{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:GBLILWNNFWQ3KMG575V2DTZVPG","short_pith_number":"pith:GBLILWNN","canonical_record":{"source":{"id":"2502.17259","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2025-02-24T15:39:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1fba8b9482ce4a2c30164a6dc7d4b98d4e57cbbb261c502d53a41963ab4282c0","abstract_canon_sha256":"daa1ac1bc82b52d677f1fd124f6d61f3ffa81eaeaa7df59de9d809b26ecd9fc3"},"schema_version":"1.0"},"canonical_sha256":"305685d9ad2da1b530ddff6ba1cf35799b4d17c6059a73ca58aa00e617e4777c","source":{"kind":"arxiv","id":"2502.17259","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.17259","created_at":"2026-07-05T11:40:33Z"},{"alias_kind":"arxiv_version","alias_value":"2502.17259v2","created_at":"2026-07-05T11:40:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.17259","created_at":"2026-07-05T11:40:33Z"},{"alias_kind":"pith_short_12","alias_value":"GBLILWNNFWQ3","created_at":"2026-07-05T11:40:33Z"},{"alias_kind":"pith_short_16","alias_value":"GBLILWNNFWQ3KMG5","created_at":"2026-07-05T11:40:33Z"},{"alias_kind":"pith_short_8","alias_value":"GBLILWNN","created_at":"2026-07-05T11:40:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:GBLILWNNFWQ3KMG575V2DTZVPG","target":"record","payload":{"canonical_record":{"source":{"id":"2502.17259","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2025-02-24T15:39:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1fba8b9482ce4a2c30164a6dc7d4b98d4e57cbbb261c502d53a41963ab4282c0","abstract_canon_sha256":"daa1ac1bc82b52d677f1fd124f6d61f3ffa81eaeaa7df59de9d809b26ecd9fc3"},"schema_version":"1.0"},"canonical_sha256":"305685d9ad2da1b530ddff6ba1cf35799b4d17c6059a73ca58aa00e617e4777c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:40:33.209172Z","signature_b64":"ptPyQFLQbi6/MQcUZM+4ZSI4S1Gva3i7WPq8zlJgcuhhVOPgPAEyaISZf2juK4OSP0LcZojnOUEhVeQ/aBI5Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"305685d9ad2da1b530ddff6ba1cf35799b4d17c6059a73ca58aa00e617e4777c","last_reissued_at":"2026-07-05T11:40:33.208681Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:40:33.208681Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.17259","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":"2026-07-05T11:40:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QOUNjs8qGofIfBJCi4vPGgp0XiMYa1wiDnVheCN0Ok1p964GGI9yKDBWaEcr8CD5Oy+CV1weq7nJLadvukSOCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T22:09:42.938304Z"},"content_sha256":"d6d0aa1651a814623c4b399cecc8cc5142fbb0b514c27b9b37c004d2a16bb37a","schema_version":"1.0","event_id":"sha256:d6d0aa1651a814623c4b399cecc8cc5142fbb0b514c27b9b37c004d2a16bb37a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:GBLILWNNFWQ3KMG575V2DTZVPG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Detecting Benchmark Contamination Through Watermarking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Alain Durmus, Chuan Guo, Pierre Fernandez, Saeed Mahloujifar, Tom Sander","submitted_at":"2025-02-24T15:39:31Z","abstract_excerpt":"Benchmark contamination poses a significant challenge to the reliability of Large Language Models (LLMs) evaluations, as it is difficult to assert whether a model has been trained on a test set. We introduce a solution to this problem by watermarking benchmarks before their release. The embedding involves reformulating the original questions with a watermarked LLM, in a way that does not alter the benchmark utility. During evaluation, we can detect ``radioactivity'', \\ie traces that the text watermarks leave in the model during training, using a theoretically grounded statistical test. We test"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.17259","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/2502.17259/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":"2026-07-05T11:40:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"twHlw0K0lp1ZhRAJEAa1Om4dO75U1ItcUCbeX7o9uCz1kMw48IaQtYoKiMrOgQZzQLxHrNrikJKSLYCW1cYOAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T22:09:42.938815Z"},"content_sha256":"76b451ffa4be33f2bbd3a94f5f3318627e59bbe0cba53673e5a0e2a6b5891ae1","schema_version":"1.0","event_id":"sha256:76b451ffa4be33f2bbd3a94f5f3318627e59bbe0cba53673e5a0e2a6b5891ae1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GBLILWNNFWQ3KMG575V2DTZVPG/bundle.json","state_url":"https://pith.science/pith/GBLILWNNFWQ3KMG575V2DTZVPG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GBLILWNNFWQ3KMG575V2DTZVPG/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":"2026-08-22T22:09:42Z","links":{"resolver":"https://pith.science/pith/GBLILWNNFWQ3KMG575V2DTZVPG","bundle":"https://pith.science/pith/GBLILWNNFWQ3KMG575V2DTZVPG/bundle.json","state":"https://pith.science/pith/GBLILWNNFWQ3KMG575V2DTZVPG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GBLILWNNFWQ3KMG575V2DTZVPG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GBLILWNNFWQ3KMG575V2DTZVPG","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":"daa1ac1bc82b52d677f1fd124f6d61f3ffa81eaeaa7df59de9d809b26ecd9fc3","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2025-02-24T15:39:31Z","title_canon_sha256":"1fba8b9482ce4a2c30164a6dc7d4b98d4e57cbbb261c502d53a41963ab4282c0"},"schema_version":"1.0","source":{"id":"2502.17259","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.17259","created_at":"2026-07-05T11:40:33Z"},{"alias_kind":"arxiv_version","alias_value":"2502.17259v2","created_at":"2026-07-05T11:40:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.17259","created_at":"2026-07-05T11:40:33Z"},{"alias_kind":"pith_short_12","alias_value":"GBLILWNNFWQ3","created_at":"2026-07-05T11:40:33Z"},{"alias_kind":"pith_short_16","alias_value":"GBLILWNNFWQ3KMG5","created_at":"2026-07-05T11:40:33Z"},{"alias_kind":"pith_short_8","alias_value":"GBLILWNN","created_at":"2026-07-05T11:40:33Z"}],"graph_snapshots":[{"event_id":"sha256:76b451ffa4be33f2bbd3a94f5f3318627e59bbe0cba53673e5a0e2a6b5891ae1","target":"graph","created_at":"2026-07-05T11:40:33Z","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/2502.17259/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Benchmark contamination poses a significant challenge to the reliability of Large Language Models (LLMs) evaluations, as it is difficult to assert whether a model has been trained on a test set. We introduce a solution to this problem by watermarking benchmarks before their release. The embedding involves reformulating the original questions with a watermarked LLM, in a way that does not alter the benchmark utility. During evaluation, we can detect ``radioactivity'', \\ie traces that the text watermarks leave in the model during training, using a theoretically grounded statistical test. We test","authors_text":"Alain Durmus, Chuan Guo, Pierre Fernandez, Saeed Mahloujifar, Tom Sander","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2025-02-24T15:39:31Z","title":"Detecting Benchmark Contamination Through Watermarking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.17259","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:d6d0aa1651a814623c4b399cecc8cc5142fbb0b514c27b9b37c004d2a16bb37a","target":"record","created_at":"2026-07-05T11:40:33Z","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":"daa1ac1bc82b52d677f1fd124f6d61f3ffa81eaeaa7df59de9d809b26ecd9fc3","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2025-02-24T15:39:31Z","title_canon_sha256":"1fba8b9482ce4a2c30164a6dc7d4b98d4e57cbbb261c502d53a41963ab4282c0"},"schema_version":"1.0","source":{"id":"2502.17259","kind":"arxiv","version":2}},"canonical_sha256":"305685d9ad2da1b530ddff6ba1cf35799b4d17c6059a73ca58aa00e617e4777c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"305685d9ad2da1b530ddff6ba1cf35799b4d17c6059a73ca58aa00e617e4777c","first_computed_at":"2026-07-05T11:40:33.208681Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:40:33.208681Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ptPyQFLQbi6/MQcUZM+4ZSI4S1Gva3i7WPq8zlJgcuhhVOPgPAEyaISZf2juK4OSP0LcZojnOUEhVeQ/aBI5Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:40:33.209172Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.17259","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d6d0aa1651a814623c4b399cecc8cc5142fbb0b514c27b9b37c004d2a16bb37a","sha256:76b451ffa4be33f2bbd3a94f5f3318627e59bbe0cba53673e5a0e2a6b5891ae1"],"state_sha256":"0064924a151697277cf93568daf2e607b58f473c8c652b1cfe3d4761ec58dce0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QPZulXGB6NQ5WINVvP/ShP4caMeE41EhuNaXgjN+oJbb2iF5rf0swKJ9Os+FPTWcV5qT4b2l8QUF+C3fGyY2CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T22:09:42.944494Z","bundle_sha256":"1bd21ca877d5c0da726614ceef5a8bc6a53d6268ff300c3dd86807478b285b7f"}}