{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:25MANYIAAPJGDHWNLJGFGUBVWS","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":"92e551ea1df9c87b9e1322dec0436a9244208028044af98fb0198e1cbfa8fa47","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2024-12-30T08:11:54Z","title_canon_sha256":"08a7b48e067990b2c99be4196d24c852e0651c38bc822215a72aed0067f7d4c2"},"schema_version":"1.0","source":{"id":"2412.20787","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.20787","created_at":"2026-07-05T09:56:58Z"},{"alias_kind":"arxiv_version","alias_value":"2412.20787v3","created_at":"2026-07-05T09:56:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.20787","created_at":"2026-07-05T09:56:58Z"},{"alias_kind":"pith_short_12","alias_value":"25MANYIAAPJG","created_at":"2026-07-05T09:56:58Z"},{"alias_kind":"pith_short_16","alias_value":"25MANYIAAPJGDHWN","created_at":"2026-07-05T09:56:58Z"},{"alias_kind":"pith_short_8","alias_value":"25MANYIA","created_at":"2026-07-05T09:56:58Z"}],"graph_snapshots":[{"event_id":"sha256:bda2b4d59a4de3a4db8eefc3a9541ef0481b058e1053e3971026228523addf61","target":"graph","created_at":"2026-07-05T09:56:58Z","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/2412.20787/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Mengyun Tang, Pengfei Jing, Sen Nie, Shi Wu, Xiaorong Shi, Xiapu Luo, Xing Zheng, Yong Yang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2024-12-30T08:11:54Z","title":"SecBench: A Comprehensive Multi-Dimensional Benchmarking Dataset for LLMs in Cybersecurity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.20787","kind":"arxiv","version":3},"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":"sha256:0b045ff4a1b2851d4e3812b7509bb602ccf986c27d986cda2f7995285cbd497d","target":"record","created_at":"2026-07-05T09:56:58Z","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":"92e551ea1df9c87b9e1322dec0436a9244208028044af98fb0198e1cbfa8fa47","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2024-12-30T08:11:54Z","title_canon_sha256":"08a7b48e067990b2c99be4196d24c852e0651c38bc822215a72aed0067f7d4c2"},"schema_version":"1.0","source":{"id":"2412.20787","kind":"arxiv","version":3}},"canonical_sha256":"d75806e10003d2619ecd5a4c535035b4a508cbfbefe8fe41e3dad90fc304dcba","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d75806e10003d2619ecd5a4c535035b4a508cbfbefe8fe41e3dad90fc304dcba","first_computed_at":"2026-07-05T09:56:58.803110Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:56:58.803110Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Pb318IGxTw9NFWbdKwFjCdUI3rOV5MPd6S5vrnhGhqWBTY6jLrmVSoNU9WRaCJX2M2AsVYW4H7dFjrgnUWMCCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:56:58.803616Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.20787","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0b045ff4a1b2851d4e3812b7509bb602ccf986c27d986cda2f7995285cbd497d","sha256:bda2b4d59a4de3a4db8eefc3a9541ef0481b058e1053e3971026228523addf61"],"state_sha256":"2b1cb39eacece004d62e5005e28d116a7fc74eafedcb989d5d25fe07fa3c362b"}