{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:22BGVMQZJZ3LNISVBOBBVMBT3D","short_pith_number":"pith:22BGVMQZ","schema_version":"1.0","canonical_sha256":"d6826ab2194e76b6a2550b821ab033d8d78c302cbdba6e4601d2f0ace580ddab","source":{"kind":"arxiv","id":"2411.16239","version":3},"attestation_state":"computed","paper":{"title":"CS-Eval: A Comprehensive Large Language Model Benchmark for CyberSecurity","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Dandan Xu, Jiutian Zeng, Min Yang, Nan Wang, Siyi Chen, Wenhan Xu, Xiangyu Liu, Yuan Zhang, Zhengmin Yu, Zonghao Ying","submitted_at":"2024-11-25T09:54:42Z","abstract_excerpt":"Over the past year, there has been a notable rise in the use of large language models (LLMs) for academic research and industrial practices within the cybersecurity field. However, it remains a lack of comprehensive and publicly accessible benchmarks to evaluate the performance of LLMs on cybersecurity tasks. To address this gap, we introduce CS-Eval, a publicly accessible, comprehensive and bilingual LLM benchmark specifically designed for cybersecurity. CS-Eval synthesizes the research hotspots from academia and practical applications from industry, curating a diverse set of high-quality que"},"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":"2411.16239","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CR","submitted_at":"2024-11-25T09:54:42Z","cross_cats_sorted":[],"title_canon_sha256":"4c7462abcc0c0714528e9a289bdb5428815a7c8358b592dc0a0af0d2643d8a76","abstract_canon_sha256":"3418646aed7dab692800a45dedfe71e89d7e512c3a3cff723417d685093c17f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:02:08.049903Z","signature_b64":"idVFwTgZfnzWy8advUMCC5KeVL5De5nepxM8uKa/hBY6ceO+PX0zihLYhlG+/T6XjAwoFWbTKvtfLYQki/svBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d6826ab2194e76b6a2550b821ab033d8d78c302cbdba6e4601d2f0ace580ddab","last_reissued_at":"2026-07-05T10:02:08.049546Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:02:08.049546Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CS-Eval: A Comprehensive Large Language Model Benchmark for CyberSecurity","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Dandan Xu, Jiutian Zeng, Min Yang, Nan Wang, Siyi Chen, Wenhan Xu, Xiangyu Liu, Yuan Zhang, Zhengmin Yu, Zonghao Ying","submitted_at":"2024-11-25T09:54:42Z","abstract_excerpt":"Over the past year, there has been a notable rise in the use of large language models (LLMs) for academic research and industrial practices within the cybersecurity field. However, it remains a lack of comprehensive and publicly accessible benchmarks to evaluate the performance of LLMs on cybersecurity tasks. To address this gap, we introduce CS-Eval, a publicly accessible, comprehensive and bilingual LLM benchmark specifically designed for cybersecurity. CS-Eval synthesizes the research hotspots from academia and practical applications from industry, curating a diverse set of high-quality que"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.16239","kind":"arxiv","version":3},"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/2411.16239/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":"2411.16239","created_at":"2026-07-05T10:02:08.049603+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.16239v3","created_at":"2026-07-05T10:02:08.049603+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.16239","created_at":"2026-07-05T10:02:08.049603+00:00"},{"alias_kind":"pith_short_12","alias_value":"22BGVMQZJZ3L","created_at":"2026-07-05T10:02:08.049603+00:00"},{"alias_kind":"pith_short_16","alias_value":"22BGVMQZJZ3LNISV","created_at":"2026-07-05T10:02:08.049603+00:00"},{"alias_kind":"pith_short_8","alias_value":"22BGVMQZ","created_at":"2026-07-05T10:02:08.049603+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/22BGVMQZJZ3LNISVBOBBVMBT3D","json":"https://pith.science/pith/22BGVMQZJZ3LNISVBOBBVMBT3D.json","graph_json":"https://pith.science/api/pith-number/22BGVMQZJZ3LNISVBOBBVMBT3D/graph.json","events_json":"https://pith.science/api/pith-number/22BGVMQZJZ3LNISVBOBBVMBT3D/events.json","paper":"https://pith.science/paper/22BGVMQZ"},"agent_actions":{"view_html":"https://pith.science/pith/22BGVMQZJZ3LNISVBOBBVMBT3D","download_json":"https://pith.science/pith/22BGVMQZJZ3LNISVBOBBVMBT3D.json","view_paper":"https://pith.science/paper/22BGVMQZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.16239&json=true","fetch_graph":"https://pith.science/api/pith-number/22BGVMQZJZ3LNISVBOBBVMBT3D/graph.json","fetch_events":"https://pith.science/api/pith-number/22BGVMQZJZ3LNISVBOBBVMBT3D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/22BGVMQZJZ3LNISVBOBBVMBT3D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/22BGVMQZJZ3LNISVBOBBVMBT3D/action/storage_attestation","attest_author":"https://pith.science/pith/22BGVMQZJZ3LNISVBOBBVMBT3D/action/author_attestation","sign_citation":"https://pith.science/pith/22BGVMQZJZ3LNISVBOBBVMBT3D/action/citation_signature","submit_replication":"https://pith.science/pith/22BGVMQZJZ3LNISVBOBBVMBT3D/action/replication_record"}},"created_at":"2026-07-05T10:02:08.049603+00:00","updated_at":"2026-07-05T10:02:08.049603+00:00"}