{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6CUDVGOGXH6V6JM7WGJJUMKLT4","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":"e5b5feaac69c3794db4cdd7bdcc1eabc01c86163f9ed6b35736e54805984b871","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-18T13:55:42Z","title_canon_sha256":"0a3130b756b60c9516f46b3a2ab93c74afd0c8b792553da2cb6f5595f9a99f6f"},"schema_version":"1.0","source":{"id":"2412.13862","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.13862","created_at":"2026-07-05T09:51:09Z"},{"alias_kind":"arxiv_version","alias_value":"2412.13862v1","created_at":"2026-07-05T09:51:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.13862","created_at":"2026-07-05T09:51:09Z"},{"alias_kind":"pith_short_12","alias_value":"6CUDVGOGXH6V","created_at":"2026-07-05T09:51:09Z"},{"alias_kind":"pith_short_16","alias_value":"6CUDVGOGXH6V6JM7","created_at":"2026-07-05T09:51:09Z"},{"alias_kind":"pith_short_8","alias_value":"6CUDVGOG","created_at":"2026-07-05T09:51:09Z"}],"graph_snapshots":[{"event_id":"sha256:ca2f559d340114ca590058afc6d4127952cacbbdda191a9e1091b9658e9ae974","target":"graph","created_at":"2026-07-05T09:51:09Z","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/2412.13862/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Since the debut of DPO, it has been shown that aligning a target LLM with human preferences via the KL-constrained RLHF loss is mathematically equivalent to a special kind of reward modeling task. Concretely, the task requires: 1) using the target LLM to parameterize the reward model, and 2) tuning the reward model so that it has a 1:1 linear relationship with the true reward. However, we identify a significant issue: the DPO loss might have multiple minimizers, of which only one satisfies the required linearity condition. The problem arises from a well-known issue of the underlying Bradley-Te","authors_text":"Hanshan Zhang, Hongfei Jiang, Junwei Bao, Yang Song, Yuzhong Hong","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-18T13:55:42Z","title":"Energy-Based Preference Model Offers Better Offline Alignment than the Bradley-Terry Preference Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.13862","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":"sha256:7cab3c029aafe35c501bb49d961b084cb40263aaf21329ba369a5bda3dfb9dd8","target":"record","created_at":"2026-07-05T09:51:09Z","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":"e5b5feaac69c3794db4cdd7bdcc1eabc01c86163f9ed6b35736e54805984b871","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-18T13:55:42Z","title_canon_sha256":"0a3130b756b60c9516f46b3a2ab93c74afd0c8b792553da2cb6f5595f9a99f6f"},"schema_version":"1.0","source":{"id":"2412.13862","kind":"arxiv","version":1}},"canonical_sha256":"f0a83a99c6b9fd5f259fb1929a314b9f26dd68d4c5233d0ae4fbd6ecfc108be7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f0a83a99c6b9fd5f259fb1929a314b9f26dd68d4c5233d0ae4fbd6ecfc108be7","first_computed_at":"2026-07-05T09:51:09.915528Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:51:09.915528Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"O0UTpqsqe7BsXAvjlXCBXF6muodMInoApPCY5K7SvdctfNFmIKvtKdwYIbbTyWGnvY/ULMoTfhevAmIZ6t/eAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:51:09.916006Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.13862","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7cab3c029aafe35c501bb49d961b084cb40263aaf21329ba369a5bda3dfb9dd8","sha256:ca2f559d340114ca590058afc6d4127952cacbbdda191a9e1091b9658e9ae974"],"state_sha256":"466891dbf9c01ffad1a1c56ea3f33205557266832daed434e8e169036182a0d5"}