{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OU3IBEBODLXZBRKAL4JG5UG6Z7","short_pith_number":"pith:OU3IBEBO","schema_version":"1.0","canonical_sha256":"753680902e1aef90c5405f126ed0decfecf84d2437185f2bde39ceb7cacdc62b","source":{"kind":"arxiv","id":"2402.03927","version":2},"attestation_state":"computed","paper":{"title":"Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Mateusz Lango, Ond\\v{r}ej Du\\v{s}ek, Patr\\'icia Schmidtov\\'a, Simone Balloccu","submitted_at":"2024-02-06T11:54:23Z","abstract_excerpt":"Natural Language Processing (NLP) research is increasingly focusing on the use of Large Language Models (LLMs), with some of the most popular ones being either fully or partially closed-source. The lack of access to model details, especially regarding training data, has repeatedly raised concerns about data contamination among researchers. Several attempts have been made to address this issue, but they are limited to anecdotal evidence and trial and error. Additionally, they overlook the problem of \\emph{indirect} data leaking, where models are iteratively improved by using data coming from us"},"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":"2402.03927","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-06T11:54:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bd95dddbfeb7ce5a30476b00c647a1bd055f954bdfe3ad3150ef910e514d50aa","abstract_canon_sha256":"29beb6563d01ec3dd62803741a085a1fd97b9de8d093b9ed03114a81ae1c37a9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:48:03.478202Z","signature_b64":"dnppt0DgRvSo0alakHmuP/XjAr5MpR7Md0Gfsab6xVvbkmv34RC5cyspdjr5//h7kND0e/Xsfx0YeGaLLlOECw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"753680902e1aef90c5405f126ed0decfecf84d2437185f2bde39ceb7cacdc62b","last_reissued_at":"2026-07-05T07:48:03.477648Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:48:03.477648Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Mateusz Lango, Ond\\v{r}ej Du\\v{s}ek, Patr\\'icia Schmidtov\\'a, Simone Balloccu","submitted_at":"2024-02-06T11:54:23Z","abstract_excerpt":"Natural Language Processing (NLP) research is increasingly focusing on the use of Large Language Models (LLMs), with some of the most popular ones being either fully or partially closed-source. The lack of access to model details, especially regarding training data, has repeatedly raised concerns about data contamination among researchers. Several attempts have been made to address this issue, but they are limited to anecdotal evidence and trial and error. Additionally, they overlook the problem of \\emph{indirect} data leaking, where models are iteratively improved by using data coming from us"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.03927","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/2402.03927/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":"2402.03927","created_at":"2026-07-05T07:48:03.477714+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.03927v2","created_at":"2026-07-05T07:48:03.477714+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.03927","created_at":"2026-07-05T07:48:03.477714+00:00"},{"alias_kind":"pith_short_12","alias_value":"OU3IBEBODLXZ","created_at":"2026-07-05T07:48:03.477714+00:00"},{"alias_kind":"pith_short_16","alias_value":"OU3IBEBODLXZBRKA","created_at":"2026-07-05T07:48:03.477714+00:00"},{"alias_kind":"pith_short_8","alias_value":"OU3IBEBO","created_at":"2026-07-05T07:48:03.477714+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03305","citing_title":"The Reliability Gap in Benchmark Auditing: Distribution Shift and Scale as Failure Modes of Contamination Detection","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03305","citing_title":"The Reliability Gap in Benchmark Auditing: Distribution Shift and Scale as Failure Modes of Contamination Detection","ref_index":2,"is_internal_anchor":false},{"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":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17829","citing_title":"Interactive Evaluation Requires a Design Science","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2511.02627","citing_title":"DecompSR: A dataset for decomposed analyses of compositional multihop spatial reasoning","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04852","citing_title":"Strengthening Human-Centric Chain-of-Thought Reasoning Integrity in LLMs via a Structured Prompt Framework","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OU3IBEBODLXZBRKAL4JG5UG6Z7","json":"https://pith.science/pith/OU3IBEBODLXZBRKAL4JG5UG6Z7.json","graph_json":"https://pith.science/api/pith-number/OU3IBEBODLXZBRKAL4JG5UG6Z7/graph.json","events_json":"https://pith.science/api/pith-number/OU3IBEBODLXZBRKAL4JG5UG6Z7/events.json","paper":"https://pith.science/paper/OU3IBEBO"},"agent_actions":{"view_html":"https://pith.science/pith/OU3IBEBODLXZBRKAL4JG5UG6Z7","download_json":"https://pith.science/pith/OU3IBEBODLXZBRKAL4JG5UG6Z7.json","view_paper":"https://pith.science/paper/OU3IBEBO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.03927&json=true","fetch_graph":"https://pith.science/api/pith-number/OU3IBEBODLXZBRKAL4JG5UG6Z7/graph.json","fetch_events":"https://pith.science/api/pith-number/OU3IBEBODLXZBRKAL4JG5UG6Z7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OU3IBEBODLXZBRKAL4JG5UG6Z7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OU3IBEBODLXZBRKAL4JG5UG6Z7/action/storage_attestation","attest_author":"https://pith.science/pith/OU3IBEBODLXZBRKAL4JG5UG6Z7/action/author_attestation","sign_citation":"https://pith.science/pith/OU3IBEBODLXZBRKAL4JG5UG6Z7/action/citation_signature","submit_replication":"https://pith.science/pith/OU3IBEBODLXZBRKAL4JG5UG6Z7/action/replication_record"}},"created_at":"2026-07-05T07:48:03.477714+00:00","updated_at":"2026-07-05T07:48:03.477714+00:00"}