{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.25158", "kind": "paper", "url": "https://arxiv.org/abs/2608.25158"}, {"id": "gh:fuzzingbrain/fuzzingbrain-bench", "kind": "repo", "url": "https://github.com/fuzzingbrain/FuzzingBrain-Bench"}], "authors": ["Ze Sheng", "Aleksandar Kezic", "Zhicheng Chen", "Jeff Huang"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.25158", "source_url": "https://arxiv.org/abs/2608.25158"}, "categories": ["Cybersecurity", "Language & Knowledge", "cs.AI"], "description": {"en": "Evaluates LLMs on discovering distinct crashes in 77 open-source software challenges using sanitizer-instrumented Docker harnesses and deterministic scoring."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.25158", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.25158", "title": "FuzzingBrain-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Texas A&M University", "University of Novi Sad"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2608.25158", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2608.25158", "source_url": "https://openalex.org/W7204476344"}, "key": "claire-radar:2608.25158", "modality": null, "name": "FuzzingBrain-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": "true", "origin_record_id": "bm_fuzzingbrain-bench_87c92c01", "origin_source": "arxiv", "recognition_confidence": "0.95", "record_sha256": "c05efc35411dc2e6b5c158610daeed7a4ea11144801feec7c20426a27513663e", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-08-27T04:14:52.836173Z", "source_url": "https://arxiv.org/abs/2608.25158"}, "publisher": null, "released": "2026-08-25", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.25158", "source_url": "https://arxiv.org/abs/2608.25158"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-25158", "source": "claire_radar", "source_benchmark_id": "2608.25158", "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/fuzzingbrain/FuzzingBrain-Bench", "githubScope": "benchmark_repo", "githubStars": 8, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2608.25158", "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 security and LLM agent evaluation are active areas, and the practical open-ended bug discovery benchmark with public code is likely to attract attention from both communities.", "score": 68}, "capabilities": [], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-27T04:14:52.836173Z", "inputHash": "eea675d0fa8bd1335e3f6f0b46e7129fc934826ef91f1a0eae7e29b1fc5b77f0", "model": "deepseek-v4-pro"}, "curation": {"canonicalNameEvidence": "FuzzingBrain-Bench V1: Evaluating Open-Ended Bug Discovery by LLMs", "canonicalNameSource": "paper_title", "decisionReason": "Corpus and harnesses are publicly available on GitHub with deterministic scoring and a leaderboard-style comparison path, qualifying as a formal benchmark.", "model": "deepseek-v4-pro", "reviewedAt": "2026-08-27T04:14:52.836173Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates LLMs on discovering distinct crashes in 77 open-source software challenges using sanitizer-instrumented Docker harnesses and deterministic scoring.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "score_submission", "evidence": {"reasonCodes": ["exact named benchmark artifact released in abstract", "benchmark release stated in one sentence", "public artifact URL"], "snippet": "We present FuzzingBrain-Bench, a benchmark for assessing AI models' ability to discover bugs in open-source software."}, "familyId": "bmf_9a7e7c8791a6", "firstSeenAt": "2026-08-27", "heat": null, "id": "bm_fuzzingbrain-bench_87c92c01", "indexedAt": "2026-08-27T04:12:10.575570Z", "industrySectors": ["Cybersecurity"], "links": {"code": "https://github.com/fuzzingbrain/FuzzingBrain-Bench", "data": null, "paper": "https://arxiv.org/abs/2608.25158", "pdf": "https://arxiv.org/pdf/2608.25158", "project": null, "report": "https://arxiv.org/abs/2608.25158"}, "metrics": [], "motivation": "Evaluating the ability of large language models (LLMs) to discover software bugs is increasingly important.", "name": "FuzzingBrain-Bench", "oneLine": "Evaluates LLMs on discovering distinct crashes in 77 open-source software challenges using sanitizer-instrumented Docker harnesses and deterministic scoring.", "paperTitle": "FuzzingBrain-Bench V1: Evaluating Open-Ended Bug Discovery by LLMs", "primaryDomain": "Cybersecurity", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.25158", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-08-27T04:12:10.575570Z"}, "publications": [], "ranking": {"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": 0.29328998349929525, "value": 8}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.55, "rank": 149, "score": 39}, "method": "attention-ranking-v13", "rank": 149, "score": 39}}, "readiness": "Runnable", "recognitionConfidence": 0.95, "relation": "introduces", "releasedAt": "2026-08-25", "source": {"authors": ["Ze Sheng", "Aleksandar Kezic", "Zhicheng Chen", "Jeff Huang"], "categories": ["cs.AI", "cs.CR", "cs.LG", "cs.SE"], "id": "2608.25158", "title": "FuzzingBrain-Bench V1: Evaluating Open-Ended Bug Discovery by LLMs", "type": "arxiv", "url": "https://arxiv.org/abs/2608.25158"}, "sourceUpdatedAt": "2026-08-25T21:09:20Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "Shifts vulnerability evaluation from predefined targets to open-ended crash discovery, providing a realistic and reproducible measure of LLM bug-finding capability."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
