{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NTHOJ7F6HAFFGEPKJBPWHP4RUO","short_pith_number":"pith:NTHOJ7F6","schema_version":"1.0","canonical_sha256":"6ccee4fcbe380a5311ea485f63bf91a39ce9d4bb4f4604f461b698d7e698d1ba","source":{"kind":"arxiv","id":"2409.09927","version":2},"attestation_state":"computed","paper":{"title":"Towards Data Contamination Detection for Modern Large Language Models: Limitations, Inconsistencies, and Oracle Challenges","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Henry Peng Zou, Vinay Samuel, Yue Zhou","submitted_at":"2024-09-16T02:04:33Z","abstract_excerpt":"As large language models achieve increasingly impressive results, questions arise about whether such performance is from generalizability or mere data memorization. Thus, numerous data contamination detection methods have been proposed. However, these approaches are often validated with traditional benchmarks and early-stage LLMs, leaving uncertainty about their effectiveness when evaluating state-of-the-art LLMs on the contamination of more challenging benchmarks. To address this gap and provide a dual investigation of SOTA LLM contamination status and detection method robustness, we evaluate"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2409.09927","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-16T02:04:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5c32a45a4f90c32b6c093eca2656b5d30e4add677290f66228601b8a3815bf19","abstract_canon_sha256":"55dd6425bf07ddbabb37224a0a20738c776a4c6e4db8db30fa8439f9b4739e75"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:45:54.834257Z","signature_b64":"zGgDkXiKFFrJGg3TgjKW/X0rPaT7K/YHFCF2d8kX+sTaR9Lyba+vqIfTwWpk6a5epnmpiqfoiVu4y/yl0KabBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ccee4fcbe380a5311ea485f63bf91a39ce9d4bb4f4604f461b698d7e698d1ba","last_reissued_at":"2026-07-05T09:45:54.833779Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:45:54.833779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Data Contamination Detection for Modern Large Language Models: Limitations, Inconsistencies, and Oracle Challenges","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Henry Peng Zou, Vinay Samuel, Yue Zhou","submitted_at":"2024-09-16T02:04:33Z","abstract_excerpt":"As large language models achieve increasingly impressive results, questions arise about whether such performance is from generalizability or mere data memorization. Thus, numerous data contamination detection methods have been proposed. However, these approaches are often validated with traditional benchmarks and early-stage LLMs, leaving uncertainty about their effectiveness when evaluating state-of-the-art LLMs on the contamination of more challenging benchmarks. To address this gap and provide a dual investigation of SOTA LLM contamination status and detection method robustness, we evaluate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.09927","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2409.09927/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2409.09927","created_at":"2026-07-05T09:45:54.833837+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.09927v2","created_at":"2026-07-05T09:45:54.833837+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.09927","created_at":"2026-07-05T09:45:54.833837+00:00"},{"alias_kind":"pith_short_12","alias_value":"NTHOJ7F6HAFF","created_at":"2026-07-05T09:45:54.833837+00:00"},{"alias_kind":"pith_short_16","alias_value":"NTHOJ7F6HAFFGEPK","created_at":"2026-07-05T09:45:54.833837+00:00"},{"alias_kind":"pith_short_8","alias_value":"NTHOJ7F6","created_at":"2026-07-05T09:45:54.833837+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.26133","citing_title":"Pretraining Data Exposure in Large Language Models: A Survey of Membership Inference, Data Contamination, and Security Implications","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NTHOJ7F6HAFFGEPKJBPWHP4RUO","json":"https://pith.science/pith/NTHOJ7F6HAFFGEPKJBPWHP4RUO.json","graph_json":"https://pith.science/api/pith-number/NTHOJ7F6HAFFGEPKJBPWHP4RUO/graph.json","events_json":"https://pith.science/api/pith-number/NTHOJ7F6HAFFGEPKJBPWHP4RUO/events.json","paper":"https://pith.science/paper/NTHOJ7F6"},"agent_actions":{"view_html":"https://pith.science/pith/NTHOJ7F6HAFFGEPKJBPWHP4RUO","download_json":"https://pith.science/pith/NTHOJ7F6HAFFGEPKJBPWHP4RUO.json","view_paper":"https://pith.science/paper/NTHOJ7F6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.09927&json=true","fetch_graph":"https://pith.science/api/pith-number/NTHOJ7F6HAFFGEPKJBPWHP4RUO/graph.json","fetch_events":"https://pith.science/api/pith-number/NTHOJ7F6HAFFGEPKJBPWHP4RUO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NTHOJ7F6HAFFGEPKJBPWHP4RUO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NTHOJ7F6HAFFGEPKJBPWHP4RUO/action/storage_attestation","attest_author":"https://pith.science/pith/NTHOJ7F6HAFFGEPKJBPWHP4RUO/action/author_attestation","sign_citation":"https://pith.science/pith/NTHOJ7F6HAFFGEPKJBPWHP4RUO/action/citation_signature","submit_replication":"https://pith.science/pith/NTHOJ7F6HAFFGEPKJBPWHP4RUO/action/replication_record"}},"created_at":"2026-07-05T09:45:54.833837+00:00","updated_at":"2026-07-05T09:45:54.833837+00:00"}