{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ET3VKCHOUHEUFKU64KZEUIGZCW","short_pith_number":"pith:ET3VKCHO","schema_version":"1.0","canonical_sha256":"24f75508eea1c942aa9ee2b24a20d91595103c650a41e976f20a4635982136f9","source":{"kind":"arxiv","id":"2501.14940","version":4},"attestation_state":"computed","paper":{"title":"CASE-Bench: Context-Aware SafEty Benchmark for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Guangzhi Sun, Jose Such, Philip C. Woodland, Shutong Feng, Xiao Zhan","submitted_at":"2025-01-24T21:55:14Z","abstract_excerpt":"Aligning large language models (LLMs) with human values is essential for their safe deployment and widespread adoption. Current LLM safety benchmarks often focus solely on the refusal of individual problematic queries, which overlooks the importance of the context where the query occurs and may cause undesired refusal of queries under safe contexts that diminish user experience. Addressing this gap, we introduce CASE-Bench, a Context-Aware SafEty Benchmark that integrates context into safety assessments of LLMs. CASE-Bench assigns distinct, formally described contexts to categorized queries ba"},"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":"2501.14940","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-24T21:55:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"feaedbe165a87611bf21d5bf4fde7c51a8c7b49597cb8655dd70d21a94f81818","abstract_canon_sha256":"fb455c6db13b5f991f67110636c42ed2776abaf88bc2e6d13b03b35cf4611728"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:18:17.455040Z","signature_b64":"+5baPlzDQO4C7vR3hYOeUykx6dQY1oToOtY6NQ1/un/jQqkrBpwpc89mXjMI+QHiTfix9RuBe6MQJqDnlLGUBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24f75508eea1c942aa9ee2b24a20d91595103c650a41e976f20a4635982136f9","last_reissued_at":"2026-06-30T01:18:17.454288Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:18:17.454288Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CASE-Bench: Context-Aware SafEty Benchmark for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Guangzhi Sun, Jose Such, Philip C. Woodland, Shutong Feng, Xiao Zhan","submitted_at":"2025-01-24T21:55:14Z","abstract_excerpt":"Aligning large language models (LLMs) with human values is essential for their safe deployment and widespread adoption. Current LLM safety benchmarks often focus solely on the refusal of individual problematic queries, which overlooks the importance of the context where the query occurs and may cause undesired refusal of queries under safe contexts that diminish user experience. Addressing this gap, we introduce CASE-Bench, a Context-Aware SafEty Benchmark that integrates context into safety assessments of LLMs. CASE-Bench assigns distinct, formally described contexts to categorized queries ba"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.14940","kind":"arxiv","version":4},"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/2501.14940/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":"2501.14940","created_at":"2026-06-30T01:18:17.454402+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.14940v4","created_at":"2026-06-30T01:18:17.454402+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.14940","created_at":"2026-06-30T01:18:17.454402+00:00"},{"alias_kind":"pith_short_12","alias_value":"ET3VKCHOUHEU","created_at":"2026-06-30T01:18:17.454402+00:00"},{"alias_kind":"pith_short_16","alias_value":"ET3VKCHOUHEUFKU6","created_at":"2026-06-30T01:18:17.454402+00:00"},{"alias_kind":"pith_short_8","alias_value":"ET3VKCHO","created_at":"2026-06-30T01:18:17.454402+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":7,"sample":[{"citing_arxiv_id":"2606.19887","citing_title":"FinRED: An Expert-Guided Benchmark Generation and Evaluation Framework for Financial LLM Red-Teaming","ref_index":34,"is_internal_anchor":true},{"citing_arxiv_id":"2512.21110","citing_title":"Beyond Context: Large Language Models' Failure to Grasp Users' Intent","ref_index":68,"is_internal_anchor":true},{"citing_arxiv_id":"2604.06233","citing_title":"Blind Refusal: Language Models Refuse to Help Users Evade Unjust, Absurd, and Illegitimate Rules","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10442","citing_title":"StereoTales: A Multilingual Framework for Open-Ended Stereotype Discovery in LLMs","ref_index":104,"is_internal_anchor":true},{"citing_arxiv_id":"2604.27861","citing_title":"TwinGate: Stateful Defense against Decompositional Jailbreaks in Untraceable Traffic via Asymmetric Contrastive Learning","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10442","citing_title":"StereoTales: A Multilingual Framework for Open-Ended Stereotype Discovery in LLMs","ref_index":104,"is_internal_anchor":true},{"citing_arxiv_id":"2604.17301","citing_title":"RoTRAG: Rule of Thumb Reasoning for Conversation Harm Detection with Retrieval-Augmented Generation","ref_index":37,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ET3VKCHOUHEUFKU64KZEUIGZCW","json":"https://pith.science/pith/ET3VKCHOUHEUFKU64KZEUIGZCW.json","graph_json":"https://pith.science/api/pith-number/ET3VKCHOUHEUFKU64KZEUIGZCW/graph.json","events_json":"https://pith.science/api/pith-number/ET3VKCHOUHEUFKU64KZEUIGZCW/events.json","paper":"https://pith.science/paper/ET3VKCHO"},"agent_actions":{"view_html":"https://pith.science/pith/ET3VKCHOUHEUFKU64KZEUIGZCW","download_json":"https://pith.science/pith/ET3VKCHOUHEUFKU64KZEUIGZCW.json","view_paper":"https://pith.science/paper/ET3VKCHO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.14940&json=true","fetch_graph":"https://pith.science/api/pith-number/ET3VKCHOUHEUFKU64KZEUIGZCW/graph.json","fetch_events":"https://pith.science/api/pith-number/ET3VKCHOUHEUFKU64KZEUIGZCW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ET3VKCHOUHEUFKU64KZEUIGZCW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ET3VKCHOUHEUFKU64KZEUIGZCW/action/storage_attestation","attest_author":"https://pith.science/pith/ET3VKCHOUHEUFKU64KZEUIGZCW/action/author_attestation","sign_citation":"https://pith.science/pith/ET3VKCHOUHEUFKU64KZEUIGZCW/action/citation_signature","submit_replication":"https://pith.science/pith/ET3VKCHOUHEUFKU64KZEUIGZCW/action/replication_record"}},"created_at":"2026-06-30T01:18:17.454402+00:00","updated_at":"2026-06-30T01:18:17.454402+00:00"}