{"record": {"aliases": ["MedRealMM: A Real-World Multimodal Benchmark for Chinese Online Medical Consultation"], "artifacts": [{"id": "arxiv:2607.09142", "kind": "paper", "url": "https://arxiv.org/abs/2607.09142"}, {"id": "hf:jdh-algo/medrealmm", "kind": "dataset", "url": "https://huggingface.co/datasets/jdh-algo/MedRealMM"}], "authors": ["Runhan Shi", "Quan Zhou", "Yuqian Xu", "Shuai Yang", "Xin Wu", "Zitong Zhou", "Hui Liu", "Bin Zha", "Zheming Wang", "Liya Li", "Wei Wei", "Jinru Ding", "Wenrao Pang", "Mouxiao Bian", "Haoyuan Hu", "Jun Xu", "Jie Xu"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2607.09142", "source_url": "https://arxiv.org/abs/2607.09142"}, "categories": ["Biology & Drug Discovery", "Multimodal"], "description": {"en": "A multimodal next-response generation benchmark derived from de-identified Chinese online medical consultations, with case-specific physician-refined rubrics."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.09142", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.09142", "title": "MedRealMM"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Shanghai Jiao Tong University", "National University of Singapore", "University of North Carolina at Chapel Hill", "University of Pennsylvania"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2607.09142", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2607.09142", "source_url": "https://openalex.org/W7168187391"}, "key": "claire-radar:2607.09142", "modality": null, "name": "MedRealMM", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"admission_policy_version": "2026-09-09.1", "confidence": "Medium", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-09-25T04:40:22Z", "data_status": "primary-source-indexed", "display_eligible": "true", "origin_record_id": "bm_medrealmm-a-real-world-multimodal-benchmar_3603cdc3", "origin_source": "arxiv", "recognition_confidence": "0.7", "record_sha256": "3ad551935f3486eefc7de080ba382d6abc4d6b9816b2015ddbbe4c38eb46afb3", "relation": "introduces", "review_model": "codex-cli-default", "review_state": "ai-reviewed", "reviewed_at": "2026-09-24T17:27:13.101905Z", "source_url": "https://arxiv.org/abs/2607.09142"}, "publisher": null, "released": "2026-07-10", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.09142", "source_url": "https://arxiv.org/abs/2607.09142"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-09142", "source": "claire_radar", "source_benchmark_id": "2607.09142", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": ["MedRealMM: A Real-World Multimodal Benchmark for Chinese Online Medical Consultation"], "annotation": "Machine Generated", "applicationDomains": ["Biology & Drug Discovery"], "area": "Multimodal", "attentionForecast": {"confidence": "Medium", "horizon": "7d", "reason": "The combination of real clinical interactions, multimodal cases, safety-sensitive rubrics, and a stated public release supports broad evaluation interest.", "score": 82}, "capabilities": [], "confidence": "Medium", "construction": "Original Synthetic", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-24T17:27:13.101905Z", "inputHash": "ea5392704dc25e836b99c290492f83d2430a7ce653deb982a2ea5eb76b8caada", "model": "codex-cli-default"}, "curation": {"admissionPolicyVersion": "2026-09-09.1", "canonicalNameEvidence": "MedRealMM: A Real-World Multimodal Benchmark for Chinese Online Medical Consultation", "canonicalNameSource": "paper_title", "decisionReason": "The source provides a formal name, standardized task, explicit rubric-based scoring contract, and a public Hugging Face dataset path.", "evaluationEvidence": {"reuse": "The dataset will be publicly available on Hugging Face at https://huggingface.co/datasets/jdh-algo/MedRealMM.", "scoring": "Each instance is paired with a case-specific rubric refined by physicians", "task": "converts each into a standardized next-response generation task"}, "model": "codex-cli-default", "reviewedAt": "2026-09-24T17:27:13.101905Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "A multimodal next-response generation benchmark derived from de-identified Chinese online medical consultations, with case-specific physician-refined rubrics.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["benchmark term in abstract", "benchmark release stated in one sentence", "evaluation protocol evidence", "public artifact URL"], "snippet": "We introduce \\textbf{MedRealMM}, a large-scale benchmark for multimodal online medical consultation built from de-identified patient-doctor interactions collected from a nationwide Chinese internet hospital."}, "familyId": "bmf_ec6422d3abe6", "firstSeenAt": "2026-08-19", "heat": null, "id": "bm_medrealmm-a-real-world-multimodal-benchmar_3603cdc3", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Pharma & Biotech"], "links": {"code": null, "data": "https://huggingface.co/datasets/jdh-algo/MedRealMM", "paper": "https://arxiv.org/abs/2607.09142", "pdf": "https://arxiv.org/pdf/2607.09142", "project": null, "report": "https://arxiv.org/abs/2607.09142"}, "metrics": [], "motivation": "Large language models (LLMs) are increasingly deployed in online medical consultation, yet existing benchmarks remain poorly aligned with real clinical practice.", "name": "MedRealMM", "oneLine": "A multimodal next-response generation benchmark derived from de-identified Chinese online medical consultations, with case-specific physician-refined rubrics.", "paperTitle": "MedRealMM: A Real-World Multimodal Benchmark for Chinese Online Medical Consultation", "primaryDomain": "Biology & Drug Discovery", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2607.09142", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-08-19T11:05:13.395391Z"}, "publications": [], "readiness": "Inspectable", "recognitionConfidence": 0.7, "relation": "introduces", "releasedAt": "2026-07-10", "reviewLifecycle": {"state": "pending"}, "source": {"authors": ["Runhan Shi and Quan Zhou and Yuqian Xu and Shuai Yang and Xin Wu and Zitong Zhou and Hui Liu and Bin Zha and Zheming Wang and Liya Li and Wei Wei and Jinru Ding and Wenrao Pang and Mouxiao Bian and Haoyuan Hu and Jun Xu and Jie Xu"], "categories": ["cs.AI", "cs.CL", "cs.CV"], "id": "2607.09142", "title": "MedRealMM: A Real-World Multimodal Benchmark for Chinese Online Medical Consultation", "type": "arxiv", "url": "https://arxiv.org/abs/2607.09142"}, "sourceUpdatedAt": "2026-07-16T10:17:24Z", "topics": ["Multimodal"], "venueAttempts": [], "whyItMatters": "It evaluates clinically desirable and unsafe response behavior using authentic text-image consultation contexts rather than synthetic or multiple-choice approximations."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
