{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XWFJQ64YVBDGEAQU4ERLOHX4WM","short_pith_number":"pith:XWFJQ64Y","schema_version":"1.0","canonical_sha256":"bd8a987b98a846620214e122b71efcb3131d1808daba34b3f5e37bb4f0c22e6b","source":{"kind":"arxiv","id":"2502.18935","version":1},"attestation_state":"computed","paper":{"title":"JailBench: A Comprehensive Chinese Security Assessment Benchmark for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Haoran Bu, Shuyi Liu, Simiao Cui, Xi Zhang, Yuming Shang","submitted_at":"2025-02-26T08:36:42Z","abstract_excerpt":"Large language models (LLMs) have demonstrated remarkable capabilities across various applications, highlighting the urgent need for comprehensive safety evaluations. In particular, the enhanced Chinese language proficiency of LLMs, combined with the unique characteristics and complexity of Chinese expressions, has driven the emergence of Chinese-specific benchmarks for safety assessment. However, these benchmarks generally fall short in effectively exposing LLM safety vulnerabilities. To address the gap, we introduce JailBench, the first comprehensive Chinese benchmark for evaluating deep-sea"},"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":"2502.18935","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-26T08:36:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"278c9ef6f0ad49b061f6686399e58c85083be93a928cc907bf77b5ac02615b93","abstract_canon_sha256":"6ee1e5746aae62f51f4fcfd290dc9747f2746474fa41a22b9069beff2bb1c9bd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:20:23.557205Z","signature_b64":"+VMN6c2MAJpP1X6lMzVZQfEUc3AThbf0yTfcouVdq0+TOOMZrWOh2s58dF4PtSm0hiYOqXklCBmm15ievBhwBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd8a987b98a846620214e122b71efcb3131d1808daba34b3f5e37bb4f0c22e6b","last_reissued_at":"2026-07-05T10:20:23.556737Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:20:23.556737Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"JailBench: A Comprehensive Chinese Security Assessment Benchmark for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Haoran Bu, Shuyi Liu, Simiao Cui, Xi Zhang, Yuming Shang","submitted_at":"2025-02-26T08:36:42Z","abstract_excerpt":"Large language models (LLMs) have demonstrated remarkable capabilities across various applications, highlighting the urgent need for comprehensive safety evaluations. In particular, the enhanced Chinese language proficiency of LLMs, combined with the unique characteristics and complexity of Chinese expressions, has driven the emergence of Chinese-specific benchmarks for safety assessment. However, these benchmarks generally fall short in effectively exposing LLM safety vulnerabilities. To address the gap, we introduce JailBench, the first comprehensive Chinese benchmark for evaluating deep-sea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.18935","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/2502.18935/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":"2502.18935","created_at":"2026-07-05T10:20:23.556796+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.18935v1","created_at":"2026-07-05T10:20:23.556796+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.18935","created_at":"2026-07-05T10:20:23.556796+00:00"},{"alias_kind":"pith_short_12","alias_value":"XWFJQ64YVBDG","created_at":"2026-07-05T10:20:23.556796+00:00"},{"alias_kind":"pith_short_16","alias_value":"XWFJQ64YVBDGEAQU","created_at":"2026-07-05T10:20:23.556796+00:00"},{"alias_kind":"pith_short_8","alias_value":"XWFJQ64Y","created_at":"2026-07-05T10:20:23.556796+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/XWFJQ64YVBDGEAQU4ERLOHX4WM","json":"https://pith.science/pith/XWFJQ64YVBDGEAQU4ERLOHX4WM.json","graph_json":"https://pith.science/api/pith-number/XWFJQ64YVBDGEAQU4ERLOHX4WM/graph.json","events_json":"https://pith.science/api/pith-number/XWFJQ64YVBDGEAQU4ERLOHX4WM/events.json","paper":"https://pith.science/paper/XWFJQ64Y"},"agent_actions":{"view_html":"https://pith.science/pith/XWFJQ64YVBDGEAQU4ERLOHX4WM","download_json":"https://pith.science/pith/XWFJQ64YVBDGEAQU4ERLOHX4WM.json","view_paper":"https://pith.science/paper/XWFJQ64Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.18935&json=true","fetch_graph":"https://pith.science/api/pith-number/XWFJQ64YVBDGEAQU4ERLOHX4WM/graph.json","fetch_events":"https://pith.science/api/pith-number/XWFJQ64YVBDGEAQU4ERLOHX4WM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XWFJQ64YVBDGEAQU4ERLOHX4WM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XWFJQ64YVBDGEAQU4ERLOHX4WM/action/storage_attestation","attest_author":"https://pith.science/pith/XWFJQ64YVBDGEAQU4ERLOHX4WM/action/author_attestation","sign_citation":"https://pith.science/pith/XWFJQ64YVBDGEAQU4ERLOHX4WM/action/citation_signature","submit_replication":"https://pith.science/pith/XWFJQ64YVBDGEAQU4ERLOHX4WM/action/replication_record"}},"created_at":"2026-07-05T10:20:23.556796+00:00","updated_at":"2026-07-05T10:20:23.556796+00:00"}