{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VV56ACGHNBNVFROMFS3CN5HLCU","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":"c3632e2924fa22c2077b7958d63e352efdf19407fe08fa18ddbc28c73dcd856f","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-26T00:29:04Z","title_canon_sha256":"8a04b0a2db9f305505a0e9522189fb754de4b05dfec9050670b851f862a4c0be"},"schema_version":"1.0","source":{"id":"2405.16388","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.16388","created_at":"2026-07-05T08:23:29Z"},{"alias_kind":"arxiv_version","alias_value":"2405.16388v1","created_at":"2026-07-05T08:23:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.16388","created_at":"2026-07-05T08:23:29Z"},{"alias_kind":"pith_short_12","alias_value":"VV56ACGHNBNV","created_at":"2026-07-05T08:23:29Z"},{"alias_kind":"pith_short_16","alias_value":"VV56ACGHNBNVFROM","created_at":"2026-07-05T08:23:29Z"},{"alias_kind":"pith_short_8","alias_value":"VV56ACGH","created_at":"2026-07-05T08:23:29Z"}],"graph_snapshots":[{"event_id":"sha256:dac668fe89c5972ffd49df61a59feaf9c723371b964ef01f3dac113586bcdf40","target":"graph","created_at":"2026-07-05T08:23:29Z","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/2405.16388/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"How can Large Language Models (LLMs) be aligned with human intentions and values? A typical solution is to gather human preference on model outputs and finetune the LLMs accordingly while ensuring that updates do not deviate too far from a reference model. Recent approaches, such as direct preference optimization (DPO), have eliminated the need for unstable and sluggish reinforcement learning optimization by introducing close-formed supervised losses. However, a significant limitation of the current approach is its design for a single reference model only, neglecting to leverage the collective","authors_text":"Dung Nguyen, Hung Le, Kelechi Ogueji, Kien Do, Quan Tran, Saloni Mittal, Svetha Venkatesh","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-26T00:29:04Z","title":"Multi-Reference Preference Optimization for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.16388","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:ccfb7491e25c64d8f5ebd927f153cfe53f715a4a27620878354c737c10687efb","target":"record","created_at":"2026-07-05T08:23:29Z","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":"c3632e2924fa22c2077b7958d63e352efdf19407fe08fa18ddbc28c73dcd856f","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-26T00:29:04Z","title_canon_sha256":"8a04b0a2db9f305505a0e9522189fb754de4b05dfec9050670b851f862a4c0be"},"schema_version":"1.0","source":{"id":"2405.16388","kind":"arxiv","version":1}},"canonical_sha256":"ad7be008c7685b52c5cc2cb626f4eb1534bed4fc8a2beb6bb3c84e9d1687f202","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ad7be008c7685b52c5cc2cb626f4eb1534bed4fc8a2beb6bb3c84e9d1687f202","first_computed_at":"2026-07-05T08:23:29.527458Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:23:29.527458Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/gDHbIj94ajkDjMJQCmfOyxJqbS8JZ2+j5QlvgRPvUyW4G5L2K4dGwAEgql8FEr8RccuY1hVs5rA6i/7qmbMCA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:23:29.527943Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.16388","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ccfb7491e25c64d8f5ebd927f153cfe53f715a4a27620878354c737c10687efb","sha256:dac668fe89c5972ffd49df61a59feaf9c723371b964ef01f3dac113586bcdf40"],"state_sha256":"b326c811cb7106c1bd8d4cda1ceccacbc1d1f9b8cc3c25fb9cf8fe6794a7fc4e"}