{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:RV2WBFKQVVJDT6HOPV353IO6VB","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":"299d7464615ccf31667e4fd3e0f393755e05c55b9e8d3448a1db2f40336a9119","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-09T20:49:42Z","title_canon_sha256":"fe188b36abdb2fd44e73fdb4f63404f9e1beea918e3ebbfdccf14d51071366bb"},"schema_version":"1.0","source":{"id":"2310.06147","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.06147","created_at":"2026-07-05T06:59:06Z"},{"alias_kind":"arxiv_version","alias_value":"2310.06147v1","created_at":"2026-07-05T06:59:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.06147","created_at":"2026-07-05T06:59:06Z"},{"alias_kind":"pith_short_12","alias_value":"RV2WBFKQVVJD","created_at":"2026-07-05T06:59:06Z"},{"alias_kind":"pith_short_16","alias_value":"RV2WBFKQVVJDT6HO","created_at":"2026-07-05T06:59:06Z"},{"alias_kind":"pith_short_8","alias_value":"RV2WBFKQ","created_at":"2026-07-05T06:59:06Z"}],"graph_snapshots":[{"event_id":"sha256:b947f71caef364ca307ec4099516408e0ac9e0217ae2ab5d9249f0a9cbbd19e6","target":"graph","created_at":"2026-07-05T06:59:06Z","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/2310.06147/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in Large Language Models (LLMs) have garnered wide attention and led to successful products such as ChatGPT and GPT-4. Their proficiency in adhering to instructions and delivering harmless, helpful, and honest (3H) responses can largely be attributed to the technique of Reinforcement Learning from Human Feedback (RLHF). In this paper, we aim to link the research in conventional RL to RL techniques used in LLM research. Demystify this technique by discussing why, when, and how RL excels. Furthermore, we explore potential future avenues that could either benefit from or contr","authors_text":"Hao Sun","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-09T20:49:42Z","title":"Reinforcement Learning in the Era of LLMs: What is Essential? What is needed? An RL Perspective on RLHF, Prompting, and Beyond"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.06147","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":"sha256:1d702ee0f0e33e757c3676c0e86693f9d93cd81e46af451046b638fe85226be0","target":"record","created_at":"2026-07-05T06:59:06Z","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":"299d7464615ccf31667e4fd3e0f393755e05c55b9e8d3448a1db2f40336a9119","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-09T20:49:42Z","title_canon_sha256":"fe188b36abdb2fd44e73fdb4f63404f9e1beea918e3ebbfdccf14d51071366bb"},"schema_version":"1.0","source":{"id":"2310.06147","kind":"arxiv","version":1}},"canonical_sha256":"8d75609550ad5239f8ee7d77dda1dea87a5a8e902768ecb532f811bc56f1068a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8d75609550ad5239f8ee7d77dda1dea87a5a8e902768ecb532f811bc56f1068a","first_computed_at":"2026-07-05T06:59:06.170921Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:59:06.170921Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XJCCx66FgfZkhnDZEelQfC0tdDsnYur0mLu42uIEcrWJMnpPd2K3Sun+EgFIq6PxrgTfgF3TJDmaPzJE2ItsBw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:59:06.171340Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.06147","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1d702ee0f0e33e757c3676c0e86693f9d93cd81e46af451046b638fe85226be0","sha256:b947f71caef364ca307ec4099516408e0ac9e0217ae2ab5d9249f0a9cbbd19e6"],"state_sha256":"60213b08ff7a1a20374ac56f4fb042af2a282b30fc857d7d8e6c5a1de1407aff"}