{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ET3VKCHOUHEUFKU64KZEUIGZCW","short_pith_number":"pith:ET3VKCHO","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"},"canonical_sha256":"24f75508eea1c942aa9ee2b24a20d91595103c650a41e976f20a4635982136f9","source":{"kind":"arxiv","id":"2501.14940","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.14940","created_at":"2026-06-30T01:18:17Z"},{"alias_kind":"arxiv_version","alias_value":"2501.14940v4","created_at":"2026-06-30T01:18:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.14940","created_at":"2026-06-30T01:18:17Z"},{"alias_kind":"pith_short_12","alias_value":"ET3VKCHOUHEU","created_at":"2026-06-30T01:18:17Z"},{"alias_kind":"pith_short_16","alias_value":"ET3VKCHOUHEUFKU6","created_at":"2026-06-30T01:18:17Z"},{"alias_kind":"pith_short_8","alias_value":"ET3VKCHO","created_at":"2026-06-30T01:18:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ET3VKCHOUHEUFKU64KZEUIGZCW","target":"record","payload":{"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"},"canonical_sha256":"24f75508eea1c942aa9ee2b24a20d91595103c650a41e976f20a4635982136f9","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"},"source_kind":"arxiv","source_id":"2501.14940","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-30T01:18:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v2BSgGS7n8vFNHyKjD5FBm865ABOjnIHr5X5I54Xdf5pqfYcMcjhU1YjjYGZ8ji5Y6l78jVLIjwEnhFuy+NeCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T21:44:58.713827Z"},"content_sha256":"c18e624497d3e58ba3f7e66d098064b6f48d823fc6761194cf089225acaad6ff","schema_version":"1.0","event_id":"sha256:c18e624497d3e58ba3f7e66d098064b6f48d823fc6761194cf089225acaad6ff"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ET3VKCHOUHEUFKU64KZEUIGZCW","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-30T01:18:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bGR/rOuCiPtDjSbN1JtaXHvAlrR5iQvjEqKXFL97tWW+B9kshAp+e60CGbgosEAVEgLPVWoV+yJMDmv/dVwvBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T21:44:58.714196Z"},"content_sha256":"5d20afd04f9050a8a80e6c40f5650e0267d58c26f1656b29b12bb16de2e12b89","schema_version":"1.0","event_id":"sha256:5d20afd04f9050a8a80e6c40f5650e0267d58c26f1656b29b12bb16de2e12b89"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ET3VKCHOUHEUFKU64KZEUIGZCW/bundle.json","state_url":"https://pith.science/pith/ET3VKCHOUHEUFKU64KZEUIGZCW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ET3VKCHOUHEUFKU64KZEUIGZCW/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-04T21:44:58Z","links":{"resolver":"https://pith.science/pith/ET3VKCHOUHEUFKU64KZEUIGZCW","bundle":"https://pith.science/pith/ET3VKCHOUHEUFKU64KZEUIGZCW/bundle.json","state":"https://pith.science/pith/ET3VKCHOUHEUFKU64KZEUIGZCW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ET3VKCHOUHEUFKU64KZEUIGZCW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ET3VKCHOUHEUFKU64KZEUIGZCW","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":"fb455c6db13b5f991f67110636c42ed2776abaf88bc2e6d13b03b35cf4611728","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-24T21:55:14Z","title_canon_sha256":"feaedbe165a87611bf21d5bf4fde7c51a8c7b49597cb8655dd70d21a94f81818"},"schema_version":"1.0","source":{"id":"2501.14940","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.14940","created_at":"2026-06-30T01:18:17Z"},{"alias_kind":"arxiv_version","alias_value":"2501.14940v4","created_at":"2026-06-30T01:18:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.14940","created_at":"2026-06-30T01:18:17Z"},{"alias_kind":"pith_short_12","alias_value":"ET3VKCHOUHEU","created_at":"2026-06-30T01:18:17Z"},{"alias_kind":"pith_short_16","alias_value":"ET3VKCHOUHEUFKU6","created_at":"2026-06-30T01:18:17Z"},{"alias_kind":"pith_short_8","alias_value":"ET3VKCHO","created_at":"2026-06-30T01:18:17Z"}],"graph_snapshots":[{"event_id":"sha256:5d20afd04f9050a8a80e6c40f5650e0267d58c26f1656b29b12bb16de2e12b89","target":"graph","created_at":"2026-06-30T01:18:17Z","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/2501.14940/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Guangzhi Sun, Jose Such, Philip C. Woodland, Shutong Feng, Xiao Zhan","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-24T21:55:14Z","title":"CASE-Bench: Context-Aware SafEty Benchmark for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.14940","kind":"arxiv","version":4},"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:c18e624497d3e58ba3f7e66d098064b6f48d823fc6761194cf089225acaad6ff","target":"record","created_at":"2026-06-30T01:18:17Z","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":"fb455c6db13b5f991f67110636c42ed2776abaf88bc2e6d13b03b35cf4611728","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-24T21:55:14Z","title_canon_sha256":"feaedbe165a87611bf21d5bf4fde7c51a8c7b49597cb8655dd70d21a94f81818"},"schema_version":"1.0","source":{"id":"2501.14940","kind":"arxiv","version":4}},"canonical_sha256":"24f75508eea1c942aa9ee2b24a20d91595103c650a41e976f20a4635982136f9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"24f75508eea1c942aa9ee2b24a20d91595103c650a41e976f20a4635982136f9","first_computed_at":"2026-06-30T01:18:17.454288Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T01:18:17.454288Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+5baPlzDQO4C7vR3hYOeUykx6dQY1oToOtY6NQ1/un/jQqkrBpwpc89mXjMI+QHiTfix9RuBe6MQJqDnlLGUBQ==","signature_status":"signed_v1","signed_at":"2026-06-30T01:18:17.455040Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.14940","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c18e624497d3e58ba3f7e66d098064b6f48d823fc6761194cf089225acaad6ff","sha256:5d20afd04f9050a8a80e6c40f5650e0267d58c26f1656b29b12bb16de2e12b89"],"state_sha256":"380c2d08eb5e658709852b64a30e7b348aa99ef31ac08e93b21707f5add6fe12"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CUfFCTYNXpP9VWoO82z29v/y2vq9mX26kfV7PbmDby516HZ5HPkgwbSXv6wMqqek888Jr+tzHWXptfmNXAZzBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-04T21:44:58.716111Z","bundle_sha256":"1c6ac20e9f700016e732fcbec519447ed8a219bd0a9fed6038d8622912866068"}}