{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:OGZPKQGTCSENJWJPZC43VTHTWU","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":"abfb85a78ed8dcffed88e09ed2b05ab13e798d77fba77565924cd420f1d98b4d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-17T02:14:15Z","title_canon_sha256":"584b9ac1112af26c04fb614f7cf26450b2070c5d7f0f2b78ffc4ce96061d3204"},"schema_version":"1.0","source":{"id":"2312.10584","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.10584","created_at":"2026-07-05T07:48:51Z"},{"alias_kind":"arxiv_version","alias_value":"2312.10584v2","created_at":"2026-07-05T07:48:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.10584","created_at":"2026-07-05T07:48:51Z"},{"alias_kind":"pith_short_12","alias_value":"OGZPKQGTCSEN","created_at":"2026-07-05T07:48:51Z"},{"alias_kind":"pith_short_16","alias_value":"OGZPKQGTCSENJWJP","created_at":"2026-07-05T07:48:51Z"},{"alias_kind":"pith_short_8","alias_value":"OGZPKQGT","created_at":"2026-07-05T07:48:51Z"}],"graph_snapshots":[{"event_id":"sha256:3b9261e1e592eeb95cbb8ca7995af9db358c47907e9f7b2c4b26428b9f3a50da","target":"graph","created_at":"2026-07-05T07:48:51Z","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/2312.10584/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Aligning intelligent agents with human preferences and values is important. This paper examines two popular alignment methods: Direct Preference Optimization (DPO) and Reward-Model-Based Policy Optimization (RMB-PO). A variant of RMB-PO, referred to as RMB-PO+ is also considered. These methods, either explicitly or implicitly, learn a reward model from preference data and differ in the data used for policy optimization to unlock the generalization ability of the reward model. In particular, compared with DPO, RMB-PO additionally uses policy-generated data, and RMB-PO+ further leverages new, pr","authors_text":"Tian Xu, Yang Yu, Ziniu Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-17T02:14:15Z","title":"Policy Optimization in RLHF: The Impact of Out-of-preference Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.10584","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:db14d638e04e0b0d82f3cb74d97b8b1a047ba8a4e0e8822cb6a5735dee02fd30","target":"record","created_at":"2026-07-05T07:48:51Z","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":"abfb85a78ed8dcffed88e09ed2b05ab13e798d77fba77565924cd420f1d98b4d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-17T02:14:15Z","title_canon_sha256":"584b9ac1112af26c04fb614f7cf26450b2070c5d7f0f2b78ffc4ce96061d3204"},"schema_version":"1.0","source":{"id":"2312.10584","kind":"arxiv","version":2}},"canonical_sha256":"71b2f540d31488d4d92fc8b9baccf3b50b1e0c4e3b7fa55b410c8ec2c178c176","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"71b2f540d31488d4d92fc8b9baccf3b50b1e0c4e3b7fa55b410c8ec2c178c176","first_computed_at":"2026-07-05T07:48:51.156747Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:48:51.156747Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"goq4tUwWKzF46D5OllH5JapUlkJEj3jIrRKJ7d2p41Yix5Do1WvkJAXt2b2m5Vp5NspcvBczxB3ZdLVM+C8uAA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:48:51.157120Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.10584","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:db14d638e04e0b0d82f3cb74d97b8b1a047ba8a4e0e8822cb6a5735dee02fd30","sha256:3b9261e1e592eeb95cbb8ca7995af9db358c47907e9f7b2c4b26428b9f3a50da"],"state_sha256":"c2e685956a8f815990aee2bf498f0e11761ed9ca54b72dc2e485b228a9dd2a02"}