{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZDKQ74O5IDJCTYTY3IQOCEH2W5","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":"61777031d3b7ef966ef96ef30258949aa1191750077615199f0c05f288bf4199","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-02-19T19:59:16Z","title_canon_sha256":"dae1cc681d0a7a65d4e534b2165aa13c710e9d63d1168369e4ee1e1b477baeb8"},"schema_version":"1.0","source":{"id":"2502.14074","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.14074","created_at":"2026-07-05T11:16:55Z"},{"alias_kind":"arxiv_version","alias_value":"2502.14074v3","created_at":"2026-07-05T11:16:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.14074","created_at":"2026-07-05T11:16:55Z"},{"alias_kind":"pith_short_12","alias_value":"ZDKQ74O5IDJC","created_at":"2026-07-05T11:16:55Z"},{"alias_kind":"pith_short_16","alias_value":"ZDKQ74O5IDJCTYTY","created_at":"2026-07-05T11:16:55Z"},{"alias_kind":"pith_short_8","alias_value":"ZDKQ74O5","created_at":"2026-07-05T11:16:55Z"}],"graph_snapshots":[{"event_id":"sha256:c8c647dfc1dd35781a816b1aea0e6da8985adbef059ef637ac27522bf73f4d62","target":"graph","created_at":"2026-07-05T11:16:55Z","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/2502.14074/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Automatic evaluation methods based on large language models (LLMs) are emerging as the standard tool for assessing the instruction-following abilities of LLM-based agents. The most common method in this paradigm, pairwise comparisons with a baseline model, critically depends on the assumption of transitive preferences. However, the validity of this assumption remains largely unexplored. In this study, we investigate the presence of non-transitivity within the AlpacaEval framework and analyze its effects on model rankings. We find that LLM judges exhibit non-transitive preferences, leading to r","authors_text":"Laura Ruis, Robert Kirk, Tim Rockt\\\"aschel, Yi Xu","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-02-19T19:59:16Z","title":"Investigating Non-Transitivity in LLM-as-a-Judge"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.14074","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":"sha256:925130be23ab0990761b4ecce1478caa07323c1b583c1ba7ab0410bb36c96400","target":"record","created_at":"2026-07-05T11:16:55Z","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":"61777031d3b7ef966ef96ef30258949aa1191750077615199f0c05f288bf4199","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-02-19T19:59:16Z","title_canon_sha256":"dae1cc681d0a7a65d4e534b2165aa13c710e9d63d1168369e4ee1e1b477baeb8"},"schema_version":"1.0","source":{"id":"2502.14074","kind":"arxiv","version":3}},"canonical_sha256":"c8d50ff1dd40d229e278da20e110fab7563db4ac00c7a5cfd9f6f402f24ce020","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c8d50ff1dd40d229e278da20e110fab7563db4ac00c7a5cfd9f6f402f24ce020","first_computed_at":"2026-07-05T11:16:55.283998Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:16:55.283998Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NKRPdZ06QYvmm+rakxr/ANz2EUXdiA1C1YyBvQSp5b7iMPj/mJcAgg9gxEsogKi421tuv+yaDyhjGEUCt5xPBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:16:55.284766Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.14074","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:925130be23ab0990761b4ecce1478caa07323c1b583c1ba7ab0410bb36c96400","sha256:c8c647dfc1dd35781a816b1aea0e6da8985adbef059ef637ac27522bf73f4d62"],"state_sha256":"10a4f65cc546f0bc733f34fbbf692aadc880f83b8f721c80006f84e3267daf32"}