{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.22323", "kind": "paper", "url": "https://arxiv.org/abs/2608.22323v1"}], "authors": ["Lai Wei", "Yuchao Chen", "Zhenbiao Cao", "Xiaojin Zhang", "Zhongyu Wei", "Bangting Wang", "Wei Chen", "Xiang Bai"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.22323", "source_url": "https://arxiv.org/abs/2608.22323"}, "categories": ["Biology & Drug Discovery", "Multimodal"], "description": {"en": "Evaluates LLMs on multimodal clinical diagnostic synthesis using 625 expert-validated cases with medical images and ICD-11 diagnoses."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.22323v1", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.22323v1", "title": "MedReaMM"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.22323", "modality": null, "name": "MedReaMM", "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": "true", "origin_record_id": "bm_medreamm_d93bafa9", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "b4a4db577c1ece054eee5541f120cf4c717eb958053cdd4c765c157cfdbaa8b9", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-08-27T04:18:56.318436Z", "source_url": "https://arxiv.org/abs/2608.22323v1"}, "publisher": null, "released": "2026-08-23", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.22323", "source_url": "https://arxiv.org/abs/2608.22323v1"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-22323", "source": "claire_radar", "source_benchmark_id": "2608.22323", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Biology & Drug Discovery"], "area": "Multimodal", "attention": {"asOf": "2026-08-26", "attemptedAt": "2026-08-25T23:36:26.005677Z", "githubRepo": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2608.22323", "observedAt": "2026-08-24T11:31:30.653116Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-08-25T23:36:26.005677Z", "state": "unavailable"}}, "status": "unavailable"}, "attentionForecast": {"confidence": "Medium", "horizon": "7d", "reason": "Medical multimodal reasoning is a high-impact area, and the expert-level focus may generate strong interest in the biomedical AI community.", "score": 60}, "capabilities": [], "confidence": "High", "construction": "Transform Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-27T04:18:56.318436Z", "inputHash": "204237f110b7aa62d1ce2f18836a43e239fcce75952077adcda023cff7cf714d", "model": "deepseek-v4-pro"}, "curation": {"canonicalNameEvidence": "MedReaMM: Evaluating Large Multimodal Models on Expert-Level Clinical Diagnostic Synthesis", "canonicalNameSource": "paper_title", "decisionReason": "The paper introduces a named benchmark with a curated case set and standardized diagnostic task, making it reusable for comparison.", "model": "deepseek-v4-pro", "reviewedAt": "2026-08-27T04:18:56.318436Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates LLMs on multimodal clinical diagnostic synthesis using 625 expert-validated cases with medical images and ICD-11 diagnoses.", "displayEligible": true, "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 bridge this gap, we introduce MedReaMM, a benchmark specifically designed to evaluate models' ability to synthesize heterogeneous clinical evidence consisting of detailed patient histories alongside multiple medical images into accurate differential diagnoses under a complete-information paradigm."}, "familyId": "bmf_0483fab0d9cb", "firstSeenAt": "2026-08-25", "heat": null, "id": "bm_medreamm_d93bafa9", "indexedAt": "2026-08-25T17:37:25.889905Z", "industrySectors": ["Pharma & Biotech"], "links": {"code": null, "data": null, "paper": "http://arxiv.org/abs/2608.22323v1", "pdf": "https://arxiv.org/pdf/2608.22323v1", "project": null, "report": "http://arxiv.org/abs/2608.22323v1"}, "metrics": [], "motivation": "The application of Large Language Models (LLMs) to diagnostic decision-making has garnered growing interest.", "name": "MedReaMM", "oneLine": "Evaluates LLMs on multimodal clinical diagnostic synthesis using 625 expert-validated cases with medical images and ICD-11 diagnoses.", "paperTitle": "MedReaMM: Evaluating Large Multimodal Models on Expert-Level Clinical Diagnostic Synthesis", "primaryDomain": "Biology & Drug Discovery", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "http://arxiv.org/abs/2608.22323v1", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-08-25T17:37:25.889905Z"}, "publications": [], "ranking": {"30d": {"confidence": "Low", "coverage": 0.0, "growth": {"components": {"githubStars": {"percentile": null, "value": null}, "hfDatasetDownloads": {"percentile": null, "value": null}, "hfPaperUpvotes": {"percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "elapsedDays": null, "historyDate": null, "rank": null, "score": null, "windowDays": 30}, "level": {"components": {"githubStars": {"percentile": null, "value": null}, "hfDatasetDownloads": {"percentile": null, "value": null}, "hfPaperUpvotes": {"percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": null}, "method": "attention-ranking-v11", "rank": null, "score": null}, "90d": {"confidence": "Low", "coverage": 0.0, "growth": {"components": {"githubStars": {"percentile": null, "value": null}, "hfDatasetDownloads": {"percentile": null, "value": null}, "hfPaperUpvotes": {"percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "elapsedDays": null, "historyDate": null, "rank": null, "score": null, "windowDays": 90}, "level": {"components": {"githubStars": {"percentile": null, "value": null}, "hfDatasetDownloads": {"percentile": null, "value": null}, "hfPaperUpvotes": {"percentile": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": null}, "method": "attention-ranking-v11", "rank": null, "score": null}}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-08-23", "source": {"authors": ["Lai Wei", "Yuchao Chen", "Zhenbiao Cao", "Xiaojin Zhang", "Zhongyu Wei", "Bangting Wang", "Wei Chen", "Xiang Bai"], "categories": ["cs.CV"], "id": "2608.22323", "title": "MedReaMM: Evaluating Large Multimodal Models on Expert-Level Clinical Diagnostic Synthesis", "type": "arxiv", "url": "http://arxiv.org/abs/2608.22323v1"}, "sourceUpdatedAt": "2026-08-23T09:37:53Z", "topics": ["Multimodal"], "venueAttempts": [], "whyItMatters": "Clinical diagnosis requires integrating heterogeneous evidence, and this benchmark highlights the gap between current models and expert-level synthesis."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
