{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:BHEEIWWARMYM576EHCA63VHSK6","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":"9f77f3bed07806e97f39a6837375d2af903d0c855ac6fc13d342179de84504b4","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-25T03:18:15Z","title_canon_sha256":"28195d3291c25f21e48733d9edaf4a797d445b9fb05f979b59fe792a95fe8813"},"schema_version":"1.0","source":{"id":"2306.14111","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.14111","created_at":"2026-07-05T07:08:59Z"},{"alias_kind":"arxiv_version","alias_value":"2306.14111v2","created_at":"2026-07-05T07:08:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.14111","created_at":"2026-07-05T07:08:59Z"},{"alias_kind":"pith_short_12","alias_value":"BHEEIWWARMYM","created_at":"2026-07-05T07:08:59Z"},{"alias_kind":"pith_short_16","alias_value":"BHEEIWWARMYM576E","created_at":"2026-07-05T07:08:59Z"},{"alias_kind":"pith_short_8","alias_value":"BHEEIWWA","created_at":"2026-07-05T07:08:59Z"}],"graph_snapshots":[{"event_id":"sha256:dbd6d429a0d1022b8ee757b557c5d775031cfebd15a99c6ea9eecbef5da15ebe","target":"graph","created_at":"2026-07-05T07:08:59Z","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/2306.14111/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning from Human Feedback (RLHF) learns from preference signals, while standard Reinforcement Learning (RL) directly learns from reward signals. Preferences arguably contain less information than rewards, which makes preference-based RL seemingly more difficult. This paper theoretically proves that, for a wide range of preference models, we can solve preference-based RL directly using existing algorithms and techniques for reward-based RL, with small or no extra costs. Specifically, (1) for preferences that are drawn from reward-based probabilistic models, we reduce the proble","authors_text":"Chi Jin, Qinghua Liu, Yuanhao Wang","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-25T03:18:15Z","title":"Is RLHF More Difficult than Standard RL?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.14111","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:a2d10257204001925f0625c4a90a7365133c1ab0bf5d4b018d18ff34c31e9a52","target":"record","created_at":"2026-07-05T07:08:59Z","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":"9f77f3bed07806e97f39a6837375d2af903d0c855ac6fc13d342179de84504b4","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-25T03:18:15Z","title_canon_sha256":"28195d3291c25f21e48733d9edaf4a797d445b9fb05f979b59fe792a95fe8813"},"schema_version":"1.0","source":{"id":"2306.14111","kind":"arxiv","version":2}},"canonical_sha256":"09c8445ac08b30ceffc43881edd4f257b658acca5c3f45d2f9ae4004fb062ea5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"09c8445ac08b30ceffc43881edd4f257b658acca5c3f45d2f9ae4004fb062ea5","first_computed_at":"2026-07-05T07:08:59.356127Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:08:59.356127Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"B0tk8GTpKsWWpGj3CNt9u58o6/t5wsuj6+neqerq3BlK7PEiMG/ib5oEI2+8GqZJqFtAzt/Dfieh5mIG4DriCA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:08:59.356616Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.14111","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a2d10257204001925f0625c4a90a7365133c1ab0bf5d4b018d18ff34c31e9a52","sha256:dbd6d429a0d1022b8ee757b557c5d775031cfebd15a99c6ea9eecbef5da15ebe"],"state_sha256":"644533b62c1c7711a43b44d0db3a2cb87ee1812305effa00d72bea6f632f099e"}