{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:UEPS22F7R4GJI5AB5CI7AVUDEX","short_pith_number":"pith:UEPS22F7","canonical_record":{"source":{"id":"2502.00678","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-02T05:50:39Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"4fad277095ff039e7c76509344cd176df39c50ab053d0723188811949f1ea7b2","abstract_canon_sha256":"a12cb1fa1e2ec97c2465d66c638d9fc068cd2ef8f6ba7aed34fd8a25d256739e"},"schema_version":"1.0"},"canonical_sha256":"a11f2d68bf8f0c947401e891f0568325d218e526f771be9a616601e9b0c7bb05","source":{"kind":"arxiv","id":"2502.00678","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:UEPS22F7R4GJI5AB5CI7AVUDEX","target":"record","payload":{"canonical_record":{"source":{"id":"2502.00678","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-02T05:50:39Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"4fad277095ff039e7c76509344cd176df39c50ab053d0723188811949f1ea7b2","abstract_canon_sha256":"a12cb1fa1e2ec97c2465d66c638d9fc068cd2ef8f6ba7aed34fd8a25d256739e"},"schema_version":"1.0"},"canonical_sha256":"a11f2d68bf8f0c947401e891f0568325d218e526f771be9a616601e9b0c7bb05","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:06:27.519855Z","signature_b64":"nDh1C57pxIwMV/xebtRZsDfANJyzNvgUwBa7RlLYzDEz+PS2d1+wowoEHf7A3sesmbZ68uzvm/ZOK5KFIj+DBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a11f2d68bf8f0c947401e891f0568325d218e526f771be9a616601e9b0c7bb05","last_reissued_at":"2026-07-05T11:06:27.519286Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:06:27.519286Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.00678","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:06:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ml9T0E/7bC8GqRb85yGfPyCeRq4a51+lFQgqWDFJV9TWaNPahxL8QAnu/uY0v8NH/9iFrCoK5bN5Na5toJqBAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T06:44:30.734714Z"},"content_sha256":"cef1f2d7c5f6b21093690ad32c21f8d9ade6d4bfd6319b6ca0e539cb4151d3eb","schema_version":"1.0","event_id":"sha256:cef1f2d7c5f6b21093690ad32c21f8d9ade6d4bfd6319b6ca0e539cb4151d3eb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:UEPS22F7R4GJI5AB5CI7AVUDEX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"How Contaminated Is Your Benchmark? Quantifying Dataset Leakage in Large Language Models with Kernel Divergence","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Hongxin Wei, Hyeong Kyu Choi, Maxim Khanov, Yixuan Li","submitted_at":"2025-02-02T05:50:39Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.00678","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/2502.00678/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:06:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rhXFBW62zDGitSy8unHvB2XGb0iSTxgRAzdsxR/dQL5+GZ9UQIr1KPMXaRq0yH225gBHULnjiGZIAI3vOgBBAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T06:44:30.735234Z"},"content_sha256":"044be3defd70d2be057622162fcc3e3e1a2420b19c3df8fec53d9c2ed5a8cc18","schema_version":"1.0","event_id":"sha256:044be3defd70d2be057622162fcc3e3e1a2420b19c3df8fec53d9c2ed5a8cc18"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UEPS22F7R4GJI5AB5CI7AVUDEX/bundle.json","state_url":"https://pith.science/pith/UEPS22F7R4GJI5AB5CI7AVUDEX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UEPS22F7R4GJI5AB5CI7AVUDEX/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T06:44:30Z","links":{"resolver":"https://pith.science/pith/UEPS22F7R4GJI5AB5CI7AVUDEX","bundle":"https://pith.science/pith/UEPS22F7R4GJI5AB5CI7AVUDEX/bundle.json","state":"https://pith.science/pith/UEPS22F7R4GJI5AB5CI7AVUDEX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UEPS22F7R4GJI5AB5CI7AVUDEX/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3Rupw8lI9HdXfi7yvj0HkXoTXl76RwtC0RBWXEMptgVDF7+gJtpnhgPNLSobHK7Fr5a15YlSebH6IoqeWxtjAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T06:44:30.740826Z","bundle_sha256":"5c68d930565a6f8a6d68f8e1ceb35cebd68738045a9ea62919c7944e877e1548"}}