{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:NLVTCPG57RPQJM72Q6YWNP7PSK","short_pith_number":"pith:NLVTCPG5","canonical_record":{"source":{"id":"2404.18824","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-29T16:05:36Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"1834f46bc141b38f01574305be5724d703d2c153463e909aeb2a539e0032598a","abstract_canon_sha256":"e19312d631805334db9720a267753e7fead5a48ba2e42236883c48b09c268015"},"schema_version":"1.0"},"canonical_sha256":"6aeb313cddfc5f04b3fa87b166bfef92958d52b500d9616f72151f10a65853c0","source":{"kind":"arxiv","id":"2404.18824","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.18824","created_at":"2026-07-05T08:13:21Z"},{"alias_kind":"arxiv_version","alias_value":"2404.18824v1","created_at":"2026-07-05T08:13:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.18824","created_at":"2026-07-05T08:13:21Z"},{"alias_kind":"pith_short_12","alias_value":"NLVTCPG57RPQ","created_at":"2026-07-05T08:13:21Z"},{"alias_kind":"pith_short_16","alias_value":"NLVTCPG57RPQJM72","created_at":"2026-07-05T08:13:21Z"},{"alias_kind":"pith_short_8","alias_value":"NLVTCPG5","created_at":"2026-07-05T08:13:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:NLVTCPG57RPQJM72Q6YWNP7PSK","target":"record","payload":{"canonical_record":{"source":{"id":"2404.18824","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-29T16:05:36Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"1834f46bc141b38f01574305be5724d703d2c153463e909aeb2a539e0032598a","abstract_canon_sha256":"e19312d631805334db9720a267753e7fead5a48ba2e42236883c48b09c268015"},"schema_version":"1.0"},"canonical_sha256":"6aeb313cddfc5f04b3fa87b166bfef92958d52b500d9616f72151f10a65853c0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:13:21.236561Z","signature_b64":"LCbtu96f3tnWPAle8ENpoH27Bb6iItyD2P49SwRPFRO7UhEQ2xOCzJ1KthKOXrrS4a+EPQT3S8j+f0dnVoQVDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6aeb313cddfc5f04b3fa87b166bfef92958d52b500d9616f72151f10a65853c0","last_reissued_at":"2026-07-05T08:13:21.236079Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:13:21.236079Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.18824","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":"2026-07-05T08:13:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g43wg6ilbs0PuPQD0lVjUIGdTlev9h3dxGCB9fFp2NCL+STC+o8hM4VaHfnnFVMfF55EmTbZnwz/GOYYxaIUAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T07:45:10.713857Z"},"content_sha256":"09f294fd8eb73ab116c3f5c6ca85b545596886acd33157f28403dfef94b838bc","schema_version":"1.0","event_id":"sha256:09f294fd8eb73ab116c3f5c6ca85b545596886acd33157f28403dfef94b838bc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:NLVTCPG57RPQJM72Q6YWNP7PSK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Benchmarking Benchmark Leakage in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Pengfei Liu, Ruijie Xu, Run-Ze Fan, Zengzhi Wang","submitted_at":"2024-04-29T16:05:36Z","abstract_excerpt":"Amid the expanding use of pre-training data, the phenomenon of benchmark dataset leakage has become increasingly prominent, exacerbated by opaque training processes and the often undisclosed inclusion of supervised data in contemporary Large Language Models (LLMs). This issue skews benchmark effectiveness and fosters potentially unfair comparisons, impeding the field's healthy development. To address this, we introduce a detection pipeline utilizing Perplexity and N-gram accuracy, two simple and scalable metrics that gauge a model's prediction precision on benchmark, to identify potential data"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.18824","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/2404.18824/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":"2026-07-05T08:13:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GaDwZrHf4l0q0c7WAVSGAM2fYMLKVEQYkhuJUTW5KtA8fkNeoX2kaiXjWugckfTUq6b/u76wD7DH1yW1eFwgCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T07:45:10.714270Z"},"content_sha256":"ce196a00f64a689d55d27a0ad1280e0dfa48189a42d8471bc195cfbe3fc65b23","schema_version":"1.0","event_id":"sha256:ce196a00f64a689d55d27a0ad1280e0dfa48189a42d8471bc195cfbe3fc65b23"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NLVTCPG57RPQJM72Q6YWNP7PSK/bundle.json","state_url":"https://pith.science/pith/NLVTCPG57RPQJM72Q6YWNP7PSK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NLVTCPG57RPQJM72Q6YWNP7PSK/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":"2026-07-08T07:45:10Z","links":{"resolver":"https://pith.science/pith/NLVTCPG57RPQJM72Q6YWNP7PSK","bundle":"https://pith.science/pith/NLVTCPG57RPQJM72Q6YWNP7PSK/bundle.json","state":"https://pith.science/pith/NLVTCPG57RPQJM72Q6YWNP7PSK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NLVTCPG57RPQJM72Q6YWNP7PSK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NLVTCPG57RPQJM72Q6YWNP7PSK","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":"e19312d631805334db9720a267753e7fead5a48ba2e42236883c48b09c268015","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-29T16:05:36Z","title_canon_sha256":"1834f46bc141b38f01574305be5724d703d2c153463e909aeb2a539e0032598a"},"schema_version":"1.0","source":{"id":"2404.18824","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.18824","created_at":"2026-07-05T08:13:21Z"},{"alias_kind":"arxiv_version","alias_value":"2404.18824v1","created_at":"2026-07-05T08:13:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.18824","created_at":"2026-07-05T08:13:21Z"},{"alias_kind":"pith_short_12","alias_value":"NLVTCPG57RPQ","created_at":"2026-07-05T08:13:21Z"},{"alias_kind":"pith_short_16","alias_value":"NLVTCPG57RPQJM72","created_at":"2026-07-05T08:13:21Z"},{"alias_kind":"pith_short_8","alias_value":"NLVTCPG5","created_at":"2026-07-05T08:13:21Z"}],"graph_snapshots":[{"event_id":"sha256:ce196a00f64a689d55d27a0ad1280e0dfa48189a42d8471bc195cfbe3fc65b23","target":"graph","created_at":"2026-07-05T08:13:21Z","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/2404.18824/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Amid the expanding use of pre-training data, the phenomenon of benchmark dataset leakage has become increasingly prominent, exacerbated by opaque training processes and the often undisclosed inclusion of supervised data in contemporary Large Language Models (LLMs). This issue skews benchmark effectiveness and fosters potentially unfair comparisons, impeding the field's healthy development. To address this, we introduce a detection pipeline utilizing Perplexity and N-gram accuracy, two simple and scalable metrics that gauge a model's prediction precision on benchmark, to identify potential data","authors_text":"Pengfei Liu, Ruijie Xu, Run-Ze Fan, Zengzhi Wang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-29T16:05:36Z","title":"Benchmarking Benchmark Leakage in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.18824","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":"sha256:09f294fd8eb73ab116c3f5c6ca85b545596886acd33157f28403dfef94b838bc","target":"record","created_at":"2026-07-05T08:13:21Z","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":"e19312d631805334db9720a267753e7fead5a48ba2e42236883c48b09c268015","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-29T16:05:36Z","title_canon_sha256":"1834f46bc141b38f01574305be5724d703d2c153463e909aeb2a539e0032598a"},"schema_version":"1.0","source":{"id":"2404.18824","kind":"arxiv","version":1}},"canonical_sha256":"6aeb313cddfc5f04b3fa87b166bfef92958d52b500d9616f72151f10a65853c0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6aeb313cddfc5f04b3fa87b166bfef92958d52b500d9616f72151f10a65853c0","first_computed_at":"2026-07-05T08:13:21.236079Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:13:21.236079Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LCbtu96f3tnWPAle8ENpoH27Bb6iItyD2P49SwRPFRO7UhEQ2xOCzJ1KthKOXrrS4a+EPQT3S8j+f0dnVoQVDg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:13:21.236561Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.18824","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:09f294fd8eb73ab116c3f5c6ca85b545596886acd33157f28403dfef94b838bc","sha256:ce196a00f64a689d55d27a0ad1280e0dfa48189a42d8471bc195cfbe3fc65b23"],"state_sha256":"1ff833db6c654bf300a069107506c888d249000a9165bfb8f1455aaed3e34a5a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JEbavj9HAnYxzTEft0huZz2wiEPDPaJDeB6XHf6dg62fYidlCBFYvTdjVNDPSz6oQD9qu22CgLUYrOBklPIsCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T07:45:10.716984Z","bundle_sha256":"18e9f85a44136eaa8a0cbcc125ef31274907261d37e15c08ecc87ef0ac4a2f0e"}}