{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VPU6VNK2JRMMP4VEDR4IKWHRUJ","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":"a33b7983543c55db71089152283878e961906c069dd354a3e96eadd81575a64c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-11T22:44:54Z","title_canon_sha256":"c12b9008e8b86bdcc927c6b588b0dbe473d73c1e846e37936fcf6b4477b2a8b3"},"schema_version":"1.0","source":{"id":"2503.08942","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.08942","created_at":"2026-07-05T11:34:05Z"},{"alias_kind":"arxiv_version","alias_value":"2503.08942v3","created_at":"2026-07-05T11:34:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.08942","created_at":"2026-07-05T11:34:05Z"},{"alias_kind":"pith_short_12","alias_value":"VPU6VNK2JRMM","created_at":"2026-07-05T11:34:05Z"},{"alias_kind":"pith_short_16","alias_value":"VPU6VNK2JRMMP4VE","created_at":"2026-07-05T11:34:05Z"},{"alias_kind":"pith_short_8","alias_value":"VPU6VNK2","created_at":"2026-07-05T11:34:05Z"}],"graph_snapshots":[{"event_id":"sha256:4b23f3143f4587b43b42587d206e0a9c7773dde9af91967a10e9dbb9987da286","target":"graph","created_at":"2026-07-05T11:34:05Z","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/2503.08942/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning from human feedback (RLHF) has become essential for improving language model capabilities, but traditional approaches rely on the assumption that human preferences follow a transitive Bradley-Terry model. This assumption fails to capture the non-transitive nature of populational human preferences. Nash learning from human feedback (NLHF), targeting non-transitive preferences, is a problem of computing the Nash equilibrium (NE) of the two-player constant-sum game defined by the human preference. We introduce Extragradient preference optimization (EGPO), a novel algorithm ","authors_text":"Maryam Fazel, Runlong Zhou, Simon S. Du","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-11T22:44:54Z","title":"Extragradient Preference Optimization (EGPO): Beyond Last-Iterate Convergence for Nash Learning from Human Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.08942","kind":"arxiv","version":3},"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:b6433adff7334683e5cd6f5206d7494c7f5b207d023f07b20126f49ac3c76944","target":"record","created_at":"2026-07-05T11:34:05Z","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":"a33b7983543c55db71089152283878e961906c069dd354a3e96eadd81575a64c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-11T22:44:54Z","title_canon_sha256":"c12b9008e8b86bdcc927c6b588b0dbe473d73c1e846e37936fcf6b4477b2a8b3"},"schema_version":"1.0","source":{"id":"2503.08942","kind":"arxiv","version":3}},"canonical_sha256":"abe9eab55a4c58c7f2a41c788558f1a24ae977932e506ef1525235a92e44bb6e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"abe9eab55a4c58c7f2a41c788558f1a24ae977932e506ef1525235a92e44bb6e","first_computed_at":"2026-07-05T11:34:05.673785Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:34:05.673785Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UCIfWrBSs621CYlhArworOW4SHs0zlOTQtJWAAva5IU/lqtGjVMGI3TcnnmAfJl8HetUUszAyzWjCNgaWfK3CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:34:05.674265Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.08942","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b6433adff7334683e5cd6f5206d7494c7f5b207d023f07b20126f49ac3c76944","sha256:4b23f3143f4587b43b42587d206e0a9c7773dde9af91967a10e9dbb9987da286"],"state_sha256":"957b8c65c8498e5abfebc2a7530673db9eb5fbc8a66c59affcadfa508f46a5a6"}