{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:BSVARF7M2FETILAECBUTQJ73NF","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":"400472037879443693bb2e84029d9204eb1d8a00aef3db379084e7abfbb393f9","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-31T18:11:26Z","title_canon_sha256":"acdf81bff36a8c29d91f4eaa06b92daedb53c2e64103c11b9e28ffb4e92dd06c"},"schema_version":"1.0","source":{"id":"2606.01382","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.01382","created_at":"2026-06-02T02:04:31Z"},{"alias_kind":"arxiv_version","alias_value":"2606.01382v1","created_at":"2026-06-02T02:04:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01382","created_at":"2026-06-02T02:04:31Z"},{"alias_kind":"pith_short_12","alias_value":"BSVARF7M2FET","created_at":"2026-06-02T02:04:31Z"},{"alias_kind":"pith_short_16","alias_value":"BSVARF7M2FETILAE","created_at":"2026-06-02T02:04:31Z"},{"alias_kind":"pith_short_8","alias_value":"BSVARF7M","created_at":"2026-06-02T02:04:31Z"}],"graph_snapshots":[{"event_id":"sha256:a13edb425e1d396a9f3fb5e36973b68b3704ec99e90b66c53ee0a708b9ead592","target":"graph","created_at":"2026-06-02T02:04:31Z","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/2606.01382/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Preference alignment is central to improving large language models, but standard reward-based formulations can be restrictive when human preferences are cyclic, non-transitive, or otherwise not representable by a scalar reward. Nash Learning from Human Feedback (NLHF) addresses this limitation by modeling alignment as a preference game and targeting a Nash equilibrium rather than a reward maximizer. However, the learning-theoretic foundations of scalable NLHF remain limited. Existing regret guarantees rely on oracle-based methods that estimate a general preference model and solve KL-regularize","authors_text":"Christian Kroer, Tianlong Nan, Tianyi Lin, Xiaopeng Li","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-31T18:11:26Z","title":"Efficient Exploration for Iterative Nash Preference Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01382","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":"sha256:6c9d5b854ebb71bed8ac40fca969ee2db8684d98d80f31f8d498d15b0184c5d9","target":"record","created_at":"2026-06-02T02:04:31Z","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":"400472037879443693bb2e84029d9204eb1d8a00aef3db379084e7abfbb393f9","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-31T18:11:26Z","title_canon_sha256":"acdf81bff36a8c29d91f4eaa06b92daedb53c2e64103c11b9e28ffb4e92dd06c"},"schema_version":"1.0","source":{"id":"2606.01382","kind":"arxiv","version":1}},"canonical_sha256":"0caa0897ecd149342c0410693827fb697c1244b2700ae9d152da382637dff371","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0caa0897ecd149342c0410693827fb697c1244b2700ae9d152da382637dff371","first_computed_at":"2026-06-02T02:04:31.866807Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T02:04:31.866807Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UB7jRaTV3qCeJ9+6TU/6OOq/v35nqkAd6fpA/MyWmyqeqMWxXyEh0rpllRLs25NS1z3G2elDrZcZrFyzS8ynCg==","signature_status":"signed_v1","signed_at":"2026-06-02T02:04:31.867170Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.01382","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6c9d5b854ebb71bed8ac40fca969ee2db8684d98d80f31f8d498d15b0184c5d9","sha256:a13edb425e1d396a9f3fb5e36973b68b3704ec99e90b66c53ee0a708b9ead592"],"state_sha256":"442b28ffc1f8df0bb8eb63d7c5347f3db9ab36224a20e961f6c055989a05a3f3"}