{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2609.08040", "kind": "paper", "url": "https://arxiv.org/abs/2609.08040"}, {"id": "gh:steven1518/vex-bench", "kind": "repo", "url": "https://github.com/steven1518/vex-bench"}], "authors": ["Jiahao Shi", "Edward Tsien", "Yifeng Di", "Hongjiao Zhang", "Yuan Tang", "Ronit Dey", "Ilona Shishov", "Gal Netanel", "Zvi Grinberg", "Vladimir Belousov", "Bat-Zion Rotman", "Ilan Pinto", "Tianyi Zhang"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2609.08040", "source_url": "https://arxiv.org/abs/2609.08040"}, "categories": ["Language & Knowledge", "Logistics & Operations", "cs.CR"], "description": {"en": "Consists of 75 real-world software supply chain vulnerability cases across Python, Java, and Go for evaluating LLM agents on exploitability assessment tasks."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2609.08040", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2609.08040", "title": "VEX-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2609.08040", "modality": null, "name": "VEX-Bench", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"admission_policy_version": "2026-09-09.1", "confidence": "High", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-10-14T09:44:51Z", "data_status": "primary-source-indexed", "display_eligible": "true", "origin_record_id": "bm_vex-bench_83da0ca3", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "5bf5020b59f6e0f2f7b28a751387cd40f192d2c8daaa309e7a05320c69746eee", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-09-09T06:27:57.312318Z", "source_url": "https://arxiv.org/abs/2609.08040"}, "publisher": null, "released": "2026-09-07", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2609.08040", "source_url": "https://arxiv.org/abs/2609.08040"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2609-08040", "source": "claire_radar", "source_benchmark_id": "2609.08040", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Logistics & Operations"], "area": "Language & Knowledge", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/steven1518/vex-bench", "githubScope": "benchmark_repo", "githubStars": 9, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2609.08040", "observedAt": "2026-10-04T15:31:48.030916Z", "signalStatus": {"githubStars": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "state": "unavailable"}}, "status": "fresh"}, "attentionForecast": {"confidence": "Medium", "horizon": "7d", "reason": "Software supply chain security is an active area with growing interest in LLM agent evaluation.", "score": 55}, "capabilities": [], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-09T06:27:57.312318Z", "inputHash": "94742d5c55d45df35c6913cd759aafff8338fc18b2b61f7b1ade37d5f4ae97f2", "model": "deepseek-v4-pro"}, "curation": {"admissionPolicyVersion": "2026-09-09.1", "canonicalNameEvidence": "VEX-Bench: Benchmarking LLM Agents for Assessing Exploitability of Software Supply Chain Vulnerabilities", "canonicalNameSource": "paper_title", "decisionReason": "The benchmark defines a concrete dataset and scoring metrics, and provides a public repository link for code and data.", "evaluationEvidence": {"reuse": "Code and data: https://github.com/steven1518/vex-bench", "scoring": "binary vulnerability-status classification and fine-grained justification classification, with metrics F1 and macro-F1 reported.", "task": "It contains 75 real-world cases mined from GitHub and labeled by security experts, covering Python, Java, and Go."}, "model": "deepseek-v4-pro", "reviewedAt": "2026-09-09T06:27:57.312318Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Consists of 75 real-world software supply chain vulnerability cases across Python, Java, and Go for evaluating LLM agents on exploitability assessment tasks.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence", "evaluation protocol evidence", "public artifact URL"], "snippet": "To address this gap, we introduce VEX-Bench, the first benchmark for evaluating LLM agents' ability to assess the exploitability of software supply chain vulnerabilities."}, "familyId": "bmf_502ee449e022", "firstSeenAt": "2026-09-09", "heat": null, "id": "bm_vex-bench_83da0ca3", "indexedAt": "2026-09-09T06:18:29.794093Z", "industrySectors": ["Logistics"], "links": {"code": "https://github.com/steven1518/vex-bench", "data": null, "paper": "https://arxiv.org/abs/2609.08040", "pdf": "https://arxiv.org/pdf/2609.08040", "project": null, "report": "https://arxiv.org/abs/2609.08040"}, "metrics": [], "motivation": "The software supply chain has become an increasingly exposed attack surface because of its reliance on intricate yet fragile dependencies.", "name": "VEX-Bench", "oneLine": "Consists of 75 real-world software supply chain vulnerability cases across Python, Java, and Go for evaluating LLM agents on exploitability assessment tasks.", "paperTitle": "VEX-Bench: Benchmarking LLM Agents for Assessing Exploitability of Software Supply Chain Vulnerabilities", "primaryDomain": "Logistics & Operations", "publication": {"evidence": "Accepted to EMNLP 2026", "evidenceLevel": "author-claim", "evidenceUrl": "https://arxiv.org/abs/2609.08040", "source": "arxiv-comments", "status": "acceptance_claimed", "venue": "EMNLP 2026", "verifiedAt": "2026-09-09T06:18:29.794093Z"}, "publications": [], "ranking": {"30d": {"confidence": "Low", "coverage": 0.55, "growth": {"components": {"githubStars": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfDatasetDownloads": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfPaperUpvotes": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "elapsedDays": 30, "historyDate": "2026-09-05", "rank": null, "score": null, "windowDays": 30}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": 0.33950455457166134, "value": 9}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.55, "rank": 39, "score": 41}, "method": "attention-ranking-v13", "rank": 39, "score": 41}, "90d": {"confidence": "Low", "coverage": 0.55, "growth": {"components": {"githubStars": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfDatasetDownloads": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}, "hfPaperUpvotes": {"normalization": "percentile", "normalized": null, "percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "elapsedDays": null, "historyDate": null, "rank": null, "score": null, "windowDays": 90}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": 0.30735371836622627, "value": 9}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.55, "rank": 141, "score": 39}, "method": "attention-ranking-v13", "rank": 141, "score": 39}}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-09-07", "source": {"authors": ["Jiahao Shi", "Edward Tsien", "Yifeng Di", "Hongjiao Zhang", "Yuan Tang", "Ronit Dey", "Ilona Shishov", "Gal Netanel", "Zvi Grinberg", "Vladimir Belousov", "Bat-Zion Rotman", "Ilan Pinto", "Tianyi Zhang"], "categories": ["cs.CR", "cs.LG", "cs.SE"], "id": "2609.08040", "title": "VEX-Bench: Benchmarking LLM Agents for Assessing Exploitability of Software Supply Chain Vulnerabilities", "type": "arxiv", "url": "https://arxiv.org/abs/2609.08040"}, "sourceUpdatedAt": "2026-09-07T22:52:09Z", "topics": ["cs.CR"], "venueAttempts": [{"decisionRaw": "Accepted to EMNLP 2026", "evidence": [{"level": "author-claim", "observedAt": "2026-09-09T06:18:29.794093Z", "rawValue": "Accepted to EMNLP 2026", "sourceType": "arxiv-comments", "sourceUrl": "https://arxiv.org/abs/2609.08040"}], "reviewStatus": "accepted", "venueName": "EMNLP 2026"}], "whyItMatters": "Addresses a gap in evaluating LLMs for known vulnerability exploitability in downstream projects, complementing zero-day benchmarks."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
