{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:YORG4F7PTZQ43JFSC5REZGFFAG","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":"30d5877cc4857b6f49dca9c4edd80febc0c86757db25f7b21fb8ff44adf06cd5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-27T09:48:29Z","title_canon_sha256":"fc3efaa077ff0942bc5099013ef05e8fb921ae26cd4e93564b25a82af7b49ac2"},"schema_version":"1.0","source":{"id":"2310.18018","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.18018","created_at":"2026-07-05T07:05:55Z"},{"alias_kind":"arxiv_version","alias_value":"2310.18018v1","created_at":"2026-07-05T07:05:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.18018","created_at":"2026-07-05T07:05:55Z"},{"alias_kind":"pith_short_12","alias_value":"YORG4F7PTZQ4","created_at":"2026-07-05T07:05:55Z"},{"alias_kind":"pith_short_16","alias_value":"YORG4F7PTZQ43JFS","created_at":"2026-07-05T07:05:55Z"},{"alias_kind":"pith_short_8","alias_value":"YORG4F7P","created_at":"2026-07-05T07:05:55Z"}],"graph_snapshots":[{"event_id":"sha256:cd9142ab16704cfcb1f4ef6f72581d5719e5ab497a090129d764cd242dc2c9fb","target":"graph","created_at":"2026-07-05T07:05:55Z","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/2310.18018/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this position paper, we argue that the classical evaluation on Natural Language Processing (NLP) tasks using annotated benchmarks is in trouble. The worst kind of data contamination happens when a Large Language Model (LLM) is trained on the test split of a benchmark, and then evaluated in the same benchmark. The extent of the problem is unknown, as it is not straightforward to measure. Contamination causes an overestimation of the performance of a contaminated model in a target benchmark and associated task with respect to their non-contaminated counterparts. The consequences can be very h","authors_text":"Eneko Agirre, Iker Garc\\'ia-Ferrero, Jon Ander Campos, Julen Etxaniz, Oier Lopez de Lacalle, Oscar Sainz","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-27T09:48:29Z","title":"NLP Evaluation in trouble: On the Need to Measure LLM Data Contamination for each Benchmark"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.18018","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":"sha256:96241e0f5123bb2d21801f35e03a53b94f30e6a59938673f56368701a551f334","target":"record","created_at":"2026-07-05T07:05:55Z","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":"30d5877cc4857b6f49dca9c4edd80febc0c86757db25f7b21fb8ff44adf06cd5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-27T09:48:29Z","title_canon_sha256":"fc3efaa077ff0942bc5099013ef05e8fb921ae26cd4e93564b25a82af7b49ac2"},"schema_version":"1.0","source":{"id":"2310.18018","kind":"arxiv","version":1}},"canonical_sha256":"c3a26e17ef9e61cda4b217624c98a501ac7e10d5f34281307b365a06327fb15f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c3a26e17ef9e61cda4b217624c98a501ac7e10d5f34281307b365a06327fb15f","first_computed_at":"2026-07-05T07:05:55.899553Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:05:55.899553Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oUH1iZseAh1J99k1MDWYY/ikU5L2YI1VepIM3rVXyFYMFIZHLXqt7quNxjQCuQJ8ymapodzrdGmp+GKeq7uWBg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:05:55.900059Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.18018","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:96241e0f5123bb2d21801f35e03a53b94f30e6a59938673f56368701a551f334","sha256:cd9142ab16704cfcb1f4ef6f72581d5719e5ab497a090129d764cd242dc2c9fb"],"state_sha256":"e356dd67be00c5746c209a130d74338911542a953f8c49d29e20e69f11245db4"}