{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2605.22175", "kind": "paper", "url": "https://arxiv.org/abs/2605.22175"}], "authors": ["Yuxuan Sun", "Yuze Zhao", "Yufeng Wang", "Yao Du", "Zhiyuan Ma", "Jinbo Wang", "Mengdi Zhang", "Kai Zhang", "Zhenya Huang"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2605.22175", "source_url": "https://arxiv.org/abs/2605.22175"}, "categories": ["Code", "Code & Software", "Software & AI Compute"], "description": {"en": "SWE-Mutation evaluates LLM-generated test suites in software engineering by using 2,636 mutated variants derived from 800 original instances across nine programming languages, measuring verification and detection rates."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2605.22175", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2605.22175", "title": "SWE-Mutation"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["University of Science and Technology of China", "Beihang University", "Peking University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2605.22175", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2605.22175", "source_url": "https://openalex.org/W7162124473"}, "key": "claire-radar:2605.22175", "modality": null, "name": "SWE-Mutation", "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_swe-mutation_d27a11bf", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "4283b51a66e367319acc4ce58f1f475ecc988792f9e58e3211a88bb10f38555e", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2605.22175"}, "publisher": null, "released": "2026-05-21", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2605.22175", "source_url": "https://arxiv.org/abs/2605.22175"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2605-22175", "source": "claire_radar", "source_benchmark_id": "2605.22175", "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": null, "hfPaperUrl": "https://huggingface.co/papers/2605.22175", "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": "High", "construction": "Transform Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-21T04:30:40.934319Z", "inputHash": "e441cc8ae619179d87f2496a3f9d36c1468825e6fe540339831478355b235ff4", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "SWE-Mutation evaluates LLM-generated test suites in software engineering by using 2,636 mutated variants derived from 800 original instances across nine programming languages, measuring verification and detection rates.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "As a first step toward constructing high-quality test suites, we introduce SWE-Mutation, a benchmark for evaluating LLM-generated test suites."}, "familyId": "bmf_a72ddf5211a2", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_swe-mutation_d27a11bf", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Software & Cloud"], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2605.22175", "paper": "https://arxiv.org/abs/2605.22175", "pdf": "https://arxiv.org/pdf/2605.22175", "project": null, "report": "https://arxiv.org/abs/2605.22175"}, "metrics": [], "motivation": "Evaluating software engineering capabilities has become a core component of modern large language models (LLMs); however, the key bottleneck hindering further scaling lies not in the scarcity of high-quality solutions, but in the lack of high-quality test suites.", "name": "SWE-Mutation", "oneLine": "SWE-Mutation evaluates LLM-generated test suites in software engineering by using 2,636 mutated variants derived from 800 original instances across nine programming languages, measuring verification and detection rates.", "paperTitle": "SWE-Mutation: Can LLMs Generate Reliable Test Suites in Software Engineering?", "primaryDomain": "Software & AI Compute", "publication": {"evidence": "ACL 2026 Findings", "evidenceLevel": "strong-author-metadata", "evidenceUrl": "https://arxiv.org/abs/2605.22175", "source": "arxiv-journal-reference", "status": "publication_reported", "venue": "ACL 2026 Findings", "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [{"evidence": [{"level": "strong-author-metadata", "observedAt": "2026-10-14T01:46:58.058199Z", "rawValue": "ACL 2026 Findings", "sourceType": "arxiv-journal-reference", "sourceUrl": "https://arxiv.org/abs/2605.22175"}], "publicationStatus": "published", "venueName": "ACL 2026 Findings"}], "publishers": [{"name": "SWE-Mutation Team", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://arxiv.org/abs/2605.22175"}], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-05-21", "source": {"authors": ["Yuxuan Sun", "Yuze Zhao", "Yufeng Wang", "Yao Du", "Zhiyuan Ma", "Jinbo Wang", "Mengdi Zhang", "Kai Zhang", "Zhenya Huang"], "categories": ["cs.SE", "cs.AI"], "id": "2605.22175", "title": "SWE-Mutation: Can LLMs Generate Reliable Test Suites in Software Engineering?", "type": "arxiv", "url": "https://arxiv.org/abs/2605.22175"}, "sourceUpdatedAt": "2026-05-21T08:45:50Z", "topics": ["Code"], "venueAttempts": [], "whyItMatters": "High-quality test suites are critical for program repair and reinforcement learning signals. SWE-Mutation reveals inadequacies in LLM-generated tests, guiding improvements in code generation and validation."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
