{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OH4WFENFACW37YY43ITAF4AG4H","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":"167bcd80e6a65439adfabaa8e10924cafa19ac5ba6f4a789883ea233202fc565","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-23T17:58:07Z","title_canon_sha256":"dbbbe7741708e0d085370e17cd4f89e68b9afc32bf00c2523e9c6284958e74c3"},"schema_version":"1.0","source":{"id":"2409.15268","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.15268","created_at":"2026-07-05T10:05:44Z"},{"alias_kind":"arxiv_version","alias_value":"2409.15268v3","created_at":"2026-07-05T10:05:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.15268","created_at":"2026-07-05T10:05:44Z"},{"alias_kind":"pith_short_12","alias_value":"OH4WFENFACW3","created_at":"2026-07-05T10:05:44Z"},{"alias_kind":"pith_short_16","alias_value":"OH4WFENFACW37YY4","created_at":"2026-07-05T10:05:44Z"},{"alias_kind":"pith_short_8","alias_value":"OH4WFENF","created_at":"2026-07-05T10:05:44Z"}],"graph_snapshots":[{"event_id":"sha256:80ea566709d6820591e7476e84ec0b8ace96c69ec6e9ddeef47054afd752eed7","target":"graph","created_at":"2026-07-05T10:05:44Z","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/2409.15268/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The release of ChatGPT in November 2022 sparked an explosion of interest in post-training and an avalanche of new preference optimization (PO) methods. These methods claim superior alignment by virtue of better correspondence with human pairwise preferences, often measured by LLM-judges. In this work, we attempt to answer the following question -- do LLM-judge preferences translate to progress on other, more concrete metrics for alignment, and if not, why not? We define a concrete metric for alignment, and introduce SOS-Bench (Substance Outweighs Style Benchmark), which is to the best of our k","authors_text":"Benjamin Feuer, John P. Dickerson, Max Cembalest, Micah Goldblum, Raz Besaleli, Samuel Dooley, Sanjana Nambiar, Teresa Datta","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-23T17:58:07Z","title":"Style Outweighs Substance: Failure Modes of LLM Judges in Alignment Benchmarking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.15268","kind":"arxiv","version":3},"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:f60c45712e834bceb93b848267a3f0efec6cd442a6c6fdd456108dbfc2b4ef03","target":"record","created_at":"2026-07-05T10:05:44Z","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":"167bcd80e6a65439adfabaa8e10924cafa19ac5ba6f4a789883ea233202fc565","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-23T17:58:07Z","title_canon_sha256":"dbbbe7741708e0d085370e17cd4f89e68b9afc32bf00c2523e9c6284958e74c3"},"schema_version":"1.0","source":{"id":"2409.15268","kind":"arxiv","version":3}},"canonical_sha256":"71f96291a500adbfe31cda2602f006e1cce8ab9dfa051eb587115678e9f3ff46","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"71f96291a500adbfe31cda2602f006e1cce8ab9dfa051eb587115678e9f3ff46","first_computed_at":"2026-07-05T10:05:44.998367Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:05:44.998367Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iFPdXLbQ/QC4R9gj6t0eqpXhZMjvcGo52s9WJ2WdewLF2VYkWHCr3GmhUDADgWwdzXycOc6RsGd4K3A/rUGBBA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:05:44.998868Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.15268","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f60c45712e834bceb93b848267a3f0efec6cd442a6c6fdd456108dbfc2b4ef03","sha256:80ea566709d6820591e7476e84ec0b8ace96c69ec6e9ddeef47054afd752eed7"],"state_sha256":"d2be6ea7f477b142dfdc95b87cd85cfb65d9825d0aba2dfa7f07eb131e45a01e"}