{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2607.09880", "kind": "paper", "url": "https://arxiv.org/abs/2607.09880"}, {"id": "hf:winall/clir-bench", "kind": "dataset", "url": "https://huggingface.co/datasets/winall/CLIR-Bench"}], "authors": ["Frank Nie", "Ethan B. Liu", "Yuan Zhu", "Loe Yan", "Wei Fan", "Jindong Han"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2607.09880", "source_url": "https://arxiv.org/abs/2607.09880"}, "categories": ["Biology & Drug Discovery", "Multimodal"], "description": {"en": "A benchmark for question answering over irregular clinical time series from ICU records, containing 6,600 QA instances across 11 clinical variables and 11 tasks. It evaluates answer accuracy and evidence use through explicit temporal evidence and answer derivation rules."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.09880", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.09880", "title": "CLIR-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Shandong University", "University of Auckland"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2607.09880", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2607.09880", "source_url": "https://openalex.org/W7168257110"}, "key": "claire-radar:2607.09880", "modality": null, "name": "CLIR-Bench", "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_clir-bench_e1c31f75", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "3c12a400dbbc734a796d3145979acb9d6cf2a4b22e02689715b4fcfb00e0c65f", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2607.09880"}, "publisher": null, "released": "2026-07-10", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.09880", "source_url": "https://arxiv.org/abs/2607.09880"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-09880", "source": "claire_radar", "source_benchmark_id": "2607.09880", "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": "winall/CLIR-Bench", "hfDatasetDownloads": 70, "hfDatasetLikes": 0, "hfPaperUpvotes": 0, "hfPaperUrl": "https://huggingface.co/papers/2607.09880", "observedAt": "2026-10-04T15:31:48.030916Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}, "hfDatasetLikes": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}, "hfPaperUpvotes": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}}, "status": "fresh"}, "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": "5dbfca2cc4764cc24ea4cbcdeb5f3380d85699a013877f6ee49c5f0213f3e6af", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "A benchmark for question answering over irregular clinical time series from ICU records, containing 6,600 QA instances across 11 clinical variables and 11 tasks. It evaluates answer accuracy and evidence use through explicit temporal evidence and answer derivation rules.", "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", "public artifact URL"], "snippet": "To fill this gap, we introduce CLIR-Bench, a benchmark for irregular clinical time series QA constructed from de-identified ICU records through a principled four-stage pipeline."}, "familyId": "bmf_eab8b70b905c", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 1, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "candidates"}, "heat": null, "id": "bm_clir-bench_e1c31f75", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Pharma & Biotech"], "links": {"code": null, "data": "https://huggingface.co/datasets/winall/CLIR-Bench", "hfPaper": "https://huggingface.co/papers/2607.09880", "paper": "https://arxiv.org/abs/2607.09880", "pdf": "https://arxiv.org/pdf/2607.09880", "project": null, "report": "https://arxiv.org/abs/2607.09880"}, "metrics": [], "motivation": "Clinical time series are central to patient monitoring, risk assessment, and clinical decision support.", "name": "CLIR-Bench", "oneLine": "A benchmark for question answering over irregular clinical time series from ICU records, containing 6,600 QA instances across 11 clinical variables and 11 tasks. It evaluates answer accuracy and evidence use through explicit temporal evidence and answer derivation rules.", "paperTitle": "CLIR-Bench: Benchmarking Multimodal Question Answering over Irregular Clinical Time Series", "primaryDomain": "Biology & Drug Discovery", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2607.09880", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "CLIR-Bench Team", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://huggingface.co/datasets/winall/CLIR-Bench"}], "ranking": {"90d": {"confidence": "Medium", "coverage": 0.45, "datasetDownloadRank": 69, "datasetRankPopulation": 85, "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": 0.4389704450145728, "value": 70}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": 0.0, "value": 0}}, "confidence": "Medium", "coverage": 0.45, "rank": 135, "score": 41}, "method": "attention-ranking-v13", "rank": 135, "score": 41}}, "readiness": "Inspectable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-07-10", "source": {"authors": ["Frank Nie", "Ethan B. Liu", "Yuan Zhu", "Loe Yan", "Wei Fan", "Jindong Han"], "categories": ["cs.CL", "cs.AI"], "id": "2607.09880", "title": "CLIR-Bench: Benchmarking Multimodal Question Answering over Irregular Clinical Time Series", "type": "arxiv", "url": "https://arxiv.org/abs/2607.09880"}, "sourceUpdatedAt": "2026-07-10T18:13:54Z", "topics": ["Multimodal"], "venueAttempts": [], "whyItMatters": "Existing benchmarks focus on regular time-series or static medical QA, while real ICU data is sparse and asynchronous. This benchmark provides a way to assess whether models can reason over irregular temporal evidence, addressing a gap in clinical NLP evaluation."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
