{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XOUAUO6W3AQXKV22SRIMVPHDGV","short_pith_number":"pith:XOUAUO6W","schema_version":"1.0","canonical_sha256":"bba80a3bd6d82175575a9450cabce3357037978904f340d74d78f421c5f9a78c","source":{"kind":"arxiv","id":"2311.16169","version":3},"attestation_state":"computed","paper":{"title":"Understanding the Effectiveness of Large Language Models in Detecting Security Vulnerabilities","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.PL","cs.SE"],"primary_cat":"cs.CR","authors_text":"Alaia Solko-Breslin, Avishree Khare, Mayur Naik, Rajeev Alur, Saikat Dutta, Ziyang Li","submitted_at":"2023-11-16T13:17:20Z","abstract_excerpt":"While automated vulnerability detection techniques have made promising progress in detecting security vulnerabilities, their scalability and applicability remain challenging. The remarkable performance of Large Language Models (LLMs), such as GPT-4 and CodeLlama, on code-related tasks has prompted recent works to explore if LLMs can be used to detect vulnerabilities. In this paper, we perform a more comprehensive study by concurrently examining a higher number of datasets, languages and LLMs, and qualitatively evaluating performance across prompts and vulnerability classes while addressing the"},"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":"2311.16169","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CR","submitted_at":"2023-11-16T13:17:20Z","cross_cats_sorted":["cs.PL","cs.SE"],"title_canon_sha256":"3b2eec5e0957c43d969ff95634d9cc34090bbd1654b113be8f945435b9b05d5c","abstract_canon_sha256":"b9b4a0a4f73bf8521b2f58087dddaf3688c52e39ffc71979c57a7a3bb383d133"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:24:31.928281Z","signature_b64":"AFwaj/SJ1nkhxughq2Wz/zDCOulZLmwWMKTte6OylaGQ16D/xE+oe0ZqgHL6lUvdsskGIIEfth46hLv7bmYbAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bba80a3bd6d82175575a9450cabce3357037978904f340d74d78f421c5f9a78c","last_reissued_at":"2026-07-05T09:24:31.927778Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:24:31.927778Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Understanding the Effectiveness of Large Language Models in Detecting Security Vulnerabilities","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.PL","cs.SE"],"primary_cat":"cs.CR","authors_text":"Alaia Solko-Breslin, Avishree Khare, Mayur Naik, Rajeev Alur, Saikat Dutta, Ziyang Li","submitted_at":"2023-11-16T13:17:20Z","abstract_excerpt":"While automated vulnerability detection techniques have made promising progress in detecting security vulnerabilities, their scalability and applicability remain challenging. The remarkable performance of Large Language Models (LLMs), such as GPT-4 and CodeLlama, on code-related tasks has prompted recent works to explore if LLMs can be used to detect vulnerabilities. In this paper, we perform a more comprehensive study by concurrently examining a higher number of datasets, languages and LLMs, and qualitatively evaluating performance across prompts and vulnerability classes while addressing the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.16169","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/2311.16169/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":"2311.16169","created_at":"2026-07-05T09:24:31.927837+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.16169v3","created_at":"2026-07-05T09:24:31.927837+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.16169","created_at":"2026-07-05T09:24:31.927837+00:00"},{"alias_kind":"pith_short_12","alias_value":"XOUAUO6W3AQX","created_at":"2026-07-05T09:24:31.927837+00:00"},{"alias_kind":"pith_short_16","alias_value":"XOUAUO6W3AQXKV22","created_at":"2026-07-05T09:24:31.927837+00:00"},{"alias_kind":"pith_short_8","alias_value":"XOUAUO6W","created_at":"2026-07-05T09:24:31.927837+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19149","citing_title":"OpenAnt: LLM-Powered Vulnerability Discovery Through Code Decomposition, Adversarial Verification, and Dynamic Testing","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2412.11194","citing_title":"Direction for Detection: A Survey of Automated Vulnerability Detection and all of its Pain Points","ref_index":156,"is_internal_anchor":false},{"citing_arxiv_id":"2507.11687","citing_title":"MetaLint: Easy-to-Hard Generalization for Code Linting","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2507.21954","citing_title":"Fine-Tuning Code Language Models to Detect Cross-Language Bugs","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2510.04056","citing_title":"QuiLL: An LLM-Based Vulnerability Assessment Framework for the Wild","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2601.16456","citing_title":"RubberDuckBench: A Benchmark for AI Coding Assistants","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01885","citing_title":"QASecClaw: A Multi-Agent LLM Approach for False Positive Reduction in Static Application Security Testing","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07900","citing_title":"Longitudinal Analyses of SAST Tools: A CodeQL Case Study","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XOUAUO6W3AQXKV22SRIMVPHDGV","json":"https://pith.science/pith/XOUAUO6W3AQXKV22SRIMVPHDGV.json","graph_json":"https://pith.science/api/pith-number/XOUAUO6W3AQXKV22SRIMVPHDGV/graph.json","events_json":"https://pith.science/api/pith-number/XOUAUO6W3AQXKV22SRIMVPHDGV/events.json","paper":"https://pith.science/paper/XOUAUO6W"},"agent_actions":{"view_html":"https://pith.science/pith/XOUAUO6W3AQXKV22SRIMVPHDGV","download_json":"https://pith.science/pith/XOUAUO6W3AQXKV22SRIMVPHDGV.json","view_paper":"https://pith.science/paper/XOUAUO6W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.16169&json=true","fetch_graph":"https://pith.science/api/pith-number/XOUAUO6W3AQXKV22SRIMVPHDGV/graph.json","fetch_events":"https://pith.science/api/pith-number/XOUAUO6W3AQXKV22SRIMVPHDGV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XOUAUO6W3AQXKV22SRIMVPHDGV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XOUAUO6W3AQXKV22SRIMVPHDGV/action/storage_attestation","attest_author":"https://pith.science/pith/XOUAUO6W3AQXKV22SRIMVPHDGV/action/author_attestation","sign_citation":"https://pith.science/pith/XOUAUO6W3AQXKV22SRIMVPHDGV/action/citation_signature","submit_replication":"https://pith.science/pith/XOUAUO6W3AQXKV22SRIMVPHDGV/action/replication_record"}},"created_at":"2026-07-05T09:24:31.927837+00:00","updated_at":"2026-07-05T09:24:31.927837+00:00"}