{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VU5ZPJZCK2HVU2GZPXERPRDINI","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":"64f7147939f100b2bb0cfea93e10228efd17666f43d80f45179a1e187bff38f2","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2025-05-27T02:07:35Z","title_canon_sha256":"e45e30ded05c802acbaf2b6a4611f37a565bbc4d5c5af319c33f2d178616a142"},"schema_version":"1.0","source":{"id":"2505.20627","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.20627","created_at":"2026-07-05T11:10:15Z"},{"alias_kind":"arxiv_version","alias_value":"2505.20627v1","created_at":"2026-07-05T11:10:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20627","created_at":"2026-07-05T11:10:15Z"},{"alias_kind":"pith_short_12","alias_value":"VU5ZPJZCK2HV","created_at":"2026-07-05T11:10:15Z"},{"alias_kind":"pith_short_16","alias_value":"VU5ZPJZCK2HVU2GZ","created_at":"2026-07-05T11:10:15Z"},{"alias_kind":"pith_short_8","alias_value":"VU5ZPJZC","created_at":"2026-07-05T11:10:15Z"}],"graph_snapshots":[{"event_id":"sha256:84f3519683f3e0a0592b8cc4b3255a050a8f490181aa6c54f1a98df17197d1b7","target":"graph","created_at":"2026-07-05T11:10:15Z","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/2505.20627/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Nash Learning from Human Feedback is a game-theoretic framework for aligning large language models (LLMs) with human preferences by modeling learning as a two-player zero-sum game. However, using raw preference as the payoff in the game highly limits the potential of the game-theoretic LLM alignment framework. In this paper, we systematically study using what choices of payoff based on the pairwise human preferences can yield desirable alignment properties. We establish necessary and sufficient conditions for Condorcet consistency, diversity through mixed strategies, and Smith consistency. The","authors_text":"Jiancong Xiao, Kaizhao Liu, Qi Long, Weijie J. Su, Zhekun Shi","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2025-05-27T02:07:35Z","title":"Fundamental Limits of Game-Theoretic LLM Alignment: Smith Consistency and Preference Matching"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20627","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":"sha256:243eb2af717330cf7a5f5607a49b6d7dfefe158d589c3aaf90cf84ead1630738","target":"record","created_at":"2026-07-05T11:10:15Z","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":"64f7147939f100b2bb0cfea93e10228efd17666f43d80f45179a1e187bff38f2","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GT","submitted_at":"2025-05-27T02:07:35Z","title_canon_sha256":"e45e30ded05c802acbaf2b6a4611f37a565bbc4d5c5af319c33f2d178616a142"},"schema_version":"1.0","source":{"id":"2505.20627","kind":"arxiv","version":1}},"canonical_sha256":"ad3b97a722568f5a68d97dc917c4686a3753e2f03e4caafae5d78af8dbcc444a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ad3b97a722568f5a68d97dc917c4686a3753e2f03e4caafae5d78af8dbcc444a","first_computed_at":"2026-07-05T11:10:15.605491Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:10:15.605491Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XCfuDFSG+HOboNsFwCre+W3FHK+mZRc922G5jtXRmq/y+2K/s0OPHymVSVNzkF6+5Lj78i67YRRmSGUebeSaDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:10:15.606012Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.20627","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:243eb2af717330cf7a5f5607a49b6d7dfefe158d589c3aaf90cf84ead1630738","sha256:84f3519683f3e0a0592b8cc4b3255a050a8f490181aa6c54f1a98df17197d1b7"],"state_sha256":"6bc4e280b1b9a804d13345157500f59cb907c9c784b44d295c30876de23db59e"}