{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:BGRULHLZNUUTXKJZINGIKWOBDJ","merge_version":"pith-open-graph-merge-v1","event_count":16,"valid_event_count":16,"invalid_event_count":0,"equivocation_count":1,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"6dda7a0559621e1148817af99ac77cf224857ec31db23d34d62502a40cf6dd1e","cross_cats_sorted":["cs.AI","cs.CR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-19T15:33:16Z","title_canon_sha256":"059ead94e76a7e85633f5d4b145c050d2fd31b851101920584dd39d41e227ca1"},"schema_version":"1.0","source":{"id":"2605.19999","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.19999","created_at":"2026-05-20T02:05:58Z"},{"alias_kind":"arxiv_version","alias_value":"2605.19999v1","created_at":"2026-05-20T02:05:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.19999","created_at":"2026-05-20T02:05:58Z"},{"alias_kind":"pith_short_12","alias_value":"BGRULHLZNUUT","created_at":"2026-05-20T02:05:58Z"},{"alias_kind":"pith_short_16","alias_value":"BGRULHLZNUUTXKJZ","created_at":"2026-05-20T02:05:58Z"},{"alias_kind":"pith_short_8","alias_value":"BGRULHLZ","created_at":"2026-05-20T02:05:58Z"}],"graph_snapshots":[{"event_id":"sha256:99c50b6ce84f3eb8101a27dad4f6079bde6347e36cc056f917331b01c10c5942","target":"graph","created_at":"2026-05-20T02:05:58Z","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/2605.19999/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Benchmark datasets are critical for reproducible, reliable, and discriminative evaluation of LLMs. However, recent studies reveal that many benchmark datasets are included in pretraining corpora, i.e., $\\textit{contaminated}$, which diminishes their value as reliable measures of model generalization. In this paper, we argue that benchmark datasets should be $\\textit{contamination-resistant}$, i.e., $\\textit{unlearnable}$, but support $\\textit{inference}$. To accomplish this, we first highlight the wide prevalence of benchmark dataset contamination and outline the properties of contamination-re","authors_text":"Ali Al-Lawati, Dongwon Lee, Jason Lucas, Suhang Wang","cross_cats":["cs.AI","cs.CR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-19T15:33:16Z","title":"LLM Benchmark Datasets Should Be Contamination-Resistant"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.19999","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":"sha256:3aa9098563bd5e0450d42674cd2279d71b505699e321c7d50e19ba5f9eb9b806","target":"record","created_at":"2026-05-20T02:05:58Z","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":"6dda7a0559621e1148817af99ac77cf224857ec31db23d34d62502a40cf6dd1e","cross_cats_sorted":["cs.AI","cs.CR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-19T15:33:16Z","title_canon_sha256":"059ead94e76a7e85633f5d4b145c050d2fd31b851101920584dd39d41e227ca1"},"schema_version":"1.0","source":{"id":"2605.19999","kind":"arxiv","version":1}},"canonical_sha256":"09a3459d796d293ba939434c8559c11a46b2ef430c2cee29ee7b4ec5dfacad02","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"09a3459d796d293ba939434c8559c11a46b2ef430c2cee29ee7b4ec5dfacad02","first_computed_at":"2026-05-20T02:05:58.550948Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T02:05:58.550948Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7vD7GbFkjU5Mp0EwotcMOOc+IIFQ9hPwUQLq/GZHRkIvAh52K6VZQeatQ3poIiT9iwPSohOsJawkdT5IgDeqCw==","signature_status":"signed_v1","signed_at":"2026-05-20T02:05:58.551443Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.19999","source_kind":"arxiv","source_version":1}}},"equivocations":[{"signer_id":"pith.science","event_type":"integrity_finding","target":"integrity","event_ids":["sha256:04a150eb6b68e974a7b662c6a2a16a8992804e9355e5092ce09afa35ff0fa4b3","sha256:06a6b79f39b8669503e993d91642666c084880814c4a1059c37e73ce655ad69d","sha256:111332c0fb4bbca9be2a750165ac99f82a2dc22a48edd9063148ab48e9178076","sha256:173ebfa35304b26d3e2bbd60dd2c3c36bf7732d1e49d80fb63652b8dfdda40d9","sha256:190cfc1a0b48bb126bdabb09c8f345d6c3704c82dcfdd24688aa00c821c4d3d9","sha256:1cf2e8f67dcbffa5ed047605f7570b42327a413865f2cea6de17fae41e6b53b0","sha256:310999c0f074b2988d438dbc676f27c39dd511cd5f1c8181af41a1e2d742daa6","sha256:67502ca32050b35efe158e1db53daf0005203eed4c0a32492ee38f0e35986c2d","sha256:78c4cfd4a7d2f945c2b0e9c1b80d2bfa92bce64f64af4567934c7defc9a11ff3","sha256:903c0cb0713b05f0a5ee7ce5f3608b869fcd29b2fe7e7c7ea85c79a4ffc444a6","sha256:94f51ebf25b87b3c85106ca68e105437803a7ae8a38ef1176e1b371383112c89","sha256:a1014426a2db556e0603b7a5b182c27b8ae42ababd6a633defabcc10481ef071","sha256:a3d244f0e09c0df8f6270da62e43372d17c9e0c6853b4d4e2265a4aa4703e5b5","sha256:bd19744409caa3d9d23f21d9049aa1d209817f8668776adc981a3fce7aa73bcd"]}],"invalid_events":[],"applied_event_ids":["sha256:3aa9098563bd5e0450d42674cd2279d71b505699e321c7d50e19ba5f9eb9b806","sha256:99c50b6ce84f3eb8101a27dad4f6079bde6347e36cc056f917331b01c10c5942"],"state_sha256":"71ff429eecd32036f3466bb903ef5f8da514171c645c6648c53b12bf70237064"}