{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:T4G7BAVUINADSSMBR2HAEUUO3N","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":"e3c299be26f75495348964205313a87ccd81c94b5f4f8d50e90db273f88fd3e6","cross_cats_sorted":["cs.AI","cs.CL","cs.GT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-30T08:00:34Z","title_canon_sha256":"72c9265a47dfa270d9dc1eedc98b412b7bc83cf20bc02c188d72c2b8ce0a5c3c"},"schema_version":"1.0","source":{"id":"2407.00617","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.00617","created_at":"2026-07-05T10:22:47Z"},{"alias_kind":"arxiv_version","alias_value":"2407.00617v4","created_at":"2026-07-05T10:22:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.00617","created_at":"2026-07-05T10:22:47Z"},{"alias_kind":"pith_short_12","alias_value":"T4G7BAVUINAD","created_at":"2026-07-05T10:22:47Z"},{"alias_kind":"pith_short_16","alias_value":"T4G7BAVUINADSSMB","created_at":"2026-07-05T10:22:47Z"},{"alias_kind":"pith_short_8","alias_value":"T4G7BAVU","created_at":"2026-07-05T10:22:47Z"}],"graph_snapshots":[{"event_id":"sha256:eb76f290a848d8ade7209aeff27d4c746b9ae3712387905c2049ee5168443785","target":"graph","created_at":"2026-07-05T10:22:47Z","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/2407.00617/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning with Human Feedback (RLHF) has achieved great success in aligning large language models (LLMs) with human preferences. Prevalent RLHF approaches are reward-based, following the Bradley-Terry (BT) model assumption, which may not fully capture the complexity of human preferences. In this paper, we explore RLHF under a general preference framework and approach it from a game-theoretic perspective. Specifically, we formulate the problem as a two-player game and propose a novel online algorithm, iterative Nash policy optimization (INPO). The key idea is to let the policy play","authors_text":"Baolin Peng, Dian Yu, Dong Yu, Haitao Mi, Linfeng Song, Mingyue Huo, Nan Jiang, Ye Tian, Yuheng Zhang","cross_cats":["cs.AI","cs.CL","cs.GT"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-30T08:00:34Z","title":"Iterative Nash Policy Optimization: Aligning LLMs with General Preferences via No-Regret Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.00617","kind":"arxiv","version":4},"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":"sha256:4ec2529893a0740b6e18cb9914a3a4132d9b7294bc12ba5f7efc9e45f1496c9a","target":"record","created_at":"2026-07-05T10:22:47Z","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":"e3c299be26f75495348964205313a87ccd81c94b5f4f8d50e90db273f88fd3e6","cross_cats_sorted":["cs.AI","cs.CL","cs.GT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-30T08:00:34Z","title_canon_sha256":"72c9265a47dfa270d9dc1eedc98b412b7bc83cf20bc02c188d72c2b8ce0a5c3c"},"schema_version":"1.0","source":{"id":"2407.00617","kind":"arxiv","version":4}},"canonical_sha256":"9f0df082b443403949818e8e02528edb54eecf8242f721b98694ebba48149768","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9f0df082b443403949818e8e02528edb54eecf8242f721b98694ebba48149768","first_computed_at":"2026-07-05T10:22:47.758553Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:22:47.758553Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8GeVcuSurQZXf5ysZUHEtvhSfUjgZVu6lnRS+YS7rUmNnYZQcrofx9mw9XVZt24fi+OF7U06a8hcOJKydTq6DA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:22:47.761391Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.00617","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4ec2529893a0740b6e18cb9914a3a4132d9b7294bc12ba5f7efc9e45f1496c9a","sha256:eb76f290a848d8ade7209aeff27d4c746b9ae3712387905c2049ee5168443785"],"state_sha256":"5811184f55d5328030fc87ad001303c4cc93e96bc91c7658541cf53c72e19ddf"}