{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:UBXHA6HCOLGEQFA7MCTV4M7K42","short_pith_number":"pith:UBXHA6HC","canonical_record":{"source":{"id":"2405.16281","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-25T15:36:37Z","cross_cats_sorted":[],"title_canon_sha256":"804025135ca614cce748b048e87a864ce27eb541485b553cd192675e6e8e09bd","abstract_canon_sha256":"6b687ff630ebc8c977e8b877b7c05831475655bb67477e9abf270d757b4e15e3"},"schema_version":"1.0"},"canonical_sha256":"a06e7078e272cc48141f60a75e33eae69cf4ceb424821aad0991ccbf8fc51291","source":{"kind":"arxiv","id":"2405.16281","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.16281","created_at":"2026-07-05T08:23:28Z"},{"alias_kind":"arxiv_version","alias_value":"2405.16281v1","created_at":"2026-07-05T08:23:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.16281","created_at":"2026-07-05T08:23:28Z"},{"alias_kind":"pith_short_12","alias_value":"UBXHA6HCOLGE","created_at":"2026-07-05T08:23:28Z"},{"alias_kind":"pith_short_16","alias_value":"UBXHA6HCOLGEQFA7","created_at":"2026-07-05T08:23:28Z"},{"alias_kind":"pith_short_8","alias_value":"UBXHA6HC","created_at":"2026-07-05T08:23:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:UBXHA6HCOLGEQFA7MCTV4M7K42","target":"record","payload":{"canonical_record":{"source":{"id":"2405.16281","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-25T15:36:37Z","cross_cats_sorted":[],"title_canon_sha256":"804025135ca614cce748b048e87a864ce27eb541485b553cd192675e6e8e09bd","abstract_canon_sha256":"6b687ff630ebc8c977e8b877b7c05831475655bb67477e9abf270d757b4e15e3"},"schema_version":"1.0"},"canonical_sha256":"a06e7078e272cc48141f60a75e33eae69cf4ceb424821aad0991ccbf8fc51291","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:23:28.118898Z","signature_b64":"c8FXm1eEEkmhYh0U1jt1tZhtKT1DiChlajkthtv+ZiCk9aYHRONxKqOUOkxke1L57hj7kZoXX7xQr1T8bvx/Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a06e7078e272cc48141f60a75e33eae69cf4ceb424821aad0991ccbf8fc51291","last_reissued_at":"2026-07-05T08:23:28.118386Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:23:28.118386Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.16281","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:23:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3joz9dGbdDq4k/Nw3vmRdta+5WnOfmuCY2kbeHAly3MeGidRaq2gUSsBMJdYfWRHeZ7LvcAd+uDRjRhwFOjJDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T15:49:00.329507Z"},"content_sha256":"796e2a6bdf0b7fd6eaf57a3a84c8415fb228cf151eccbcda8e68a9a08f104632","schema_version":"1.0","event_id":"sha256:796e2a6bdf0b7fd6eaf57a3a84c8415fb228cf151eccbcda8e68a9a08f104632"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:UBXHA6HCOLGEQFA7MCTV4M7K42","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ConStat: Performance-Based Contamination Detection in Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jasper Dekoninck, Mark Niklas M\\\"uller, Martin Vechev","submitted_at":"2024-05-25T15:36:37Z","abstract_excerpt":"Public benchmarks play an essential role in the evaluation of large language models. However, data contamination can lead to inflated performance, rendering them unreliable for model comparison. It is therefore crucial to detect contamination and estimate its impact on measured performance. Unfortunately, existing detection methods can be easily evaded and fail to quantify contamination. To overcome these limitations, we propose a novel definition of contamination as artificially inflated and non-generalizing benchmark performance instead of the inclusion of benchmark samples in the training d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.16281","kind":"arxiv","version":1},"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/2405.16281/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":"2026-07-05T08:23:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4IbnHQMR7OLmKMGv3UqurSzeUXVAZwDAIOKIyINfh1G4eeEWatK71ujVQUmnEM8+EMsyJL/3pSCMfbtdJuyvCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T15:49:00.329881Z"},"content_sha256":"469d77fa2f1f4cbfd0071e130bfcecd4dde81f6930a8e86a42111923cc26132b","schema_version":"1.0","event_id":"sha256:469d77fa2f1f4cbfd0071e130bfcecd4dde81f6930a8e86a42111923cc26132b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UBXHA6HCOLGEQFA7MCTV4M7K42/bundle.json","state_url":"https://pith.science/pith/UBXHA6HCOLGEQFA7MCTV4M7K42/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UBXHA6HCOLGEQFA7MCTV4M7K42/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":"2026-07-06T15:49:00Z","links":{"resolver":"https://pith.science/pith/UBXHA6HCOLGEQFA7MCTV4M7K42","bundle":"https://pith.science/pith/UBXHA6HCOLGEQFA7MCTV4M7K42/bundle.json","state":"https://pith.science/pith/UBXHA6HCOLGEQFA7MCTV4M7K42/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UBXHA6HCOLGEQFA7MCTV4M7K42/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UBXHA6HCOLGEQFA7MCTV4M7K42","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":"6b687ff630ebc8c977e8b877b7c05831475655bb67477e9abf270d757b4e15e3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-25T15:36:37Z","title_canon_sha256":"804025135ca614cce748b048e87a864ce27eb541485b553cd192675e6e8e09bd"},"schema_version":"1.0","source":{"id":"2405.16281","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.16281","created_at":"2026-07-05T08:23:28Z"},{"alias_kind":"arxiv_version","alias_value":"2405.16281v1","created_at":"2026-07-05T08:23:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.16281","created_at":"2026-07-05T08:23:28Z"},{"alias_kind":"pith_short_12","alias_value":"UBXHA6HCOLGE","created_at":"2026-07-05T08:23:28Z"},{"alias_kind":"pith_short_16","alias_value":"UBXHA6HCOLGEQFA7","created_at":"2026-07-05T08:23:28Z"},{"alias_kind":"pith_short_8","alias_value":"UBXHA6HC","created_at":"2026-07-05T08:23:28Z"}],"graph_snapshots":[{"event_id":"sha256:469d77fa2f1f4cbfd0071e130bfcecd4dde81f6930a8e86a42111923cc26132b","target":"graph","created_at":"2026-07-05T08:23:28Z","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/2405.16281/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Public benchmarks play an essential role in the evaluation of large language models. However, data contamination can lead to inflated performance, rendering them unreliable for model comparison. It is therefore crucial to detect contamination and estimate its impact on measured performance. Unfortunately, existing detection methods can be easily evaded and fail to quantify contamination. To overcome these limitations, we propose a novel definition of contamination as artificially inflated and non-generalizing benchmark performance instead of the inclusion of benchmark samples in the training d","authors_text":"Jasper Dekoninck, Mark Niklas M\\\"uller, Martin Vechev","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-25T15:36:37Z","title":"ConStat: Performance-Based Contamination Detection in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.16281","kind":"arxiv","version":1},"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":"sha256:796e2a6bdf0b7fd6eaf57a3a84c8415fb228cf151eccbcda8e68a9a08f104632","target":"record","created_at":"2026-07-05T08:23:28Z","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":"6b687ff630ebc8c977e8b877b7c05831475655bb67477e9abf270d757b4e15e3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-25T15:36:37Z","title_canon_sha256":"804025135ca614cce748b048e87a864ce27eb541485b553cd192675e6e8e09bd"},"schema_version":"1.0","source":{"id":"2405.16281","kind":"arxiv","version":1}},"canonical_sha256":"a06e7078e272cc48141f60a75e33eae69cf4ceb424821aad0991ccbf8fc51291","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a06e7078e272cc48141f60a75e33eae69cf4ceb424821aad0991ccbf8fc51291","first_computed_at":"2026-07-05T08:23:28.118386Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:23:28.118386Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"c8FXm1eEEkmhYh0U1jt1tZhtKT1DiChlajkthtv+ZiCk9aYHRONxKqOUOkxke1L57hj7kZoXX7xQr1T8bvx/Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:23:28.118898Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.16281","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:796e2a6bdf0b7fd6eaf57a3a84c8415fb228cf151eccbcda8e68a9a08f104632","sha256:469d77fa2f1f4cbfd0071e130bfcecd4dde81f6930a8e86a42111923cc26132b"],"state_sha256":"e9358ec4a68c048d67b39b560c27e84f2abd5aa60487e49e47b31ccc690e34e9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hAJYRG6Fp4KDkQvU3hp0jThIsLlICGwN7msTm32lXwz3BX82C1n1ohOrBQ9Y0OIaBgnKCziFZ1sr4ZMvvyR0AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T15:49:00.331839Z","bundle_sha256":"575d9b667934bda14a43d9989e75704b7f16b97c2d823db631fecd6a05ee396b"}}