{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.07591", "kind": "paper", "url": "https://arxiv.org/abs/2606.07591"}, {"id": "gh:internscience/researchclawbench", "kind": "repo", "url": "https://github.com/InternScience/ResearchClawBench"}], "authors": ["Wanghan Xu", "Shuo Li", "Tianlin Ye", "Qinglong Cao", "Yixin Chen", "Hengjian Gao", "Yiheng Wang", "Qi Li", "Kun Li", "Sheng Xu", "Shengdu Chai", "Fangchen Yu", "Xiangyu Zhao", "Zhangrui Zhao", "Weijie Ma", "Zijie Guo", "Koutian Wu", "Haoyu Zhou", "Haoxiang Yin", "Lixue Cheng", "Chaofan Hu", "Haoxuan Li", "Lu Mi", "Xuxuan Xie", "Yifan Zhou", "Ruizhe Chen", "Zhiwang Zhou", "Xingjian Guo", "Yuhao Zhou", "Xuming He", "Shengyuan Xu", "Xinyu Gu", "Jiamin Wu", "Mianxin Liu", "Chunfeng Song", "Fenghua Ling", "Dongzhan Zhou", "Shixiang Tang", "Yuqiang Li", "Mao Su", "Peng Ye", "Siqi Sun", "Bin Wang", "Xue Yang", "Zhenfei Yin", "Tianfan Fu", "Guangtao Zhai", "Wanli Ouyang", "Bo Zhang", "Lei Bai", "Wenlong Zhang"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.07591", "source_url": "https://arxiv.org/abs/2606.07591"}, "categories": ["General AI", "Language & Knowledge", "cs.LG"], "description": {"en": "ResearchClawBench evaluates autonomous scientific research agents across 40 tasks from 10 domains, each grounded in a published paper with provided literature and raw data. It uses expert-curated multimodal rubrics to score target-paper-level re-discovery."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.07591", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.07591", "title": "ResearchClawBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2606.07591", "modality": null, "name": "ResearchClawBench", "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_researchclawbench_4d57a097", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "ff7c2920b8359a712294f5b73d8fbe7b868442bfb66a5d3135edf59a36e20bb7", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.07591"}, "publisher": null, "released": "2026-05-28", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.07591", "source_url": "https://arxiv.org/abs/2606.07591"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-07591", "source": "claire_radar", "source_benchmark_id": "2606.07591", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Language & Knowledge", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/InternScience/ResearchClawBench", "githubScope": "benchmark_repo", "githubStars": 267, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 106, "hfPaperUrl": "https://huggingface.co/papers/2606.07591", "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", "lastSuccessfulDate": "2026-09-30", "state": "stale"}}, "status": "fresh"}, "capabilities": [], "confidence": "High", "construction": "Transform Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "76aa8b49483bc5675f84dd79a9cdb2fb4dea680995d1ef2abf931cd7dd935e20", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "ResearchClawBench evaluates autonomous scientific research agents across 40 tasks from 10 domains, each grounded in a published paper with provided literature and raw data. It uses expert-curated multimodal rubrics to score target-paper-level re-discovery.", "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 ResearchClawBench, a benchmark for evaluating autonomous scientific research across 40 tasks from 10 scientific domains."}, "familyId": "bmf_4fbc99503d1c", "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/InternScience/ResearchClawBench", "url": "https://github.com/InternScience/ResearchClawBench"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/InternScience/ResearchClawBench", "url": "https://huggingface.co/papers/2606.07591"}], "scope": "benchmark_repo", "url": "https://github.com/InternScience/ResearchClawBench", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_researchclawbench_4d57a097", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/InternScience/ResearchClawBench", "data": null, "hfPaper": "https://huggingface.co/papers/2606.07591", "paper": "https://arxiv.org/abs/2606.07591", "pdf": "https://arxiv.org/pdf/2606.07591", "project": null, "report": "https://arxiv.org/abs/2606.07591"}, "metrics": [], "motivation": "AI coding agents are increasingly used for scientific work, but their end-to-end autonomous research capability remains difficult to verify.", "name": "ResearchClawBench", "oneLine": "ResearchClawBench evaluates autonomous scientific research agents across 40 tasks from 10 domains, each grounded in a published paper with provided literature and raw data. It uses expert-curated multimodal rubrics to score target-paper-level re-discovery.", "paperTitle": "ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.07591", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "InternScience", "organizationType": "community", "role": "benchmark-publisher", "sourceUrl": "https://github.com/InternScience/ResearchClawBench"}], "ranking": {}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-05-28", "source": {"authors": ["Wanghan Xu", "Shuo Li", "Tianlin Ye", "Qinglong Cao", "Yixin Chen", "Hengjian Gao", "Yiheng Wang", "Qi Li", "Kun Li", "Sheng Xu", "Shengdu Chai", "Fangchen Yu", "Xiangyu Zhao", "Zhangrui Zhao", "Weijie Ma", "Zijie Guo", "Koutian Wu", "Haoyu Zhou", "Haoxiang Yin", "Lixue Cheng", "Chaofan Hu", "Haoxuan Li", "Lu Mi", "Xuxuan Xie", "Yifan Zhou", "Ruizhe Chen", "Zhiwang Zhou", "Xingjian Guo", "Yuhao Zhou", "Xuming He", "Shengyuan Xu", "Xinyu Gu", "Jiamin Wu", "Mianxin Liu", "Chunfeng Song", "Fenghua Ling", "Dongzhan Zhou", "Shixiang Tang", "Yuqiang Li", "Mao Su", "Peng Ye", "Siqi Sun", "Bin Wang", "Xue Yang", "Zhenfei Yin", "Tianfan Fu", "Guangtao Zhai", "Wanli Ouyang", "Bo Zhang", "Lei Bai", "Wenlong Zhang"], "categories": ["cs.LG", "cs.AI", "cs.CL"], "id": "2606.07591", "title": "ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research", "type": "arxiv", "url": "https://arxiv.org/abs/2606.07591"}, "sourceUpdatedAt": "2026-07-03T01:40:25Z", "topics": ["cs.LG"], "venueAttempts": [], "whyItMatters": "Autonomous research agents claim to accelerate science, but their end-to-end capability is unverified. ResearchClawBench provides a standardized evaluation frontier to measure progress toward reliable research re-discovery."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
