{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:25MANYIAAPJGDHWNLJGFGUBVWS","short_pith_number":"pith:25MANYIA","schema_version":"1.0","canonical_sha256":"d75806e10003d2619ecd5a4c535035b4a508cbfbefe8fe41e3dad90fc304dcba","source":{"kind":"arxiv","id":"2412.20787","version":3},"attestation_state":"computed","paper":{"title":"SecBench: A Comprehensive Multi-Dimensional Benchmarking Dataset for LLMs in Cybersecurity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Mengyun Tang, Pengfei Jing, Sen Nie, Shi Wu, Xiaorong Shi, Xiapu Luo, Xing Zheng, Yong Yang","submitted_at":"2024-12-30T08:11:54Z","abstract_excerpt":"Evaluating Large Language Models (LLMs) is crucial for understanding their capabilities and limitations across various applications, including natural language processing and code generation. Existing benchmarks like MMLU, C-Eval, and HumanEval assess general LLM performance but lack focus on specific expert domains such as cybersecurity. Previous attempts to create cybersecurity datasets have faced limitations, including insufficient data volume and a reliance on multiple-choice questions (MCQs). To address these gaps, we propose SecBench, a multi-dimensional benchmarking dataset designed to "},"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":"2412.20787","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2024-12-30T08:11:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"08a7b48e067990b2c99be4196d24c852e0651c38bc822215a72aed0067f7d4c2","abstract_canon_sha256":"92e551ea1df9c87b9e1322dec0436a9244208028044af98fb0198e1cbfa8fa47"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:56:58.803616Z","signature_b64":"Pb318IGxTw9NFWbdKwFjCdUI3rOV5MPd6S5vrnhGhqWBTY6jLrmVSoNU9WRaCJX2M2AsVYW4H7dFjrgnUWMCCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d75806e10003d2619ecd5a4c535035b4a508cbfbefe8fe41e3dad90fc304dcba","last_reissued_at":"2026-07-05T09:56:58.803110Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:56:58.803110Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SecBench: A Comprehensive Multi-Dimensional Benchmarking Dataset for LLMs in Cybersecurity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Mengyun Tang, Pengfei Jing, Sen Nie, Shi Wu, Xiaorong Shi, Xiapu Luo, Xing Zheng, Yong Yang","submitted_at":"2024-12-30T08:11:54Z","abstract_excerpt":"Evaluating Large Language Models (LLMs) is crucial for understanding their capabilities and limitations across various applications, including natural language processing and code generation. Existing benchmarks like MMLU, C-Eval, and HumanEval assess general LLM performance but lack focus on specific expert domains such as cybersecurity. Previous attempts to create cybersecurity datasets have faced limitations, including insufficient data volume and a reliance on multiple-choice questions (MCQs). To address these gaps, we propose SecBench, a multi-dimensional benchmarking dataset designed to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.20787","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/2412.20787/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":"2412.20787","created_at":"2026-07-05T09:56:58.803170+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.20787v3","created_at":"2026-07-05T09:56:58.803170+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.20787","created_at":"2026-07-05T09:56:58.803170+00:00"},{"alias_kind":"pith_short_12","alias_value":"25MANYIAAPJG","created_at":"2026-07-05T09:56:58.803170+00:00"},{"alias_kind":"pith_short_16","alias_value":"25MANYIAAPJGDHWN","created_at":"2026-07-05T09:56:58.803170+00:00"},{"alias_kind":"pith_short_8","alias_value":"25MANYIA","created_at":"2026-07-05T09:56:58.803170+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24819","citing_title":"HelpBench: Assessing the Ability of LLMs to Provide Privacy, Safety, and Security Advice","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2507.14201","citing_title":"ExCyTIn-Bench: Evaluating LLM agents on Cyber Threat Investigation","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2509.06921","citing_title":"Neuro-Symbolic AI for Cybersecurity: State of the Art, Challenges, and Opportunities","ref_index":179,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08316","citing_title":"AI-Driven Security Alert Screening and Alert Fatigue Mitigation in Security Operations Centers: A Comprehensive Survey","ref_index":171,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19533","citing_title":"Cyber Defense Benchmark: Agentic Threat Hunting Evaluation for LLMs in SecOps","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/25MANYIAAPJGDHWNLJGFGUBVWS","json":"https://pith.science/pith/25MANYIAAPJGDHWNLJGFGUBVWS.json","graph_json":"https://pith.science/api/pith-number/25MANYIAAPJGDHWNLJGFGUBVWS/graph.json","events_json":"https://pith.science/api/pith-number/25MANYIAAPJGDHWNLJGFGUBVWS/events.json","paper":"https://pith.science/paper/25MANYIA"},"agent_actions":{"view_html":"https://pith.science/pith/25MANYIAAPJGDHWNLJGFGUBVWS","download_json":"https://pith.science/pith/25MANYIAAPJGDHWNLJGFGUBVWS.json","view_paper":"https://pith.science/paper/25MANYIA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.20787&json=true","fetch_graph":"https://pith.science/api/pith-number/25MANYIAAPJGDHWNLJGFGUBVWS/graph.json","fetch_events":"https://pith.science/api/pith-number/25MANYIAAPJGDHWNLJGFGUBVWS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/25MANYIAAPJGDHWNLJGFGUBVWS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/25MANYIAAPJGDHWNLJGFGUBVWS/action/storage_attestation","attest_author":"https://pith.science/pith/25MANYIAAPJGDHWNLJGFGUBVWS/action/author_attestation","sign_citation":"https://pith.science/pith/25MANYIAAPJGDHWNLJGFGUBVWS/action/citation_signature","submit_replication":"https://pith.science/pith/25MANYIAAPJGDHWNLJGFGUBVWS/action/replication_record"}},"created_at":"2026-07-05T09:56:58.803170+00:00","updated_at":"2026-07-05T09:56:58.803170+00:00"}