{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:OFL64GKAEEMVG554EVSUDXRLPP","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":"daae445a51e2a427bfcea876e510deed84e3323428d81a54a87aac28fb428960","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-24T15:38:21Z","title_canon_sha256":"8e0cd30d3799c63141dd375130da4f7c9a8538f0741830ffb90c9ed1aeef5d5c"},"schema_version":"1.0","source":{"id":"2310.15941","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.15941","created_at":"2026-07-05T07:04:32Z"},{"alias_kind":"arxiv_version","alias_value":"2310.15941v1","created_at":"2026-07-05T07:04:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.15941","created_at":"2026-07-05T07:04:32Z"},{"alias_kind":"pith_short_12","alias_value":"OFL64GKAEEMV","created_at":"2026-07-05T07:04:32Z"},{"alias_kind":"pith_short_16","alias_value":"OFL64GKAEEMVG554","created_at":"2026-07-05T07:04:32Z"},{"alias_kind":"pith_short_8","alias_value":"OFL64GKA","created_at":"2026-07-05T07:04:32Z"}],"graph_snapshots":[{"event_id":"sha256:9fd3801f878d3db322c8dfe59b2a76f70af33d388902a029a9b2fc171fd6fd3c","target":"graph","created_at":"2026-07-05T07:04:32Z","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/2310.15941/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Bego\\~na Altuna, German Rigau, Iker Garc\\'ia-Ferrero, Itziar Gonzalez-Dios, Javier \\'Alvez","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-24T15:38:21Z","title":"This is not a Dataset: A Large Negation Benchmark to Challenge Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.15941","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":"sha256:0a328b23d2e7d10aaa508f5d49996a35902958cf0da1829aeab12cc9c0fc7658","target":"record","created_at":"2026-07-05T07:04:32Z","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":"daae445a51e2a427bfcea876e510deed84e3323428d81a54a87aac28fb428960","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-24T15:38:21Z","title_canon_sha256":"8e0cd30d3799c63141dd375130da4f7c9a8538f0741830ffb90c9ed1aeef5d5c"},"schema_version":"1.0","source":{"id":"2310.15941","kind":"arxiv","version":1}},"canonical_sha256":"7157ee194021195377bc256541de2b7bdad6fb6bc309499ba0dc95aea4fb7c97","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7157ee194021195377bc256541de2b7bdad6fb6bc309499ba0dc95aea4fb7c97","first_computed_at":"2026-07-05T07:04:32.781350Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:04:32.781350Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GUS5qapYosenURBGQ5eDxv4jbPvZwVf4naj7EYM8YHxbQU/DExF1X32/yhU3RbMpSj5CKHsjz/JyRIZ2m0HwDw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:04:32.781806Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.15941","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0a328b23d2e7d10aaa508f5d49996a35902958cf0da1829aeab12cc9c0fc7658","sha256:9fd3801f878d3db322c8dfe59b2a76f70af33d388902a029a9b2fc171fd6fd3c"],"state_sha256":"00706a9c914c239684bbfbad33134742fbb8db098ac308cf5cdace6c74b20bbb"}