{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BUCUAWQD6ALUK3F4SPSN4PA6ZD","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":"4029b1bd7d02d8d4453fe8366b5bfa632e2a0412df0f8bc2973b99bd7776dc95","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-12T16:24:51Z","title_canon_sha256":"dbac65a66d6a1e94760d0145e2c40bcb119e68e36669da9ac6fdee23a3cecf2d"},"schema_version":"1.0","source":{"id":"2408.06266","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.06266","created_at":"2026-07-05T09:07:02Z"},{"alias_kind":"arxiv_version","alias_value":"2408.06266v5","created_at":"2026-07-05T09:07:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.06266","created_at":"2026-07-05T09:07:02Z"},{"alias_kind":"pith_short_12","alias_value":"BUCUAWQD6ALU","created_at":"2026-07-05T09:07:02Z"},{"alias_kind":"pith_short_16","alias_value":"BUCUAWQD6ALUK3F4","created_at":"2026-07-05T09:07:02Z"},{"alias_kind":"pith_short_8","alias_value":"BUCUAWQD","created_at":"2026-07-05T09:07:02Z"}],"graph_snapshots":[{"event_id":"sha256:508e7d1a98425b01b56d8f86939145fe66fd0e8a5abd40f90085f113d5b92b39","target":"graph","created_at":"2026-07-05T09:07:02Z","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/2408.06266/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) are often aligned using contrastive alignment objectives and preference pair datasets. The interaction between model, paired data, and objective makes alignment a complicated procedure, sometimes producing subpar results. We study this and find that (i) preference data gives a better learning signal when the underlying responses are contrastive, and (ii) alignment objectives lead to better performance when they specify more control over the model during training. Based on these insights, we introduce Contrastive Learning from AI Revisions (CLAIR), a data-creation m","authors_text":"Amanpreet Singh, Chris Develder, Christopher Potts, Douwe Kiela, Karel D'Oosterlinck, Shikib Mehri, Thomas Demeester, Winnie Xu","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-12T16:24:51Z","title":"Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.06266","kind":"arxiv","version":5},"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":"sha256:544d5ad85f0eb7f26c1bbd63ea4f367aa8b7878bd17accbcbcd289e3bf4672e1","target":"record","created_at":"2026-07-05T09:07:02Z","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":"4029b1bd7d02d8d4453fe8366b5bfa632e2a0412df0f8bc2973b99bd7776dc95","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-12T16:24:51Z","title_canon_sha256":"dbac65a66d6a1e94760d0145e2c40bcb119e68e36669da9ac6fdee23a3cecf2d"},"schema_version":"1.0","source":{"id":"2408.06266","kind":"arxiv","version":5}},"canonical_sha256":"0d05405a03f017456cbc93e4de3c1ec8c2ad6e561d7d123eeb90844c72910e1c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0d05405a03f017456cbc93e4de3c1ec8c2ad6e561d7d123eeb90844c72910e1c","first_computed_at":"2026-07-05T09:07:02.107080Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:07:02.107080Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tQBdufhgyCOJjSZAR7r40dJv3glyUVjlXe8Ox6bJnIbD7tMCkdm78HsPJywAN8Fv0x/ulpToqkfpoIMtONkOCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:07:02.107506Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.06266","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:544d5ad85f0eb7f26c1bbd63ea4f367aa8b7878bd17accbcbcd289e3bf4672e1","sha256:508e7d1a98425b01b56d8f86939145fe66fd0e8a5abd40f90085f113d5b92b39"],"state_sha256":"92ab0a9d546e8d3783357d4326680bcc61b883ecd0c2fc0578ce29121fb33b50"}