{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.16262", "kind": "paper", "url": "https://arxiv.org/abs/2606.16262"}], "authors": ["Wenjie Wang", "Yue Huang", "Zipeng Ling", "Han Bao", "Hang hua", "Xiaonan Luo", "Yu Jiang", "Shiyi Du", "Yuexing Hao", "Xiaomin Li", "Yuchen Ma", "Dianzhuo Wang", "Yanfang Ye", "Xiangliang Zhang"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.16262", "source_url": "https://arxiv.org/abs/2606.16262"}, "categories": ["Code & Software", "General AI", "cs.SE"], "description": {"en": "UXBench evaluates LLM-generated UX critiques through local web fixtures, coverage-gated exploration, and a downstream repair agent, measuring report actionability across seven rubric dimensions."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.16262", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.16262", "title": "UXBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["University of Notre Dame", "University of Pennsylvania", "University of Rochester", "Carnegie Mellon University", "Massachusetts Institute of Technology", "Harvard University", "Ludwig-Maximilians-Universität München"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.16262", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.16262", "source_url": "https://openalex.org/W7164908373"}, "key": "claire-radar:2606.16262", "modality": null, "name": "UXBench", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "Medium", "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_uxbench_0fa77b90", "origin_source": "arxiv", "recognition_confidence": "0.85", "record_sha256": "711c0331708ccda5eda9e5aac0d4e904ff90ea8ced10947cbf3c8e064e8e9b71", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.16262"}, "publisher": null, "released": "2026-06-15", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.16262", "source_url": "https://arxiv.org/abs/2606.16262"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-16262", "source": "claire_radar", "source_benchmark_id": "2606.16262", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Code & Software", "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/2606.16262", "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": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "c63b53bd30985886c51073e1def18aa13779f17349489f89d391f905ad7fb9c7", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "UXBench evaluates LLM-generated UX critiques through local web fixtures, coverage-gated exploration, and a downstream repair agent, measuring report actionability across seven rubric dimensions.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence"], "snippet": "We introduce UXBench, a benchmark for evaluating LLMs as interaction-grounded UX judges."}, "familyId": "bmf_8d180072bdf4", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_uxbench_0fa77b90", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.16262", "paper": "https://arxiv.org/abs/2606.16262", "pdf": "https://arxiv.org/pdf/2606.16262", "project": null, "report": "https://arxiv.org/abs/2606.16262"}, "metrics": [], "motivation": "Large language models (LLMs) are increasingly deployed as UX judges that inspect interfaces, diagnose usability problems, and propose repairs.", "name": "UXBench", "oneLine": "UXBench evaluates LLM-generated UX critiques through local web fixtures, coverage-gated exploration, and a downstream repair agent, measuring report actionability across seven rubric dimensions.", "paperTitle": "UXBench: Measuring the Actionability of LLM-Generated UX Critiques", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.16262", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 0.85, "relation": "introduces", "releasedAt": "2026-06-15", "source": {"authors": ["Wenjie Wang", "Yue Huang", "Zipeng Ling", "Han Bao", "Hang hua", "Xiaonan Luo", "Yu Jiang", "Shiyi Du", "Yuexing Hao", "Xiaomin Li", "Yuchen Ma", "Dianzhuo Wang", "Yanfang Ye and Xiangliang Zhang"], "categories": ["cs.SE", "cs.AI"], "id": "2606.16262", "title": "UXBench: Measuring the Actionability of LLM-Generated UX Critiques", "type": "arxiv", "url": "https://arxiv.org/abs/2606.16262"}, "sourceUpdatedAt": "2026-06-15T06:08:39Z", "topics": ["cs.SE"], "venueAttempts": [], "whyItMatters": "There is a need for a controlled evaluation of UX critique reliability and actionability across product surfaces, but UXBench currently lacks a public release path or ongoing scoring service, limiting its standalone comparison value."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
