{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PFXKAVC4TSSZOP56EH3MINHMFI","short_pith_number":"pith:PFXKAVC4","schema_version":"1.0","canonical_sha256":"796ea0545c9ca5973fbe21f6c434ec2a044c12dffcd9b6e2fcf41f612c8a29ab","source":{"kind":"arxiv","id":"2406.10311","version":2},"attestation_state":"computed","paper":{"title":"CHiSafetyBench: A Chinese Hierarchical Safety 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":"Bikun Yang, Kaikai Zhao, Kai Wang, Meijuan An, Shiguo Lian, Wenjing Zhang, Xuejiao Lei, Zhaoxiang Liu","submitted_at":"2024-06-14T06:47:40Z","abstract_excerpt":"With the profound development of large language models(LLMs), their safety concerns have garnered increasing attention. However, there is a scarcity of Chinese safety benchmarks for LLMs, and the existing safety taxonomies are inadequate, lacking comprehensive safety detection capabilities in authentic Chinese scenarios. In this work, we introduce CHiSafetyBench, a dedicated safety benchmark for evaluating LLMs' capabilities in identifying risky content and refusing answering risky questions in Chinese contexts. CHiSafetyBench incorporates a dataset that covers a hierarchical Chinese safety ta"},"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":"2406.10311","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-14T06:47:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"466bc715addcf93fed644d445d92a5c162b8a4c6d408bda452dc675f5929ccda","abstract_canon_sha256":"b8f67e09e4c36992a98653b7cdd99ad4637d4091bb272fa42b577abd3c4ac826"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:01:35.388205Z","signature_b64":"NisGH0e6yqD2F9261V+y4ltsuK+UOTUoTtR+QLMQc0MsN1hzEajUQJp8fv65PLnVvcIjZIhdYrqC+WbbVennBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"796ea0545c9ca5973fbe21f6c434ec2a044c12dffcd9b6e2fcf41f612c8a29ab","last_reissued_at":"2026-07-05T09:01:35.387794Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:01:35.387794Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CHiSafetyBench: A Chinese Hierarchical Safety 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":"Bikun Yang, Kaikai Zhao, Kai Wang, Meijuan An, Shiguo Lian, Wenjing Zhang, Xuejiao Lei, Zhaoxiang Liu","submitted_at":"2024-06-14T06:47:40Z","abstract_excerpt":"With the profound development of large language models(LLMs), their safety concerns have garnered increasing attention. However, there is a scarcity of Chinese safety benchmarks for LLMs, and the existing safety taxonomies are inadequate, lacking comprehensive safety detection capabilities in authentic Chinese scenarios. In this work, we introduce CHiSafetyBench, a dedicated safety benchmark for evaluating LLMs' capabilities in identifying risky content and refusing answering risky questions in Chinese contexts. CHiSafetyBench incorporates a dataset that covers a hierarchical Chinese safety ta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.10311","kind":"arxiv","version":2},"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/2406.10311/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":"2406.10311","created_at":"2026-07-05T09:01:35.387848+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.10311v2","created_at":"2026-07-05T09:01:35.387848+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.10311","created_at":"2026-07-05T09:01:35.387848+00:00"},{"alias_kind":"pith_short_12","alias_value":"PFXKAVC4TSSZ","created_at":"2026-07-05T09:01:35.387848+00:00"},{"alias_kind":"pith_short_16","alias_value":"PFXKAVC4TSSZOP56","created_at":"2026-07-05T09:01:35.387848+00:00"},{"alias_kind":"pith_short_8","alias_value":"PFXKAVC4","created_at":"2026-07-05T09:01:35.387848+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.03871","citing_title":"A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models","ref_index":254,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PFXKAVC4TSSZOP56EH3MINHMFI","json":"https://pith.science/pith/PFXKAVC4TSSZOP56EH3MINHMFI.json","graph_json":"https://pith.science/api/pith-number/PFXKAVC4TSSZOP56EH3MINHMFI/graph.json","events_json":"https://pith.science/api/pith-number/PFXKAVC4TSSZOP56EH3MINHMFI/events.json","paper":"https://pith.science/paper/PFXKAVC4"},"agent_actions":{"view_html":"https://pith.science/pith/PFXKAVC4TSSZOP56EH3MINHMFI","download_json":"https://pith.science/pith/PFXKAVC4TSSZOP56EH3MINHMFI.json","view_paper":"https://pith.science/paper/PFXKAVC4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.10311&json=true","fetch_graph":"https://pith.science/api/pith-number/PFXKAVC4TSSZOP56EH3MINHMFI/graph.json","fetch_events":"https://pith.science/api/pith-number/PFXKAVC4TSSZOP56EH3MINHMFI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PFXKAVC4TSSZOP56EH3MINHMFI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PFXKAVC4TSSZOP56EH3MINHMFI/action/storage_attestation","attest_author":"https://pith.science/pith/PFXKAVC4TSSZOP56EH3MINHMFI/action/author_attestation","sign_citation":"https://pith.science/pith/PFXKAVC4TSSZOP56EH3MINHMFI/action/citation_signature","submit_replication":"https://pith.science/pith/PFXKAVC4TSSZOP56EH3MINHMFI/action/replication_record"}},"created_at":"2026-07-05T09:01:35.387848+00:00","updated_at":"2026-07-05T09:01:35.387848+00:00"}