{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:LVFUD2OH63RCBS2ADJN5UGIL45","short_pith_number":"pith:LVFUD2OH","schema_version":"1.0","canonical_sha256":"5d4b41e9c7f6e220cb401a5bda190be764f4cf387d3be0b76f53432f5b79b379","source":{"kind":"arxiv","id":"2307.13989","version":1},"attestation_state":"computed","paper":{"title":"This is not correct! Negation-aware Evaluation of Language Generation Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Diego Miguel Lozano, Georg Groh, Miriam Ansch\\\"utz","submitted_at":"2023-07-26T06:54:31Z","abstract_excerpt":"Large language models underestimate the impact of negations on how much they change the meaning of a sentence. Therefore, learned evaluation metrics based on these models are insensitive to negations. In this paper, we propose NegBLEURT, a negation-aware version of the BLEURT evaluation metric. For that, we designed a rule-based sentence negation tool and used it to create the CANNOT negation evaluation dataset. Based on this dataset, we fine-tuned a sentence transformer and an evaluation metric to improve their negation sensitivity. Evaluating these models on existing benchmarks shows that ou"},"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":"2307.13989","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-07-26T06:54:31Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e99bad7b8641cc217a8a7c20ab77fc87818e0551889680a732bf70f9f06975aa","abstract_canon_sha256":"2a21ec805407f198ba0cd965027e71aefcf06edfebaba78014ec296db436a784"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:34:55.927397Z","signature_b64":"DYNiz2Lfz2skUtvhNEKbdvHKqTkLdU0GetwwrunXdaKxQEq5RmpJmQn2QspSTtDI+ieucMITlLQCH2m+oSloCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d4b41e9c7f6e220cb401a5bda190be764f4cf387d3be0b76f53432f5b79b379","last_reissued_at":"2026-07-05T06:34:55.926954Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:34:55.926954Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"This is not correct! Negation-aware Evaluation of Language Generation Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Diego Miguel Lozano, Georg Groh, Miriam Ansch\\\"utz","submitted_at":"2023-07-26T06:54:31Z","abstract_excerpt":"Large language models underestimate the impact of negations on how much they change the meaning of a sentence. Therefore, learned evaluation metrics based on these models are insensitive to negations. In this paper, we propose NegBLEURT, a negation-aware version of the BLEURT evaluation metric. For that, we designed a rule-based sentence negation tool and used it to create the CANNOT negation evaluation dataset. Based on this dataset, we fine-tuned a sentence transformer and an evaluation metric to improve their negation sensitivity. Evaluating these models on existing benchmarks shows that ou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.13989","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/2307.13989/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":"2307.13989","created_at":"2026-07-05T06:34:55.927012+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.13989v1","created_at":"2026-07-05T06:34:55.927012+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.13989","created_at":"2026-07-05T06:34:55.927012+00:00"},{"alias_kind":"pith_short_12","alias_value":"LVFUD2OH63RC","created_at":"2026-07-05T06:34:55.927012+00:00"},{"alias_kind":"pith_short_16","alias_value":"LVFUD2OH63RCBS2A","created_at":"2026-07-05T06:34:55.927012+00:00"},{"alias_kind":"pith_short_8","alias_value":"LVFUD2OH","created_at":"2026-07-05T06:34:55.927012+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.10216","citing_title":"Similarity Gates Approve Reversals: A Validity Audit of Embedding-Cosine Thresholds in Agent Systems","ref_index":2023,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LVFUD2OH63RCBS2ADJN5UGIL45","json":"https://pith.science/pith/LVFUD2OH63RCBS2ADJN5UGIL45.json","graph_json":"https://pith.science/api/pith-number/LVFUD2OH63RCBS2ADJN5UGIL45/graph.json","events_json":"https://pith.science/api/pith-number/LVFUD2OH63RCBS2ADJN5UGIL45/events.json","paper":"https://pith.science/paper/LVFUD2OH"},"agent_actions":{"view_html":"https://pith.science/pith/LVFUD2OH63RCBS2ADJN5UGIL45","download_json":"https://pith.science/pith/LVFUD2OH63RCBS2ADJN5UGIL45.json","view_paper":"https://pith.science/paper/LVFUD2OH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.13989&json=true","fetch_graph":"https://pith.science/api/pith-number/LVFUD2OH63RCBS2ADJN5UGIL45/graph.json","fetch_events":"https://pith.science/api/pith-number/LVFUD2OH63RCBS2ADJN5UGIL45/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LVFUD2OH63RCBS2ADJN5UGIL45/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LVFUD2OH63RCBS2ADJN5UGIL45/action/storage_attestation","attest_author":"https://pith.science/pith/LVFUD2OH63RCBS2ADJN5UGIL45/action/author_attestation","sign_citation":"https://pith.science/pith/LVFUD2OH63RCBS2ADJN5UGIL45/action/citation_signature","submit_replication":"https://pith.science/pith/LVFUD2OH63RCBS2ADJN5UGIL45/action/replication_record"}},"created_at":"2026-07-05T06:34:55.927012+00:00","updated_at":"2026-07-05T06:34:55.927012+00:00"}