{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:P4NWVCUBU25YNLDLLXJ7ZRS6FR","short_pith_number":"pith:P4NWVCUB","schema_version":"1.0","canonical_sha256":"7f1b6a8a81a6bb86ac6b5dd3fcc65e2c72d5cbba95fb9ed97a7430ec53e73ff7","source":{"kind":"arxiv","id":"2502.06039","version":1},"attestation_state":"computed","paper":{"title":"Benchmarking Prompt Engineering Techniques for Secure Code Generation with GPT Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.SE","authors_text":"Fabio Gabrielli, Marc Bruni, Martin Kropp, Mohammad Ghafari","submitted_at":"2025-02-09T21:23:07Z","abstract_excerpt":"Prompt engineering reduces reasoning mistakes in Large Language Models (LLMs). However, its effectiveness in mitigating vulnerabilities in LLM-generated code remains underexplored. To address this gap, we implemented a benchmark to automatically assess the impact of various prompt engineering strategies on code security. Our benchmark leverages two peer-reviewed prompt datasets and employs static scanners to evaluate code security at scale. We tested multiple prompt engineering techniques on GPT-3.5-turbo, GPT-4o, and GPT-4o-mini. Our results show that for GPT-4o and GPT-4o-mini, a security-fo"},"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":"2502.06039","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-02-09T21:23:07Z","cross_cats_sorted":["cs.AI","cs.CR"],"title_canon_sha256":"dccd0c4042a5e63f4828da0816eecdc4ea56c0e36f4e3fc96809a2dfb5c33ffa","abstract_canon_sha256":"9043af2a60218b9fe40eb4c035a10c939e091c0ff951315ad8bc61e7ea22ae9e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:11:46.774527Z","signature_b64":"czoHxauxA5miz/x/VqsP7wyACIii7KoY6dJPiz1cCfPJoDh6pyTLx3N2SjCUaSJsOVeYle1nYsQD1NZjLNAtCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f1b6a8a81a6bb86ac6b5dd3fcc65e2c72d5cbba95fb9ed97a7430ec53e73ff7","last_reissued_at":"2026-07-05T10:11:46.774045Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:11:46.774045Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Benchmarking Prompt Engineering Techniques for Secure Code Generation with GPT Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR"],"primary_cat":"cs.SE","authors_text":"Fabio Gabrielli, Marc Bruni, Martin Kropp, Mohammad Ghafari","submitted_at":"2025-02-09T21:23:07Z","abstract_excerpt":"Prompt engineering reduces reasoning mistakes in Large Language Models (LLMs). However, its effectiveness in mitigating vulnerabilities in LLM-generated code remains underexplored. To address this gap, we implemented a benchmark to automatically assess the impact of various prompt engineering strategies on code security. Our benchmark leverages two peer-reviewed prompt datasets and employs static scanners to evaluate code security at scale. We tested multiple prompt engineering techniques on GPT-3.5-turbo, GPT-4o, and GPT-4o-mini. Our results show that for GPT-4o and GPT-4o-mini, a security-fo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.06039","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/2502.06039/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":"2502.06039","created_at":"2026-07-05T10:11:46.774101+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.06039v1","created_at":"2026-07-05T10:11:46.774101+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.06039","created_at":"2026-07-05T10:11:46.774101+00:00"},{"alias_kind":"pith_short_12","alias_value":"P4NWVCUBU25Y","created_at":"2026-07-05T10:11:46.774101+00:00"},{"alias_kind":"pith_short_16","alias_value":"P4NWVCUBU25YNLDL","created_at":"2026-07-05T10:11:46.774101+00:00"},{"alias_kind":"pith_short_8","alias_value":"P4NWVCUB","created_at":"2026-07-05T10:11:46.774101+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/P4NWVCUBU25YNLDLLXJ7ZRS6FR","json":"https://pith.science/pith/P4NWVCUBU25YNLDLLXJ7ZRS6FR.json","graph_json":"https://pith.science/api/pith-number/P4NWVCUBU25YNLDLLXJ7ZRS6FR/graph.json","events_json":"https://pith.science/api/pith-number/P4NWVCUBU25YNLDLLXJ7ZRS6FR/events.json","paper":"https://pith.science/paper/P4NWVCUB"},"agent_actions":{"view_html":"https://pith.science/pith/P4NWVCUBU25YNLDLLXJ7ZRS6FR","download_json":"https://pith.science/pith/P4NWVCUBU25YNLDLLXJ7ZRS6FR.json","view_paper":"https://pith.science/paper/P4NWVCUB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.06039&json=true","fetch_graph":"https://pith.science/api/pith-number/P4NWVCUBU25YNLDLLXJ7ZRS6FR/graph.json","fetch_events":"https://pith.science/api/pith-number/P4NWVCUBU25YNLDLLXJ7ZRS6FR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P4NWVCUBU25YNLDLLXJ7ZRS6FR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P4NWVCUBU25YNLDLLXJ7ZRS6FR/action/storage_attestation","attest_author":"https://pith.science/pith/P4NWVCUBU25YNLDLLXJ7ZRS6FR/action/author_attestation","sign_citation":"https://pith.science/pith/P4NWVCUBU25YNLDLLXJ7ZRS6FR/action/citation_signature","submit_replication":"https://pith.science/pith/P4NWVCUBU25YNLDLLXJ7ZRS6FR/action/replication_record"}},"created_at":"2026-07-05T10:11:46.774101+00:00","updated_at":"2026-07-05T10:11:46.774101+00:00"}