{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:J55DC5GBKLIKYKYET7WXGCQOXF","short_pith_number":"pith:J55DC5GB","canonical_record":{"source":{"id":"2311.06233","kind":"arxiv","version":7},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-10T18:48:58Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"90afff29a0d688b5ebd8b48f5cd0e75acbc2dd944f34518b13be14fd8b846c16","abstract_canon_sha256":"cfbec0ec5ff587c4f708969c04f1139156851a7f17830a227a7cd11b53591e50"},"schema_version":"1.0"},"canonical_sha256":"4f7a3174c152d0ac2b049fed730a0eb9715e58bbbe2140b88bf1c3599fbda354","source":{"kind":"arxiv","id":"2311.06233","version":7},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.06233","created_at":"2026-07-05T10:54:30Z"},{"alias_kind":"arxiv_version","alias_value":"2311.06233v7","created_at":"2026-07-05T10:54:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.06233","created_at":"2026-07-05T10:54:30Z"},{"alias_kind":"pith_short_12","alias_value":"J55DC5GBKLIK","created_at":"2026-07-05T10:54:30Z"},{"alias_kind":"pith_short_16","alias_value":"J55DC5GBKLIKYKYE","created_at":"2026-07-05T10:54:30Z"},{"alias_kind":"pith_short_8","alias_value":"J55DC5GB","created_at":"2026-07-05T10:54:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:J55DC5GBKLIKYKYET7WXGCQOXF","target":"record","payload":{"canonical_record":{"source":{"id":"2311.06233","kind":"arxiv","version":7},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-10T18:48:58Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"90afff29a0d688b5ebd8b48f5cd0e75acbc2dd944f34518b13be14fd8b846c16","abstract_canon_sha256":"cfbec0ec5ff587c4f708969c04f1139156851a7f17830a227a7cd11b53591e50"},"schema_version":"1.0"},"canonical_sha256":"4f7a3174c152d0ac2b049fed730a0eb9715e58bbbe2140b88bf1c3599fbda354","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:54:30.812919Z","signature_b64":"8/2wM+yPBta8r3z3dfepOU/ybGapg/mIvhRjadcIz/BnslYl6pxhacVzDP/tE9JGA0JPO5TitR/ENUrXd0axCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f7a3174c152d0ac2b049fed730a0eb9715e58bbbe2140b88bf1c3599fbda354","last_reissued_at":"2026-07-05T10:54:30.812456Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:54:30.812456Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.06233","source_version":7,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:54:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EnjxF2TzD+ykYeflsCRI4sIcentYwgfbgmUtpq2ewpcn4lLFFl4bwLybqP7akJ33iybWOBgSQU8WDTFuREr3AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T18:21:23.634030Z"},"content_sha256":"8b0652fe787c27800afabc9a9335d7899491f8962bb0d891482c55048db8d6ad","schema_version":"1.0","event_id":"sha256:8b0652fe787c27800afabc9a9335d7899491f8962bb0d891482c55048db8d6ad"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:J55DC5GBKLIKYKYET7WXGCQOXF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Data Contamination Quiz: A Tool to Detect and Estimate Contamination in Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Mihai Surdeanu, Shahriar Golchin","submitted_at":"2023-11-10T18:48:58Z","abstract_excerpt":"We propose the Data Contamination Quiz (DCQ), a simple and effective approach to detect data contamination in large language models (LLMs) and estimate the amount of it. Specifically, we frame data contamination detection as a series of multiple-choice questions, devising a quiz format wherein three perturbed versions of each instance, subsampled from a specific dataset partition, are created. These changes only include word-level perturbations. The generated perturbations, along with the original dataset instance, form the options in the DCQ, with an extra option accommodating the selection o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.06233","kind":"arxiv","version":7},"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/2311.06233/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":"2026-07-05T10:54:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"usYxqWoNTYZwGwVQuZRhBsLRV6VVrDaw2AaA9qYThOlv2kyQAaeuQjJ6ocEBaOnQZgXpKz9IGUY/mz6GSoPzAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T18:21:23.634649Z"},"content_sha256":"68c251f3eb177d3495c28c7b1fd5d727e88f8da7a6f6e643d980c758f2ca06b1","schema_version":"1.0","event_id":"sha256:68c251f3eb177d3495c28c7b1fd5d727e88f8da7a6f6e643d980c758f2ca06b1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/J55DC5GBKLIKYKYET7WXGCQOXF/bundle.json","state_url":"https://pith.science/pith/J55DC5GBKLIKYKYET7WXGCQOXF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/J55DC5GBKLIKYKYET7WXGCQOXF/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":"2026-08-21T18:21:23Z","links":{"resolver":"https://pith.science/pith/J55DC5GBKLIKYKYET7WXGCQOXF","bundle":"https://pith.science/pith/J55DC5GBKLIKYKYET7WXGCQOXF/bundle.json","state":"https://pith.science/pith/J55DC5GBKLIKYKYET7WXGCQOXF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/J55DC5GBKLIKYKYET7WXGCQOXF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:J55DC5GBKLIKYKYET7WXGCQOXF","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":"cfbec0ec5ff587c4f708969c04f1139156851a7f17830a227a7cd11b53591e50","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-10T18:48:58Z","title_canon_sha256":"90afff29a0d688b5ebd8b48f5cd0e75acbc2dd944f34518b13be14fd8b846c16"},"schema_version":"1.0","source":{"id":"2311.06233","kind":"arxiv","version":7}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.06233","created_at":"2026-07-05T10:54:30Z"},{"alias_kind":"arxiv_version","alias_value":"2311.06233v7","created_at":"2026-07-05T10:54:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.06233","created_at":"2026-07-05T10:54:30Z"},{"alias_kind":"pith_short_12","alias_value":"J55DC5GBKLIK","created_at":"2026-07-05T10:54:30Z"},{"alias_kind":"pith_short_16","alias_value":"J55DC5GBKLIKYKYE","created_at":"2026-07-05T10:54:30Z"},{"alias_kind":"pith_short_8","alias_value":"J55DC5GB","created_at":"2026-07-05T10:54:30Z"}],"graph_snapshots":[{"event_id":"sha256:68c251f3eb177d3495c28c7b1fd5d727e88f8da7a6f6e643d980c758f2ca06b1","target":"graph","created_at":"2026-07-05T10:54:30Z","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/2311.06233/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose the Data Contamination Quiz (DCQ), a simple and effective approach to detect data contamination in large language models (LLMs) and estimate the amount of it. Specifically, we frame data contamination detection as a series of multiple-choice questions, devising a quiz format wherein three perturbed versions of each instance, subsampled from a specific dataset partition, are created. These changes only include word-level perturbations. The generated perturbations, along with the original dataset instance, form the options in the DCQ, with an extra option accommodating the selection o","authors_text":"Mihai Surdeanu, Shahriar Golchin","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-10T18:48:58Z","title":"Data Contamination Quiz: A Tool to Detect and Estimate Contamination in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.06233","kind":"arxiv","version":7},"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":"sha256:8b0652fe787c27800afabc9a9335d7899491f8962bb0d891482c55048db8d6ad","target":"record","created_at":"2026-07-05T10:54:30Z","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":"cfbec0ec5ff587c4f708969c04f1139156851a7f17830a227a7cd11b53591e50","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-10T18:48:58Z","title_canon_sha256":"90afff29a0d688b5ebd8b48f5cd0e75acbc2dd944f34518b13be14fd8b846c16"},"schema_version":"1.0","source":{"id":"2311.06233","kind":"arxiv","version":7}},"canonical_sha256":"4f7a3174c152d0ac2b049fed730a0eb9715e58bbbe2140b88bf1c3599fbda354","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4f7a3174c152d0ac2b049fed730a0eb9715e58bbbe2140b88bf1c3599fbda354","first_computed_at":"2026-07-05T10:54:30.812456Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:54:30.812456Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8/2wM+yPBta8r3z3dfepOU/ybGapg/mIvhRjadcIz/BnslYl6pxhacVzDP/tE9JGA0JPO5TitR/ENUrXd0axCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:54:30.812919Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.06233","source_kind":"arxiv","source_version":7}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8b0652fe787c27800afabc9a9335d7899491f8962bb0d891482c55048db8d6ad","sha256:68c251f3eb177d3495c28c7b1fd5d727e88f8da7a6f6e643d980c758f2ca06b1"],"state_sha256":"4da414a995153d96094b235420460179587478c251c3a3c0e30b845e421343bd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DU30QZeFboxJc1t/JmwQhAQS8+gz1s+E1dsWAsVxQv76uuOYnipMUhFK7RBR+rnLiogHG+arAXW9n03bqNVoCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T18:21:23.640944Z","bundle_sha256":"d732c458a4108f9a4331286af9ee9ae4368e5db9684abae6542ba39808fcc7c4"}}