{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5FM2ZUM4XU7LQYUHMZ5AJLI7UI","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":"10c18b63a55193510fd81a4015cd33bb1d7d7a67cdfc50b2b12be50979ddcb7f","cross_cats_sorted":["cs.AI","cs.LO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-03T04:34:04Z","title_canon_sha256":"d7db49f1d38eadff83befbe6bc0c9d2219265938ea0bd7f1f6e1c59af87b584b"},"schema_version":"1.0","source":{"id":"2410.02205","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.02205","created_at":"2026-07-05T10:11:25Z"},{"alias_kind":"arxiv_version","alias_value":"2410.02205v3","created_at":"2026-07-05T10:11:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.02205","created_at":"2026-07-05T10:11:25Z"},{"alias_kind":"pith_short_12","alias_value":"5FM2ZUM4XU7L","created_at":"2026-07-05T10:11:25Z"},{"alias_kind":"pith_short_16","alias_value":"5FM2ZUM4XU7LQYUH","created_at":"2026-07-05T10:11:25Z"},{"alias_kind":"pith_short_8","alias_value":"5FM2ZUM4","created_at":"2026-07-05T10:11:25Z"}],"graph_snapshots":[{"event_id":"sha256:8f344f0fa8595e05e902936edeaf8d304aa302138ec419e886669da445e4b36d","target":"graph","created_at":"2026-07-05T10:11:25Z","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/2410.02205/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) are expected to be predictable and trustworthy to support reliable decision-making systems. Yet current LLMs often show inconsistencies in their judgments. In this work, we examine logical preference consistency as a foundational requirement for building more dependable LLM systems, ensuring stable and coherent decision-making while minimizing erratic or contradictory outputs. To quantify the logical preference consistency, we propose a universal evaluation framework based on three fundamental properties: transitivity, commutativity and negation invariance. Through","authors_text":"Ehsan Shareghi, Ivan Vuli\\'c, Nigel Collier, Tianya Liang, Yinhong Liu, Zhijiang Guo","cross_cats":["cs.AI","cs.LO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-03T04:34:04Z","title":"Aligning with Logic: Measuring, Evaluating and Improving Logical Preference Consistency in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.02205","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":"sha256:768ced8f3123d884741ba451b4cfc71bd41bd904c32b645633f9e95dd78beb3b","target":"record","created_at":"2026-07-05T10:11:25Z","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":"10c18b63a55193510fd81a4015cd33bb1d7d7a67cdfc50b2b12be50979ddcb7f","cross_cats_sorted":["cs.AI","cs.LO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-03T04:34:04Z","title_canon_sha256":"d7db49f1d38eadff83befbe6bc0c9d2219265938ea0bd7f1f6e1c59af87b584b"},"schema_version":"1.0","source":{"id":"2410.02205","kind":"arxiv","version":3}},"canonical_sha256":"e959acd19cbd3eb86287667a04ad1fa21741acbf62568dcf86a468834e5b9b61","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e959acd19cbd3eb86287667a04ad1fa21741acbf62568dcf86a468834e5b9b61","first_computed_at":"2026-07-05T10:11:25.186308Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:11:25.186308Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2boW8usPY4EZWtHJkZBNthw+yg4kl1nsj/C6ghCYtQBTogu16wLBtlczIpD3fuc6APLHH+VNZmtlwlDJDcKnBA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:11:25.186959Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.02205","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:768ced8f3123d884741ba451b4cfc71bd41bd904c32b645633f9e95dd78beb3b","sha256:8f344f0fa8595e05e902936edeaf8d304aa302138ec419e886669da445e4b36d"],"state_sha256":"55a3df32de410119803d94717e52eb6bb7dc85341f556e60690a7720a271725f"}