{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:TJD4ZQGSBKCRB32SLHQRUGDKJO","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":"cb43e9394dc2478bebc3d0e8f64e426d7edaf5ca101c9c5c904566f12ea0d7a0","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-27T18:53:09Z","title_canon_sha256":"70ce8c02607e37fa7013f5824e95e60c6bbb921c726867a704d519efc7fdc6b5"},"schema_version":"1.0","source":{"id":"2312.16682","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.16682","created_at":"2026-07-05T08:10:59Z"},{"alias_kind":"arxiv_version","alias_value":"2312.16682v2","created_at":"2026-07-05T08:10:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.16682","created_at":"2026-07-05T08:10:59Z"},{"alias_kind":"pith_short_12","alias_value":"TJD4ZQGSBKCR","created_at":"2026-07-05T08:10:59Z"},{"alias_kind":"pith_short_16","alias_value":"TJD4ZQGSBKCRB32S","created_at":"2026-07-05T08:10:59Z"},{"alias_kind":"pith_short_8","alias_value":"TJD4ZQGS","created_at":"2026-07-05T08:10:59Z"}],"graph_snapshots":[{"event_id":"sha256:b18e63a385d5726b5a032f6be16bc0c5943da68279c9f042c76157a22296051e","target":"graph","created_at":"2026-07-05T08:10:59Z","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/2312.16682/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Practitioners commonly align large language models using pairwise preferences, i.e., given labels of the type response A is preferred to response B for a given input. Perhaps less commonly, methods have also been developed for binary feedback, i.e. training models given labels of type response A is good or bad. We show how an existing performant binary feedback method, the Cringe Loss (Adolphs et al., 2022), can be generalized to the pairwise preference setting using a simple soft margin extension. Pairwise Cringe Loss is straightforward to implement and efficient to train, and we find it outp","authors_text":"Andrew Lee, Jason Weston, Jing Xu, Sainbayar Sukhbaatar","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-27T18:53:09Z","title":"Some things are more CRINGE than others: Iterative Preference Optimization with the Pairwise Cringe Loss"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.16682","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:d14a8c5a580d538424949af39fb7c977e6e9807d258641efa4d584a73d1379ae","target":"record","created_at":"2026-07-05T08:10:59Z","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":"cb43e9394dc2478bebc3d0e8f64e426d7edaf5ca101c9c5c904566f12ea0d7a0","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-27T18:53:09Z","title_canon_sha256":"70ce8c02607e37fa7013f5824e95e60c6bbb921c726867a704d519efc7fdc6b5"},"schema_version":"1.0","source":{"id":"2312.16682","kind":"arxiv","version":2}},"canonical_sha256":"9a47ccc0d20a8510ef5259e11a186a4b9b1fc19c073306c5763f7528d403961b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9a47ccc0d20a8510ef5259e11a186a4b9b1fc19c073306c5763f7528d403961b","first_computed_at":"2026-07-05T08:10:59.829100Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:10:59.829100Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ae6YBtrJBu1N+K/CI+sfuz1Z1BfAZMwg23GQu4gyGMNkELHk6YrAGk7WLsw7ksg5lhagXb7Ju3H0Wr/mlFK+AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:10:59.829656Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.16682","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d14a8c5a580d538424949af39fb7c977e6e9807d258641efa4d584a73d1379ae","sha256:b18e63a385d5726b5a032f6be16bc0c5943da68279c9f042c76157a22296051e"],"state_sha256":"4ac80c2c67b5e0d86b5e6395750c546e5e2cf3def7497b8ba9a68731d0774f3b"}