{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2605.29933", "kind": "paper", "url": "https://arxiv.org/abs/2605.29933"}], "authors": ["Feng Xiao", "Dazhi Fu", "Chris Ding", "Jicong Fan"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2605.29933", "source_url": "https://arxiv.org/abs/2605.29933"}, "categories": ["General AI", "Vision & 3D", "cs.LG"], "description": {"en": "CLUBench evaluates clustering algorithms across 131 datasets (tabular, text, image) using 24 algorithms, measuring clustering performance via standard metrics like NMI, ARI, etc."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2605.29933", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2605.29933", "title": "CLUBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Chinese University of Hong Kong, Shenzhen"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2605.29933", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2605.29933", "source_url": "https://openalex.org/W7162768770"}, "key": "claire-radar:2605.29933", "modality": null, "name": "CLUBench", "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_clubench_c6a13ff8", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "2c455eb224cc4aaf6b70d6283ff7d37cb9b8e94b0ea4d802ed3a84e030e8f648", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2605.29933"}, "publisher": null, "released": "2026-05-28", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2605.29933", "source_url": "https://arxiv.org/abs/2605.29933"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2605-29933", "source": "claire_radar", "source_benchmark_id": "2605.29933", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Vision & 3D", "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/2605.29933", "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": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "158ee8839053bf817bcdc58d04d9f4faab1c3ba40bea0ab4db54de0ed202b987", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "CLUBench evaluates clustering algorithms across 131 datasets (tabular, text, image) using 24 algorithms, measuring clustering performance via standard metrics like NMI, ARI, etc.", "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": "To address this gap, we introduce CLUBench, a comprehensive clustering benchmark comprising 24 algorithms of diverse principles evaluated on 131 datasets across tabular, text, and image data, involving 178,815 experiments."}, "familyId": "bmf_22a6f1914a19", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_clubench_c6a13ff8", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2605.29933", "paper": "https://arxiv.org/abs/2605.29933", "pdf": "https://arxiv.org/pdf/2605.29933", "project": null, "report": "https://arxiv.org/abs/2605.29933"}, "metrics": [], "motivation": "Clustering is a fundamental problem in data science with a long-standing research history, yielding numerous insightful algorithms.", "name": "CLUBench", "oneLine": "CLUBench evaluates clustering algorithms across 131 datasets (tabular, text, image) using 24 algorithms, measuring clustering performance via standard metrics like NMI, ARI, etc.", "paperTitle": "CLUBench: A Clustering Benchmark", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2605.29933", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "arXiv", "organizationType": "community", "role": "benchmark-publisher", "sourceUrl": "https://arxiv.org/abs/2605.29933"}], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-05-28", "source": {"authors": ["Feng Xiao", "Dazhi Fu", "Chris Ding", "Jicong Fan"], "categories": ["cs.LG"], "id": "2605.29933", "title": "CLUBench: A Clustering Benchmark", "type": "arxiv", "url": "https://arxiv.org/abs/2605.29933"}, "sourceUpdatedAt": "2026-05-28T13:45:37Z", "topics": ["cs.LG"], "venueAttempts": [], "whyItMatters": "There is no comprehensive comparison of classical, deep, and foundation-model clustering methods. CLUBench provides systematic insights into algorithm selection and performance across data types."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
