{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:72CC5TMHV62TH7RYXQN77EROJB","short_pith_number":"pith:72CC5TMH","schema_version":"1.0","canonical_sha256":"fe842ecd87afb533fe38bc1bff922e485eceb7111db226a5e01a6424d1de62f2","source":{"kind":"arxiv","id":"2601.13864","version":2},"attestation_state":"computed","paper":{"title":"HardSecBench: Benchmarking the Security Awareness of LLMs for Hardware Code Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Jiangming Li, Jian Yang, Jie Jin, Jingxian Shuai, Jun Chen, Qirui Chen, Shenghao Ye, Shuangwu Chen, Xiaobin Tan, Xufei Su, Zijian Wen","submitted_at":"2026-01-20T11:27:40Z","abstract_excerpt":"Large language models (LLMs) are increasingly used for hardware and firmware code generation, but existing studies primarily evaluate functional correctness while largely overlooking security. However, LLM-generated code that appears functionally sound may embed security flaws which could induce catastrophic damages after deployment. This critical research gap motivates us to design a benchmark for assessing security awareness under realistic specifications. In this work, we introduce HardSecBench, a benchmark with 924 tasks spanning Verilog Register Transfer Level (RTL) and firmware-level C, "},"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":"2601.13864","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2026-01-20T11:27:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"eade4b371319757d13c0575d07a25195fd588eb2c766c1f508aa1a8f659ec0e8","abstract_canon_sha256":"93c43782097ee8a5620e4ff7974b2a20c9e6187408948ead0e5dff4ef35bf4a0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:13:20.145933Z","signature_b64":"f2fSLA6jIPD72cVGEL9MOca62eQy9bQO4LEThsmIHvFLfoMY4ihP0Xh/Z2BynK7P/VphgaGtqxb4NDvEFirXBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe842ecd87afb533fe38bc1bff922e485eceb7111db226a5e01a6424d1de62f2","last_reissued_at":"2026-06-23T02:13:20.145521Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:13:20.145521Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HardSecBench: Benchmarking the Security Awareness of LLMs for Hardware Code Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Jiangming Li, Jian Yang, Jie Jin, Jingxian Shuai, Jun Chen, Qirui Chen, Shenghao Ye, Shuangwu Chen, Xiaobin Tan, Xufei Su, Zijian Wen","submitted_at":"2026-01-20T11:27:40Z","abstract_excerpt":"Large language models (LLMs) are increasingly used for hardware and firmware code generation, but existing studies primarily evaluate functional correctness while largely overlooking security. However, LLM-generated code that appears functionally sound may embed security flaws which could induce catastrophic damages after deployment. This critical research gap motivates us to design a benchmark for assessing security awareness under realistic specifications. In this work, we introduce HardSecBench, a benchmark with 924 tasks spanning Verilog Register Transfer Level (RTL) and firmware-level C, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.13864","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/2601.13864/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":"2601.13864","created_at":"2026-06-23T02:13:20.145579+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.13864v2","created_at":"2026-06-23T02:13:20.145579+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.13864","created_at":"2026-06-23T02:13:20.145579+00:00"},{"alias_kind":"pith_short_12","alias_value":"72CC5TMHV62T","created_at":"2026-06-23T02:13:20.145579+00:00"},{"alias_kind":"pith_short_16","alias_value":"72CC5TMHV62TH7RY","created_at":"2026-06-23T02:13:20.145579+00:00"},{"alias_kind":"pith_short_8","alias_value":"72CC5TMH","created_at":"2026-06-23T02:13:20.145579+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/72CC5TMHV62TH7RYXQN77EROJB","json":"https://pith.science/pith/72CC5TMHV62TH7RYXQN77EROJB.json","graph_json":"https://pith.science/api/pith-number/72CC5TMHV62TH7RYXQN77EROJB/graph.json","events_json":"https://pith.science/api/pith-number/72CC5TMHV62TH7RYXQN77EROJB/events.json","paper":"https://pith.science/paper/72CC5TMH"},"agent_actions":{"view_html":"https://pith.science/pith/72CC5TMHV62TH7RYXQN77EROJB","download_json":"https://pith.science/pith/72CC5TMHV62TH7RYXQN77EROJB.json","view_paper":"https://pith.science/paper/72CC5TMH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.13864&json=true","fetch_graph":"https://pith.science/api/pith-number/72CC5TMHV62TH7RYXQN77EROJB/graph.json","fetch_events":"https://pith.science/api/pith-number/72CC5TMHV62TH7RYXQN77EROJB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/72CC5TMHV62TH7RYXQN77EROJB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/72CC5TMHV62TH7RYXQN77EROJB/action/storage_attestation","attest_author":"https://pith.science/pith/72CC5TMHV62TH7RYXQN77EROJB/action/author_attestation","sign_citation":"https://pith.science/pith/72CC5TMHV62TH7RYXQN77EROJB/action/citation_signature","submit_replication":"https://pith.science/pith/72CC5TMHV62TH7RYXQN77EROJB/action/replication_record"}},"created_at":"2026-06-23T02:13:20.145579+00:00","updated_at":"2026-06-23T02:13:20.145579+00:00"}