{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:K6C2GOHFAYEVXL7M7B2KOYCKJ5","short_pith_number":"pith:K6C2GOHF","canonical_record":{"source":{"id":"2502.14425","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-20T10:23:27Z","cross_cats_sorted":[],"title_canon_sha256":"8f0da2076a1d1455b77ebd7f471605f7741d41518c2e3cd4215b090f176912e9","abstract_canon_sha256":"49753bbac55a7aa86076b3c0e13b1a4005461d39627bcfbd553662f408ff1517"},"schema_version":"1.0"},"canonical_sha256":"5785a338e506095bafecf874a7604a4f5c3443fcd4af2326ca695b2c351a473d","source":{"kind":"arxiv","id":"2502.14425","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.14425","created_at":"2026-07-05T11:16:06Z"},{"alias_kind":"arxiv_version","alias_value":"2502.14425v2","created_at":"2026-07-05T11:16:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.14425","created_at":"2026-07-05T11:16:06Z"},{"alias_kind":"pith_short_12","alias_value":"K6C2GOHFAYEV","created_at":"2026-07-05T11:16:06Z"},{"alias_kind":"pith_short_16","alias_value":"K6C2GOHFAYEVXL7M","created_at":"2026-07-05T11:16:06Z"},{"alias_kind":"pith_short_8","alias_value":"K6C2GOHF","created_at":"2026-07-05T11:16:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:K6C2GOHFAYEVXL7M7B2KOYCKJ5","target":"record","payload":{"canonical_record":{"source":{"id":"2502.14425","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-20T10:23:27Z","cross_cats_sorted":[],"title_canon_sha256":"8f0da2076a1d1455b77ebd7f471605f7741d41518c2e3cd4215b090f176912e9","abstract_canon_sha256":"49753bbac55a7aa86076b3c0e13b1a4005461d39627bcfbd553662f408ff1517"},"schema_version":"1.0"},"canonical_sha256":"5785a338e506095bafecf874a7604a4f5c3443fcd4af2326ca695b2c351a473d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:06.420565Z","signature_b64":"YeOLA2v47X0P7bwhbMCCaYoXJVrxsruHdW0UztrxzWzN9ZW4iCtKVD+wvGwMUiu2OVerLTAfPv/X8jtN2xZaDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5785a338e506095bafecf874a7604a4f5c3443fcd4af2326ca695b2c351a473d","last_reissued_at":"2026-07-05T11:16:06.420004Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:06.420004Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.14425","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":"2026-07-05T11:16:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mIDZ7G0NIC6YYJ1ugDzf23H7HdgmRZyo4sxF7G42yru0zIHsl/QX9wmIFTs8UNEtVsyNiMZEvpxos6WFGKqjBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T09:16:34.804432Z"},"content_sha256":"95dd8ea1ddbad6bc09ec1c83597511a68788f1fc2486e41cf72b2b117314d32f","schema_version":"1.0","event_id":"sha256:95dd8ea1ddbad6bc09ec1c83597511a68788f1fc2486e41cf72b2b117314d32f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:K6C2GOHFAYEVXL7M7B2KOYCKJ5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Survey on Data Contamination for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Yi Chang, Yuan Wu, Yuxing Cheng","submitted_at":"2025-02-20T10:23:27Z","abstract_excerpt":"Recent advancements in Large Language Models (LLMs) have demonstrated significant progress in various areas, such as text generation and code synthesis. However, the reliability of performance evaluation has come under scrutiny due to data contamination-the unintended overlap between training and test datasets. This overlap has the potential to artificially inflate model performance, as LLMs are typically trained on extensive datasets scraped from publicly available sources. These datasets often inadvertently overlap with the benchmarks used for evaluation, leading to an overestimation of the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.14425","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/2502.14425/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":"2026-07-05T11:16:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FwBpiItE3JfHjHmVP8xgCinKHixGODK9rDai5YlnEsjsaBRcfyYtujeaeat87dBVX+8RnQW9mfXfhqHxRTNDBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T09:16:34.805362Z"},"content_sha256":"48cf94064efa88ec388ee7eaf21be06fc9a6afd945fd06ac8a7841a6f5aa62d2","schema_version":"1.0","event_id":"sha256:48cf94064efa88ec388ee7eaf21be06fc9a6afd945fd06ac8a7841a6f5aa62d2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/K6C2GOHFAYEVXL7M7B2KOYCKJ5/bundle.json","state_url":"https://pith.science/pith/K6C2GOHFAYEVXL7M7B2KOYCKJ5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/K6C2GOHFAYEVXL7M7B2KOYCKJ5/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":"2026-08-05T09:16:34Z","links":{"resolver":"https://pith.science/pith/K6C2GOHFAYEVXL7M7B2KOYCKJ5","bundle":"https://pith.science/pith/K6C2GOHFAYEVXL7M7B2KOYCKJ5/bundle.json","state":"https://pith.science/pith/K6C2GOHFAYEVXL7M7B2KOYCKJ5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/K6C2GOHFAYEVXL7M7B2KOYCKJ5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:K6C2GOHFAYEVXL7M7B2KOYCKJ5","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":"49753bbac55a7aa86076b3c0e13b1a4005461d39627bcfbd553662f408ff1517","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-20T10:23:27Z","title_canon_sha256":"8f0da2076a1d1455b77ebd7f471605f7741d41518c2e3cd4215b090f176912e9"},"schema_version":"1.0","source":{"id":"2502.14425","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.14425","created_at":"2026-07-05T11:16:06Z"},{"alias_kind":"arxiv_version","alias_value":"2502.14425v2","created_at":"2026-07-05T11:16:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.14425","created_at":"2026-07-05T11:16:06Z"},{"alias_kind":"pith_short_12","alias_value":"K6C2GOHFAYEV","created_at":"2026-07-05T11:16:06Z"},{"alias_kind":"pith_short_16","alias_value":"K6C2GOHFAYEVXL7M","created_at":"2026-07-05T11:16:06Z"},{"alias_kind":"pith_short_8","alias_value":"K6C2GOHF","created_at":"2026-07-05T11:16:06Z"}],"graph_snapshots":[{"event_id":"sha256:48cf94064efa88ec388ee7eaf21be06fc9a6afd945fd06ac8a7841a6f5aa62d2","target":"graph","created_at":"2026-07-05T11:16:06Z","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/2502.14425/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in Large Language Models (LLMs) have demonstrated significant progress in various areas, such as text generation and code synthesis. However, the reliability of performance evaluation has come under scrutiny due to data contamination-the unintended overlap between training and test datasets. This overlap has the potential to artificially inflate model performance, as LLMs are typically trained on extensive datasets scraped from publicly available sources. These datasets often inadvertently overlap with the benchmarks used for evaluation, leading to an overestimation of the ","authors_text":"Yi Chang, Yuan Wu, Yuxing Cheng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-20T10:23:27Z","title":"A Survey on Data Contamination for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.14425","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":"sha256:95dd8ea1ddbad6bc09ec1c83597511a68788f1fc2486e41cf72b2b117314d32f","target":"record","created_at":"2026-07-05T11:16:06Z","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":"49753bbac55a7aa86076b3c0e13b1a4005461d39627bcfbd553662f408ff1517","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-20T10:23:27Z","title_canon_sha256":"8f0da2076a1d1455b77ebd7f471605f7741d41518c2e3cd4215b090f176912e9"},"schema_version":"1.0","source":{"id":"2502.14425","kind":"arxiv","version":2}},"canonical_sha256":"5785a338e506095bafecf874a7604a4f5c3443fcd4af2326ca695b2c351a473d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5785a338e506095bafecf874a7604a4f5c3443fcd4af2326ca695b2c351a473d","first_computed_at":"2026-07-05T11:16:06.420004Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:16:06.420004Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YeOLA2v47X0P7bwhbMCCaYoXJVrxsruHdW0UztrxzWzN9ZW4iCtKVD+wvGwMUiu2OVerLTAfPv/X8jtN2xZaDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:16:06.420565Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.14425","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:95dd8ea1ddbad6bc09ec1c83597511a68788f1fc2486e41cf72b2b117314d32f","sha256:48cf94064efa88ec388ee7eaf21be06fc9a6afd945fd06ac8a7841a6f5aa62d2"],"state_sha256":"ccacdef264e7519cc280767a4cf1b6062c3cb06ae16e8f133d3f70852ff096ea"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EGq2gNSkPorvl2EQZaBuIPhvGmflkSIACP0/PPqDSItnGziCoPlL9O+q6L3OAxp0iy+/IykgcyfTeIjBNGV3Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T09:16:34.812091Z","bundle_sha256":"f09c5ede8ac7a78b5d0f39f755b9b60756628e70400d3122fba8fd689b7ac14a"}}