{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2607.26155", "kind": "paper", "url": "https://arxiv.org/abs/2607.26155"}], "authors": ["Yuan Zhu", "Ethan B. Liu", "Frank Nie", "Wei Fan", "Haibo Pu", "Jindong Han"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2607.26155", "source_url": "https://arxiv.org/abs/2607.26155"}, "categories": ["Biology & Drug Discovery", "Multimodal"], "description": {"en": "ClinLens evaluates clinical data-science agents on 200 executable tasks over five linked MIMIC resources (EHR, notes, ECG, chest X-rays, echocardiograms), organized by a 4x5 taxonomy of patient-time scopes and analysis capabilities. Scoring uses a STRICTPASS metric requiring correct artifacts, semantics, and final answers."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.26155", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.26155", "title": "ClinLens"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Shandong University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2607.26155", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2607.26155", "source_url": "https://openalex.org/W7171829800"}, "key": "claire-radar:2607.26155", "modality": null, "name": "ClinLens", "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_clinlens_3ca0c7ce", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "b92f34d26285b33c334282ebfa3d2c5936cd0daf2f8569a82b3d43b7d5960e32", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2607.26155"}, "publisher": null, "released": "2026-07-28", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.26155", "source_url": "https://arxiv.org/abs/2607.26155"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-26155", "source": "claire_radar", "source_benchmark_id": "2607.26155", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Biology & Drug Discovery"], "area": "Multimodal", "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/2607.26155", "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": "2514840c4290af7724ea0fced91dd766511f6a845a9ed87a6edd46736e690d6f", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "ClinLens evaluates clinical data-science agents on 200 executable tasks over five linked MIMIC resources (EHR, notes, ECG, chest X-rays, echocardiograms), organized by a 4x5 taxonomy of patient-time scopes and analysis capabilities. Scoring uses a STRICTPASS metric requiring correct artifacts, semantics, and final answers.", "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": "We introduce CLINLENS, a benchmark of 200 executable tasks over five linked MIMIC resources spanning structured electronic health records, notes, electrocardiograms, chest radiographs, and echocardiograms."}, "familyId": "bmf_0887f3ebbae5", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_clinlens_3ca0c7ce", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Pharma & Biotech"], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2607.26155", "paper": "https://arxiv.org/abs/2607.26155", "pdf": "https://arxiv.org/pdf/2607.26155", "project": null, "report": "https://arxiv.org/abs/2607.26155"}, "metrics": [], "motivation": "Clinical data-science agents must transform heterogeneous longitudinal records into auditable analyses, yet existing benchmarks largely isolate medical question answering, structured-table reasoning, or generic scientific repositories.", "name": "ClinLens", "oneLine": "ClinLens evaluates clinical data-science agents on 200 executable tasks over five linked MIMIC resources (EHR, notes, ECG, chest X-rays, echocardiograms), organized by a 4x5 taxonomy of patient-time scopes and analysis capabilities. Scoring uses a STRICTPASS metric requiring correct artifacts, semantics, and final answers.", "paperTitle": "ClinLens: Towards Long-Horizon Coding Agents for Longitudinal Multimodal Clinical Data Science", "primaryDomain": "Biology & Drug Discovery", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2607.26155", "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": "2026-07-28", "source": {"authors": ["Yuan Zhu", "Ethan B. Liu", "Frank Nie", "Jindong Han"], "categories": ["cs.AI"], "id": "2607.26155", "title": "ClinLens: Towards Long-Horizon Coding Agents for Longitudinal Multimodal Clinical Data Science", "type": "arxiv", "url": "https://arxiv.org/abs/2607.26155"}, "sourceUpdatedAt": "2026-07-28T18:01:48Z", "topics": ["Multimodal"], "venueAttempts": [], "whyItMatters": "Existing benchmarks isolate medical QA or table reasoning, lacking integrated longitudinal clinical data science. ClinLens fills this gap with a program-first reverse synthesis approach, exposing a gap between runnable code and correct clinical analysis, guiding improvements in clinical agent reliability."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
