{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:MVPY77PA7SN25YB3NCXSXA6KGI","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":"7f5c41da9c610e22f2017b23e32e572af7c838008761ad26fe648d377ac3189d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-26T03:03:15Z","title_canon_sha256":"85ad238eacc5dfc119900464d65748a8de9baed9d1952b158160aede94dce7dd"},"schema_version":"1.0","source":{"id":"2607.16240","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.16240","created_at":"2026-07-21T00:20:07Z"},{"alias_kind":"arxiv_version","alias_value":"2607.16240v1","created_at":"2026-07-21T00:20:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.16240","created_at":"2026-07-21T00:20:07Z"},{"alias_kind":"pith_short_12","alias_value":"MVPY77PA7SN2","created_at":"2026-07-21T00:20:07Z"},{"alias_kind":"pith_short_16","alias_value":"MVPY77PA7SN25YB3","created_at":"2026-07-21T00:20:07Z"},{"alias_kind":"pith_short_8","alias_value":"MVPY77PA","created_at":"2026-07-21T00:20:07Z"}],"graph_snapshots":[{"event_id":"sha256:1a6f9c75b6006c4d12cf26a723e7d4f99236d01afcbf2fbb9f66c9b19318c578","target":"graph","created_at":"2026-07-21T00:20:07Z","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/2607.16240/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Direct Alignment Algorithms (DAAs) such as DPO have become a common way to post-train and align LLMs with human preferences. However, DAAs have been observed to over-optimize their implicit reward model and decrease the likelihood of preferred responses. This results in a decrease in the total likelihood assigned to responses seen in the preference dataset, potentially resulting in undesirable behavior. To counteract this undesired side-effect of DAAs, we examine the effect of using objectives that add a regularization term to maintain the total length-normalized probabilities of the chosen an","authors_text":"Barry-John Theobald, Federico Danieli, Katherine Metcalf, Shawn Im, Skyler Seto","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-26T03:03:15Z","title":"Normalized Rewards for Preference Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.16240","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":"sha256:02a0b66b6c173cb0952dd37c9e1fd16c9ca73aa93fa2a2a801341c7764d071b5","target":"record","created_at":"2026-07-21T00:20:07Z","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":"7f5c41da9c610e22f2017b23e32e572af7c838008761ad26fe648d377ac3189d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-26T03:03:15Z","title_canon_sha256":"85ad238eacc5dfc119900464d65748a8de9baed9d1952b158160aede94dce7dd"},"schema_version":"1.0","source":{"id":"2607.16240","kind":"arxiv","version":1}},"canonical_sha256":"655f8ffde0fc9baee03b68af2b83ca321468a3ecc1a77cfcfe69204ebd607198","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"655f8ffde0fc9baee03b68af2b83ca321468a3ecc1a77cfcfe69204ebd607198","first_computed_at":"2026-07-21T00:20:07.574798Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-21T00:20:07.574798Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UU1bGEizjpRjIYKYOufDoJk99ckSjFJT7OiuTbyYOlT6lpMRcRhHItzez7FGwc4P9B3qmwo7vlRvskbLMFaBAA==","signature_status":"signed_v1","signed_at":"2026-07-21T00:20:07.575661Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.16240","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:02a0b66b6c173cb0952dd37c9e1fd16c9ca73aa93fa2a2a801341c7764d071b5","sha256:1a6f9c75b6006c4d12cf26a723e7d4f99236d01afcbf2fbb9f66c9b19318c578"],"state_sha256":"f9ee969882b7d54e838aa1fc6f0b84b6a8b1032814c9794191ce438bc467b0cd"}