{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.12805", "kind": "paper", "url": "https://arxiv.org/abs/2608.12805"}], "authors": ["Akanta Das", "Farhad Al-Amin Dipto", "Mrinmoy Sarkar Anto", "David Rehkopf", "Ayin Vala", "Tanmoy Sarkar Pias"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.12805", "source_url": "https://arxiv.org/abs/2608.12805"}, "categories": ["Biology & Drug Discovery", "Language & Knowledge", "cs.LG"], "description": {"en": "CoMedBench evaluates synthetic medical data fidelity and downstream utility across 37 dataset-task pairs from seven public sources, using a common clinical-validity framework and shared training and evaluation engine."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.12805", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.12805", "title": "CoMedBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Bangladesh University of Engineering and Technology", "Stanford Medicine", "Stanford University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2608.12805", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2608.12805", "source_url": "https://openalex.org/W7203495476"}, "key": "claire-radar:2608.12805", "modality": null, "name": "CoMedBench", "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_comedbench_50407db9", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "0d6ff6caaaed8fe2ef92f118bdaf517a8379ab4ec47bc66df8da614e1a56a875", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2608.12805"}, "publisher": null, "released": "2026-08-13", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.12805", "source_url": "https://arxiv.org/abs/2608.12805"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-12805", "source": "claire_radar", "source_benchmark_id": "2608.12805", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Machine Generated", "applicationDomains": ["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/2608.12805", "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": "Original Synthetic", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "3dee9274de668d7383680dcaf1e8bc0c99f5dcd98d549e0d8e80998c575d1493", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "CoMedBench evaluates synthetic medical data fidelity and downstream utility across 37 dataset-task pairs from seven public sources, using a common clinical-validity framework and shared training and evaluation engine.", "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": "We introduce CoMedBench, a reproducible benchmark that evaluates a family of generators under a common clinical-validity framework and one shared training and evaluation engine, spanning static tabular and temporal downstream tasks on established critical-care datasets."}, "familyId": "bmf_572ffe3d9a69", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_comedbench_50407db9", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Pharma & Biotech"], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2608.12805", "paper": "https://arxiv.org/abs/2608.12805", "pdf": "https://arxiv.org/pdf/2608.12805", "project": null, "report": "https://arxiv.org/abs/2608.12805"}, "metrics": [], "motivation": "Access to clinical data is essential for developing reliable healthcare machine learning systems, but direct use of electronic health records is constrained by privacy regulation, institutional review, data-use agreements, and the risk of re-identification.", "name": "CoMedBench", "oneLine": "CoMedBench evaluates synthetic medical data fidelity and downstream utility across 37 dataset-task pairs from seven public sources, using a common clinical-validity framework and shared training and evaluation engine.", "paperTitle": "CoMedBench: A Multi-Source Benchmark of Synthetic Medical Data Fidelity and Downstream Utility", "primaryDomain": "Biology & Drug Discovery", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.12805", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {"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": "2026-08-13", "source": {"authors": ["Akanta Das", "Farhad Al-Amin Dipto", "Mrinmoy Sarkar Anto", "David Rehkopf", "Ayin Vala", "Tanmoy Sarkar Pias"], "categories": ["cs.LG"], "id": "2608.12805", "title": "CoMedBench: A Multi-Source Benchmark of Synthetic Medical Data Fidelity and Downstream Utility", "type": "arxiv", "url": "https://arxiv.org/abs/2608.12805"}, "sourceUpdatedAt": "2026-08-17T21:54:19Z", "topics": ["cs.LG"], "venueAttempts": [], "whyItMatters": "Provides a reproducible benchmark for comparing synthetic data generators across multiple datasets and tasks, addressing the lack of comprehensive evaluation in prior studies and aiding in deciding when synthetic data is viable for model development."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
