{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7UE2LBGVMS7CL6UYVGB5DA4HXU","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":"9358c1e1b97e5225f3e9fccd5abd4d0bdd2c91ac577c66c575a2525f0a15f64d","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-28T04:47:39Z","title_canon_sha256":"27b317a04d9c51ed3b6c630d682253a853f9f1a06634e07983dfb83bbf85685d"},"schema_version":"1.0","source":{"id":"2410.20727","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.20727","created_at":"2026-07-05T10:16:59Z"},{"alias_kind":"arxiv_version","alias_value":"2410.20727v2","created_at":"2026-07-05T10:16:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.20727","created_at":"2026-07-05T10:16:59Z"},{"alias_kind":"pith_short_12","alias_value":"7UE2LBGVMS7C","created_at":"2026-07-05T10:16:59Z"},{"alias_kind":"pith_short_16","alias_value":"7UE2LBGVMS7CL6UY","created_at":"2026-07-05T10:16:59Z"},{"alias_kind":"pith_short_8","alias_value":"7UE2LBGV","created_at":"2026-07-05T10:16:59Z"}],"graph_snapshots":[{"event_id":"sha256:299a9c84a6547caf0e9f9f02582f9094d419c9b63b285b13eebaf3e13ae3ae70","target":"graph","created_at":"2026-07-05T10:16:59Z","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/2410.20727/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in aligning large language models with human preferences have corroborated the growing importance of best-of-N distillation (BOND). However, the iterative BOND algorithm is prohibitively expensive in practice due to the sample and computation inefficiency. This paper addresses the problem by revealing a unified game-theoretic connection between iterative BOND and self-play alignment, which unifies seemingly disparate algorithmic paradigms. Based on the connection, we establish a novel framework, WIN rate Dominance (WIND), with a series of efficient algorithms for regularized wi","authors_text":"Bo Dai, Dale Schuurmans, Hanjun Dai, Jincheng Mei, Shicong Cen, Tong Yang, Yuejie Chi, Zixin Wen","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-28T04:47:39Z","title":"Faster WIND: Accelerating Iterative Best-of-$N$ Distillation for LLM Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.20727","kind":"arxiv","version":2},"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:cfda6797991d6340b9d824f5960600686f2435c470017461bd823af346b93566","target":"record","created_at":"2026-07-05T10:16:59Z","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":"9358c1e1b97e5225f3e9fccd5abd4d0bdd2c91ac577c66c575a2525f0a15f64d","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-28T04:47:39Z","title_canon_sha256":"27b317a04d9c51ed3b6c630d682253a853f9f1a06634e07983dfb83bbf85685d"},"schema_version":"1.0","source":{"id":"2410.20727","kind":"arxiv","version":2}},"canonical_sha256":"fd09a584d564be25fa98a983d18387bd25f5f47f2c0595330dbbd6a2132ca21b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fd09a584d564be25fa98a983d18387bd25f5f47f2c0595330dbbd6a2132ca21b","first_computed_at":"2026-07-05T10:16:59.232236Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:16:59.232236Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0H4xELCO506t1wxRmquYHBpCSnHs2rUMdbAXHI7tcybdiXSBL8dZ55ze2l/6smca+hHcJIVdFHIQ9+qKCAcOAg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:16:59.232622Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.20727","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cfda6797991d6340b9d824f5960600686f2435c470017461bd823af346b93566","sha256:299a9c84a6547caf0e9f9f02582f9094d419c9b63b285b13eebaf3e13ae3ae70"],"state_sha256":"bceead37a093dc2d92fb85b5d2af54e4ac65d38f7d447221117938d26c598df8"}