{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.23654", "kind": "paper", "url": "https://arxiv.org/abs/2606.23654"}, {"id": "gh:frontisai/enterpriseclawbench", "kind": "repo", "url": "https://github.com/FrontisAI/EnterpriseClawBench"}], "authors": ["Jincheng Zhong", "Weizhi Wang", "Che Jiang", "Kai Tian", "Zhenzhao Yuan", "Junlin Yang", "Dianqiao Lei", "Kaiyan Zhang"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.23654", "source_url": "https://arxiv.org/abs/2606.23654"}, "categories": ["Agents", "General AI", "Language & Knowledge"], "description": {"en": "Evaluates coding agents on realistic enterprise workflows using 852 reproducible tasks with recovered fixtures, prompts, role classes, skill subclasses, hard rules, and semantic rubrics. Scoring covers artifact delivery, visual quality, cost, runtime, and skill transfer."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.23654", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.23654", "title": "EnterpriseClawBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2606.23654", "modality": null, "name": "EnterpriseClawBench", "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_enterpriseclawbench_252ea1ca", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "8541e62e45176904b08758c90aba86a18d7faff6975fa1dc97c2b6ab500f8258", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.23654"}, "publisher": null, "released": "2026-06-22", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.23654", "source_url": "https://arxiv.org/abs/2606.23654"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-23654", "source": "claire_radar", "source_benchmark_id": "2606.23654", "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/FrontisAI/EnterpriseClawBench", "githubScope": "benchmark_repo", "githubStars": 49, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 81, "hfPaperUrl": "https://huggingface.co/papers/2606.23654", "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": "2026-10-04", "state": "stale"}}, "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": "2da25124a1691b0d43a4edc485fe703246c2b9b27ab36a755cf69301364cde2b", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates coding agents on realistic enterprise workflows using 852 reproducible tasks with recovered fixtures, prompts, role classes, skill subclasses, hard rules, and semantic rubrics. Scoring covers artifact delivery, visual quality, cost, runtime, and skill transfer.", "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", "public artifact URL"], "snippet": "We introduce EnterpriseClawBench, an enterprise agent benchmark constructed from proprietary, real-world agent sessions."}, "familyId": "bmf_7de792287b02", "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/FrontisAI/EnterpriseClawBench", "url": "https://github.com/FrontisAI/EnterpriseClawBench"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/FrontisAI/EnterpriseClawBench", "url": "https://huggingface.co/papers/2606.23654"}, {"basis": "huggingface-paper-association", "linkedUrl": "https://github.com/FrontisAI/EnterpriseClawBench", "url": "https://huggingface.co/api/papers/2606.23654"}, {"basis": "linked-from-report", "linkedUrl": "https://github.com/FrontisAI/EnterpriseClawBench", "url": "https://arxiv.org/abs/2606.23654"}], "scope": "benchmark_repo", "url": "https://github.com/FrontisAI/EnterpriseClawBench", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_enterpriseclawbench_252ea1ca", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/FrontisAI/EnterpriseClawBench", "data": null, "hfPaper": "https://huggingface.co/papers/2606.23654", "paper": "https://arxiv.org/abs/2606.23654", "pdf": "https://arxiv.org/pdf/2606.23654", "project": null, "report": "https://arxiv.org/abs/2606.23654"}, "metrics": [], "motivation": "Enterprise agents increasingly operate inside workspaces: they read heterogeneous files, invoke tools, and deliver business artifacts.", "name": "EnterpriseClawBench", "oneLine": "Evaluates coding agents on realistic enterprise workflows using 852 reproducible tasks with recovered fixtures, prompts, role classes, skill subclasses, hard rules, and semantic rubrics. Scoring covers artifact delivery, visual quality, cost, runtime, and skill transfer.", "paperTitle": "EnterpriseClawBench: Benchmarking Agents from Real Workplace Sessions", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.23654", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "FrontisAI", "organizationType": "company-research-lab", "role": "benchmark-publisher", "sourceUrl": "https://github.com/FrontisAI/EnterpriseClawBench"}], "ranking": {}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-22", "source": {"authors": ["Jincheng Zhong", "Weizhi Wang", "Che Jiang", "Kai Tian", "Zhenzhao Yuan", "Junlin Yang", "Dianqiao Lei", "Kaiyan Zhang"], "categories": ["cs.CL", "cs.SE"], "id": "2606.23654", "title": "EnterpriseClawBench: Benchmarking Agents from Real Workplace Sessions", "type": "arxiv", "url": "https://arxiv.org/abs/2606.23654"}, "sourceUpdatedAt": "2026-06-22T17:39:43Z", "topics": ["Agents"], "venueAttempts": [], "whyItMatters": "Enterprise agent evaluation often collapses performance into a single score, ignoring cost, runtime, and artifact quality. This benchmark provides a multi-faceted scoring contract and a reusable construction/evaluation protocol, enabling practical comparisons of harness-model systems in real workplace settings."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
