{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TO7IFMAXTHFECEHGDFOCRFM34Z","short_pith_number":"pith:TO7IFMAX","schema_version":"1.0","canonical_sha256":"9bbe82b01799ca4110e6195c28959be6545a865b6716d4d9c8af635c905acd22","source":{"kind":"arxiv","id":"2605.01769","version":3},"attestation_state":"computed","paper":{"title":"VulKey: Automated Vulnerability Repair Guided by Domain-Specific Repair Patterns","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A framework guides LLMs using a three-level hierarchy of security knowledge to generate more accurate vulnerability patches.","cross_cats":["cs.SE"],"primary_cat":"cs.CR","authors_text":"Jia Li, Michael R. Lyu, Yuxin Su, Zhuangbin Chen","submitted_at":"2026-05-03T08:07:41Z","abstract_excerpt":"The increasing prevalence of software vulnerabilities highlights the need for effective Automatic Vulnerability Repair (AVR) tools. While LLM-based approaches are promising, they struggle to incorporate structured security knowledge from sources like CWE and NVD. Current methods either use this information superficially by concatenating the CWE-ID into the input prompt, yielding negligible benefits, or rely on few-shot learning with rigid, non-generalizable examples, which limits their effectiveness in real-world scenarios.\n  To address this gap, we propose VulKey, an LLM-based AVR framework t"},"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":"2605.01769","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-05-03T08:07:41Z","cross_cats_sorted":["cs.SE"],"title_canon_sha256":"9b5420b54fcdbef37be73fc34bb282380219ff8107fc39a34be47a9865433095","abstract_canon_sha256":"ff1fdcdaeda2d112faa8e061ad590c485aa839e2ba1dc374c5a246d584553269"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:16:30.427121Z","signature_b64":"n8qEb89AGrzfmK7mpm8ZbjVw7EJFBSjbv3WyhcCCqEk4xVBKHQm68mVMBrHncCpSY/8pZF9hmarW1dtzlAUsDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9bbe82b01799ca4110e6195c28959be6545a865b6716d4d9c8af635c905acd22","last_reissued_at":"2026-06-30T01:16:30.426369Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:16:30.426369Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VulKey: Automated Vulnerability Repair Guided by Domain-Specific Repair Patterns","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A framework guides LLMs using a three-level hierarchy of security knowledge to generate more accurate vulnerability patches.","cross_cats":["cs.SE"],"primary_cat":"cs.CR","authors_text":"Jia Li, Michael R. Lyu, Yuxin Su, Zhuangbin Chen","submitted_at":"2026-05-03T08:07:41Z","abstract_excerpt":"The increasing prevalence of software vulnerabilities highlights the need for effective Automatic Vulnerability Repair (AVR) tools. While LLM-based approaches are promising, they struggle to incorporate structured security knowledge from sources like CWE and NVD. Current methods either use this information superficially by concatenating the CWE-ID into the input prompt, yielding negligible benefits, or rely on few-shot learning with rigid, non-generalizable examples, which limits their effectiveness in real-world scenarios.\n  To address this gap, we propose VulKey, an LLM-based AVR framework t"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"On the real-world C/C++ dataset PrimeVul, VulKey achieves 31.5% repair accuracy, surpassing the best baseline by 7.6% and outperforming leading tools such as VulMaster and GPT-5. Moreover, VulKey demonstrates cross-language and cross-model generalizability, with state-of-the-art performance on the Java benchmark Vul4J.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the three-level hierarchical abstraction (CWE type, syntactic actions, semantic key elements) can be reliably matched to unseen vulnerabilities and will provide sufficient guidance for the fine-tuned LLM to produce correct, generalizable patches without overfitting to the abstracted patterns.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"VulKey reaches 31.5% repair accuracy on real C/C++ vulnerabilities by matching hierarchical expert patterns to guide LLM patch generation, beating prior baselines by 7.6%.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A framework guides LLMs using a three-level hierarchy of security knowledge to generate more accurate vulnerability patches.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"b72f16bed5a12d041e59797591786c8fce28667245d0ded4d2250233df852676"},"source":{"id":"2605.01769","kind":"arxiv","version":3},"verdict":{"id":"c372abf6-1f79-47dd-97f7-4c34cf691e96","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T14:53:42.091341Z","strongest_claim":"On the real-world C/C++ dataset PrimeVul, VulKey achieves 31.5% repair accuracy, surpassing the best baseline by 7.6% and outperforming leading tools such as VulMaster and GPT-5. Moreover, VulKey demonstrates cross-language and cross-model generalizability, with state-of-the-art performance on the Java benchmark Vul4J.","one_line_summary":"VulKey reaches 31.5% repair accuracy on real C/C++ vulnerabilities by matching hierarchical expert patterns to guide LLM patch generation, beating prior baselines by 7.6%.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the three-level hierarchical abstraction (CWE type, syntactic actions, semantic key elements) can be reliably matched to unseen vulnerabilities and will provide sufficient guidance for the fine-tuned LLM to produce correct, generalizable patches without overfitting to the abstracted patterns.","pith_extraction_headline":"A framework guides LLMs using a three-level hierarchy of security knowledge to generate more accurate vulnerability patches."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.01769/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-20T17:36:55.237408Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-20T05:01:22.844908Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T16:59:22.080843Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"cf6cfd576a54d472bbb710a8dcc77feb22648925982b0b84d2acae1161607bb8"},"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":"2605.01769","created_at":"2026-06-30T01:16:30.426481+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.01769v3","created_at":"2026-06-30T01:16:30.426481+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.01769","created_at":"2026-06-30T01:16:30.426481+00:00"},{"alias_kind":"pith_short_12","alias_value":"TO7IFMAXTHFE","created_at":"2026-06-30T01:16:30.426481+00:00"},{"alias_kind":"pith_short_16","alias_value":"TO7IFMAXTHFECEHG","created_at":"2026-06-30T01:16:30.426481+00:00"},{"alias_kind":"pith_short_8","alias_value":"TO7IFMAX","created_at":"2026-06-30T01:16:30.426481+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.07276","citing_title":"Signal Reshaping for GRPO in Weak-Feedback Agentic Code Repair","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TO7IFMAXTHFECEHGDFOCRFM34Z","json":"https://pith.science/pith/TO7IFMAXTHFECEHGDFOCRFM34Z.json","graph_json":"https://pith.science/api/pith-number/TO7IFMAXTHFECEHGDFOCRFM34Z/graph.json","events_json":"https://pith.science/api/pith-number/TO7IFMAXTHFECEHGDFOCRFM34Z/events.json","paper":"https://pith.science/paper/TO7IFMAX"},"agent_actions":{"view_html":"https://pith.science/pith/TO7IFMAXTHFECEHGDFOCRFM34Z","download_json":"https://pith.science/pith/TO7IFMAXTHFECEHGDFOCRFM34Z.json","view_paper":"https://pith.science/paper/TO7IFMAX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.01769&json=true","fetch_graph":"https://pith.science/api/pith-number/TO7IFMAXTHFECEHGDFOCRFM34Z/graph.json","fetch_events":"https://pith.science/api/pith-number/TO7IFMAXTHFECEHGDFOCRFM34Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TO7IFMAXTHFECEHGDFOCRFM34Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TO7IFMAXTHFECEHGDFOCRFM34Z/action/storage_attestation","attest_author":"https://pith.science/pith/TO7IFMAXTHFECEHGDFOCRFM34Z/action/author_attestation","sign_citation":"https://pith.science/pith/TO7IFMAXTHFECEHGDFOCRFM34Z/action/citation_signature","submit_replication":"https://pith.science/pith/TO7IFMAXTHFECEHGDFOCRFM34Z/action/replication_record"}},"created_at":"2026-06-30T01:16:30.426481+00:00","updated_at":"2026-06-30T01:16:30.426481+00:00"}