{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LK2FMP73IGWNYNS32FPYHKBVCR","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":"2592a67e1d2845f71f66277b95d9dd9a22d331c95eb2dc6821bf5e9701fe1604","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-25T18:35:54Z","title_canon_sha256":"b37d0bce3a0f8b6ee224a38cf6f46297cc2967fc0e2e045a01ab90e9f0880b90"},"schema_version":"1.0","source":{"id":"2404.16966","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.16966","created_at":"2026-07-05T08:28:09Z"},{"alias_kind":"arxiv_version","alias_value":"2404.16966v2","created_at":"2026-07-05T08:28:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.16966","created_at":"2026-07-05T08:28:09Z"},{"alias_kind":"pith_short_12","alias_value":"LK2FMP73IGWN","created_at":"2026-07-05T08:28:09Z"},{"alias_kind":"pith_short_16","alias_value":"LK2FMP73IGWNYNS3","created_at":"2026-07-05T08:28:09Z"},{"alias_kind":"pith_short_8","alias_value":"LK2FMP73","created_at":"2026-07-05T08:28:09Z"}],"graph_snapshots":[{"event_id":"sha256:b3bc15ffa15bdc3c62646552c9cee38c38aaa5fe06e35ccdb6a0f495d7fdad6e","target":"graph","created_at":"2026-07-05T08:28:09Z","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/2404.16966/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Benchmarks have emerged as the central approach for evaluating Large Language Models (LLMs). The research community often relies on a model's average performance across the test prompts of a benchmark to evaluate the model's performance. This is consistent with the assumption that the test prompts within a benchmark represent a random sample from a real-world distribution of interest. We note that this is generally not the case; instead, we hold that the distribution of interest varies according to the specific use case. We find that (1) the correlation in model performance across test prompts","authors_text":"Charlotte Siska, James Bono, Katerina Marazopoulou, Melissa Ailem","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-25T18:35:54Z","title":"Examining the robustness of LLM evaluation to the distributional assumptions of benchmarks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.16966","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":"sha256:6254a41f2abb6df447df878310d976fa8bf452254df8f8a70e4875b1d7b74820","target":"record","created_at":"2026-07-05T08:28:09Z","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":"2592a67e1d2845f71f66277b95d9dd9a22d331c95eb2dc6821bf5e9701fe1604","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-25T18:35:54Z","title_canon_sha256":"b37d0bce3a0f8b6ee224a38cf6f46297cc2967fc0e2e045a01ab90e9f0880b90"},"schema_version":"1.0","source":{"id":"2404.16966","kind":"arxiv","version":2}},"canonical_sha256":"5ab4563ffb41acdc365bd15f83a835145239e62fe79a715921fdde2b44f13c15","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5ab4563ffb41acdc365bd15f83a835145239e62fe79a715921fdde2b44f13c15","first_computed_at":"2026-07-05T08:28:09.487943Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:28:09.487943Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fwMTlBz1FLqimKlPMCyopygKHf0IkZnrNqT/b4FXepqcWWpp6wC3CPUXos17zU9fJZVZE44fpZI7XLrSMKqTBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:28:09.488404Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.16966","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6254a41f2abb6df447df878310d976fa8bf452254df8f8a70e4875b1d7b74820","sha256:b3bc15ffa15bdc3c62646552c9cee38c38aaa5fe06e35ccdb6a0f495d7fdad6e"],"state_sha256":"016e48ef30f48a0e43b362ff45db633c9b6c5b504393b217b2908b37db328b9a"}