{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2KVGUZ2O463XWWY2EPRNHQUJRZ","short_pith_number":"pith:2KVGUZ2O","schema_version":"1.0","canonical_sha256":"d2aa6a674ee7b77b5b1a23e2d3c2898e457144750dff1a94bdc3dba9819a1055","source":{"kind":"arxiv","id":"2406.07595","version":4},"attestation_state":"computed","paper":{"title":"VulDetectBench: Evaluating the Deep Capability of Vulnerability Detection with Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.SE"],"primary_cat":"cs.CR","authors_text":"Lang Gao, Mingxin Yang, Ping Chen, Wei Chen, Xiaojin Zhang, Yu Liu, Yu Xie","submitted_at":"2024-06-11T13:42:57Z","abstract_excerpt":"Large Language Models (LLMs) have training corpora containing large amounts of program code, greatly improving the model's code comprehension and generation capabilities. However, sound comprehensive research on detecting program vulnerabilities, a more specific task related to code, and evaluating the performance of LLMs in this more specialized scenario is still lacking. To address common challenges in vulnerability analysis, our study introduces a new benchmark, VulDetectBench, specifically designed to assess the vulnerability detection capabilities of LLMs. The benchmark comprehensively ev"},"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":"2406.07595","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CR","submitted_at":"2024-06-11T13:42:57Z","cross_cats_sorted":["cs.AI","cs.SE"],"title_canon_sha256":"2b91e851a29f4439178a9f716a790baf3e65d111c7feda0a819b645038f745c9","abstract_canon_sha256":"7881e379c06c75c22d36ea3689261acc27f7785d90724da7c135449c6e41b1db"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:57:38.925467Z","signature_b64":"2umUJaONTk0UR/2bP86oSzy/2Fgo/Vy3x/UkXOFd7gxYa1lPgmjo6Q13J2vtHXpB6Q507Xrg3/ZfebAfogBiCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d2aa6a674ee7b77b5b1a23e2d3c2898e457144750dff1a94bdc3dba9819a1055","last_reissued_at":"2026-07-05T08:57:38.924970Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:57:38.924970Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VulDetectBench: Evaluating the Deep Capability of Vulnerability Detection with Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.SE"],"primary_cat":"cs.CR","authors_text":"Lang Gao, Mingxin Yang, Ping Chen, Wei Chen, Xiaojin Zhang, Yu Liu, Yu Xie","submitted_at":"2024-06-11T13:42:57Z","abstract_excerpt":"Large Language Models (LLMs) have training corpora containing large amounts of program code, greatly improving the model's code comprehension and generation capabilities. However, sound comprehensive research on detecting program vulnerabilities, a more specific task related to code, and evaluating the performance of LLMs in this more specialized scenario is still lacking. To address common challenges in vulnerability analysis, our study introduces a new benchmark, VulDetectBench, specifically designed to assess the vulnerability detection capabilities of LLMs. The benchmark comprehensively ev"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.07595","kind":"arxiv","version":4},"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/2406.07595/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":"2406.07595","created_at":"2026-07-05T08:57:38.925031+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.07595v4","created_at":"2026-07-05T08:57:38.925031+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.07595","created_at":"2026-07-05T08:57:38.925031+00:00"},{"alias_kind":"pith_short_12","alias_value":"2KVGUZ2O463X","created_at":"2026-07-05T08:57:38.925031+00:00"},{"alias_kind":"pith_short_16","alias_value":"2KVGUZ2O463XWWY2","created_at":"2026-07-05T08:57:38.925031+00:00"},{"alias_kind":"pith_short_8","alias_value":"2KVGUZ2O","created_at":"2026-07-05T08:57:38.925031+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20502","citing_title":"Calibration Without Comprehension: Diagnosing the Limits of Fine-Tuning LLMs for Vulnerability Detection in Systems Software","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30587","citing_title":"Words Speak Louder Than Code: Investigating Cognitive Heuristics in LLM-Based Code Vulnerability Detection","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2510.04056","citing_title":"QuiLL: An LLM-Based Vulnerability Assessment Framework for the Wild","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27714","citing_title":"How Code Representation Shapes False-Positive Dynamics in Cross-Language LLM Vulnerability Detection","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2KVGUZ2O463XWWY2EPRNHQUJRZ","json":"https://pith.science/pith/2KVGUZ2O463XWWY2EPRNHQUJRZ.json","graph_json":"https://pith.science/api/pith-number/2KVGUZ2O463XWWY2EPRNHQUJRZ/graph.json","events_json":"https://pith.science/api/pith-number/2KVGUZ2O463XWWY2EPRNHQUJRZ/events.json","paper":"https://pith.science/paper/2KVGUZ2O"},"agent_actions":{"view_html":"https://pith.science/pith/2KVGUZ2O463XWWY2EPRNHQUJRZ","download_json":"https://pith.science/pith/2KVGUZ2O463XWWY2EPRNHQUJRZ.json","view_paper":"https://pith.science/paper/2KVGUZ2O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.07595&json=true","fetch_graph":"https://pith.science/api/pith-number/2KVGUZ2O463XWWY2EPRNHQUJRZ/graph.json","fetch_events":"https://pith.science/api/pith-number/2KVGUZ2O463XWWY2EPRNHQUJRZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2KVGUZ2O463XWWY2EPRNHQUJRZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2KVGUZ2O463XWWY2EPRNHQUJRZ/action/storage_attestation","attest_author":"https://pith.science/pith/2KVGUZ2O463XWWY2EPRNHQUJRZ/action/author_attestation","sign_citation":"https://pith.science/pith/2KVGUZ2O463XWWY2EPRNHQUJRZ/action/citation_signature","submit_replication":"https://pith.science/pith/2KVGUZ2O463XWWY2EPRNHQUJRZ/action/replication_record"}},"created_at":"2026-07-05T08:57:38.925031+00:00","updated_at":"2026-07-05T08:57:38.925031+00:00"}