{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DKGK4ZLJKCQ5ACVVWWMRGHEAY2","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":"6499c02dbaf48d7295d14a104615d127cd3ac88d48cd77ccd1630a04ae0c7efe","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-31T02:05:40Z","title_canon_sha256":"018c4931c618138776105ec1d8dd6a4c81cac1cf47bc37c539ea25ceb3097cf3"},"schema_version":"1.0","source":{"id":"2404.00530","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.00530","created_at":"2026-07-05T09:58:19Z"},{"alias_kind":"arxiv_version","alias_value":"2404.00530v2","created_at":"2026-07-05T09:58:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.00530","created_at":"2026-07-05T09:58:19Z"},{"alias_kind":"pith_short_12","alias_value":"DKGK4ZLJKCQ5","created_at":"2026-07-05T09:58:19Z"},{"alias_kind":"pith_short_16","alias_value":"DKGK4ZLJKCQ5ACVV","created_at":"2026-07-05T09:58:19Z"},{"alias_kind":"pith_short_8","alias_value":"DKGK4ZLJ","created_at":"2026-07-05T09:58:19Z"}],"graph_snapshots":[{"event_id":"sha256:236e206b2e5cd24218beb5ea70d7eb9e558d747d0c985d3b06af043681b3a645","target":"graph","created_at":"2026-07-05T09:58:19Z","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/2404.00530/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A common technique for aligning large language models (LLMs) relies on acquiring human preferences by comparing multiple generations conditioned on a fixed context. This method, however, relies solely on pairwise comparisons, where the generations are evaluated within an identical context. While effective to such conditional preferences often fail to encompass the nuanced and multidimensional nature of human preferences. In this work, we revisit the traditional paradigm of preference acquisition and propose a new axis based on eliciting preferences jointly over the instruction-response pairs. ","authors_text":"Aditya Grover, Ashima Suvarna, Gantavya Bhatt, Hritik Bansal, Kai-Wei Chang, Nanyun Peng","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-31T02:05:40Z","title":"Comparing Bad Apples to Good Oranges: Aligning Large Language Models via Joint Preference Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.00530","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:f9dc122f8d9e666ab3760a0f8fb5b097e7142124596b7b9744023a1aa110ec6e","target":"record","created_at":"2026-07-05T09:58:19Z","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":"6499c02dbaf48d7295d14a104615d127cd3ac88d48cd77ccd1630a04ae0c7efe","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-31T02:05:40Z","title_canon_sha256":"018c4931c618138776105ec1d8dd6a4c81cac1cf47bc37c539ea25ceb3097cf3"},"schema_version":"1.0","source":{"id":"2404.00530","kind":"arxiv","version":2}},"canonical_sha256":"1a8cae656950a1d00ab5b599131c80c6a38178a46b8d0e30821bde48de5df349","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1a8cae656950a1d00ab5b599131c80c6a38178a46b8d0e30821bde48de5df349","first_computed_at":"2026-07-05T09:58:19.643650Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:58:19.643650Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VmkG+Odq0v1ZeKfP5o45YGpw8jOElt5BupmcfCQ1AdK3aV7uzO53AKEaIoaXkPirEC4CgxSWVj/YUmARfJwGCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:58:19.644150Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.00530","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f9dc122f8d9e666ab3760a0f8fb5b097e7142124596b7b9744023a1aa110ec6e","sha256:236e206b2e5cd24218beb5ea70d7eb9e558d747d0c985d3b06af043681b3a645"],"state_sha256":"f9c9fa46cfb7de619ce2844a0c2e42b19dc1ea8a7af843e1fc0cae0ce460ebfe"}