{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:5FP2D5NO6JDBKAC4XRRYNIYNKW","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":"4bc2c0a4316b5214693f3e05734176b6eaaeef5cec4598507dc573f103ec9ef6","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-16T11:03:04Z","title_canon_sha256":"8e8be7923f90e8911e71913086f49241ca53f97d948426fa8eecb073a5cc3484"},"schema_version":"1.0","source":{"id":"2311.09783","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.09783","created_at":"2026-07-05T08:04:16Z"},{"alias_kind":"arxiv_version","alias_value":"2311.09783v2","created_at":"2026-07-05T08:04:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.09783","created_at":"2026-07-05T08:04:16Z"},{"alias_kind":"pith_short_12","alias_value":"5FP2D5NO6JDB","created_at":"2026-07-05T08:04:16Z"},{"alias_kind":"pith_short_16","alias_value":"5FP2D5NO6JDBKAC4","created_at":"2026-07-05T08:04:16Z"},{"alias_kind":"pith_short_8","alias_value":"5FP2D5NO","created_at":"2026-07-05T08:04:16Z"}],"graph_snapshots":[{"event_id":"sha256:943ca5e4c585627be9289aa3351796215981d2c5c160d8e52eb67cf9295d2861","target":"graph","created_at":"2026-07-05T08:04:16Z","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/2311.09783/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent observations have underscored a disparity between the inflated benchmark scores and the actual performance of LLMs, raising concerns about potential contamination of evaluation benchmarks. This issue is especially critical for closed-source models and certain open-source models where training data transparency is lacking. In this paper we study data contamination by proposing two methods tailored for both open-source and proprietary LLMs. We first introduce a retrieval-based system to explore potential overlaps between evaluation benchmarks and pretraining corpora. We further present a ","authors_text":"Arman Cohan, Chunyuan Deng, Mark Gerstein, Xiangru Tang, Yilun Zhao","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-16T11:03:04Z","title":"Investigating Data Contamination in Modern Benchmarks for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.09783","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":"sha256:284fe10f4d45c12555a2d9b2d28fb8bd8a66a1e9858981b1f21aff95d245ab5d","target":"record","created_at":"2026-07-05T08:04:16Z","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":"4bc2c0a4316b5214693f3e05734176b6eaaeef5cec4598507dc573f103ec9ef6","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-16T11:03:04Z","title_canon_sha256":"8e8be7923f90e8911e71913086f49241ca53f97d948426fa8eecb073a5cc3484"},"schema_version":"1.0","source":{"id":"2311.09783","kind":"arxiv","version":2}},"canonical_sha256":"e95fa1f5aef24615005cbc6386a30d55b5aa0db6ba538e06847384deb636bd64","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e95fa1f5aef24615005cbc6386a30d55b5aa0db6ba538e06847384deb636bd64","first_computed_at":"2026-07-05T08:04:16.024474Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:04:16.024474Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MbQokWUl3HCJZlgFqdgWcIEaSTS+38y8yTHWODigA3XwVuVjWLMP3Hxh5l9ayfL8UX2ths+BdFZp9CVbd0AdAg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:04:16.024884Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.09783","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:284fe10f4d45c12555a2d9b2d28fb8bd8a66a1e9858981b1f21aff95d245ab5d","sha256:943ca5e4c585627be9289aa3351796215981d2c5c160d8e52eb67cf9295d2861"],"state_sha256":"db6a97ddd29cfd6eb6bef384b1d6db3c065e9f8aa928cc1a4b5ddb479d8c1002"}