{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:QGXQFMC7RLBGHBDWJXRK2QD7RP","short_pith_number":"pith:QGXQFMC7","canonical_record":{"source":{"id":"2402.15938","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-24T23:54:41Z","cross_cats_sorted":["cs.AI","cs.CR","cs.LG","cs.SE"],"title_canon_sha256":"6168d1b0261d280aae827826537ba50543c50ef47531402ece974af33013c721","abstract_canon_sha256":"9c34f9551bb8089148627729ed0bc65c186d7514d32a2d6c808a260f9d8c2e83"},"schema_version":"1.0"},"canonical_sha256":"81af02b05f8ac26384764de2ad407f8bfeba4a77468a488c2ff1771b9dc00b93","source":{"kind":"arxiv","id":"2402.15938","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.15938","created_at":"2026-07-05T08:25:32Z"},{"alias_kind":"arxiv_version","alias_value":"2402.15938v3","created_at":"2026-07-05T08:25:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.15938","created_at":"2026-07-05T08:25:32Z"},{"alias_kind":"pith_short_12","alias_value":"QGXQFMC7RLBG","created_at":"2026-07-05T08:25:32Z"},{"alias_kind":"pith_short_16","alias_value":"QGXQFMC7RLBGHBDW","created_at":"2026-07-05T08:25:32Z"},{"alias_kind":"pith_short_8","alias_value":"QGXQFMC7","created_at":"2026-07-05T08:25:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:QGXQFMC7RLBGHBDWJXRK2QD7RP","target":"record","payload":{"canonical_record":{"source":{"id":"2402.15938","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-24T23:54:41Z","cross_cats_sorted":["cs.AI","cs.CR","cs.LG","cs.SE"],"title_canon_sha256":"6168d1b0261d280aae827826537ba50543c50ef47531402ece974af33013c721","abstract_canon_sha256":"9c34f9551bb8089148627729ed0bc65c186d7514d32a2d6c808a260f9d8c2e83"},"schema_version":"1.0"},"canonical_sha256":"81af02b05f8ac26384764de2ad407f8bfeba4a77468a488c2ff1771b9dc00b93","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:25:32.414514Z","signature_b64":"LVQKNECTppcSmJkumd9b49PfniDnnt0hQuzmHo6Beu8+e0b4uwLJE0foGJs+nd/VThR/Q+5rvY1+zTHrsB0oBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"81af02b05f8ac26384764de2ad407f8bfeba4a77468a488c2ff1771b9dc00b93","last_reissued_at":"2026-07-05T08:25:32.414055Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:25:32.414055Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.15938","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:25:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aMOlKiaNeN8anm3Vi6Qsd9FV7VBOnDwN/c84mZP9kJiw6F5LrAAh4/jwtrPikQzzLfwj6pmT1F+hHTZet1taCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:06:23.274934Z"},"content_sha256":"637a789183b0af48903672a43fcf60b0507110f352ed96edcbffb86aee39ddc2","schema_version":"1.0","event_id":"sha256:637a789183b0af48903672a43fcf60b0507110f352ed96edcbffb86aee39ddc2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:QGXQFMC7RLBGHBDWJXRK2QD7RP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Generalization or Memorization: Data Contamination and Trustworthy Evaluation for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR","cs.LG","cs.SE"],"primary_cat":"cs.CL","authors_text":"Bin Gu, Ge Li, Huanyu Liu, Mengfei Yang, Xue Jiang, Yihong Dong, Zhi Jin","submitted_at":"2024-02-24T23:54:41Z","abstract_excerpt":"Recent statements about the impressive capabilities of large language models (LLMs) are usually supported by evaluating on open-access benchmarks. Considering the vast size and wide-ranging sources of LLMs' training data, it could explicitly or implicitly include test data, leading to LLMs being more susceptible to data contamination. However, due to the opacity of training data, the black-box access of models, and the rapid growth of synthetic training data, detecting and mitigating data contamination for LLMs faces significant challenges. In this paper, we propose CDD, which stands for Conta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.15938","kind":"arxiv","version":3},"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/2402.15938/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":"2026-07-05T08:25:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BE1bv3RpAWuV4Qz3azRCr1i9assQmvUZxaUYQmtyzo2vcsHeTDgbKF5gYq/SLmdRmVJhaObstSnzKNNjffUqCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:06:23.275304Z"},"content_sha256":"f761651826ef400c19fe2445ff53b723833983579bd81c865cca572327b3b17e","schema_version":"1.0","event_id":"sha256:f761651826ef400c19fe2445ff53b723833983579bd81c865cca572327b3b17e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QGXQFMC7RLBGHBDWJXRK2QD7RP/bundle.json","state_url":"https://pith.science/pith/QGXQFMC7RLBGHBDWJXRK2QD7RP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QGXQFMC7RLBGHBDWJXRK2QD7RP/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":"2026-07-07T08:06:23Z","links":{"resolver":"https://pith.science/pith/QGXQFMC7RLBGHBDWJXRK2QD7RP","bundle":"https://pith.science/pith/QGXQFMC7RLBGHBDWJXRK2QD7RP/bundle.json","state":"https://pith.science/pith/QGXQFMC7RLBGHBDWJXRK2QD7RP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QGXQFMC7RLBGHBDWJXRK2QD7RP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QGXQFMC7RLBGHBDWJXRK2QD7RP","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":"9c34f9551bb8089148627729ed0bc65c186d7514d32a2d6c808a260f9d8c2e83","cross_cats_sorted":["cs.AI","cs.CR","cs.LG","cs.SE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-24T23:54:41Z","title_canon_sha256":"6168d1b0261d280aae827826537ba50543c50ef47531402ece974af33013c721"},"schema_version":"1.0","source":{"id":"2402.15938","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.15938","created_at":"2026-07-05T08:25:32Z"},{"alias_kind":"arxiv_version","alias_value":"2402.15938v3","created_at":"2026-07-05T08:25:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.15938","created_at":"2026-07-05T08:25:32Z"},{"alias_kind":"pith_short_12","alias_value":"QGXQFMC7RLBG","created_at":"2026-07-05T08:25:32Z"},{"alias_kind":"pith_short_16","alias_value":"QGXQFMC7RLBGHBDW","created_at":"2026-07-05T08:25:32Z"},{"alias_kind":"pith_short_8","alias_value":"QGXQFMC7","created_at":"2026-07-05T08:25:32Z"}],"graph_snapshots":[{"event_id":"sha256:f761651826ef400c19fe2445ff53b723833983579bd81c865cca572327b3b17e","target":"graph","created_at":"2026-07-05T08:25:32Z","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/2402.15938/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent statements about the impressive capabilities of large language models (LLMs) are usually supported by evaluating on open-access benchmarks. Considering the vast size and wide-ranging sources of LLMs' training data, it could explicitly or implicitly include test data, leading to LLMs being more susceptible to data contamination. However, due to the opacity of training data, the black-box access of models, and the rapid growth of synthetic training data, detecting and mitigating data contamination for LLMs faces significant challenges. In this paper, we propose CDD, which stands for Conta","authors_text":"Bin Gu, Ge Li, Huanyu Liu, Mengfei Yang, Xue Jiang, Yihong Dong, Zhi Jin","cross_cats":["cs.AI","cs.CR","cs.LG","cs.SE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-24T23:54:41Z","title":"Generalization or Memorization: Data Contamination and Trustworthy Evaluation for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.15938","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":"sha256:637a789183b0af48903672a43fcf60b0507110f352ed96edcbffb86aee39ddc2","target":"record","created_at":"2026-07-05T08:25:32Z","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":"9c34f9551bb8089148627729ed0bc65c186d7514d32a2d6c808a260f9d8c2e83","cross_cats_sorted":["cs.AI","cs.CR","cs.LG","cs.SE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-24T23:54:41Z","title_canon_sha256":"6168d1b0261d280aae827826537ba50543c50ef47531402ece974af33013c721"},"schema_version":"1.0","source":{"id":"2402.15938","kind":"arxiv","version":3}},"canonical_sha256":"81af02b05f8ac26384764de2ad407f8bfeba4a77468a488c2ff1771b9dc00b93","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"81af02b05f8ac26384764de2ad407f8bfeba4a77468a488c2ff1771b9dc00b93","first_computed_at":"2026-07-05T08:25:32.414055Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:25:32.414055Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LVQKNECTppcSmJkumd9b49PfniDnnt0hQuzmHo6Beu8+e0b4uwLJE0foGJs+nd/VThR/Q+5rvY1+zTHrsB0oBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:25:32.414514Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.15938","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:637a789183b0af48903672a43fcf60b0507110f352ed96edcbffb86aee39ddc2","sha256:f761651826ef400c19fe2445ff53b723833983579bd81c865cca572327b3b17e"],"state_sha256":"4e41abd28e9497cfd16a10fad1a86b500b8b2b6605f26de93632e8a30d4fadd4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LztRwsS0LJpRj3z0a9mb4YmwHYvzDZt9pUF5NTA8yYgB3WSKZGRkVltdk+Or13HAM3yrxZwofNp8R5yPtVKODA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T08:06:23.277266Z","bundle_sha256":"b65abe99a4619a2bee810cbb07cfafb2392b55e32418f7d2e2e22d09d4e41c7d"}}