{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NCDSNOZEPNEUSALGH3LGPZWT7Z","short_pith_number":"pith:NCDSNOZE","schema_version":"1.0","canonical_sha256":"688726bb247b494901663ed667e6d3fe5860d639a1430721fcefe359400a16c5","source":{"kind":"arxiv","id":"2403.08429","version":1},"attestation_state":"computed","paper":{"title":"Software Vulnerability and Functionality Assessment using LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Rasmus Ingemann Tuffveson Jensen, Salwa Alamir, Vali Tawosi","submitted_at":"2024-03-13T11:29:13Z","abstract_excerpt":"While code review is central to the software development process, it can be tedious and expensive to carry out. In this paper, we investigate whether and how Large Language Models (LLMs) can aid with code reviews. Our investigation focuses on two tasks that we argue are fundamental to good reviews: (i) flagging code with security vulnerabilities and (ii) performing software functionality validation, i.e., ensuring that code meets its intended functionality. To test performance on both tasks, we use zero-shot and chain-of-thought prompting to obtain final ``approve or reject'' recommendations. "},"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":"2403.08429","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-03-13T11:29:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f94a06e87b631f6875f1bf4a7cc702ac5dde1f02e441e594abac65f6f4d1ccd9","abstract_canon_sha256":"6a00e00cc59ecee169439515f0c2a877bd34b7fee9539aee714df65dba88113e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:55:38.921953Z","signature_b64":"FDDZ9P+TNpTwlemfzeI03lFLdey8IhHZ4r99++nYsqkeiwkA3n/BRrS6LP4H2WQXYer0MautoS163ZP7HKabBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"688726bb247b494901663ed667e6d3fe5860d639a1430721fcefe359400a16c5","last_reissued_at":"2026-07-05T07:55:38.921547Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:55:38.921547Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Software Vulnerability and Functionality Assessment using LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Rasmus Ingemann Tuffveson Jensen, Salwa Alamir, Vali Tawosi","submitted_at":"2024-03-13T11:29:13Z","abstract_excerpt":"While code review is central to the software development process, it can be tedious and expensive to carry out. In this paper, we investigate whether and how Large Language Models (LLMs) can aid with code reviews. Our investigation focuses on two tasks that we argue are fundamental to good reviews: (i) flagging code with security vulnerabilities and (ii) performing software functionality validation, i.e., ensuring that code meets its intended functionality. To test performance on both tasks, we use zero-shot and chain-of-thought prompting to obtain final ``approve or reject'' recommendations. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.08429","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/2403.08429/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":"2403.08429","created_at":"2026-07-05T07:55:38.921607+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.08429v1","created_at":"2026-07-05T07:55:38.921607+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.08429","created_at":"2026-07-05T07:55:38.921607+00:00"},{"alias_kind":"pith_short_12","alias_value":"NCDSNOZEPNEU","created_at":"2026-07-05T07:55:38.921607+00:00"},{"alias_kind":"pith_short_16","alias_value":"NCDSNOZEPNEUSALG","created_at":"2026-07-05T07:55:38.921607+00:00"},{"alias_kind":"pith_short_8","alias_value":"NCDSNOZE","created_at":"2026-07-05T07:55:38.921607+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.16899","citing_title":"Towards Effective Complementary Security Analysis using Large Language Models","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NCDSNOZEPNEUSALGH3LGPZWT7Z","json":"https://pith.science/pith/NCDSNOZEPNEUSALGH3LGPZWT7Z.json","graph_json":"https://pith.science/api/pith-number/NCDSNOZEPNEUSALGH3LGPZWT7Z/graph.json","events_json":"https://pith.science/api/pith-number/NCDSNOZEPNEUSALGH3LGPZWT7Z/events.json","paper":"https://pith.science/paper/NCDSNOZE"},"agent_actions":{"view_html":"https://pith.science/pith/NCDSNOZEPNEUSALGH3LGPZWT7Z","download_json":"https://pith.science/pith/NCDSNOZEPNEUSALGH3LGPZWT7Z.json","view_paper":"https://pith.science/paper/NCDSNOZE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.08429&json=true","fetch_graph":"https://pith.science/api/pith-number/NCDSNOZEPNEUSALGH3LGPZWT7Z/graph.json","fetch_events":"https://pith.science/api/pith-number/NCDSNOZEPNEUSALGH3LGPZWT7Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NCDSNOZEPNEUSALGH3LGPZWT7Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NCDSNOZEPNEUSALGH3LGPZWT7Z/action/storage_attestation","attest_author":"https://pith.science/pith/NCDSNOZEPNEUSALGH3LGPZWT7Z/action/author_attestation","sign_citation":"https://pith.science/pith/NCDSNOZEPNEUSALGH3LGPZWT7Z/action/citation_signature","submit_replication":"https://pith.science/pith/NCDSNOZEPNEUSALGH3LGPZWT7Z/action/replication_record"}},"created_at":"2026-07-05T07:55:38.921607+00:00","updated_at":"2026-07-05T07:55:38.921607+00:00"}