{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2609.07441", "kind": "paper", "url": "https://arxiv.org/abs/2609.07441"}, {"kind": "website", "url": "https://tabbench-bio.eu"}], "authors": ["Jules Kreuer", "Sofiane Ouaari", "Julia Hellmig", "Julius Braitinger", "Nico Pfeifer"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2609.07441", "source_url": "https://arxiv.org/abs/2609.07441"}, "categories": ["Biology & Drug Discovery", "General AI", "Language & Knowledge", "cs.LG"], "description": {"en": "A living benchmark of 43 high-dimensional biomedical tables with a standardized cross-validation protocol and Elo-based ranking of ML models."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2609.07441", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2609.07441", "title": "TabBench-Bio"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["University of Tübingen"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2609.07441", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2609.07441", "source_url": "https://openalex.org/W7212038832"}, "key": "claire-radar:2609.07441", "modality": null, "name": "TabBench-Bio", "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_tabbench-bio_8ce5fdeb", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "a690ec08e0b5a28adafbcceb00866d76c0d8fe047dc39c5d2c9aca1cd901aa34", "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/2609.07441"}, "publisher": null, "released": "2026-09-07", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2609.07441", "source_url": "https://arxiv.org/abs/2609.07441"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2609-07441", "source": "claire_radar", "source_benchmark_id": "2609.07441", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI", "Biology & Drug Discovery"], "area": "Language & Knowledge", "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/2609.07441", "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"}, "attentionForecast": {"confidence": "Low", "horizon": "7d", "reason": "Biomedical tabular benchmarks attract a specialized audience, and the leaderboard provides a clear entry point.", "score": 40}, "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": "b0d17439dfbed692336f548d6b75cfc9bcbc1dd7cd3a75c2d8518e72e042a031", "model": "deepseek-v4-pro"}, "curation": {"admissionPolicyVersion": "2026-09-09.1", "canonicalNameEvidence": "TabBench-Bio: A Living Benchmark for Machine Learning on High-Dimensional Biomedical Tables", "canonicalNameSource": "paper_title", "decisionReason": "The benchmark offers a public leaderboard interface and a defined evaluation protocol, enabling external participation.", "evaluationEvidence": {"reuse": "The interactive leaderboard is available at: https://tabbench-bio.eu", "scoring": "Elo scores computed via paired bootstrap over the target pool.", "task": "43 biomedical datasets spanning multiple domains, compared under a shared cross-validation protocol across 28 feature-by-sample operating points."}, "model": "deepseek-v4-pro", "reviewedAt": "2026-09-09T06:27:57.312318Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "A living benchmark of 43 high-dimensional biomedical tables with a standardized cross-validation protocol and Elo-based ranking of ML models.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence", "evaluation protocol evidence", "public artifact URL"], "snippet": "We introduce TabBench-Bio, a living and interactive benchmark of 43 biomedical datasets spanning multiple domains."}, "familyId": "bmf_dfcd50ff062c", "firstSeenAt": "2026-09-09", "heat": null, "id": "bm_tabbench-bio_8ce5fdeb", "indexedAt": "2026-09-09T06:18:29.794093Z", "industrySectors": ["Pharma & Biotech"], "links": {"code": null, "data": null, "paper": "https://arxiv.org/abs/2609.07441", "pdf": "https://arxiv.org/pdf/2609.07441", "project": "https://tabbench-bio.eu", "report": "https://arxiv.org/abs/2609.07441"}, "metrics": [], "motivation": "Biomedical tables often combine thousands of measured variables with only tens or hundreds of labelled samples, a regime that is poorly represented in general-purpose tabular benchmarks.", "name": "TabBench-Bio", "oneLine": "A living benchmark of 43 high-dimensional biomedical tables with a standardized cross-validation protocol and Elo-based ranking of ML models.", "paperTitle": "TabBench-Bio: A Living Benchmark for Machine Learning on High-Dimensional Biomedical Tables", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2609.07441", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-09-09T06:18:29.794093Z"}, "publications": [], "ranking": {"30d": {"confidence": "Low", "coverage": 0.0, "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": null, "value": null}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": null}, "method": "attention-ranking-v13", "rank": null, "score": null}, "90d": {"confidence": "Low", "coverage": 0.0, "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": null, "value": null}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": null}, "method": "attention-ranking-v13", "rank": null, "score": null}}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-09-07", "source": {"authors": ["Jules Kreuer", "Sofiane Ouaari", "Julia Hellmig", "Julius Braitinger", "Nico Pfeifer"], "categories": ["cs.LG", "cs.AI"], "id": "2609.07441", "title": "TabBench-Bio: A Living Benchmark for Machine Learning on High-Dimensional Biomedical Tables", "type": "arxiv", "url": "https://arxiv.org/abs/2609.07441"}, "sourceUpdatedAt": "2026-09-07T12:50:08Z", "topics": ["cs.LG"], "venueAttempts": [], "whyItMatters": "Fills the gap in tabular benchmarks for the high-feature, low-sample regime prevalent in biomedicine."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
