{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.26216", "kind": "paper", "url": "https://arxiv.org/abs/2606.26216"}], "authors": ["Jintao Huang", "Fengqing Jiang", "Radha Poovendran", "Zhiqiang Lin"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.26216", "source_url": "https://arxiv.org/abs/2606.26216"}, "categories": ["Cybersecurity", "Vision & 3D", "cs.CR"], "description": {"en": "CyberChainBench evaluates LLM-based agents on smart contract security across vulnerability detection, exploit generation, and patch synthesis, using 541 real exploit incidents with on-chain evaluation on historical forks."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.26216", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.26216", "title": "CyberChainBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2606.26216", "modality": null, "name": "CyberChainBench", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "High", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-10-14T09:44:51Z", "data_status": "primary-source-indexed", "display_eligible": "unknown", "origin_record_id": "bm_cyberchainbench_89e4f090", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "09a3db2231c1a782f2ac79f8f23acffc369a69d7089b371ef73d6a49ee1fb60c", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.26216"}, "publisher": null, "released": "2026-06-24", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.26216", "source_url": "https://arxiv.org/abs/2606.26216"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-26216", "source": "claire_radar", "source_benchmark_id": "2606.26216", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Cybersecurity"], "area": "Vision & 3D", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2606.26216", "observedAt": "2026-10-04T03:02:42.754940Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "state": "unavailable"}}, "status": "unavailable"}, "capabilities": [], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "372a1ccbf58b9582df8654725de82f7b7ee7945ae56f4e91c642fe524ce71754", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "CyberChainBench evaluates LLM-based agents on smart contract security across vulnerability detection, exploit generation, and patch synthesis, using 541 real exploit incidents with on-chain evaluation on historical forks.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "We present CyberChainBench, a benchmark for evaluating LLM-based agents on smart contract security across three complementary tasks: vulnerability detection, exploit generation, and patch synthesis."}, "familyId": "bmf_073d2b7764c1", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_cyberchainbench_89e4f090", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Cybersecurity"], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.26216", "paper": "https://arxiv.org/abs/2606.26216", "pdf": "https://arxiv.org/pdf/2606.26216", "project": null, "report": "https://arxiv.org/abs/2606.26216"}, "metrics": [], "motivation": "We present CyberChainBench, a benchmark for evaluating LLM-based agents on smart contract security across three complementary tasks: vulnerability detection, exploit generation, and patch synthesis.", "name": "CyberChainBench", "oneLine": "CyberChainBench evaluates LLM-based agents on smart contract security across vulnerability detection, exploit generation, and patch synthesis, using 541 real exploit incidents with on-chain evaluation on historical forks.", "paperTitle": "CyberChainBench: Can AI Agents Secure Smart Contracts Against Real-World On-Chain Vulnerabilities?", "primaryDomain": "Cybersecurity", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.26216", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "arXiv", "organizationType": "community", "role": "benchmark-publisher", "sourceUrl": "https://arxiv.org/abs/2606.26216"}], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-24", "source": {"authors": ["Jintao Huang", "Fengqing Jiang", "Radha Poovendran", "Zhiqiang Lin"], "categories": ["cs.CR", "cs.AI"], "id": "2606.26216", "title": "CyberChainBench: Can AI Agents Secure Smart Contracts Against Real-World On-Chain Vulnerabilities?", "type": "arxiv", "url": "https://arxiv.org/abs/2606.26216"}, "sourceUpdatedAt": "2026-06-24T17:58:16Z", "topics": ["cs.CR"], "venueAttempts": [], "whyItMatters": "Smart contract security requires realistic, end-to-end evaluation of agent capabilities; CyberChainBench provides structured ground truth and economic impact metrics to measure practical effectiveness."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
