{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WBE6NTQYZVLE3R7JB2IUBTAHOE","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":"bf4c113976f9f65a9fd8ad4736ac17b8e789af63dd341ad7619ce980e946357b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-12T06:08:46Z","title_canon_sha256":"eb0a707d330f4267ff25e84e783ff5f704a5dddb4b80ec8cf096cc113a6d565d"},"schema_version":"1.0","source":{"id":"2412.08972","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.08972","created_at":"2026-07-05T11:12:23Z"},{"alias_kind":"arxiv_version","alias_value":"2412.08972v2","created_at":"2026-07-05T11:12:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.08972","created_at":"2026-07-05T11:12:23Z"},{"alias_kind":"pith_short_12","alias_value":"WBE6NTQYZVLE","created_at":"2026-07-05T11:12:23Z"},{"alias_kind":"pith_short_16","alias_value":"WBE6NTQYZVLE3R7J","created_at":"2026-07-05T11:12:23Z"},{"alias_kind":"pith_short_8","alias_value":"WBE6NTQY","created_at":"2026-07-05T11:12:23Z"}],"graph_snapshots":[{"event_id":"sha256:bce07bfbd6c6c12d1d8011fe6634e85e511b07e94c9ae809c2fe4bd5f4d6f764","target":"graph","created_at":"2026-07-05T11:12:23Z","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/2412.08972/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper introduces RuleArena, a novel and challenging benchmark designed to evaluate the ability of large language models (LLMs) to follow complex, real-world rules in reasoning. Covering three practical domains -- airline baggage fees, NBA transactions, and tax regulations -- RuleArena assesses LLMs' proficiency in handling intricate natural language instructions that demand long-context understanding, logical reasoning, and accurate mathematical computation. Two key attributes distinguish RuleArena from traditional rule-based reasoning benchmarks: (1) it extends beyond standard first-orde","authors_text":"En Yu, Liangming Pan, Ruiwen Zhou, Sitao Cheng, Wenyue Hua, William Yang Wang, Xiaobao Wu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-12T06:08:46Z","title":"RuleArena: A Benchmark for Rule-Guided Reasoning with LLMs in Real-World Scenarios"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.08972","kind":"arxiv","version":2},"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":"sha256:896cc0b68c22d6c1cdbc88048d062adff4fe40b6efa6b99cd52ad2e78b13bb95","target":"record","created_at":"2026-07-05T11:12:23Z","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":"bf4c113976f9f65a9fd8ad4736ac17b8e789af63dd341ad7619ce980e946357b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-12T06:08:46Z","title_canon_sha256":"eb0a707d330f4267ff25e84e783ff5f704a5dddb4b80ec8cf096cc113a6d565d"},"schema_version":"1.0","source":{"id":"2412.08972","kind":"arxiv","version":2}},"canonical_sha256":"b049e6ce18cd564dc7e90e9140cc077136bd9dd01002ac7769ac1feea819eb65","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b049e6ce18cd564dc7e90e9140cc077136bd9dd01002ac7769ac1feea819eb65","first_computed_at":"2026-07-05T11:12:23.312450Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:12:23.312450Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HzJO4hMbdEQ+hoqFQnXS8mpAbvGLUVpoKVtKErK5pg82Xjr9fuT01q37A93mwAbXGZlQBPLJIFh3C5GuhXxRCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:12:23.313075Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.08972","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:896cc0b68c22d6c1cdbc88048d062adff4fe40b6efa6b99cd52ad2e78b13bb95","sha256:bce07bfbd6c6c12d1d8011fe6634e85e511b07e94c9ae809c2fe4bd5f4d6f764"],"state_sha256":"5332b1291d8712abf4d5aba6d0d6c4c4aa8743c974ea14339affd8c020dbc33e"}