{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5LBZH3EQFCKC6PENCZV5JQ27EH","short_pith_number":"pith:5LBZH3EQ","schema_version":"1.0","canonical_sha256":"eac393ec9028942f3c8d166bd4c35f21fd353190d6d529c470ae66aff28e3eea","source":{"kind":"arxiv","id":"2406.11147","version":3},"attestation_state":"computed","paper":{"title":"Vul-RAG: Enhancing LLM-based Vulnerability Detection via Knowledge-level RAG","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Bihuan Chen, Geng Zheng, Jiayi Feng, Kaixin Wang, Mingwei Liu, Tao Ma, Wentai Deng, Xin Peng, Xueying Du, Yiling Lou, Yi Zou, Yujia Wang","submitted_at":"2024-06-17T02:25:45Z","abstract_excerpt":"Although LLMs have shown promising potential in vulnerability detection, this study reveals their limitations in distinguishing between vulnerable and similar-but-benign patched code (only 0.06 - 0.14 accuracy). It shows that LLMs struggle to capture the root causes of vulnerabilities during vulnerability detection. To address this challenge, we propose enhancing LLMs with multi-dimensional vulnerability knowledge distilled from historical vulnerabilities and fixes. We design a novel knowledge-level Retrieval-Augmented Generation framework Vul-RAG, which improves LLMs with an accuracy increase"},"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":"2406.11147","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-06-17T02:25:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7f7f689f703d641645553de3335352ae0e8d448dc46f2ff591080564ab33a0ae","abstract_canon_sha256":"1826b783065c467a03154cf32a9c2d964bf1e58af8164a8bd110fe0b5532c0da"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:30.962990Z","signature_b64":"j2Mzil9uH67nYGHTa7aAZ5JTwAkZsmH7B8pORnvVwLPcqNk8/XXoG96DnV0ojAbRwLd6SfBx24Ak2vGNPptoCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eac393ec9028942f3c8d166bd4c35f21fd353190d6d529c470ae66aff28e3eea","last_reissued_at":"2026-07-05T11:22:30.962479Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:30.962479Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Vul-RAG: Enhancing LLM-based Vulnerability Detection via Knowledge-level RAG","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Bihuan Chen, Geng Zheng, Jiayi Feng, Kaixin Wang, Mingwei Liu, Tao Ma, Wentai Deng, Xin Peng, Xueying Du, Yiling Lou, Yi Zou, Yujia Wang","submitted_at":"2024-06-17T02:25:45Z","abstract_excerpt":"Although LLMs have shown promising potential in vulnerability detection, this study reveals their limitations in distinguishing between vulnerable and similar-but-benign patched code (only 0.06 - 0.14 accuracy). It shows that LLMs struggle to capture the root causes of vulnerabilities during vulnerability detection. To address this challenge, we propose enhancing LLMs with multi-dimensional vulnerability knowledge distilled from historical vulnerabilities and fixes. We design a novel knowledge-level Retrieval-Augmented Generation framework Vul-RAG, which improves LLMs with an accuracy increase"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11147","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/2406.11147/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":"2406.11147","created_at":"2026-07-05T11:22:30.962543+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.11147v3","created_at":"2026-07-05T11:22:30.962543+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11147","created_at":"2026-07-05T11:22:30.962543+00:00"},{"alias_kind":"pith_short_12","alias_value":"5LBZH3EQFCKC","created_at":"2026-07-05T11:22:30.962543+00:00"},{"alias_kind":"pith_short_16","alias_value":"5LBZH3EQFCKC6PEN","created_at":"2026-07-05T11:22:30.962543+00:00"},{"alias_kind":"pith_short_8","alias_value":"5LBZH3EQ","created_at":"2026-07-05T11:22:30.962543+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21397","citing_title":"Evaluating LLMs for Real-World Web Vulnerability Detection","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11755","citing_title":"Acoda: Adversarial Code Obfuscation for Defending against LLM-based Analysis","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00047","citing_title":"Comprehensive AI governance requires addressing non-model gains","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21779","citing_title":"FuzzingBrain V2: A Multi-Agent LLM System for Automated Vulnerability Discovery and Reproduction","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18153","citing_title":"Three Heads Are Better Than One: A Multi-perspective Reasoning Framework for Enhanced Vulnerability Detection","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2510.04056","citing_title":"QuiLL: An LLM-Based Vulnerability Assessment Framework for the Wild","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2409.02977","citing_title":"Large Language Model-Based Agents for Software Engineering: A Survey","ref_index":131,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11950","citing_title":"AnyPoC: Universal Proof-of-Concept Test Generation for Scalable LLM-Based Bug Detection","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03140","citing_title":"Evaluating Retrieval-Augmented Generation for Explainable Malware Analysis","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5LBZH3EQFCKC6PENCZV5JQ27EH","json":"https://pith.science/pith/5LBZH3EQFCKC6PENCZV5JQ27EH.json","graph_json":"https://pith.science/api/pith-number/5LBZH3EQFCKC6PENCZV5JQ27EH/graph.json","events_json":"https://pith.science/api/pith-number/5LBZH3EQFCKC6PENCZV5JQ27EH/events.json","paper":"https://pith.science/paper/5LBZH3EQ"},"agent_actions":{"view_html":"https://pith.science/pith/5LBZH3EQFCKC6PENCZV5JQ27EH","download_json":"https://pith.science/pith/5LBZH3EQFCKC6PENCZV5JQ27EH.json","view_paper":"https://pith.science/paper/5LBZH3EQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.11147&json=true","fetch_graph":"https://pith.science/api/pith-number/5LBZH3EQFCKC6PENCZV5JQ27EH/graph.json","fetch_events":"https://pith.science/api/pith-number/5LBZH3EQFCKC6PENCZV5JQ27EH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5LBZH3EQFCKC6PENCZV5JQ27EH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5LBZH3EQFCKC6PENCZV5JQ27EH/action/storage_attestation","attest_author":"https://pith.science/pith/5LBZH3EQFCKC6PENCZV5JQ27EH/action/author_attestation","sign_citation":"https://pith.science/pith/5LBZH3EQFCKC6PENCZV5JQ27EH/action/citation_signature","submit_replication":"https://pith.science/pith/5LBZH3EQFCKC6PENCZV5JQ27EH/action/replication_record"}},"created_at":"2026-07-05T11:22:30.962543+00:00","updated_at":"2026-07-05T11:22:30.962543+00:00"}