{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2609.07603", "kind": "paper", "url": "https://arxiv.org/abs/2609.07603"}, {"id": "gh:fengxianji/fincuabuild", "kind": "repo", "url": "https://github.com/FengxianJi/FinCUABuild"}], "authors": ["Jingpu Yang", "Fengxian Ji", "Jinri Guo", "Tianhao Li", "Qian Jiang", "Fan Zhang", "Min Peng", "Qianqian Xie", "Preslav Nakov", "Zhuohan Xie"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2609.07603", "source_url": "https://arxiv.org/abs/2609.07603"}, "categories": ["Agents & Tool Use", "Finance", "cs.AI"], "description": {"en": "Evaluates construction of dynamic financial computer-using agent (CUA) tasks across 576 requests spanning 24 workflows and runtime variations, with qualification based on execution tests and quality checks."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2609.07603", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2609.07603", "title": "FinCUABuildBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Northeastern University", "Wuhan University", "Mohamed bin Zayed University of Artificial Intelligence"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2609.07603", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2609.07603", "source_url": "https://openalex.org/W7211998128"}, "key": "claire-radar:2609.07603", "modality": null, "name": "FinCUABuildBench", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"admission_policy_version": "2026-09-09.1", "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_fincuabuildbench_238a4701", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "976bbe20acf5be8930b4da0508eab17bef5041e744b135ab282c1b8deaee8a3b", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-09-09T06:27:57.312318Z", "source_url": "https://arxiv.org/abs/2609.07603"}, "publisher": null, "released": "2026-09-07", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2609.07603", "source_url": "https://arxiv.org/abs/2609.07603"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2609-07603", "source": "claire_radar", "source_benchmark_id": "2609.07603", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Finance"], "area": "Agents & Tool Use", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/FengxianJi/FinCUABuild", "githubScope": "benchmark_repo", "githubStars": 2, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 1, "hfPaperUrl": "https://huggingface.co/papers/2609.07603", "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": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}}, "status": "fresh"}, "attentionForecast": {"confidence": "Low", "horizon": "7d", "reason": "The niche focus on financial CUA benchmark construction and early release date likely limit immediate broad attention, though short-term interest from specialized communities may occur.", "score": 35}, "capabilities": [], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-09T06:27:57.312318Z", "inputHash": "03b74264db8ee4c2c1a87ffc87e1255f7faee04b077b74b93d4b1f8782a8de9d", "model": "deepseek-v4-pro"}, "curation": {"admissionPolicyVersion": "2026-09-09.1", "canonicalNameEvidence": "we introduce FinCUABuildBench, a benchmark for evaluating financial CUA task construction", "canonicalNameSource": "abstract", "decisionReason": "The benchmark has explicit task specifications, a scoring mechanism, and publicly available code, supporting standalone reuse.", "evaluationEvidence": {"reuse": "Code: https://github.com/FengxianJi/FinCUABuild", "scoring": "a task qualification mechanism based on execution tests and quality checks", "task": "576 construction requests covering 24 financial workflows and three types of runtime variation"}, "model": "deepseek-v4-pro", "reviewedAt": "2026-09-09T06:27:57.312318Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates construction of dynamic financial computer-using agent (CUA) tasks across 576 requests spanning 24 workflows and runtime variations, with qualification based on execution tests and quality checks.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["exact named benchmark artifact released in abstract", "benchmark release stated in one sentence", "evaluation protocol evidence", "public artifact URL"], "snippet": "To solve these, we introduce FinCUABuildBench, a benchmark for evaluating financial CUA task construction, featuring: (i) 576 construction requests covering 24 financial workflows and three types of runtime variation; (ii) standardized input, budget, and output specifications; and (iii) a task qualification mechanism based on execution tests and quality checks."}, "familyId": "bmf_5608550734ae", "firstSeenAt": "2026-09-09", "heat": null, "id": "bm_fincuabuildbench_238a4701", "indexedAt": "2026-09-09T06:18:29.794093Z", "industrySectors": ["Financial Services"], "links": {"code": "https://github.com/FengxianJi/FinCUABuild", "data": null, "paper": "https://arxiv.org/abs/2609.07603", "pdf": "https://arxiv.org/pdf/2609.07603", "project": null, "report": "https://arxiv.org/abs/2609.07603"}, "metrics": [], "motivation": "Financial scenarios are diverse and complex, spanning varying data conditions, tool configurations, and workflows.", "name": "FinCUABuildBench", "oneLine": "Evaluates construction of dynamic financial computer-using agent (CUA) tasks across 576 requests spanning 24 workflows and runtime variations, with qualification based on execution tests and quality checks.", "paperTitle": "FinCUABuild: Can Agents Build Reliable Benchmarks for Dynamic Financial Computer Use?", "primaryDomain": "Finance", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2609.07603", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-09-09T06:18:29.794093Z"}, "publications": [], "ranking": {"30d": {"confidence": "High", "coverage": 0.85, "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": 30, "historyDate": "2026-09-05", "rank": null, "score": null, "windowDays": 30}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": 0.16198483906027114, "value": 2}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": 0.12906235291407148, "value": 1}}, "confidence": "High", "coverage": 0.85, "rank": 214, "score": 20}, "method": "attention-ranking-v13", "rank": 214, "score": 20}, "90d": {"confidence": "Medium", "coverage": 0.7, "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": 0.1466449917496476, "value": 2}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": 0.12247537038455211, "value": 1}}, "confidence": "Medium", "coverage": 0.7, "rank": 370, "score": 25}, "method": "attention-ranking-v13", "rank": 370, "score": 25}}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-09-07", "source": {"authors": ["Jingpu Yang", "Fengxian Ji", "Jinri Guo", "Tianhao Li", "Qian Jiang", "Fan Zhang", "Min Peng", "Qianqian Xie", "Preslav Nakov", "Zhuohan Xie"], "categories": ["cs.AI"], "id": "2609.07603", "title": "FinCUABuild: Can Agents Build Reliable Benchmarks for Dynamic Financial Computer Use?", "type": "arxiv", "url": "https://arxiv.org/abs/2609.07603"}, "sourceUpdatedAt": "2026-09-07T15:13:23Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "Addresses the scarcity of scalable financial CUA evaluation tasks by enabling automated benchmark construction, providing a standardized protocol to compare generation methods."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
