{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:74PTVZBMG4UGQLHPUZPNUTR6Y5","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":"cffdc3eb4bd170415122ef86e494fe508f316853c8a3500a2e3bd1c716a3e9e8","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2025-10-07T09:22:22Z","title_canon_sha256":"4e18b29d9f13a804e3375affd741e73cd68c186a7c9a39c801d0d03b6b16d288"},"schema_version":"1.0","source":{"id":"2510.05709","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.05709","created_at":"2026-06-05T01:15:16Z"},{"alias_kind":"arxiv_version","alias_value":"2510.05709v2","created_at":"2026-06-05T01:15:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.05709","created_at":"2026-06-05T01:15:16Z"},{"alias_kind":"pith_short_12","alias_value":"74PTVZBMG4UG","created_at":"2026-06-05T01:15:16Z"},{"alias_kind":"pith_short_16","alias_value":"74PTVZBMG4UGQLHP","created_at":"2026-06-05T01:15:16Z"},{"alias_kind":"pith_short_8","alias_value":"74PTVZBM","created_at":"2026-06-05T01:15:16Z"}],"graph_snapshots":[{"event_id":"sha256:9d20f969846bfba6ea1c47d276659f3e86a9c11fbd070b1f988bf9e47157807c","target":"graph","created_at":"2026-06-05T01:15:16Z","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/2510.05709/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"LLM benchmarking metrics often misstate performance and uncertainty as they rely on two assumptions that frequently do not hold in practice: (i) a sufficient number of evaluations are available for classical inference, and (ii) test prompts are independent. We propose a corrective Bayesian hierarchical model with embedding-space clustering that provides robust performance metrics in limited-data settings while correcting for prompt dependence. We apply the approach to adversarial robustness benchmarks, showing consistent recovery of clustering structure, resulting in more reliable performance ","authors_text":"Annie Gray, Isobel Thornton, James Bishop, Mary Llewellyn","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2025-10-07T09:22:22Z","title":"Correcting Prompt Dependence in LLM Benchmarks: A Bayesian Hierarchical Model with Embedding-Space Clustering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.05709","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":"sha256:05244254fbd2767f0caad2bf17258db7c1f3c9e1956f1f0624410ab88aa084f0","target":"record","created_at":"2026-06-05T01:15:16Z","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":"cffdc3eb4bd170415122ef86e494fe508f316853c8a3500a2e3bd1c716a3e9e8","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2025-10-07T09:22:22Z","title_canon_sha256":"4e18b29d9f13a804e3375affd741e73cd68c186a7c9a39c801d0d03b6b16d288"},"schema_version":"1.0","source":{"id":"2510.05709","kind":"arxiv","version":2}},"canonical_sha256":"ff1f3ae42c3728682cefa65eda4e3ec7460dc9dce9ce1805ad7980e3e97d89bc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ff1f3ae42c3728682cefa65eda4e3ec7460dc9dce9ce1805ad7980e3e97d89bc","first_computed_at":"2026-06-05T01:15:16.841830Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-05T01:15:16.841830Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"c0H8v85ezNy8c21h1bgillB5NPrMoek0FKjxBDNvLuvoNDFjKuV3iez5NZG5RWdHTiIiGk7nt24JA/OAYGPQAA==","signature_status":"signed_v1","signed_at":"2026-06-05T01:15:16.842755Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.05709","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:05244254fbd2767f0caad2bf17258db7c1f3c9e1956f1f0624410ab88aa084f0","sha256:9d20f969846bfba6ea1c47d276659f3e86a9c11fbd070b1f988bf9e47157807c"],"state_sha256":"10381fa43e6209840d240d0bec060e26cddd9cbe208a7c77494b979526080a7e"}