{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:II34YPF5KRA5STMD2DD5LR757Y","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":"de803f6a4a9b47e4131826274c17b72527e8e84f45b040121ea4f4de21a36fa2","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-17T22:40:54Z","title_canon_sha256":"c4f75dc4c741aac01767a7feff0578c6e864f2b4b0266c16c407926d86238187"},"schema_version":"1.0","source":{"id":"2409.17169","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.17169","created_at":"2026-07-05T11:15:39Z"},{"alias_kind":"arxiv_version","alias_value":"2409.17169v4","created_at":"2026-07-05T11:15:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.17169","created_at":"2026-07-05T11:15:39Z"},{"alias_kind":"pith_short_12","alias_value":"II34YPF5KRA5","created_at":"2026-07-05T11:15:39Z"},{"alias_kind":"pith_short_16","alias_value":"II34YPF5KRA5STMD","created_at":"2026-07-05T11:15:39Z"},{"alias_kind":"pith_short_8","alias_value":"II34YPF5","created_at":"2026-07-05T11:15:39Z"}],"graph_snapshots":[{"event_id":"sha256:3ab1176162a4719510ce659aad862432eecb35bc09e5a6655871e5d80f4b48d2","target":"graph","created_at":"2026-07-05T11:15:39Z","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/2409.17169/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Aligning large language models (LLMs) to human preferences is a crucial step in building helpful and safe AI tools, which usually involve training on supervised datasets. Popular algorithms such as Direct Preference Optimization (DPO) rely on pairs of AI-generated responses ranked according to human annotation. The response pair annotation process might bring human bias. Building a correct preference dataset is the costly part of the alignment pipeline. To improve annotation efficiency and quality in the LLMs alignment, we propose REAL: Response Embedding-based Alignment for LLMs, a strategy f","authors_text":"Honggen Zhang, Igor Molybog, June Zhang, Xufeng Zhao","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-17T22:40:54Z","title":"REAL: Response Embedding-based Alignment for LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.17169","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":"sha256:0e86785637c20a7d6f0dab602085d2617311f4e89d31c41b425161fa3f7f64ca","target":"record","created_at":"2026-07-05T11:15:39Z","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":"de803f6a4a9b47e4131826274c17b72527e8e84f45b040121ea4f4de21a36fa2","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-17T22:40:54Z","title_canon_sha256":"c4f75dc4c741aac01767a7feff0578c6e864f2b4b0266c16c407926d86238187"},"schema_version":"1.0","source":{"id":"2409.17169","kind":"arxiv","version":4}},"canonical_sha256":"4237cc3cbd5441d94d83d0c7d5c7fdfe081aa87a47d0d017b6f37630efdcf5a3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4237cc3cbd5441d94d83d0c7d5c7fdfe081aa87a47d0d017b6f37630efdcf5a3","first_computed_at":"2026-07-05T11:15:39.492892Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:15:39.492892Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5A9nm3Vc45L92cs+ZwnqOjvVrx/bMshSrdoB2/4V6qAL49cSZnko+LkQUJn349OQVkdyd8yaZ36fmGqM8OnzBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:15:39.493518Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.17169","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0e86785637c20a7d6f0dab602085d2617311f4e89d31c41b425161fa3f7f64ca","sha256:3ab1176162a4719510ce659aad862432eecb35bc09e5a6655871e5d80f4b48d2"],"state_sha256":"e0061ff9b59d43419275a3dea1f2fedc137a22c1d398669c82e87ef39ade9285"}