{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XWWVQBXM6G3Q7VFSDCW6KYT4WJ","short_pith_number":"pith:XWWVQBXM","schema_version":"1.0","canonical_sha256":"bdad5806ecf1b70fd4b218ade5627cb27e791cd8e1661e9269ed97a85e62f300","source":{"kind":"arxiv","id":"2411.07781","version":1},"attestation_state":"computed","paper":{"title":"RedCode: Risky Code Execution and Generation Benchmark for Code Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Andy Zhou, Bo Li, Chengquan Guo, Chulin Xie, Dawn Song, Xun Liu, Yi Zeng, Zinan Lin","submitted_at":"2024-11-12T13:30:06Z","abstract_excerpt":"With the rapidly increasing capabilities and adoption of code agents for AI-assisted coding, safety concerns, such as generating or executing risky code, have become significant barriers to the real-world deployment of these agents. To provide comprehensive and practical evaluations on the safety of code agents, we propose RedCode, a benchmark for risky code execution and generation: (1) RedCode-Exec provides challenging prompts that could lead to risky code execution, aiming to evaluate code agents' ability to recognize and handle unsafe code. We provide a total of 4,050 risky test cases in P"},"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":"2411.07781","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-11-12T13:30:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"af34f38dea61b3c98defedbfc9989ae02eb10ccc279706ba78a3f31047e2dfe8","abstract_canon_sha256":"5ad5b5d483daf37292f905793bca551666fb7ee48440ce2189e8c074e30a0c7d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:34:28.560343Z","signature_b64":"BUi8nFHY36TSH8QbMyx/s3/a6KSuJl9X9OvEMXZ9Cw92KUvgDaM4PRnhxOP6reHfkpSmwDmGjJrcaySaUFJMAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bdad5806ecf1b70fd4b218ade5627cb27e791cd8e1661e9269ed97a85e62f300","last_reissued_at":"2026-07-05T09:34:28.559889Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:34:28.559889Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RedCode: Risky Code Execution and Generation Benchmark for Code Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Andy Zhou, Bo Li, Chengquan Guo, Chulin Xie, Dawn Song, Xun Liu, Yi Zeng, Zinan Lin","submitted_at":"2024-11-12T13:30:06Z","abstract_excerpt":"With the rapidly increasing capabilities and adoption of code agents for AI-assisted coding, safety concerns, such as generating or executing risky code, have become significant barriers to the real-world deployment of these agents. To provide comprehensive and practical evaluations on the safety of code agents, we propose RedCode, a benchmark for risky code execution and generation: (1) RedCode-Exec provides challenging prompts that could lead to risky code execution, aiming to evaluate code agents' ability to recognize and handle unsafe code. We provide a total of 4,050 risky test cases in P"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.07781","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/2411.07781/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":"2411.07781","created_at":"2026-07-05T09:34:28.559945+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.07781v1","created_at":"2026-07-05T09:34:28.559945+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.07781","created_at":"2026-07-05T09:34:28.559945+00:00"},{"alias_kind":"pith_short_12","alias_value":"XWWVQBXM6G3Q","created_at":"2026-07-05T09:34:28.559945+00:00"},{"alias_kind":"pith_short_16","alias_value":"XWWVQBXM6G3Q7VFS","created_at":"2026-07-05T09:34:28.559945+00:00"},{"alias_kind":"pith_short_8","alias_value":"XWWVQBXM","created_at":"2026-07-05T09:34:28.559945+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05743","citing_title":"The Balkanization of Execution-Security Research for AI Coding Agents: Isolation, Access Control, and Time-of-Check-to-Time-of-Use Vulnerabilities","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XWWVQBXM6G3Q7VFSDCW6KYT4WJ","json":"https://pith.science/pith/XWWVQBXM6G3Q7VFSDCW6KYT4WJ.json","graph_json":"https://pith.science/api/pith-number/XWWVQBXM6G3Q7VFSDCW6KYT4WJ/graph.json","events_json":"https://pith.science/api/pith-number/XWWVQBXM6G3Q7VFSDCW6KYT4WJ/events.json","paper":"https://pith.science/paper/XWWVQBXM"},"agent_actions":{"view_html":"https://pith.science/pith/XWWVQBXM6G3Q7VFSDCW6KYT4WJ","download_json":"https://pith.science/pith/XWWVQBXM6G3Q7VFSDCW6KYT4WJ.json","view_paper":"https://pith.science/paper/XWWVQBXM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.07781&json=true","fetch_graph":"https://pith.science/api/pith-number/XWWVQBXM6G3Q7VFSDCW6KYT4WJ/graph.json","fetch_events":"https://pith.science/api/pith-number/XWWVQBXM6G3Q7VFSDCW6KYT4WJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XWWVQBXM6G3Q7VFSDCW6KYT4WJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XWWVQBXM6G3Q7VFSDCW6KYT4WJ/action/storage_attestation","attest_author":"https://pith.science/pith/XWWVQBXM6G3Q7VFSDCW6KYT4WJ/action/author_attestation","sign_citation":"https://pith.science/pith/XWWVQBXM6G3Q7VFSDCW6KYT4WJ/action/citation_signature","submit_replication":"https://pith.science/pith/XWWVQBXM6G3Q7VFSDCW6KYT4WJ/action/replication_record"}},"created_at":"2026-07-05T09:34:28.559945+00:00","updated_at":"2026-07-05T09:34:28.559945+00:00"}