{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:O4UR3IOXQQFJLB6M2DYGAP6QHW","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":"5effdfe3da4c7b9e483b953cb386385e7def5ad87ab67e3a84571e29ea7ace83","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-01T17:59:20Z","title_canon_sha256":"ae1180af663dafd07b80ea3c86f409cb2bfdd21191226a763ba7b51e9ed885c0"},"schema_version":"1.0","source":{"id":"2405.00675","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.00675","created_at":"2026-07-05T09:16:14Z"},{"alias_kind":"arxiv_version","alias_value":"2405.00675v5","created_at":"2026-07-05T09:16:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.00675","created_at":"2026-07-05T09:16:14Z"},{"alias_kind":"pith_short_12","alias_value":"O4UR3IOXQQFJ","created_at":"2026-07-05T09:16:14Z"},{"alias_kind":"pith_short_16","alias_value":"O4UR3IOXQQFJLB6M","created_at":"2026-07-05T09:16:14Z"},{"alias_kind":"pith_short_8","alias_value":"O4UR3IOX","created_at":"2026-07-05T09:16:14Z"}],"graph_snapshots":[{"event_id":"sha256:017b94d795a1e845e6a8aedcdace1660c74d65d2e0afc8f798558936604f398d","target":"graph","created_at":"2026-07-05T09:16:14Z","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/2405.00675/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Standard reinforcement learning from human feedback (RLHF) approaches relying on parametric models like the Bradley-Terry model fall short in capturing the intransitivity and irrationality in human preferences. Recent advancements suggest that directly working with preference probabilities can yield a more accurate reflection of human preferences, enabling more flexible and accurate language model alignment. In this paper, we propose a self-play-based method for language model alignment, which treats the problem as a constant-sum two-player game aimed at identifying the Nash equilibrium policy","authors_text":"Huizhuo Yuan, Kaixuan Ji, Quanquan Gu, Yiming Yang, Yue Wu, Zhiqing Sun","cross_cats":["cs.AI","cs.CL","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-01T17:59:20Z","title":"Self-Play Preference Optimization for Language Model Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.00675","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:ac42b2c00665ca9b665bdaf8ebf3d090a3dd7aedf1f61f1ac9298dc70662bd78","target":"record","created_at":"2026-07-05T09:16:14Z","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":"5effdfe3da4c7b9e483b953cb386385e7def5ad87ab67e3a84571e29ea7ace83","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-01T17:59:20Z","title_canon_sha256":"ae1180af663dafd07b80ea3c86f409cb2bfdd21191226a763ba7b51e9ed885c0"},"schema_version":"1.0","source":{"id":"2405.00675","kind":"arxiv","version":5}},"canonical_sha256":"77291da1d7840a9587ccd0f0603fd03d96df368267ddbd9352a7506d438adf2b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"77291da1d7840a9587ccd0f0603fd03d96df368267ddbd9352a7506d438adf2b","first_computed_at":"2026-07-05T09:16:14.917071Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:16:14.917071Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6C7RQrUx4DZZNNMUqdwhOex40LMk5GC/rtjM+iXRCaf5EDJzQdL15l61wuubtexvnmRIx6XgQPXqysSUZQR+Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:16:14.917567Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.00675","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ac42b2c00665ca9b665bdaf8ebf3d090a3dd7aedf1f61f1ac9298dc70662bd78","sha256:017b94d795a1e845e6a8aedcdace1660c74d65d2e0afc8f798558936604f398d"],"state_sha256":"4e9beb2dae4d356ba408e1734e10d0997b5cb844a3b5c43e1f98126a2a5f11df"}