{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WB7EZGELNIKZPILA7I4SSP3YJF","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":"662e72c08dbe360c771ef645651c1a0723423ab3c8961421d75b3c7cd95c2834","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-06T18:01:02Z","title_canon_sha256":"7c10a2d85e2589a81cf648713d07695a17847ae38795887808e9abf56c6e53fb"},"schema_version":"1.0","source":{"id":"2406.04412","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.04412","created_at":"2026-07-05T10:23:19Z"},{"alias_kind":"arxiv_version","alias_value":"2406.04412v2","created_at":"2026-07-05T10:23:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.04412","created_at":"2026-07-05T10:23:19Z"},{"alias_kind":"pith_short_12","alias_value":"WB7EZGELNIKZ","created_at":"2026-07-05T10:23:19Z"},{"alias_kind":"pith_short_16","alias_value":"WB7EZGELNIKZPILA","created_at":"2026-07-05T10:23:19Z"},{"alias_kind":"pith_short_8","alias_value":"WB7EZGEL","created_at":"2026-07-05T10:23:19Z"}],"graph_snapshots":[{"event_id":"sha256:a8817fad17f039a8f85079743deb43d64f0ff75a5b3effa8bbdfcb3de1aea48e","target":"graph","created_at":"2026-07-05T10:23:19Z","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/2406.04412/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Aligning large language models (LLMs) with human preferences becomes a key component to obtaining state-of-the-art performance, but it yields a huge cost to construct a large human-annotated preference dataset. To tackle this problem, we propose a new framework, Spread Preference Annotation with direct preference judgment (SPA), that boosts the alignment of LLMs using only a very small amount of human-annotated preference data. Our key idea is leveraging the human prior knowledge within the small (seed) data and progressively improving the alignment of LLM, by iteratively generating the respon","authors_text":"Dongyoung Kim, Jaehyung Kim, Jinwoo Shin, Kimin Lee","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-06T18:01:02Z","title":"Spread Preference Annotation: Direct Preference Judgment for Efficient LLM Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.04412","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:b0faae9b6c9d959e6c46cb9c388d3a1b945decf5ff49e9076d07b6bb5ae7b25f","target":"record","created_at":"2026-07-05T10:23:19Z","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":"662e72c08dbe360c771ef645651c1a0723423ab3c8961421d75b3c7cd95c2834","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-06T18:01:02Z","title_canon_sha256":"7c10a2d85e2589a81cf648713d07695a17847ae38795887808e9abf56c6e53fb"},"schema_version":"1.0","source":{"id":"2406.04412","kind":"arxiv","version":2}},"canonical_sha256":"b07e4c988b6a1597a160fa39293f78496487744c383c155ed427fb4600b58021","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b07e4c988b6a1597a160fa39293f78496487744c383c155ed427fb4600b58021","first_computed_at":"2026-07-05T10:23:19.892937Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:23:19.892937Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fQ6SL+BzAp6jln3aIxklzzetJMJQmP35ryEUhMASfrvcfmoiaACAC+ZLcm6ElwKoeVY7oWOxXITjHOP3bYZmBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:23:19.893435Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.04412","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b0faae9b6c9d959e6c46cb9c388d3a1b945decf5ff49e9076d07b6bb5ae7b25f","sha256:a8817fad17f039a8f85079743deb43d64f0ff75a5b3effa8bbdfcb3de1aea48e"],"state_sha256":"36d83889263769da3e163cc9eb366c149376b50ae56547caa453eef3ca674896"}