{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:W4QGK2V2WID7IVUKYYED4ZM6DC","short_pith_number":"pith:W4QGK2V2","schema_version":"1.0","canonical_sha256":"b720656abab207f4568ac6083e659e188fbd12074e11e0ae7aba7678d5f7f783","source":{"kind":"arxiv","id":"2607.00107","version":1},"attestation_state":"computed","paper":{"title":"The Illusion of Safety: Multi-Tier Verification of AI vs. Human C++ Code","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Fadul Sikder, Jeff (Yu) Lei, Saif Mahmud, Yuede Ji, Zhang Haotian","submitted_at":"2026-06-30T19:48:35Z","abstract_excerpt":"Large language models increasingly generate C++, a memory-unsafe language where a single overlooked violation can become an exploitable bug. Yet most security evaluations of AI-generated code rely on static analysis alone, which flags warnings without confirming runtime violations or reasoning about untested paths. We ask whether AI-generated C++ is measurably less safe than human-written code, and whether common verification tools agree on the risk. We introduce VULBENCH-CPP, a benchmark of 8,918 C++ programs from three open-weight LLMs (Gemma 3 27B IT, LLaMA 3.3 70B Instruct, Qwen 2.5 Coder "},"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":"2607.00107","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-06-30T19:48:35Z","cross_cats_sorted":[],"title_canon_sha256":"658e85761e1c1aad7e86c2a02066e6513ce88b7c4bd47e548a5727cf309849ca","abstract_canon_sha256":"3a1bbe19e4c525f9a0389d9c6252b9304d678f9647bc5acd4984db4d0fb29676"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-02T00:18:34.718009Z","signature_b64":"GQKYf8VNcMFe8LWo9mvfUsBAGGcxXede+xEskEfBoJW8EZhsi3fChSxFt48k5+127Dv7rQYaGGKaN718drIaBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b720656abab207f4568ac6083e659e188fbd12074e11e0ae7aba7678d5f7f783","last_reissued_at":"2026-07-02T00:18:34.717495Z","signature_status":"signed_v1","first_computed_at":"2026-07-02T00:18:34.717495Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Illusion of Safety: Multi-Tier Verification of AI vs. Human C++ Code","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Fadul Sikder, Jeff (Yu) Lei, Saif Mahmud, Yuede Ji, Zhang Haotian","submitted_at":"2026-06-30T19:48:35Z","abstract_excerpt":"Large language models increasingly generate C++, a memory-unsafe language where a single overlooked violation can become an exploitable bug. Yet most security evaluations of AI-generated code rely on static analysis alone, which flags warnings without confirming runtime violations or reasoning about untested paths. We ask whether AI-generated C++ is measurably less safe than human-written code, and whether common verification tools agree on the risk. We introduce VULBENCH-CPP, a benchmark of 8,918 C++ programs from three open-weight LLMs (Gemma 3 27B IT, LLaMA 3.3 70B Instruct, Qwen 2.5 Coder "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.00107","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/2607.00107/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":"2607.00107","created_at":"2026-07-02T00:18:34.717568+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.00107v1","created_at":"2026-07-02T00:18:34.717568+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.00107","created_at":"2026-07-02T00:18:34.717568+00:00"},{"alias_kind":"pith_short_12","alias_value":"W4QGK2V2WID7","created_at":"2026-07-02T00:18:34.717568+00:00"},{"alias_kind":"pith_short_16","alias_value":"W4QGK2V2WID7IVUK","created_at":"2026-07-02T00:18:34.717568+00:00"},{"alias_kind":"pith_short_8","alias_value":"W4QGK2V2","created_at":"2026-07-02T00:18:34.717568+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/W4QGK2V2WID7IVUKYYED4ZM6DC","json":"https://pith.science/pith/W4QGK2V2WID7IVUKYYED4ZM6DC.json","graph_json":"https://pith.science/api/pith-number/W4QGK2V2WID7IVUKYYED4ZM6DC/graph.json","events_json":"https://pith.science/api/pith-number/W4QGK2V2WID7IVUKYYED4ZM6DC/events.json","paper":"https://pith.science/paper/W4QGK2V2"},"agent_actions":{"view_html":"https://pith.science/pith/W4QGK2V2WID7IVUKYYED4ZM6DC","download_json":"https://pith.science/pith/W4QGK2V2WID7IVUKYYED4ZM6DC.json","view_paper":"https://pith.science/paper/W4QGK2V2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.00107&json=true","fetch_graph":"https://pith.science/api/pith-number/W4QGK2V2WID7IVUKYYED4ZM6DC/graph.json","fetch_events":"https://pith.science/api/pith-number/W4QGK2V2WID7IVUKYYED4ZM6DC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W4QGK2V2WID7IVUKYYED4ZM6DC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W4QGK2V2WID7IVUKYYED4ZM6DC/action/storage_attestation","attest_author":"https://pith.science/pith/W4QGK2V2WID7IVUKYYED4ZM6DC/action/author_attestation","sign_citation":"https://pith.science/pith/W4QGK2V2WID7IVUKYYED4ZM6DC/action/citation_signature","submit_replication":"https://pith.science/pith/W4QGK2V2WID7IVUKYYED4ZM6DC/action/replication_record"}},"created_at":"2026-07-02T00:18:34.717568+00:00","updated_at":"2026-07-02T00:18:34.717568+00:00"}