{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2609.04842", "kind": "paper", "url": "https://arxiv.org/abs/2609.04842"}], "authors": ["Sourav Malakar", "Harshit Nigam", "Akash Ghosh", "Sriparna Saha", "Amlan Chakrabarti", "Saptarsi Goswami", "Priti Singh"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2609.04842", "source_url": "https://arxiv.org/abs/2609.04842"}, "categories": ["Biology & Drug Discovery", "Multimodal", "Reasoning"], "description": {"en": "MMTClinic evaluates large language models on clinical time-series question answering and reasoning across five languages and three tasks: mortality prediction, heart rate forecasting, and SOFA score estimation."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2609.04842", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2609.04842", "title": "MMTClinic"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Indian Institute of Technology Patna", "University of Calcutta"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2609.04842", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2609.04842", "source_url": "https://openalex.org/W7211868433"}, "key": "claire-radar:2609.04842", "modality": null, "name": "MMTClinic", "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": "false", "origin_record_id": "bm_mmtclinic_8420d333", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "fb3164f563af7c27b99cc536badab5a8f6dc92a6388d2995e2732db79d7379fe", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-name-audit-deferred", "reviewed_at": "2026-09-08T00:56:29.478814Z", "source_url": "https://arxiv.org/abs/2609.04842"}, "publisher": null, "released": "2026-09-04", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2609.04842", "source_url": "https://arxiv.org/abs/2609.04842"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2609-04842", "source": "claire_radar", "source_benchmark_id": "2609.04842", "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/2609.04842", "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": "The benchmark addresses a specialized clinical AI niche with moderate topical breadth and no released artifacts, limiting early attention.", "score": 35}, "capabilities": ["Reasoning"], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-08T08:59:06.803818Z", "inputHash": "959f2c03e6e1582faf45c74a14dbb7460c050a754ea1a81462e3c775a7f3f76c", "model": "deepseek-v4-flash"}, "curation": {"decisionReason": "The benchmark defines a repeatable evaluation with specific tasks and metrics, and a public release is promised upon acceptance.", "model": "deepseek-v4-pro", "policy": "source-evidence-v2", "reviewedAt": "2026-09-08T00:56:29.478814Z", "state": "ai-name-audit-deferred"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "MMTClinic evaluates large language models on clinical time-series question answering and reasoning across five languages and three tasks: mortality prediction, heart rate forecasting, and SOFA score estimation.", "displayEligible": false, "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"], "snippet": "To fill this gap, we present MMTClinic, a benchmark designed to evaluate large language models (LLMs) on complex reasoning and question-answering tasks involving clinical time-series."}, "familyId": "bmf_b9dc49f52361", "firstSeenAt": "2026-09-07", "heat": null, "id": "bm_mmtclinic_8420d333", "indexedAt": "2026-09-07T00:39:11.978130Z", "industrySectors": ["Pharma & Biotech"], "links": {"code": null, "data": null, "paper": "https://arxiv.org/abs/2609.04842", "pdf": "https://arxiv.org/pdf/2609.04842", "project": null, "report": "https://arxiv.org/abs/2609.04842"}, "metrics": [], "motivation": "Time-series data in clinical settings is crucial for capturing dynamic changes in a patient's health over time, enabling timely diagnosis, personalized treatment, and early detection of critical events.", "name": "MMTClinic", "oneLine": "MMTClinic evaluates large language models on clinical time-series question answering and reasoning across five languages and three tasks: mortality prediction, heart rate forecasting, and SOFA score estimation.", "paperTitle": "MMTClinic: Multimodal, Multilingual Time Series Question Answering and Reasoning Benchmark for Clinical Domain", "primaryDomain": "Biology & Drug Discovery", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2609.04842", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-09-07T00:39:11.978130Z"}, "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": "2026-09-04", "source": {"authors": ["Sourav Malakar", "Harshit Nigam", "Akash Ghosh", "Sriparna Saha", "Amlan Chakrabarti", "Saptarsi Goswami", "Priti Singh"], "categories": ["cs.CL", "cs.AI"], "id": "2609.04842", "title": "MMTClinic: Multimodal, Multilingual Time Series Question Answering and Reasoning Benchmark for Clinical Domain", "type": "arxiv", "url": "https://arxiv.org/abs/2609.04842"}, "sourceUpdatedAt": "2026-09-04T07:59:19Z", "topics": ["Multimodal", "Reasoning"], "venueAttempts": [], "whyItMatters": "It addresses the lack of multimodal, multilingual, and time-series-grounded benchmarks for clinical AI, supporting assessment of models in linguistically diverse and clinically complex scenarios."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
