{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:A5XQ5KETUINKDV4OZPJHST5DNU","short_pith_number":"pith:A5XQ5KET","canonical_record":{"source":{"id":"2404.00699","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-31T14:32:02Z","cross_cats_sorted":[],"title_canon_sha256":"720e013ca78df7680eaa9f630dcc39d895bddbb16c700eaf07e9120b8d5c05f4","abstract_canon_sha256":"479d95028bb8859b16ae0439db543f59d5ff502c76deca78113ee4c6e9d41fcf"},"schema_version":"1.0"},"canonical_sha256":"076f0ea893a21aa1d78ecbd2794fa36d0aee31fbafe68d895527c87a3651e35b","source":{"kind":"arxiv","id":"2404.00699","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.00699","created_at":"2026-07-05T11:34:41Z"},{"alias_kind":"arxiv_version","alias_value":"2404.00699v5","created_at":"2026-07-05T11:34:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.00699","created_at":"2026-07-05T11:34:41Z"},{"alias_kind":"pith_short_12","alias_value":"A5XQ5KETUINK","created_at":"2026-07-05T11:34:41Z"},{"alias_kind":"pith_short_16","alias_value":"A5XQ5KETUINKDV4O","created_at":"2026-07-05T11:34:41Z"},{"alias_kind":"pith_short_8","alias_value":"A5XQ5KET","created_at":"2026-07-05T11:34:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:A5XQ5KETUINKDV4OZPJHST5DNU","target":"record","payload":{"canonical_record":{"source":{"id":"2404.00699","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-31T14:32:02Z","cross_cats_sorted":[],"title_canon_sha256":"720e013ca78df7680eaa9f630dcc39d895bddbb16c700eaf07e9120b8d5c05f4","abstract_canon_sha256":"479d95028bb8859b16ae0439db543f59d5ff502c76deca78113ee4c6e9d41fcf"},"schema_version":"1.0"},"canonical_sha256":"076f0ea893a21aa1d78ecbd2794fa36d0aee31fbafe68d895527c87a3651e35b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:34:41.638439Z","signature_b64":"hxg2+r3JArUhGRpmlLmKmYI2Ak9u1pTa3vsrXq97ZA6+kD8sDhR+YM44XmjrBWEJM0RWIty+q6Varae17wMwAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"076f0ea893a21aa1d78ecbd2794fa36d0aee31fbafe68d895527c87a3651e35b","last_reissued_at":"2026-07-05T11:34:41.637902Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:34:41.637902Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.00699","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:34:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VfEr2YDYVi3cxb7Xjs/Lphat47QPobyPe/L/knh2PocGxHtXuNGb9r+xJBM4m/pOyrpGw3DquNLeRKvTRrC4Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T21:36:57.432206Z"},"content_sha256":"0821e9c9294e8cfa847e6fe2b3b72f6e5eafe0ac49af4f937ff969f8678f8f9a","schema_version":"1.0","event_id":"sha256:0821e9c9294e8cfa847e6fe2b3b72f6e5eafe0ac49af4f937ff969f8678f8f9a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:A5XQ5KETUINKDV4OZPJHST5DNU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Comprehensive Survey of Contamination Detection Methods in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bosheng Ding, Caiming Xiong, Chengwei Qin, Fangkai Jiao, Hailin Chen, Mathieu Ravaut, Ruochen Zhao, Shafiq Joty, Xingxuan Li","submitted_at":"2024-03-31T14:32:02Z","abstract_excerpt":"With the rise of Large Language Models (LLMs) in recent years, abundant new opportunities are emerging, but also new challenges, among which contamination is quickly becoming critical. Business applications and fundraising in Artificial Intelligence (AI) have reached a scale at which a few percentage points gained on popular question-answering benchmarks could translate into dozens of millions of dollars, placing high pressure on model integrity. At the same time, it is becoming harder and harder to keep track of the data that LLMs have seen; if not impossible with closed-source models like GP"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.00699","kind":"arxiv","version":5},"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/2404.00699/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":"2026-07-05T11:34:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8wy7w/Rr217/42YFYXmdHpzV/VzuATOVkYcJu1mWQWymlrP0nzw3vE8BEQw4XJBSVYX2R1C7vwAUAJecrWHnBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T21:36:57.433330Z"},"content_sha256":"a028ce059affa55ca199a6f0f382a3ba5e3d37f7dd2ced12a4c50649c9f64962","schema_version":"1.0","event_id":"sha256:a028ce059affa55ca199a6f0f382a3ba5e3d37f7dd2ced12a4c50649c9f64962"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/A5XQ5KETUINKDV4OZPJHST5DNU/bundle.json","state_url":"https://pith.science/pith/A5XQ5KETUINKDV4OZPJHST5DNU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/A5XQ5KETUINKDV4OZPJHST5DNU/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":"2026-08-06T21:36:57Z","links":{"resolver":"https://pith.science/pith/A5XQ5KETUINKDV4OZPJHST5DNU","bundle":"https://pith.science/pith/A5XQ5KETUINKDV4OZPJHST5DNU/bundle.json","state":"https://pith.science/pith/A5XQ5KETUINKDV4OZPJHST5DNU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/A5XQ5KETUINKDV4OZPJHST5DNU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:A5XQ5KETUINKDV4OZPJHST5DNU","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":"479d95028bb8859b16ae0439db543f59d5ff502c76deca78113ee4c6e9d41fcf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-31T14:32:02Z","title_canon_sha256":"720e013ca78df7680eaa9f630dcc39d895bddbb16c700eaf07e9120b8d5c05f4"},"schema_version":"1.0","source":{"id":"2404.00699","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.00699","created_at":"2026-07-05T11:34:41Z"},{"alias_kind":"arxiv_version","alias_value":"2404.00699v5","created_at":"2026-07-05T11:34:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.00699","created_at":"2026-07-05T11:34:41Z"},{"alias_kind":"pith_short_12","alias_value":"A5XQ5KETUINK","created_at":"2026-07-05T11:34:41Z"},{"alias_kind":"pith_short_16","alias_value":"A5XQ5KETUINKDV4O","created_at":"2026-07-05T11:34:41Z"},{"alias_kind":"pith_short_8","alias_value":"A5XQ5KET","created_at":"2026-07-05T11:34:41Z"}],"graph_snapshots":[{"event_id":"sha256:a028ce059affa55ca199a6f0f382a3ba5e3d37f7dd2ced12a4c50649c9f64962","target":"graph","created_at":"2026-07-05T11:34:41Z","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/2404.00699/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the rise of Large Language Models (LLMs) in recent years, abundant new opportunities are emerging, but also new challenges, among which contamination is quickly becoming critical. Business applications and fundraising in Artificial Intelligence (AI) have reached a scale at which a few percentage points gained on popular question-answering benchmarks could translate into dozens of millions of dollars, placing high pressure on model integrity. At the same time, it is becoming harder and harder to keep track of the data that LLMs have seen; if not impossible with closed-source models like GP","authors_text":"Bosheng Ding, Caiming Xiong, Chengwei Qin, Fangkai Jiao, Hailin Chen, Mathieu Ravaut, Ruochen Zhao, Shafiq Joty, Xingxuan Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-31T14:32:02Z","title":"A Comprehensive Survey of Contamination Detection Methods in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.00699","kind":"arxiv","version":5},"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":"sha256:0821e9c9294e8cfa847e6fe2b3b72f6e5eafe0ac49af4f937ff969f8678f8f9a","target":"record","created_at":"2026-07-05T11:34:41Z","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":"479d95028bb8859b16ae0439db543f59d5ff502c76deca78113ee4c6e9d41fcf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-31T14:32:02Z","title_canon_sha256":"720e013ca78df7680eaa9f630dcc39d895bddbb16c700eaf07e9120b8d5c05f4"},"schema_version":"1.0","source":{"id":"2404.00699","kind":"arxiv","version":5}},"canonical_sha256":"076f0ea893a21aa1d78ecbd2794fa36d0aee31fbafe68d895527c87a3651e35b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"076f0ea893a21aa1d78ecbd2794fa36d0aee31fbafe68d895527c87a3651e35b","first_computed_at":"2026-07-05T11:34:41.637902Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:34:41.637902Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hxg2+r3JArUhGRpmlLmKmYI2Ak9u1pTa3vsrXq97ZA6+kD8sDhR+YM44XmjrBWEJM0RWIty+q6Varae17wMwAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:34:41.638439Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.00699","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0821e9c9294e8cfa847e6fe2b3b72f6e5eafe0ac49af4f937ff969f8678f8f9a","sha256:a028ce059affa55ca199a6f0f382a3ba5e3d37f7dd2ced12a4c50649c9f64962"],"state_sha256":"37481ada37651b2eab220deaa0da40b39dfe3e05f6e96954a0f31f7bc377d844"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/v0Lw+1YXicol3reO5HGu5ZqgwR834HwCZ5KhHlS2R58blTy/zIUOHJFBwJZUyr2ecZObMWUdkpm4grdmJ8lDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T21:36:57.438313Z","bundle_sha256":"a75af6ee436b5bbb57078dede339e57e8f42ba82d36c9008e7e53d4e9f2e637a"}}