{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JFMCL4L2CTEZBDY4NYX75I4XQO","short_pith_number":"pith:JFMCL4L2","schema_version":"1.0","canonical_sha256":"495825f17a14c9908f1c6e2ffea3978391b2e1fb8a4d346d78eb75cc403a120a","source":{"kind":"arxiv","id":"2504.13474","version":1},"attestation_state":"computed","paper":{"title":"Everything You Wanted to Know About LLM-based Vulnerability Detection But Were Afraid to Ask","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Fengyuan Xu, Hao Wu, Minghui Xu, Sheng Zhong, Xiao Li, Xiuzhen Cheng, Yue Li, Yue Zhang","submitted_at":"2025-04-18T05:32:47Z","abstract_excerpt":"Large Language Models are a promising tool for automated vulnerability detection, thanks to their success in code generation and repair. However, despite widespread adoption, a critical question remains: Are LLMs truly effective at detecting real-world vulnerabilities? Current evaluations, which often assess models on isolated functions or files, ignore the broader execution and data-flow context essential for understanding vulnerabilities. This oversight leads to two types of misleading outcomes: incorrect conclusions and flawed rationales, collectively undermining the reliability of prior as"},"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":"2504.13474","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2025-04-18T05:32:47Z","cross_cats_sorted":[],"title_canon_sha256":"bcc99616dbffc5d2d197226afc13d2a141a033c4e35cc1e86ecec64ec7656635","abstract_canon_sha256":"6a4f21079aec7900b13f7b90fe3831fff30686237a83cba84f89c15a5931cb73"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:50:55.921697Z","signature_b64":"0x/auvPHQMryXERXnJbt85yUE6cy6rPXgB6SbR80esyD0qdKmm7iynyUYWHvpDj4STjrXgkOCS2i6j7DCFtwDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"495825f17a14c9908f1c6e2ffea3978391b2e1fb8a4d346d78eb75cc403a120a","last_reissued_at":"2026-07-05T10:50:55.920507Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:50:55.920507Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Everything You Wanted to Know About LLM-based Vulnerability Detection But Were Afraid to Ask","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Fengyuan Xu, Hao Wu, Minghui Xu, Sheng Zhong, Xiao Li, Xiuzhen Cheng, Yue Li, Yue Zhang","submitted_at":"2025-04-18T05:32:47Z","abstract_excerpt":"Large Language Models are a promising tool for automated vulnerability detection, thanks to their success in code generation and repair. However, despite widespread adoption, a critical question remains: Are LLMs truly effective at detecting real-world vulnerabilities? Current evaluations, which often assess models on isolated functions or files, ignore the broader execution and data-flow context essential for understanding vulnerabilities. This oversight leads to two types of misleading outcomes: incorrect conclusions and flawed rationales, collectively undermining the reliability of prior as"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.13474","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/2504.13474/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":"2504.13474","created_at":"2026-07-05T10:50:55.920700+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.13474v1","created_at":"2026-07-05T10:50:55.920700+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.13474","created_at":"2026-07-05T10:50:55.920700+00:00"},{"alias_kind":"pith_short_12","alias_value":"JFMCL4L2CTEZ","created_at":"2026-07-05T10:50:55.920700+00:00"},{"alias_kind":"pith_short_16","alias_value":"JFMCL4L2CTEZBDY4","created_at":"2026-07-05T10:50:55.920700+00:00"},{"alias_kind":"pith_short_8","alias_value":"JFMCL4L2","created_at":"2026-07-05T10:50:55.920700+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01138","citing_title":"Antaeus: Hunting Repository-Level Logic Vulnerabilities via Context-Grounded LLM Reasoning","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2601.22655","citing_title":"Do Fine-Tuned LLMs Understand Vulnerabilities? An Investigation into the Semantic Trap","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21779","citing_title":"FuzzingBrain V2: A Multi-Agent LLM System for Automated Vulnerability Discovery and Reproduction","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18153","citing_title":"Three Heads Are Better Than One: A Multi-perspective Reasoning Framework for Enhanced Vulnerability Detection","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06184","citing_title":"Teaching LLMs Program Semantics via Symbolic Execution Traces","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JFMCL4L2CTEZBDY4NYX75I4XQO","json":"https://pith.science/pith/JFMCL4L2CTEZBDY4NYX75I4XQO.json","graph_json":"https://pith.science/api/pith-number/JFMCL4L2CTEZBDY4NYX75I4XQO/graph.json","events_json":"https://pith.science/api/pith-number/JFMCL4L2CTEZBDY4NYX75I4XQO/events.json","paper":"https://pith.science/paper/JFMCL4L2"},"agent_actions":{"view_html":"https://pith.science/pith/JFMCL4L2CTEZBDY4NYX75I4XQO","download_json":"https://pith.science/pith/JFMCL4L2CTEZBDY4NYX75I4XQO.json","view_paper":"https://pith.science/paper/JFMCL4L2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.13474&json=true","fetch_graph":"https://pith.science/api/pith-number/JFMCL4L2CTEZBDY4NYX75I4XQO/graph.json","fetch_events":"https://pith.science/api/pith-number/JFMCL4L2CTEZBDY4NYX75I4XQO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JFMCL4L2CTEZBDY4NYX75I4XQO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JFMCL4L2CTEZBDY4NYX75I4XQO/action/storage_attestation","attest_author":"https://pith.science/pith/JFMCL4L2CTEZBDY4NYX75I4XQO/action/author_attestation","sign_citation":"https://pith.science/pith/JFMCL4L2CTEZBDY4NYX75I4XQO/action/citation_signature","submit_replication":"https://pith.science/pith/JFMCL4L2CTEZBDY4NYX75I4XQO/action/replication_record"}},"created_at":"2026-07-05T10:50:55.920700+00:00","updated_at":"2026-07-05T10:50:55.920700+00:00"}