{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:OFL64GKAEEMVG554EVSUDXRLPP","short_pith_number":"pith:OFL64GKA","schema_version":"1.0","canonical_sha256":"7157ee194021195377bc256541de2b7bdad6fb6bc309499ba0dc95aea4fb7c97","source":{"kind":"arxiv","id":"2310.15941","version":1},"attestation_state":"computed","paper":{"title":"This is not a Dataset: A Large Negation Benchmark to Challenge Large Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bego\\~na Altuna, German Rigau, Iker Garc\\'ia-Ferrero, Itziar Gonzalez-Dios, Javier \\'Alvez","submitted_at":"2023-10-24T15:38:21Z","abstract_excerpt":"Although large language models (LLMs) have apparently acquired a certain level of grammatical knowledge and the ability to make generalizations, they fail to interpret negation, a crucial step in Natural Language Processing. We try to clarify the reasons for the sub-optimal performance of LLMs understanding negation. We introduce a large semi-automatically generated dataset of circa 400,000 descriptive sentences about commonsense knowledge that can be true or false in which negation is present in about 2/3 of the corpus in different forms. We have used our dataset with the largest available op"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2310.15941","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-24T15:38:21Z","cross_cats_sorted":[],"title_canon_sha256":"8e0cd30d3799c63141dd375130da4f7c9a8538f0741830ffb90c9ed1aeef5d5c","abstract_canon_sha256":"daae445a51e2a427bfcea876e510deed84e3323428d81a54a87aac28fb428960"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:04:32.781806Z","signature_b64":"GUS5qapYosenURBGQ5eDxv4jbPvZwVf4naj7EYM8YHxbQU/DExF1X32/yhU3RbMpSj5CKHsjz/JyRIZ2m0HwDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7157ee194021195377bc256541de2b7bdad6fb6bc309499ba0dc95aea4fb7c97","last_reissued_at":"2026-07-05T07:04:32.781350Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:04:32.781350Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"This is not a Dataset: A Large Negation Benchmark to Challenge Large Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bego\\~na Altuna, German Rigau, Iker Garc\\'ia-Ferrero, Itziar Gonzalez-Dios, Javier \\'Alvez","submitted_at":"2023-10-24T15:38:21Z","abstract_excerpt":"Although large language models (LLMs) have apparently acquired a certain level of grammatical knowledge and the ability to make generalizations, they fail to interpret negation, a crucial step in Natural Language Processing. We try to clarify the reasons for the sub-optimal performance of LLMs understanding negation. We introduce a large semi-automatically generated dataset of circa 400,000 descriptive sentences about commonsense knowledge that can be true or false in which negation is present in about 2/3 of the corpus in different forms. We have used our dataset with the largest available op"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.15941","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/2310.15941/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2310.15941","created_at":"2026-07-05T07:04:32.781408+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.15941v1","created_at":"2026-07-05T07:04:32.781408+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.15941","created_at":"2026-07-05T07:04:32.781408+00:00"},{"alias_kind":"pith_short_12","alias_value":"OFL64GKAEEMV","created_at":"2026-07-05T07:04:32.781408+00:00"},{"alias_kind":"pith_short_16","alias_value":"OFL64GKAEEMVG554","created_at":"2026-07-05T07:04:32.781408+00:00"},{"alias_kind":"pith_short_8","alias_value":"OFL64GKA","created_at":"2026-07-05T07:04:32.781408+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.09735","citing_title":"Discrimination by LLMs: Cross-lingual Bias Assessment and Mitigation in Decision-Making and Summarisation","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OFL64GKAEEMVG554EVSUDXRLPP","json":"https://pith.science/pith/OFL64GKAEEMVG554EVSUDXRLPP.json","graph_json":"https://pith.science/api/pith-number/OFL64GKAEEMVG554EVSUDXRLPP/graph.json","events_json":"https://pith.science/api/pith-number/OFL64GKAEEMVG554EVSUDXRLPP/events.json","paper":"https://pith.science/paper/OFL64GKA"},"agent_actions":{"view_html":"https://pith.science/pith/OFL64GKAEEMVG554EVSUDXRLPP","download_json":"https://pith.science/pith/OFL64GKAEEMVG554EVSUDXRLPP.json","view_paper":"https://pith.science/paper/OFL64GKA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.15941&json=true","fetch_graph":"https://pith.science/api/pith-number/OFL64GKAEEMVG554EVSUDXRLPP/graph.json","fetch_events":"https://pith.science/api/pith-number/OFL64GKAEEMVG554EVSUDXRLPP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OFL64GKAEEMVG554EVSUDXRLPP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OFL64GKAEEMVG554EVSUDXRLPP/action/storage_attestation","attest_author":"https://pith.science/pith/OFL64GKAEEMVG554EVSUDXRLPP/action/author_attestation","sign_citation":"https://pith.science/pith/OFL64GKAEEMVG554EVSUDXRLPP/action/citation_signature","submit_replication":"https://pith.science/pith/OFL64GKAEEMVG554EVSUDXRLPP/action/replication_record"}},"created_at":"2026-07-05T07:04:32.781408+00:00","updated_at":"2026-07-05T07:04:32.781408+00:00"}