{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:BRJYHP3KF755T5NWTS76QWTQIG","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":"957eb7699dc93da4ea5add8af7853cdeed038013dd8e59c8ccd783ee39062516","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-27T06:34:54Z","title_canon_sha256":"9af1010e0c1bc8d8da8cf715fe649089750060ad540e6ad1ab2ad570a0b866a0"},"schema_version":"1.0","source":{"id":"2312.16430","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.16430","created_at":"2026-07-05T07:59:59Z"},{"alias_kind":"arxiv_version","alias_value":"2312.16430v5","created_at":"2026-07-05T07:59:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.16430","created_at":"2026-07-05T07:59:59Z"},{"alias_kind":"pith_short_12","alias_value":"BRJYHP3KF755","created_at":"2026-07-05T07:59:59Z"},{"alias_kind":"pith_short_16","alias_value":"BRJYHP3KF755T5NW","created_at":"2026-07-05T07:59:59Z"},{"alias_kind":"pith_short_8","alias_value":"BRJYHP3K","created_at":"2026-07-05T07:59:59Z"}],"graph_snapshots":[{"event_id":"sha256:e47728d11a806d83abcfe27c56f440cd5dea3bcd56c3125514eecece7d22188a","target":"graph","created_at":"2026-07-05T07:59:59Z","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/2312.16430/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Preference learning is a key technology for aligning language models with human values. Reinforcement Learning from Human Feedback (RLHF) is a model-based algorithm to optimize preference learning, which first fits a reward model for preference scores and then optimizes the generating policy with an on-policy PPO algorithm to maximize the reward. The processing of RLHF is complex, time-consuming, and unstable. The Direct Preference Optimization (DPO) algorithm uses an off-policy algorithm to directly optimize the generating policy and eliminates the need for a reward model. DPO is more data-ef","authors_text":"Chao Wei, Xing Huang, Zaifan Jiang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-27T06:34:54Z","title":"Preference as Reward, Maximum Preference Optimization with Importance Sampling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.16430","kind":"arxiv","version":5},"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":"sha256:6d6cd5a21471dbda2434c769aef4d80df2d18682c7205bbed0f8b88093380106","target":"record","created_at":"2026-07-05T07:59:59Z","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":"957eb7699dc93da4ea5add8af7853cdeed038013dd8e59c8ccd783ee39062516","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-27T06:34:54Z","title_canon_sha256":"9af1010e0c1bc8d8da8cf715fe649089750060ad540e6ad1ab2ad570a0b866a0"},"schema_version":"1.0","source":{"id":"2312.16430","kind":"arxiv","version":5}},"canonical_sha256":"0c5383bf6a2ffbd9f5b69cbfe85a7041b3f828c3aa801e8d8e978023b5369566","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0c5383bf6a2ffbd9f5b69cbfe85a7041b3f828c3aa801e8d8e978023b5369566","first_computed_at":"2026-07-05T07:59:59.488602Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:59:59.488602Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xZKf4CWjHYXnoROLy/9Nvr2CwMT84xHnOAnZS/jZcxuH2oWXJfgU2OK3UmQUCPID7LFelarIadKyOlJviJyICQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:59:59.488999Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.16430","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6d6cd5a21471dbda2434c769aef4d80df2d18682c7205bbed0f8b88093380106","sha256:e47728d11a806d83abcfe27c56f440cd5dea3bcd56c3125514eecece7d22188a"],"state_sha256":"7ee2614d7a3a64ca5c5b6327593726f4b90f11e8de6303af7b92798ff5a75b3b"}