{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:3B3QFTDF427RD6CWRQLMAGXBOF","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":"99522b91743a4d84326fc86980148d6b5cdfee0dad1857aab5acf4a345321c8e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-16T15:25:14Z","title_canon_sha256":"569d14f60508783cfd4a3bf94408309cc180689670d80c03deb421ce2692b633"},"schema_version":"1.0","source":{"id":"2310.10505","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.10505","created_at":"2026-07-05T08:19:37Z"},{"alias_kind":"arxiv_version","alias_value":"2310.10505v4","created_at":"2026-07-05T08:19:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.10505","created_at":"2026-07-05T08:19:37Z"},{"alias_kind":"pith_short_12","alias_value":"3B3QFTDF427R","created_at":"2026-07-05T08:19:37Z"},{"alias_kind":"pith_short_16","alias_value":"3B3QFTDF427RD6CW","created_at":"2026-07-05T08:19:37Z"},{"alias_kind":"pith_short_8","alias_value":"3B3QFTDF","created_at":"2026-07-05T08:19:37Z"}],"graph_snapshots":[{"event_id":"sha256:28509ace7693238a239e6bfb03391c74a661d0367919175be9b35aa013b60887","target":"graph","created_at":"2026-07-05T08:19:37Z","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/2310.10505/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning from Human Feedback (RLHF) is key to aligning Large Language Models (LLMs), typically paired with the Proximal Policy Optimization (PPO) algorithm. While PPO is a powerful method designed for general reinforcement learning tasks, it is overly sophisticated for LLMs, leading to laborious hyper-parameter tuning and significant computation burdens. To make RLHF efficient, we present ReMax, which leverages 3 properties of RLHF: fast simulation, deterministic transitions, and trajectory-level rewards. These properties are not exploited in PPO, making it less suitable for RLHF","authors_text":"Ruoyu Sun, Tian Xu, Yang Yu, Yushun Zhang, Zhihang Lin, Zhi-Quan Luo, Ziniu Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-16T15:25:14Z","title":"ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.10505","kind":"arxiv","version":4},"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":"sha256:6887423d245b39aa661e21bcda40398197f84e3b2ee4096c4615f21c7610deed","target":"record","created_at":"2026-07-05T08:19:37Z","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":"99522b91743a4d84326fc86980148d6b5cdfee0dad1857aab5acf4a345321c8e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-16T15:25:14Z","title_canon_sha256":"569d14f60508783cfd4a3bf94408309cc180689670d80c03deb421ce2692b633"},"schema_version":"1.0","source":{"id":"2310.10505","kind":"arxiv","version":4}},"canonical_sha256":"d87702cc65e6bf11f8568c16c01ae17144ee76c93ac559c12e0717da1fb88955","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d87702cc65e6bf11f8568c16c01ae17144ee76c93ac559c12e0717da1fb88955","first_computed_at":"2026-07-05T08:19:37.655148Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:19:37.655148Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"F1u0GXzD/1dlnKw/uIMGL62c8IL2mhwu87i2Gby6GaAPkoLH16X7O01oPKpxRcFqW+7VjTn6gnJM0y3d2Zj/AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:19:37.655584Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.10505","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6887423d245b39aa661e21bcda40398197f84e3b2ee4096c4615f21c7610deed","sha256:28509ace7693238a239e6bfb03391c74a661d0367919175be9b35aa013b60887"],"state_sha256":"9475f2b9625bc042297bbc52df49b0e1a6aea8997c48300699f41b832f1d5c20"}