{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DDECFACTQE2T6BTQLUHE5MCAPS","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":"b660cc79eabc2663da93ba989bad64f2aac0d16f8473ce419f69890b8ebbdd41","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-01T19:12:25Z","title_canon_sha256":"8299e860488dfabf231c255972a09fa41193af54417b9d54466120cdb35c21ee"},"schema_version":"1.0","source":{"id":"2402.01781","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.01781","created_at":"2026-07-05T08:39:30Z"},{"alias_kind":"arxiv_version","alias_value":"2402.01781v2","created_at":"2026-07-05T08:39:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.01781","created_at":"2026-07-05T08:39:30Z"},{"alias_kind":"pith_short_12","alias_value":"DDECFACTQE2T","created_at":"2026-07-05T08:39:30Z"},{"alias_kind":"pith_short_16","alias_value":"DDECFACTQE2T6BTQ","created_at":"2026-07-05T08:39:30Z"},{"alias_kind":"pith_short_8","alias_value":"DDECFACT","created_at":"2026-07-05T08:39:30Z"}],"graph_snapshots":[{"event_id":"sha256:d26a0f085183c93bc0e2592ebe0afe64bdfa585758f4ec7e20d631ef3ff48d65","target":"graph","created_at":"2026-07-05T08:39:30Z","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/2402.01781/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Model (LLM) leaderboards based on benchmark rankings are regularly used to guide practitioners in model selection. Often, the published leaderboard rankings are taken at face value - we show this is a (potentially costly) mistake. Under existing leaderboards, the relative performance of LLMs is highly sensitive to (often minute) details. We show that for popular multiple-choice question benchmarks (e.g., MMLU), minor perturbations to the benchmark, such as changing the order of choices or the method of answer selection, result in changes in rankings up to 8 positions. We explain","authors_text":"Areeb Alowisheq, Faisal Mirza, Haidar Khan, Hisham Abdullah Alyahya, M Saiful Bari, Nora Altwairesh, Norah Alzahrani, Nouf Alotaibi, Shaykhah Alsubaie, Sultan Alrashed, Yazeed Alnumay, Yusef Almushaykeh","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-01T19:12:25Z","title":"When Benchmarks are Targets: Revealing the Sensitivity of Large Language Model Leaderboards"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.01781","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:c7724e3d590ba64a08ccb986f88e97c0c74fbaf7e58a2d53e2377c6436a92f12","target":"record","created_at":"2026-07-05T08:39:30Z","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":"b660cc79eabc2663da93ba989bad64f2aac0d16f8473ce419f69890b8ebbdd41","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-01T19:12:25Z","title_canon_sha256":"8299e860488dfabf231c255972a09fa41193af54417b9d54466120cdb35c21ee"},"schema_version":"1.0","source":{"id":"2402.01781","kind":"arxiv","version":2}},"canonical_sha256":"18c822805381353f06705d0e4eb0407c80de9aeda52762e640fdee0fa6644c8d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"18c822805381353f06705d0e4eb0407c80de9aeda52762e640fdee0fa6644c8d","first_computed_at":"2026-07-05T08:39:30.627437Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:39:30.627437Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6Ol9YPvouXt6YdchvkvXV5+Yllz2r2HAIGOsntOoxItQDHoa/tXfrxrRDhmvePWMIraezk64Ozqj/u0cx0d5DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:39:30.627989Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.01781","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c7724e3d590ba64a08ccb986f88e97c0c74fbaf7e58a2d53e2377c6436a92f12","sha256:d26a0f085183c93bc0e2592ebe0afe64bdfa585758f4ec7e20d631ef3ff48d65"],"state_sha256":"48edf535c0728e1128e02d34d52bdcffc4aa4242d2b2c3067342d05eac8ba09e"}