{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ID2IWZPZ3W7JBARHK3N6AIWTWO","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":"f3000f8e55a2d404f69586ced76b2e938783b79e5cfe831c1f00b0bae4dafa4a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-28T19:38:44Z","title_canon_sha256":"5f01988124339c1d0df05fba51b06e729b5ecb9a01bef61fe7a742ddf19cff17"},"schema_version":"1.0","source":{"id":"2605.30504","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.30504","created_at":"2026-06-01T01:02:57Z"},{"alias_kind":"arxiv_version","alias_value":"2605.30504v1","created_at":"2026-06-01T01:02:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30504","created_at":"2026-06-01T01:02:57Z"},{"alias_kind":"pith_short_12","alias_value":"ID2IWZPZ3W7J","created_at":"2026-06-01T01:02:57Z"},{"alias_kind":"pith_short_16","alias_value":"ID2IWZPZ3W7JBARH","created_at":"2026-06-01T01:02:57Z"},{"alias_kind":"pith_short_8","alias_value":"ID2IWZPZ","created_at":"2026-06-01T01:02:57Z"}],"graph_snapshots":[{"event_id":"sha256:355e431bd656e7ef5794134e49c4886f17f6fe70bed6466c35238ba89670929c","target":"graph","created_at":"2026-06-01T01:02:57Z","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/2605.30504/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"LLM benchmark labels are frozen at release and silently propagated into downstream benchmarks, errors and all. We introduce an Item Response Theory-based indicator that surfaces likely mislabels at 95% precision in the top 200 examples across seven preference and multiple-choice benchmarks using responses from 114 models, outperforming a supervised classifier. We trace these errors to mechanical labeling heuristics, upstream annotation mistakes inherited unchanged from source datasets, and fundamentally ambiguous items without a defensible single label. The same model fit reveals that reward m","authors_text":"Daniel M. Bikel, Sander Land","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-28T19:38:44Z","title":"Auditing LLM Benchmarks with Item Response Theory"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30504","kind":"arxiv","version":1},"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":"sha256:7e8e6bc55231205916bdf6bcdc7486a3e2d67cc09ba70929bda3e592455e2ce0","target":"record","created_at":"2026-06-01T01:02:57Z","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":"f3000f8e55a2d404f69586ced76b2e938783b79e5cfe831c1f00b0bae4dafa4a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-28T19:38:44Z","title_canon_sha256":"5f01988124339c1d0df05fba51b06e729b5ecb9a01bef61fe7a742ddf19cff17"},"schema_version":"1.0","source":{"id":"2605.30504","kind":"arxiv","version":1}},"canonical_sha256":"40f48b65f9ddbe90822756dbe022d3b39c8933b28cca5f190832a9e0ddef8f1c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"40f48b65f9ddbe90822756dbe022d3b39c8933b28cca5f190832a9e0ddef8f1c","first_computed_at":"2026-06-01T01:02:57.967168Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-01T01:02:57.967168Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Q+W6p4FAwWJBMZRr6t0N9YUEsX4qTEmYBtZ/670xhJXHdE4ijNXUbjNWqW2sT6smTi1DYkCrnVXs3wDdBp5YCA==","signature_status":"signed_v1","signed_at":"2026-06-01T01:02:57.968095Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.30504","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7e8e6bc55231205916bdf6bcdc7486a3e2d67cc09ba70929bda3e592455e2ce0","sha256:355e431bd656e7ef5794134e49c4886f17f6fe70bed6466c35238ba89670929c"],"state_sha256":"b6df5062a1dcf0f13bd21885b46c731a8c7294cc2a96b02ac8fd339111aa7227"}