{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:DZNKDN3OKJOCSV76CLXD5RVW4I","short_pith_number":"pith:DZNKDN3O","schema_version":"1.0","canonical_sha256":"1e5aa1b76e525c2957fe12ee3ec6b6e23cccd8c5f22bf9783ae36806e3ad3941","source":{"kind":"arxiv","id":"2608.02693","version":1},"attestation_state":"computed","paper":{"title":"PRWeaver: Evaluating LLM-Based Code Auditors against Long-Horizon Malicious Pull Requests","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.SE","authors_text":"Mingfei Cheng, Xiaofei Xie, Yuekun Wang","submitted_at":"2026-08-03T10:05:08Z","abstract_excerpt":"LLM-based code auditors are increasingly integrated into pull-request (PR) workflows, yet their reliability against adversarial changes distributed across repository evolution remains poorly understood. We introduce PRWeaver, a benchmark of 208 execution-validated attacks from ten real-world repositories, each instantiated under four matched review renderings (832 renderings in total). We evaluate three PR-auditing agents across six auditor-model systems. Across all systems, decomposing an attack changes detection by at most five percentage points, showing that commit boundaries alone do not e"},"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":"2608.02693","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-08-03T10:05:08Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"0ad8952eeb0732e02d8e0e000e51a2bd9c569fcf22dc20c7703bf705d0a3929b","abstract_canon_sha256":"2c76ed730545ca17da170c397d178b834b96d54707d58ae553bb51167ea9ecc8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-05T00:39:26.057281Z","signature_b64":"flrP2bg9wDvkBSeNEhM/xuUqckPk3XkB1Bt5Gr+lM5EhleBWqqViAbHnhfbmt2tkb0KWhR8c5UH7MYMca/OXDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e5aa1b76e525c2957fe12ee3ec6b6e23cccd8c5f22bf9783ae36806e3ad3941","last_reissued_at":"2026-08-05T00:39:26.053936Z","signature_status":"signed_v1","first_computed_at":"2026-08-05T00:39:26.053936Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PRWeaver: Evaluating LLM-Based Code Auditors against Long-Horizon Malicious Pull Requests","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.SE","authors_text":"Mingfei Cheng, Xiaofei Xie, Yuekun Wang","submitted_at":"2026-08-03T10:05:08Z","abstract_excerpt":"LLM-based code auditors are increasingly integrated into pull-request (PR) workflows, yet their reliability against adversarial changes distributed across repository evolution remains poorly understood. We introduce PRWeaver, a benchmark of 208 execution-validated attacks from ten real-world repositories, each instantiated under four matched review renderings (832 renderings in total). We evaluate three PR-auditing agents across six auditor-model systems. Across all systems, decomposing an attack changes detection by at most five percentage points, showing that commit boundaries alone do not e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.02693","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/2608.02693/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":"2608.02693","created_at":"2026-08-05T00:39:26.055585+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.02693v1","created_at":"2026-08-05T00:39:26.055585+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.02693","created_at":"2026-08-05T00:39:26.055585+00:00"},{"alias_kind":"pith_short_12","alias_value":"DZNKDN3OKJOC","created_at":"2026-08-05T00:39:26.055585+00:00"},{"alias_kind":"pith_short_16","alias_value":"DZNKDN3OKJOCSV76","created_at":"2026-08-05T00:39:26.055585+00:00"},{"alias_kind":"pith_short_8","alias_value":"DZNKDN3O","created_at":"2026-08-05T00:39:26.055585+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/DZNKDN3OKJOCSV76CLXD5RVW4I","json":"https://pith.science/pith/DZNKDN3OKJOCSV76CLXD5RVW4I.json","graph_json":"https://pith.science/api/pith-number/DZNKDN3OKJOCSV76CLXD5RVW4I/graph.json","events_json":"https://pith.science/api/pith-number/DZNKDN3OKJOCSV76CLXD5RVW4I/events.json","paper":"https://pith.science/paper/DZNKDN3O"},"agent_actions":{"view_html":"https://pith.science/pith/DZNKDN3OKJOCSV76CLXD5RVW4I","download_json":"https://pith.science/pith/DZNKDN3OKJOCSV76CLXD5RVW4I.json","view_paper":"https://pith.science/paper/DZNKDN3O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.02693&json=true","fetch_graph":"https://pith.science/api/pith-number/DZNKDN3OKJOCSV76CLXD5RVW4I/graph.json","fetch_events":"https://pith.science/api/pith-number/DZNKDN3OKJOCSV76CLXD5RVW4I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DZNKDN3OKJOCSV76CLXD5RVW4I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DZNKDN3OKJOCSV76CLXD5RVW4I/action/storage_attestation","attest_author":"https://pith.science/pith/DZNKDN3OKJOCSV76CLXD5RVW4I/action/author_attestation","sign_citation":"https://pith.science/pith/DZNKDN3OKJOCSV76CLXD5RVW4I/action/citation_signature","submit_replication":"https://pith.science/pith/DZNKDN3OKJOCSV76CLXD5RVW4I/action/replication_record"}},"created_at":"2026-08-05T00:39:26.055585+00:00","updated_at":"2026-08-05T00:39:26.055585+00:00"}