{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YAXXFRAXPOQ5LZIONBWQ3YA5TJ","short_pith_number":"pith:YAXXFRAX","schema_version":"1.0","canonical_sha256":"c02f72c4177ba1d5e50e686d0de01d9a74fd4807f825a54f8b4d6741162d23e2","source":{"kind":"arxiv","id":"2501.18160","version":3},"attestation_state":"computed","paper":{"title":"RepoAudit: An Autonomous LLM-Agent for Repository-Level Code Auditing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.PL"],"primary_cat":"cs.SE","authors_text":"Chengpeng Wang, Jinyao Guo, Xiangyu Zhang, Xiangzhe Xu, Zian Su","submitted_at":"2025-01-30T05:56:30Z","abstract_excerpt":"Code auditing is the process of reviewing code with the aim of identifying bugs. Large Language Models (LLMs) have demonstrated promising capabilities for this task without requiring compilation, while also supporting user-friendly customization. However, auditing a code repository with LLMs poses significant challenges: limited context windows and hallucinations can degrade the quality of bug reports, and analyzing large-scale repositories incurs substantial time and token costs, hindering efficiency and scalability.\n  This work introduces an LLM-based agent, RepoAudit, designed to perform au"},"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":"2501.18160","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-01-30T05:56:30Z","cross_cats_sorted":["cs.PL"],"title_canon_sha256":"cf3742192867138487a35f93be85579084532f8da2cffcf2af707c1e646f9188","abstract_canon_sha256":"a3b5b32378aeece5dbc90e9511ff72a2de0468185b5563220a1b386c956b4cfb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:24.949615Z","signature_b64":"qFxbkugjsGkz4TOGXZAZIoYcr8ujEZT3wr5isJKjcW3ZEbGmiGO41RBelWs/r2ydRWaVHfQpq7q4WmJ19pg6BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c02f72c4177ba1d5e50e686d0de01d9a74fd4807f825a54f8b4d6741162d23e2","last_reissued_at":"2026-07-05T11:12:24.948980Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:24.948980Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RepoAudit: An Autonomous LLM-Agent for Repository-Level Code Auditing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.PL"],"primary_cat":"cs.SE","authors_text":"Chengpeng Wang, Jinyao Guo, Xiangyu Zhang, Xiangzhe Xu, Zian Su","submitted_at":"2025-01-30T05:56:30Z","abstract_excerpt":"Code auditing is the process of reviewing code with the aim of identifying bugs. Large Language Models (LLMs) have demonstrated promising capabilities for this task without requiring compilation, while also supporting user-friendly customization. However, auditing a code repository with LLMs poses significant challenges: limited context windows and hallucinations can degrade the quality of bug reports, and analyzing large-scale repositories incurs substantial time and token costs, hindering efficiency and scalability.\n  This work introduces an LLM-based agent, RepoAudit, designed to perform au"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.18160","kind":"arxiv","version":3},"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/2501.18160/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":"2501.18160","created_at":"2026-07-05T11:12:24.949056+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.18160v3","created_at":"2026-07-05T11:12:24.949056+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.18160","created_at":"2026-07-05T11:12:24.949056+00:00"},{"alias_kind":"pith_short_12","alias_value":"YAXXFRAXPOQ5","created_at":"2026-07-05T11:12:24.949056+00:00"},{"alias_kind":"pith_short_16","alias_value":"YAXXFRAXPOQ5LZIO","created_at":"2026-07-05T11:12:24.949056+00:00"},{"alias_kind":"pith_short_8","alias_value":"YAXXFRAX","created_at":"2026-07-05T11:12:24.949056+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22263","citing_title":"Revelio: Cost-Efficient Agentic Memory Safety Vulnerability Detection For Repository-Scale Codebases","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.21397","citing_title":"Evaluating LLMs for Real-World Web Vulnerability Detection","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01138","citing_title":"Antaeus: Hunting Repository-Level Logic Vulnerabilities via Context-Grounded LLM Reasoning","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2507.15671","citing_title":"BugScope: Learn to Find Bugs Like Human","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15097","citing_title":"Veritas: Grounding LLM Agents for Reliable Vulnerability Reasoning over Stripped Binaries","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2603.27224","citing_title":"Finding Memory Leaks in C/C++ Programs via Neuro-Symbolic Augmented Static Analysis","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04845","citing_title":"Agentic Repository Mining: A Multi-Task Evaluation","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10767","citing_title":"VulWeaver: Weaving Broken Semantics for Grounded Vulnerability Detection","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05753","citing_title":"An End-to-End Approach for Fixing Concurrency Bugs via SHB-Based Context Extractor","ref_index":110,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19049","citing_title":"Refute-or-Promote: An Adversarial Stage-Gated Multi-Agent Review Methodology for High-Precision LLM-Assisted Defect Discovery","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21765","citing_title":"PrismaDV: Automated Task-Aware Data Unit Test Generation","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02091","citing_title":"How Compliant Are GitHub Actions Workflows? A Checklist-Based Study with LLM-Assisted Auditing","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YAXXFRAXPOQ5LZIONBWQ3YA5TJ","json":"https://pith.science/pith/YAXXFRAXPOQ5LZIONBWQ3YA5TJ.json","graph_json":"https://pith.science/api/pith-number/YAXXFRAXPOQ5LZIONBWQ3YA5TJ/graph.json","events_json":"https://pith.science/api/pith-number/YAXXFRAXPOQ5LZIONBWQ3YA5TJ/events.json","paper":"https://pith.science/paper/YAXXFRAX"},"agent_actions":{"view_html":"https://pith.science/pith/YAXXFRAXPOQ5LZIONBWQ3YA5TJ","download_json":"https://pith.science/pith/YAXXFRAXPOQ5LZIONBWQ3YA5TJ.json","view_paper":"https://pith.science/paper/YAXXFRAX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.18160&json=true","fetch_graph":"https://pith.science/api/pith-number/YAXXFRAXPOQ5LZIONBWQ3YA5TJ/graph.json","fetch_events":"https://pith.science/api/pith-number/YAXXFRAXPOQ5LZIONBWQ3YA5TJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YAXXFRAXPOQ5LZIONBWQ3YA5TJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YAXXFRAXPOQ5LZIONBWQ3YA5TJ/action/storage_attestation","attest_author":"https://pith.science/pith/YAXXFRAXPOQ5LZIONBWQ3YA5TJ/action/author_attestation","sign_citation":"https://pith.science/pith/YAXXFRAXPOQ5LZIONBWQ3YA5TJ/action/citation_signature","submit_replication":"https://pith.science/pith/YAXXFRAXPOQ5LZIONBWQ3YA5TJ/action/replication_record"}},"created_at":"2026-07-05T11:12:24.949056+00:00","updated_at":"2026-07-05T11:12:24.949056+00:00"}