{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:3LOBCWSM4LN7CCMTY7DL3WZVB5","short_pith_number":"pith:3LOBCWSM","schema_version":"1.0","canonical_sha256":"dadc115a4ce2dbf10993c7c6bddb350f4b2eeef9fa4e66dec8d0d2913df0b03e","source":{"kind":"arxiv","id":"2305.19426","version":1},"attestation_state":"computed","paper":{"title":"ScoNe: Benchmarking Negation Reasoning in Language Models With Fine-Tuning and In-Context Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Atticus Geiger, Christopher Potts, Jingyuan Selena She, Samuel R. Bowman","submitted_at":"2023-05-30T21:43:11Z","abstract_excerpt":"A number of recent benchmarks seek to assess how well models handle natural language negation. However, these benchmarks lack the controlled example paradigms that would allow us to infer whether a model had learned how negation morphemes semantically scope. To fill these analytical gaps, we present the Scoped Negation NLI (ScoNe-NLI) benchmark, which contains contrast sets of six examples with up to two negations where either zero, one, or both negative morphemes affect the NLI label. We use ScoNe-NLI to assess fine-tuning and in-context learning strategies. We find that RoBERTa and DeBERTa m"},"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":"2305.19426","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-30T21:43:11Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"aad4c71a9acbb5bf9d8278862f568ae117a916db30c962c4ff946a4c54803a12","abstract_canon_sha256":"aa8e14b83b49db5442a43dd3b2367e78c65292eac4da3bcd0859577b1c219669"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:09:23.916982Z","signature_b64":"tbOjyJUFHWBHHNA2w2MzTuLdmkx0o/z03xQUuQ+nmEKVG9q5Ot/qyDKm0mdkjof2kaPLBk8/P8cj7lPFYA/1CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dadc115a4ce2dbf10993c7c6bddb350f4b2eeef9fa4e66dec8d0d2913df0b03e","last_reissued_at":"2026-07-05T08:09:23.916550Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:09:23.916550Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ScoNe: Benchmarking Negation Reasoning in Language Models With Fine-Tuning and In-Context Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Atticus Geiger, Christopher Potts, Jingyuan Selena She, Samuel R. Bowman","submitted_at":"2023-05-30T21:43:11Z","abstract_excerpt":"A number of recent benchmarks seek to assess how well models handle natural language negation. However, these benchmarks lack the controlled example paradigms that would allow us to infer whether a model had learned how negation morphemes semantically scope. To fill these analytical gaps, we present the Scoped Negation NLI (ScoNe-NLI) benchmark, which contains contrast sets of six examples with up to two negations where either zero, one, or both negative morphemes affect the NLI label. We use ScoNe-NLI to assess fine-tuning and in-context learning strategies. We find that RoBERTa and DeBERTa m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.19426","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/2305.19426/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":"2305.19426","created_at":"2026-07-05T08:09:23.916603+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.19426v1","created_at":"2026-07-05T08:09:23.916603+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.19426","created_at":"2026-07-05T08:09:23.916603+00:00"},{"alias_kind":"pith_short_12","alias_value":"3LOBCWSM4LN7","created_at":"2026-07-05T08:09:23.916603+00:00"},{"alias_kind":"pith_short_16","alias_value":"3LOBCWSM4LN7CCMT","created_at":"2026-07-05T08:09:23.916603+00:00"},{"alias_kind":"pith_short_8","alias_value":"3LOBCWSM","created_at":"2026-07-05T08:09:23.916603+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3LOBCWSM4LN7CCMTY7DL3WZVB5","json":"https://pith.science/pith/3LOBCWSM4LN7CCMTY7DL3WZVB5.json","graph_json":"https://pith.science/api/pith-number/3LOBCWSM4LN7CCMTY7DL3WZVB5/graph.json","events_json":"https://pith.science/api/pith-number/3LOBCWSM4LN7CCMTY7DL3WZVB5/events.json","paper":"https://pith.science/paper/3LOBCWSM"},"agent_actions":{"view_html":"https://pith.science/pith/3LOBCWSM4LN7CCMTY7DL3WZVB5","download_json":"https://pith.science/pith/3LOBCWSM4LN7CCMTY7DL3WZVB5.json","view_paper":"https://pith.science/paper/3LOBCWSM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.19426&json=true","fetch_graph":"https://pith.science/api/pith-number/3LOBCWSM4LN7CCMTY7DL3WZVB5/graph.json","fetch_events":"https://pith.science/api/pith-number/3LOBCWSM4LN7CCMTY7DL3WZVB5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3LOBCWSM4LN7CCMTY7DL3WZVB5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3LOBCWSM4LN7CCMTY7DL3WZVB5/action/storage_attestation","attest_author":"https://pith.science/pith/3LOBCWSM4LN7CCMTY7DL3WZVB5/action/author_attestation","sign_citation":"https://pith.science/pith/3LOBCWSM4LN7CCMTY7DL3WZVB5/action/citation_signature","submit_replication":"https://pith.science/pith/3LOBCWSM4LN7CCMTY7DL3WZVB5/action/replication_record"}},"created_at":"2026-07-05T08:09:23.916603+00:00","updated_at":"2026-07-05T08:09:23.916603+00:00"}