{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XU2JQF4J5BSGHV36SYB3MP65MQ","short_pith_number":"pith:XU2JQF4J","schema_version":"1.0","canonical_sha256":"bd34981789e86463d77e9603b63fdd641400576fb8bcd6ad95e02c6fbf3971d5","source":{"kind":"arxiv","id":"2308.10345","version":1},"attestation_state":"computed","paper":{"title":"Can Large Language Models Find And Fix Vulnerable Software?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SE","authors_text":"David Noever","submitted_at":"2023-08-20T19:33:12Z","abstract_excerpt":"In this study, we evaluated the capability of Large Language Models (LLMs), particularly OpenAI's GPT-4, in detecting software vulnerabilities, comparing their performance against traditional static code analyzers like Snyk and Fortify. Our analysis covered numerous repositories, including those from NASA and the Department of Defense. GPT-4 identified approximately four times the vulnerabilities than its counterparts. Furthermore, it provided viable fixes for each vulnerability, demonstrating a low rate of false positives. Our tests encompassed 129 code samples across eight programming langua"},"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":"2308.10345","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2023-08-20T19:33:12Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6240e28e45b9af21e4404506e0a5286ffaae18a08c3d0007a1f406e26d9dcf05","abstract_canon_sha256":"a21b698f136d4a32b2c37549cc49232dce2ccf5ef207dba2de19edcf5655abd7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:43:08.079076Z","signature_b64":"J42wm7EEKPUaVaby3W6vFckUR0vRLiKOmC5bI8HRhubOtsApiNjfcoC0dWfDccOAqySvtJgqYRWQx2do3JamBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd34981789e86463d77e9603b63fdd641400576fb8bcd6ad95e02c6fbf3971d5","last_reissued_at":"2026-07-05T06:43:08.078701Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:43:08.078701Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can Large Language Models Find And Fix Vulnerable Software?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SE","authors_text":"David Noever","submitted_at":"2023-08-20T19:33:12Z","abstract_excerpt":"In this study, we evaluated the capability of Large Language Models (LLMs), particularly OpenAI's GPT-4, in detecting software vulnerabilities, comparing their performance against traditional static code analyzers like Snyk and Fortify. Our analysis covered numerous repositories, including those from NASA and the Department of Defense. GPT-4 identified approximately four times the vulnerabilities than its counterparts. Furthermore, it provided viable fixes for each vulnerability, demonstrating a low rate of false positives. Our tests encompassed 129 code samples across eight programming langua"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.10345","kind":"arxiv","version":1},"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/2308.10345/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":"2308.10345","created_at":"2026-07-05T06:43:08.078758+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.10345v1","created_at":"2026-07-05T06:43:08.078758+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.10345","created_at":"2026-07-05T06:43:08.078758+00:00"},{"alias_kind":"pith_short_12","alias_value":"XU2JQF4J5BSG","created_at":"2026-07-05T06:43:08.078758+00:00"},{"alias_kind":"pith_short_16","alias_value":"XU2JQF4J5BSGHV36","created_at":"2026-07-05T06:43:08.078758+00:00"},{"alias_kind":"pith_short_8","alias_value":"XU2JQF4J","created_at":"2026-07-05T06:43:08.078758+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.28893","citing_title":"Towards Demystifying and Repairing LLM-in-the-Loop Vulnerabilities","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23091","citing_title":"Security of LLM-generated Code: A Comparative Analysis","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2505.13766","citing_title":"A Blueprint for AI-Driven Software Quality: Integrating LLMs with Established Standards","ref_index":172,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02548","citing_title":"From Theory to Practice: Code Generation Using LLMs for CAPEC and CWE Frameworks","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XU2JQF4J5BSGHV36SYB3MP65MQ","json":"https://pith.science/pith/XU2JQF4J5BSGHV36SYB3MP65MQ.json","graph_json":"https://pith.science/api/pith-number/XU2JQF4J5BSGHV36SYB3MP65MQ/graph.json","events_json":"https://pith.science/api/pith-number/XU2JQF4J5BSGHV36SYB3MP65MQ/events.json","paper":"https://pith.science/paper/XU2JQF4J"},"agent_actions":{"view_html":"https://pith.science/pith/XU2JQF4J5BSGHV36SYB3MP65MQ","download_json":"https://pith.science/pith/XU2JQF4J5BSGHV36SYB3MP65MQ.json","view_paper":"https://pith.science/paper/XU2JQF4J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.10345&json=true","fetch_graph":"https://pith.science/api/pith-number/XU2JQF4J5BSGHV36SYB3MP65MQ/graph.json","fetch_events":"https://pith.science/api/pith-number/XU2JQF4J5BSGHV36SYB3MP65MQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XU2JQF4J5BSGHV36SYB3MP65MQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XU2JQF4J5BSGHV36SYB3MP65MQ/action/storage_attestation","attest_author":"https://pith.science/pith/XU2JQF4J5BSGHV36SYB3MP65MQ/action/author_attestation","sign_citation":"https://pith.science/pith/XU2JQF4J5BSGHV36SYB3MP65MQ/action/citation_signature","submit_replication":"https://pith.science/pith/XU2JQF4J5BSGHV36SYB3MP65MQ/action/replication_record"}},"created_at":"2026-07-05T06:43:08.078758+00:00","updated_at":"2026-07-05T06:43:08.078758+00:00"}