{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2605.24945", "kind": "paper", "url": "https://arxiv.org/abs/2605.24945"}, {"id": "gh:lixruize-del/nwp-benchmark", "kind": "repo", "url": "https://github.com/lixruize-del/NWP-Benchmark"}], "authors": ["Ruize Li", "Zhibin Wen", "Tao Han", "Hao Chen", "Fenghua Ling", "Wei Zhang", "Song Guo", "Lei Bai"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2605.24945", "source_url": "https://arxiv.org/abs/2605.24945"}, "categories": ["General AI", "Language & Knowledge", "cs.LG"], "description": {"en": "Evaluates data-driven numerical weather forecasting models under operational conditions, using strictly out-of-distribution test data from 2025 and integrating low-latency operational analysis and large-scale in-situ observations from over 10,000 stations. It provides metrics for global forecasting and for extreme events such as heatwaves, cold surges, and tropical cyclones."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2605.24945", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2605.24945", "title": "RealBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2605.24945", "modality": null, "name": "RealBench", "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_realbench_3d168523", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "1227ac8ba54ee497fc70d9f003d2983a30ac8b2eed660ee10f66e5cfb779170c", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2605.24945"}, "publisher": null, "released": "2026-05-24", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2605.24945", "source_url": "https://arxiv.org/abs/2605.24945"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2605-24945", "source": "claire_radar", "source_benchmark_id": "2605.24945", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Language & Knowledge", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/lixruize-del/NWP-Benchmark", "githubScope": "benchmark_repo", "githubStars": 8, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 0, "hfPaperUrl": "https://huggingface.co/papers/2605.24945", "observedAt": "2026-10-04T15:31:48.030916Z", "signalStatus": {"githubStars": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "lastSuccessfulDate": "2026-09-30", "state": "stale"}}, "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": "09b5679de8cfa25c72850359b6871f73ef98c3bab38d223f8171a79b473b10c5", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates data-driven numerical weather forecasting models under operational conditions, using strictly out-of-distribution test data from 2025 and integrating low-latency operational analysis and large-scale in-situ observations from over 10,000 stations. It provides metrics for global forecasting and for extreme events such as heatwaves, cold surges, and tropical cyclones.", "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": "In this work, we introduce RealBench, a next-generation benchmark for AI weather forecasting that emphasizes realistic evaluation under operational conditions."}, "familyId": "bmf_f0848f948867", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [{"evidence": [{"basis": "existing-code-link", "linkedUrl": "https://github.com/lixruize-del/NWP-Benchmark", "url": "https://github.com/lixruize-del/NWP-Benchmark"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/lixruize-del/NWP-Benchmark", "url": "https://huggingface.co/papers/2605.24945"}, {"basis": "linked-from-report", "linkedUrl": "https://github.com/lixruize-del/NWP-Benchmark", "url": "https://arxiv.org/abs/2605.24945"}, {"basis": "linked-from-report", "linkedUrl": "https://github.com/lixruize-del/NWP-Benchmark.", "url": "https://arxiv.org/abs/2605.24945"}], "scope": "project_repo", "url": "https://github.com/lixruize-del/NWP-Benchmark", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_realbench_3d168523", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/lixruize-del/NWP-Benchmark", "data": null, "hfPaper": "https://huggingface.co/papers/2605.24945", "paper": "https://arxiv.org/abs/2605.24945", "pdf": "https://arxiv.org/pdf/2605.24945", "project": null, "report": "https://arxiv.org/abs/2605.24945"}, "metrics": [], "motivation": "Accurate evaluation of weather forecasting models is critical for their reliable deployment in real-world applications.", "name": "RealBench", "oneLine": "Evaluates data-driven numerical weather forecasting models under operational conditions, using strictly out-of-distribution test data from 2025 and integrating low-latency operational analysis and large-scale in-situ observations from over 10,000 stations. It provides metrics for global forecasting and for extreme events such as heatwaves, cold surges, and tropical cyclones.", "paperTitle": "RealBench: Benchmarking Data-Driven Numerical Weather Forecasting Under Operational Conditions and Extreme Event Challenges", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2605.24945", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "NWP-Benchmark contributors", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://github.com/lixruize-del/NWP-Benchmark"}], "ranking": {}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-05-24", "source": {"authors": ["Ruize Li", "Zhibin Wen", "Tao Han", "Hao Chen", "Fenghua Ling", "Wei Zhang", "Song Guo", "Lei Bai"], "categories": ["cs.LG", "cs.AI", "physics.ao-ph"], "id": "2605.24945", "title": "RealBench: Benchmarking Data-Driven Numerical Weather Forecasting Under Operational Conditions and Extreme Event Challenges", "type": "arxiv", "url": "https://arxiv.org/abs/2605.24945"}, "sourceUpdatedAt": "2026-05-24T08:46:17Z", "topics": ["cs.LG"], "venueAttempts": [], "whyItMatters": "Existing benchmarks rely on reanalysis products that do not reflect real-time operational constraints, leading to mismatches between benchmark scores and real-world performance. This benchmark provides a more faithful and operationally relevant evaluation paradigm."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
