{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:32NFY22FY52USPXXMYDOR6GR3E","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":"d018a10666ae5b07df4bd965037ea2ba82f55aad5a05527685e1e01b3b943123","cross_cats_sorted":["cs.AI","cs.CR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-16T16:48:57Z","title_canon_sha256":"5a6829efe222142752a94fceb73bd5e46c3b5b452b766ec6ddc2264d54fbac04"},"schema_version":"1.0","source":{"id":"2308.08493","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.08493","created_at":"2026-07-05T07:47:58Z"},{"alias_kind":"arxiv_version","alias_value":"2308.08493v3","created_at":"2026-07-05T07:47:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.08493","created_at":"2026-07-05T07:47:58Z"},{"alias_kind":"pith_short_12","alias_value":"32NFY22FY52U","created_at":"2026-07-05T07:47:58Z"},{"alias_kind":"pith_short_16","alias_value":"32NFY22FY52USPXX","created_at":"2026-07-05T07:47:58Z"},{"alias_kind":"pith_short_8","alias_value":"32NFY22F","created_at":"2026-07-05T07:47:58Z"}],"graph_snapshots":[{"event_id":"sha256:85e17cea34438bc1a2b36a7808920fa5ef0639da8440bbb34271e3c6f4edf3e8","target":"graph","created_at":"2026-07-05T07:47:58Z","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/2308.08493/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data contamination, i.e., the presence of test data from downstream tasks in the training data of large language models (LLMs), is a potential major issue in measuring LLMs' real effectiveness on other tasks. We propose a straightforward yet effective method for identifying data contamination within LLMs. At its core, our approach starts by identifying potential contamination at the instance level; using this information, our approach then assesses wider contamination at the partition level. To estimate contamination of individual instances, we employ \"guided instruction:\" a prompt consisting ","authors_text":"Mihai Surdeanu, Shahriar Golchin","cross_cats":["cs.AI","cs.CR","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-16T16:48:57Z","title":"Time Travel in LLMs: Tracing Data Contamination in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.08493","kind":"arxiv","version":3},"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":"sha256:1ea443f2669e8f1ff6dcaa80e89218042dccf7eef797e2397242492cbebd17d5","target":"record","created_at":"2026-07-05T07:47:58Z","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":"d018a10666ae5b07df4bd965037ea2ba82f55aad5a05527685e1e01b3b943123","cross_cats_sorted":["cs.AI","cs.CR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-16T16:48:57Z","title_canon_sha256":"5a6829efe222142752a94fceb73bd5e46c3b5b452b766ec6ddc2264d54fbac04"},"schema_version":"1.0","source":{"id":"2308.08493","kind":"arxiv","version":3}},"canonical_sha256":"de9a5c6b45c775493ef76606e8f8d1d934b4a4a8c6036b61b2d1a8e9556feac3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"de9a5c6b45c775493ef76606e8f8d1d934b4a4a8c6036b61b2d1a8e9556feac3","first_computed_at":"2026-07-05T07:47:58.442200Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:47:58.442200Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ab6Ac+A9pHDPIjd7jdTW7L3ccfQtW0VQvwbyT5I6egj8zQxugEcZ8/8pDQ5uHgvgymeFc/dNAUMXzW5rZsPjDg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:47:58.442777Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.08493","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1ea443f2669e8f1ff6dcaa80e89218042dccf7eef797e2397242492cbebd17d5","sha256:85e17cea34438bc1a2b36a7808920fa5ef0639da8440bbb34271e3c6f4edf3e8"],"state_sha256":"6fad4795fccf1563ee12b38ac7b620d6dd229c25e84a495f8245187754dbb571"}