20f826ef2ddc"},"schema_version":"1.0","source":{"id":"2402.10342","kind":"arxiv","version":2}},"canonical_sha256":"c9b6f0ead67eed01487dfcd987aee1d7fff42b4373ce1ddc5d4808604977ff3b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c9b6f0ead67eed01487dfcd987aee1d7fff42b4373ce1ddc5d4808604977ff3b","first_computed_at":"2026-07-05T08:43:53.233685Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:43:53.233685Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VHvC/nyTQtA3vKo+qTIKkwc3ADCAkdqiBsylHc3Q/8fVNvwu80y2srKNjUw3O3TCPefttc0Cthzf59zCbE1WBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:43:53.234148Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.10342","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:657dce4a67e04329f252fc406c8c784668c999e4ec4a74aca8747bb2bed54b03","sha256:1e8aebcc0bfd3a7c6468145884cc65b9750b20bb5392a200d92e69fdc327a280"],"state_sha256":"d08158a2b77eecd4a87f6ae70bea2c16fc235135225f2d9efc9da9b9a331ff46"}