{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.01028", "kind": "paper", "url": "https://arxiv.org/abs/2606.01028"}], "authors": ["Yuepeng Wang", "Ken Kawano", "Yoshihiko Fujisawa", "Yongqi Zhou", "Akifumi Wachi", "Mehrshad Sadria", "Lei Zhou", "Richard Weiss", "Katsuki Fujisawa", "Ying Chen", "Xin Liu", "Kyoung-Sook Kim", "Xiao Hu", "Sebastien Gros", "Xun Shen"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.01028", "source_url": "https://arxiv.org/abs/2606.01028"}, "categories": ["Biology & Drug Discovery", "Language & Knowledge", "cs.LG"], "description": {"en": "Provides a continuous-time reinforcement learning environment for dynamic medical treatment recommendation, built from clinical data with physics-informed neural networks. Supports offline and online RL with configurable parameters."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.01028", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.01028", "title": "MedGym"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Tokyo University of Agriculture and Technology", "Institute of Science Tokyo", "National University of Singapore", "Altos Labs", "National Institute of Advanced Industrial Science and Technology", "Emory University", "Norwegian University of Science and Technology"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.01028", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.01028", "source_url": "https://openalex.org/W7163199561"}, "key": "claire-radar:2606.01028", "modality": null, "name": "MedGym", "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_medgym_d9be6475", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "c40a1ef90511daa0e08f0be00580b86059127540fb649822bfb596589e936718", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.01028"}, "publisher": null, "released": "2026-05-31", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.01028", "source_url": "https://arxiv.org/abs/2606.01028"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-01028", "source": "claire_radar", "source_benchmark_id": "2606.01028", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Biology & Drug Discovery"], "area": "Language & Knowledge", "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/2606.01028", "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": "2026-08-21T04:30:40.934319Z", "inputHash": "95a9aebde44e8244c4f90094756fbefb76d4dfde9aa581d721d7573e9a406ab4", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Provides a continuous-time reinforcement learning environment for dynamic medical treatment recommendation, built from clinical data with physics-informed neural networks. Supports offline and online RL with configurable parameters.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence"], "snippet": "To address this gap, we introduce MedGym, a benchmark environment for dynamic treatment recommendation."}, "familyId": "bmf_0a3477dc88fd", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_medgym_d9be6475", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Pharma & Biotech"], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.01028", "paper": "https://arxiv.org/abs/2606.01028", "pdf": "https://arxiv.org/pdf/2606.01028", "project": null, "report": "https://arxiv.org/abs/2606.01028"}, "metrics": [], "motivation": "Medical treatment recommendation poses several challenges to reinforcement learning (RL): patient physiology evolves in continuous time, measurements and interventions are performed at irregular intervals, and treatment effects vary substantially across individuals.", "name": "MedGym", "oneLine": "Provides a continuous-time reinforcement learning environment for dynamic medical treatment recommendation, built from clinical data with physics-informed neural networks. Supports offline and online RL with configurable parameters.", "paperTitle": "MedGym:A Unified Continuous-Time Benchmark for Dynamic Medical Treatment Reinforcement Learning", "primaryDomain": "Biology & Drug Discovery", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.01028", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "MedGym Team", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://arxiv.org/abs/2606.01028"}], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-05-31", "source": {"authors": ["Yuepeng Wang", "Ken Kawano", "Yongqi Zhou", "Yoshihiko Fujisawa", "Richard Weiss", "Akifumi Wachi", "Katsuki Fujisawa", "Ying Chen", "Mehrshad Sadria", "Xin Liu", "Kyoung-Sook Kim", "Xiao Hu", "Sebastien Gros", "Xun Shen"], "categories": ["cs.LG"], "id": "2606.01028", "title": "MedGym:A Unified Continuous-Time Benchmark for Dynamic Medical Treatment Reinforcement Learning", "type": "arxiv", "url": "https://arxiv.org/abs/2606.01028"}, "sourceUpdatedAt": "2026-05-31T05:36:03Z", "topics": ["cs.LG"], "venueAttempts": [], "whyItMatters": "Offers a realistic testbed for RL methods in continuous-time medical settings, enabling evaluation of personalization, safety, and online deployment gaps. Standardizes comparisons between discrete and continuous time approaches."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
