{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UEPS22F7R4GJI5AB5CI7AVUDEX","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":"a12cb1fa1e2ec97c2465d66c638d9fc068cd2ef8f6ba7aed34fd8a25d256739e","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-02T05:50:39Z","title_canon_sha256":"4fad277095ff039e7c76509344cd176df39c50ab053d0723188811949f1ea7b2"},"schema_version":"1.0","source":{"id":"2502.00678","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.00678","created_at":"2026-07-05T11:06:27Z"},{"alias_kind":"arxiv_version","alias_value":"2502.00678v2","created_at":"2026-07-05T11:06:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.00678","created_at":"2026-07-05T11:06:27Z"},{"alias_kind":"pith_short_12","alias_value":"UEPS22F7R4GJ","created_at":"2026-07-05T11:06:27Z"},{"alias_kind":"pith_short_16","alias_value":"UEPS22F7R4GJI5AB","created_at":"2026-07-05T11:06:27Z"},{"alias_kind":"pith_short_8","alias_value":"UEPS22F7","created_at":"2026-07-05T11:06:27Z"}],"graph_snapshots":[{"event_id":"sha256:044be3defd70d2be057622162fcc3e3e1a2420b19c3df8fec53d9c2ed5a8cc18","target":"graph","created_at":"2026-07-05T11:06:27Z","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/2502.00678/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Dataset contamination, where evaluation datasets overlap with pre-training corpora, inflates performance metrics and undermines the reliability of model evaluations. Measuring dataset contamination thus becomes essential to ensure that performance evaluations genuinely reflect a model's ability to generalize to unseen data, rather than relying on memorized examples. To address this problem, we propose Kernel Divergence Score (KDS), a novel method that evaluates dataset contamination by computing the divergence between the kernel similarity matrix of sample embeddings, before and after fine-tun","authors_text":"Hongxin Wei, Hyeong Kyu Choi, Maxim Khanov, Yixuan Li","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-02T05:50:39Z","title":"How Contaminated Is Your Benchmark? Quantifying Dataset Leakage in Large Language Models with Kernel Divergence"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.00678","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:cef1f2d7c5f6b21093690ad32c21f8d9ade6d4bfd6319b6ca0e539cb4151d3eb","target":"record","created_at":"2026-07-05T11:06:27Z","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":"a12cb1fa1e2ec97c2465d66c638d9fc068cd2ef8f6ba7aed34fd8a25d256739e","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-02T05:50:39Z","title_canon_sha256":"4fad277095ff039e7c76509344cd176df39c50ab053d0723188811949f1ea7b2"},"schema_version":"1.0","source":{"id":"2502.00678","kind":"arxiv","version":2}},"canonical_sha256":"a11f2d68bf8f0c947401e891f0568325d218e526f771be9a616601e9b0c7bb05","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a11f2d68bf8f0c947401e891f0568325d218e526f771be9a616601e9b0c7bb05","first_computed_at":"2026-07-05T11:06:27.519286Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:06:27.519286Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nDh1C57pxIwMV/xebtRZsDfANJyzNvgUwBa7RlLYzDEz+PS2d1+wowoEHf7A3sesmbZ68uzvm/ZOK5KFIj+DBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:06:27.519855Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.00678","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cef1f2d7c5f6b21093690ad32c21f8d9ade6d4bfd6319b6ca0e539cb4151d3eb","sha256:044be3defd70d2be057622162fcc3e3e1a2420b19c3df8fec53d9c2ed5a8cc18"],"state_sha256":"9d069f16141367fcaf90799099349b893d6c385d969fd77a10c19c96bac6918b"}