{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.18936", "kind": "paper", "url": "https://arxiv.org/abs/2606.18936"}], "authors": ["Linghao Feng", "Yinqian Sun", "Dongqi Liang", "Sicheng Shen", "Chenfei Yan", "Yuxuan Peng", "Yilin Zhao", "Haibo Tong", "Kai Li", "FeiFei Zhao", "Yi Zeng"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.18936", "source_url": "https://arxiv.org/abs/2606.18936"}, "categories": ["General AI", "Safety", "Safety & Trustworthiness"], "description": {"en": "SciRisk-Bench evaluates AI4Science safety across 7 disciplines and 10 risk dimensions, assessing whether models recognize and avoid risks in scientific contexts."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.18936", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.18936", "title": "SciRisk-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Center for Excellence in Brain Science and Intelligence Technology", "Institute of Automation", "University of Chinese Academy of Sciences"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.18936", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.18936", "source_url": "https://openalex.org/W7165134926"}, "key": "claire-radar:2606.18936", "modality": null, "name": "SciRisk-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_scirisk-bench_01fe7487", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "4d1ba01a630ffb06e48c76c8ffceacd144b14920bf4f6ad4dea9ee2a44cd0bb5", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.18936"}, "publisher": null, "released": "2026-06-17", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.18936", "source_url": "https://arxiv.org/abs/2606.18936"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-18936", "source": "claire_radar", "source_benchmark_id": "2606.18936", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Safety & Trustworthiness", "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/2606.18936", "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": "69d4859f097c9b756f5ed7ded2d6ddc8fe2d2f3ba138678da77cb8fa4cf7da45", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "SciRisk-Bench evaluates AI4Science safety across 7 disciplines and 10 risk dimensions, assessing whether models recognize and avoid risks in scientific contexts.", "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 introduce \\textbf{SciRisk-Bench}, a benchmark designed to evaluate AI4Science safety from two complementary perspectives: explicit risk dimensions and scientific disciplines."}, "familyId": "bmf_700b9be2aca9", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_scirisk-bench_01fe7487", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.18936", "paper": "https://arxiv.org/abs/2606.18936", "pdf": "https://arxiv.org/pdf/2606.18936", "project": null, "report": "https://arxiv.org/abs/2606.18936"}, "metrics": [], "motivation": "Large language models (LLMs) are increasingly embedded in AI for Science (AI4Science) workflows, from scientific question answering and literature analysis to laboratory planning and autonomous discovery.", "name": "SciRisk-Bench", "oneLine": "SciRisk-Bench evaluates AI4Science safety across 7 disciplines and 10 risk dimensions, assessing whether models recognize and avoid risks in scientific contexts.", "paperTitle": "SciRisk-Bench: A Risk-Dimension-Aware Benchmark for AI4Science Safety", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.18936", "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/2606.18936"}], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-17", "source": {"authors": ["Linghao Feng", "Yinqian Sun", "Dongqi Liang", "Sicheng Shen", "Chenfei Yan", "Yuxuan Peng", "Yilin Zhao", "Haibo Tong", "Kai Li", "FeiFei Zhao", "Yi Zeng"], "categories": ["cs.AI", "cs.CY"], "id": "2606.18936", "title": "SciRisk-Bench: A Risk-Dimension-Aware Benchmark for AI4Science Safety", "type": "arxiv", "url": "https://arxiv.org/abs/2606.18936"}, "sourceUpdatedAt": "2026-06-24T12:13:08Z", "topics": ["Safety"], "venueAttempts": [], "whyItMatters": "Existing AI4Science safety benchmarks lack explicit risk dimensions; SciRisk-Bench provides fine-grained diagnosis of safety issues across disciplines."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
