{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2607.27030", "kind": "paper", "url": "https://arxiv.org/abs/2607.27030"}, {"id": "gh:weareaisle/hof-bench", "kind": "repo", "url": "https://github.com/weareaisle/HoF-Bench"}, {"id": "hf:aisleinc/hof-bench", "kind": "dataset", "url": "https://huggingface.co/datasets/aisleinc/HoF-Bench"}], "authors": ["Petr Simecek", "Elnaz Babayeva", "Jiri Balhar", "Michal Bida", "Michal Buran", "Vaclav Cadek", "Luigino Camastra", "Tomas Dulka", "Michal Janocko", "Tomas Klohna", "Pavel Kohout", "Ondrej Kokes", "Adam Krivka", "Jakub Kubik", "Patrik Mada", "Igor Morgenstern", "Marek Pavelka", "Joshua Rogers", "Petr Stastny", "Jan Tattermusch", "Dmitrijs Trizna", "Martin Votruba", "Guido Vranken", "Jakub Zikl", "Evelina Gabasova", "Stanislav Fort"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2607.27030", "source_url": "https://arxiv.org/abs/2607.27030"}, "categories": ["Cybersecurity", "Language & Knowledge", "cs.CR"], "description": {"en": "Evaluates vulnerability discovery in source code using 95 real CVEs across 8 repositories pinned at vulnerable commits, with a detector-blinded judge crediting findings that match code path, root cause, attack condition, and impact."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.27030", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.27030", "title": "HoF-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Central European Institute of Technology"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2607.27030", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2607.27030", "source_url": "https://openalex.org/W7171874421"}, "key": "claire-radar:2607.27030", "modality": null, "name": "HoF-Bench", "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_hof-bench_be2a2445", "origin_source": "arxiv", "recognition_confidence": "0.95", "record_sha256": "f59867e4df9753b8d095f8029e009db65a5edafbe1a5bf5ecd6f210f816c7be1", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2607.27030"}, "publisher": null, "released": "2026-07-29", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.27030", "source_url": "https://arxiv.org/abs/2607.27030"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-27030", "source": "claire_radar", "source_benchmark_id": "2607.27030", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Cybersecurity"], "area": "Language & Knowledge", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/weareaisle/HoF-Bench", "githubScope": "benchmark_repo", "githubStars": 8, "hfDailySubmittedAt": null, "hfDataset": "aisleinc/HoF-Bench", "hfDatasetDownloads": 73, "hfDatasetLikes": 5, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2607.27030", "observedAt": "2026-10-04T15:31:48.030916Z", "signalStatus": {"githubStars": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}, "hfDatasetDownloads": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}, "hfDatasetLikes": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}, "hfPaperUpvotes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "state": "unavailable"}}, "status": "fresh"}, "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": "806022f73a2c918564f8b111f9fdc1026a65bd72f6c8256ba6bd81f2b84b4854", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates vulnerability discovery in source code using 95 real CVEs across 8 repositories pinned at vulnerable commits, with a detector-blinded judge crediting findings that match code path, root cause, attack condition, and impact.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence", "public artifact URL"], "snippet": "We introduce HoF-Bench (named after AISLE's public Hall of Fame), a benchmark built from 95 of these public AI-discovered CVEs across eight repositories pinned at vulnerable commits."}, "familyId": "bmf_69c4fa77605b", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [{"evidence": [{"basis": "existing-code-link", "linkedUrl": "https://github.com/weareaisle/HoF-Bench", "url": "https://github.com/weareaisle/HoF-Bench"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/weareaisle/HoF-Bench", "url": "https://huggingface.co/papers/2607.27030"}, {"basis": "linked-from-report", "linkedUrl": "https://github.com/weareaisle/HoF-Bench", "url": "https://arxiv.org/abs/2607.27030"}], "scope": "benchmark_repo", "url": "https://github.com/weareaisle/HoF-Bench", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_hof-bench_be2a2445", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Cybersecurity"], "links": {"code": "https://github.com/weareaisle/HoF-Bench", "data": "https://huggingface.co/datasets/aisleinc/HoF-Bench", "hfPaper": "https://huggingface.co/papers/2607.27030", "paper": "https://arxiv.org/abs/2607.27030", "pdf": "https://arxiv.org/pdf/2607.27030", "project": null, "report": "https://arxiv.org/abs/2607.27030"}, "metrics": [], "motivation": "LLM-based analyzers have begun finding real vulnerabilities in mature open-source projects: AISLE's analyzer is credited with more than 280 CVEs across 78 projects, including OpenSSL, curl, and GnuTLS.", "name": "HoF-Bench", "oneLine": "Evaluates vulnerability discovery in source code using 95 real CVEs across 8 repositories pinned at vulnerable commits, with a detector-blinded judge crediting findings that match code path, root cause, attack condition, and impact.", "paperTitle": "HoF-Bench: Rediscovering Real AI-Discovered CVEs Without Frontier Models", "primaryDomain": "Cybersecurity", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2607.27030", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "AISLE", "organizationType": "company-research-lab", "role": "benchmark-publisher", "sourceUrl": "https://github.com/weareaisle/HoF-Bench"}], "ranking": {"90d": {"confidence": "High", "coverage": 0.85, "datasetDownloadRank": 68, "datasetRankPopulation": 85, "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": 0.29328998349929525, "value": 8}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": 0.4432322913835386, "value": 73}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "High", "coverage": 0.85, "rank": 162, "score": 37}, "method": "attention-ranking-v13", "rank": 162, "score": 37}}, "readiness": "Runnable", "recognitionConfidence": 0.95, "relation": "introduces", "releasedAt": "2026-07-29", "source": {"authors": ["Petr Simecek", "Elnaz Babayeva", "Jiri Balhar", "Michal Bida", "Michal Buran", "Vaclav Cadek", "Luigino Camastra", "Tomas Dulka", "Michal Janocko", "Tomas Klohna", "Pavel Kohout", "Ondrej Kokes", "Adam Krivka", "Jakub Kubik", "Patrik Mada", "Igor Morgenstern", "Marek Pavelka", "Joshua Rogers", "Petr Stastny", "Jan Tattermusch", "Dmitrijs Trizna", "Martin Votruba", "Guido Vranken", "Jakub Zikl", "Evelina Gabasova", "and Stanislav Fort"], "categories": ["cs.CR", "cs.LG"], "id": "2607.27030", "title": "HoF-Bench: Rediscovering Real AI-Discovered CVEs Without Frontier Models", "type": "arxiv", "url": "https://arxiv.org/abs/2607.27030"}, "sourceUpdatedAt": "2026-07-29T15:25:07Z", "topics": ["cs.CR"], "venueAttempts": [], "whyItMatters": "Provides a realistic test bed for comparing vulnerability scanners on rediscovery of known real-world vulnerabilities, with a strict scoring protocol and reusable dataset."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
