{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WD2SZFTUSY4XHZAVCRBXOD3PCN","short_pith_number":"pith:WD2SZFTU","schema_version":"1.0","canonical_sha256":"b0f52c9674963973e4151443770f6f13667e6bcafc626062b8cdd8b37289a007","source":{"kind":"arxiv","id":"2506.05692","version":3},"attestation_state":"computed","paper":{"title":"SafeGenBench: A Benchmark Framework for Security Vulnerability Detection in LLM-Generated Code","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Bing Zhao, Chao Peng, Hongwan Gao, Jingzhe Ding, Xiang Gao, Xinchen Gu, Xinghang Li","submitted_at":"2025-06-06T02:48:02Z","abstract_excerpt":"The code generation capabilities of large language models(LLMs) have emerged as a critical dimension in evaluating their overall performance. However, prior research has largely overlooked the security risks inherent in the generated code. In this work, we introduce SafeGenBench, a benchmark specifically designed to assess the security of LLM-generated code. The dataset encompasses a wide range of common software development scenarios and vulnerability types. Building upon this benchmark, we develop an automatic evaluation framework that leverages both static application security testing(SAST)"},"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":"2506.05692","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CR","submitted_at":"2025-06-06T02:48:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8b50f2da7217fa5b9164f0f0f89ebb5ffb5162abf846f931f93ae45dd9cabfc2","abstract_canon_sha256":"1d1dba21c71a3e266974a7cca8c28d87c804049cc2246dc01e19b6fb33400154"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:24:22.237820Z","signature_b64":"gjnVkG10P+FfFvLBu0472m32c8gUoS9a8Kbbg/0dnjP/gwrWn7Pkmdu2BpsIv4/oSl8JLbnhdVgl5KbpgKA5Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0f52c9674963973e4151443770f6f13667e6bcafc626062b8cdd8b37289a007","last_reissued_at":"2026-07-05T11:24:22.237275Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:24:22.237275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SafeGenBench: A Benchmark Framework for Security Vulnerability Detection in LLM-Generated Code","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Bing Zhao, Chao Peng, Hongwan Gao, Jingzhe Ding, Xiang Gao, Xinchen Gu, Xinghang Li","submitted_at":"2025-06-06T02:48:02Z","abstract_excerpt":"The code generation capabilities of large language models(LLMs) have emerged as a critical dimension in evaluating their overall performance. However, prior research has largely overlooked the security risks inherent in the generated code. In this work, we introduce SafeGenBench, a benchmark specifically designed to assess the security of LLM-generated code. The dataset encompasses a wide range of common software development scenarios and vulnerability types. Building upon this benchmark, we develop an automatic evaluation framework that leverages both static application security testing(SAST)"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05692","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/2506.05692/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":"2506.05692","created_at":"2026-07-05T11:24:22.237341+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.05692v3","created_at":"2026-07-05T11:24:22.237341+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05692","created_at":"2026-07-05T11:24:22.237341+00:00"},{"alias_kind":"pith_short_12","alias_value":"WD2SZFTUSY4X","created_at":"2026-07-05T11:24:22.237341+00:00"},{"alias_kind":"pith_short_16","alias_value":"WD2SZFTUSY4XHZAV","created_at":"2026-07-05T11:24:22.237341+00:00"},{"alias_kind":"pith_short_8","alias_value":"WD2SZFTU","created_at":"2026-07-05T11:24:22.237341+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19887","citing_title":"FinRED: An Expert-Guided Benchmark Generation and Evaluation Framework for Financial LLM Red-Teaming","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31159","citing_title":"An Empirical Study of Security Calibration in Large Language Models for Code","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21615","citing_title":"ASSEMBLAGE-DEEPHISTORY: A Cross-Build Binary Dataset with Temporal Coverage","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12746","citing_title":"CoT-Guard: Small Models for Strong Monitoring","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05867","citing_title":"On Fixing Insecure AI-Generated Code through Model Fine-Tuning and Prompting Strategies","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17014","citing_title":"False Security Confidence in Benign LLM Code Generation","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20179","citing_title":"Taint-Style Vulnerability Detection and Confirmation for Node.js Packages Using LLM Agent Reasoning","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WD2SZFTUSY4XHZAVCRBXOD3PCN","json":"https://pith.science/pith/WD2SZFTUSY4XHZAVCRBXOD3PCN.json","graph_json":"https://pith.science/api/pith-number/WD2SZFTUSY4XHZAVCRBXOD3PCN/graph.json","events_json":"https://pith.science/api/pith-number/WD2SZFTUSY4XHZAVCRBXOD3PCN/events.json","paper":"https://pith.science/paper/WD2SZFTU"},"agent_actions":{"view_html":"https://pith.science/pith/WD2SZFTUSY4XHZAVCRBXOD3PCN","download_json":"https://pith.science/pith/WD2SZFTUSY4XHZAVCRBXOD3PCN.json","view_paper":"https://pith.science/paper/WD2SZFTU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.05692&json=true","fetch_graph":"https://pith.science/api/pith-number/WD2SZFTUSY4XHZAVCRBXOD3PCN/graph.json","fetch_events":"https://pith.science/api/pith-number/WD2SZFTUSY4XHZAVCRBXOD3PCN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WD2SZFTUSY4XHZAVCRBXOD3PCN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WD2SZFTUSY4XHZAVCRBXOD3PCN/action/storage_attestation","attest_author":"https://pith.science/pith/WD2SZFTUSY4XHZAVCRBXOD3PCN/action/author_attestation","sign_citation":"https://pith.science/pith/WD2SZFTUSY4XHZAVCRBXOD3PCN/action/citation_signature","submit_replication":"https://pith.science/pith/WD2SZFTUSY4XHZAVCRBXOD3PCN/action/replication_record"}},"created_at":"2026-07-05T11:24:22.237341+00:00","updated_at":"2026-07-05T11:24:22.237341+00:00"}