{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.05574", "kind": "paper", "url": "https://arxiv.org/abs/2606.05574"}], "authors": ["Fake Lin", "Binbin Hu", "Xi Zhu", "Ziwei Zhao", "Zhi Zheng", "Ziqi Liu", "Zhiqiang Zhang", "Jun Zhou", "Tong Xu"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.05574", "source_url": "https://arxiv.org/abs/2606.05574"}, "categories": ["Code & Software", "Software & AI Compute", "cs.SE"], "description": {"en": "SmellBench is a code refactoring benchmark that proactively injects code smells into clean code snippets. It contains 294 cases across 7 smell types, 3 difficulty levels, and 2 instruction settings, with evaluation covering functional correctness, localization, and refactoring quality."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.05574", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.05574", "title": "SmellBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["University of Science and Technology of China", "Ant Group (China)", "Rutgers, The State University of New Jersey"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.05574", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.05574", "source_url": "https://openalex.org/W7163680634"}, "key": "claire-radar:2606.05574", "modality": null, "name": "SmellBench", "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_smellbench_001e20cd", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "4863e0d24387faa236e82d9321212e3ae0a88282fd7c309d9d0a56e69fbaa5e6", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.05574"}, "publisher": null, "released": "2026-06-04", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.05574", "source_url": "https://arxiv.org/abs/2606.05574"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-05574", "source": "claire_radar", "source_benchmark_id": "2606.05574", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Software & AI Compute"], "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": 0, "hfPaperUrl": "https://huggingface.co/papers/2606.05574", "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", "lastSuccessfulDate": "2026-09-25", "state": "stale"}}, "status": "stale"}, "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": "94c03122ac4db821a90f20da7ea46bef2eb8fc4b0d1eee8d23af746250dd6e73", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "SmellBench is a code refactoring benchmark that proactively injects code smells into clean code snippets. It contains 294 cases across 7 smell types, 3 difficulty levels, and 2 instruction settings, with evaluation covering functional correctness, localization, and refactoring quality.", "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": "In this paper, we propose SmellBench, an extensible code refactoring benchmark that proactively injects code smells into clean code snippets from real-world repositories."}, "familyId": "bmf_d68b77fdba3e", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_smellbench_001e20cd", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Software & Cloud"], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.05574", "paper": "https://arxiv.org/abs/2606.05574", "pdf": "https://arxiv.org/pdf/2606.05574", "project": null, "report": "https://arxiv.org/abs/2606.05574"}, "metrics": [], "motivation": "Code Agents have achieved remarkable advances in recent years, exhibiting strong capabilities across a wide range of software engineering tasks.", "name": "SmellBench", "oneLine": "SmellBench is a code refactoring benchmark that proactively injects code smells into clean code snippets. It contains 294 cases across 7 smell types, 3 difficulty levels, and 2 instruction settings, with evaluation covering functional correctness, localization, and refactoring quality.", "paperTitle": "SmellBench: Towards Fine-Grained Evaluation of Code Agents on Refactoring Tasks", "primaryDomain": "Software & AI Compute", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.05574", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-04", "source": {"authors": ["Fake Lin", "Binbin Hu", "Xi Zhu", "Ziwei Zhao", "Zhi Zheng", "Ziqi Liu", "Zhiqiang Zhang", "Jun Zhou", "Tong Xu"], "categories": ["cs.SE"], "id": "2606.05574", "title": "SmellBench: Towards Fine-Grained Evaluation of Code Agents on Refactoring Tasks", "type": "arxiv", "url": "https://arxiv.org/abs/2606.05574"}, "sourceUpdatedAt": "2026-06-04T01:49:07Z", "topics": ["cs.SE"], "venueAttempts": [], "whyItMatters": "Existing benchmarks focus on functional correctness, not long-term maintainability. SmellBench could evaluate code agents' ability to produce maintainable code."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
