{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:LVFUD2OH63RCBS2ADJN5UGIL45","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":"2a21ec805407f198ba0cd965027e71aefcf06edfebaba78014ec296db436a784","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-07-26T06:54:31Z","title_canon_sha256":"e99bad7b8641cc217a8a7c20ab77fc87818e0551889680a732bf70f9f06975aa"},"schema_version":"1.0","source":{"id":"2307.13989","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.13989","created_at":"2026-07-05T06:34:55Z"},{"alias_kind":"arxiv_version","alias_value":"2307.13989v1","created_at":"2026-07-05T06:34:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.13989","created_at":"2026-07-05T06:34:55Z"},{"alias_kind":"pith_short_12","alias_value":"LVFUD2OH63RC","created_at":"2026-07-05T06:34:55Z"},{"alias_kind":"pith_short_16","alias_value":"LVFUD2OH63RCBS2A","created_at":"2026-07-05T06:34:55Z"},{"alias_kind":"pith_short_8","alias_value":"LVFUD2OH","created_at":"2026-07-05T06:34:55Z"}],"graph_snapshots":[{"event_id":"sha256:9e60b9b78c49861f9364b81941a01365d96154605772a7a53c55a047478c00d5","target":"graph","created_at":"2026-07-05T06:34:55Z","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/2307.13989/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Diego Miguel Lozano, Georg Groh, Miriam Ansch\\\"utz","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-07-26T06:54:31Z","title":"This is not correct! Negation-aware Evaluation of Language Generation Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.13989","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":"sha256:070370fa98b071928de8fa69c0275a24fb16f99831e8a90336dcb15bda5dfee8","target":"record","created_at":"2026-07-05T06:34:55Z","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":"2a21ec805407f198ba0cd965027e71aefcf06edfebaba78014ec296db436a784","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-07-26T06:54:31Z","title_canon_sha256":"e99bad7b8641cc217a8a7c20ab77fc87818e0551889680a732bf70f9f06975aa"},"schema_version":"1.0","source":{"id":"2307.13989","kind":"arxiv","version":1}},"canonical_sha256":"5d4b41e9c7f6e220cb401a5bda190be764f4cf387d3be0b76f53432f5b79b379","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5d4b41e9c7f6e220cb401a5bda190be764f4cf387d3be0b76f53432f5b79b379","first_computed_at":"2026-07-05T06:34:55.926954Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:34:55.926954Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DYNiz2Lfz2skUtvhNEKbdvHKqTkLdU0GetwwrunXdaKxQEq5RmpJmQn2QspSTtDI+ieucMITlLQCH2m+oSloCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:34:55.927397Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.13989","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:070370fa98b071928de8fa69c0275a24fb16f99831e8a90336dcb15bda5dfee8","sha256:9e60b9b78c49861f9364b81941a01365d96154605772a7a53c55a047478c00d5"],"state_sha256":"52982d3d16e3093ed5a805dac984eac757d3277dc154cceb87e352f2229dfabb"}