{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.18726", "kind": "paper", "url": "https://arxiv.org/abs/2608.18726"}, {"id": "gh:acodercat/atmoscoder-bench", "kind": "repo", "url": "https://github.com/acodercat/AtmosCoder-Bench"}], "authors": ["Maohao Ran", "Chendong Ma", "Yanting Zhang", "Dailing Jiang", "Yusen Huang", "Meng Gao", "Jun Song"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.18726", "source_url": "https://arxiv.org/abs/2608.18726"}, "categories": ["General AI", "Language & Knowledge", "cs.CL"], "description": {"en": "AtmosCoder-Bench is an execution-grounded benchmark for LLMs on atmospheric science computation, with 436 problems and 3,910 variants, grading by executing code solutions against ground truth."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.18726", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.18726", "title": "AtmosCoder-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Hong Kong Baptist University", "Hong Kong University of Science and Technology", "Chinese University of Hong Kong, Shenzhen"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2608.18726", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2608.18726", "source_url": "https://openalex.org/W7203935202"}, "key": "claire-radar:2608.18726", "modality": null, "name": "AtmosCoder-Bench", "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_atmoscoder-bench_24ddfa7c", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "416249dd3715f691a9789eedb3dbde74b03c26b4e9d5f260d635b9f83defe6b0", "relation": "introduces", "review_model": "deepseek-v4-flash", "review_state": "ai-reviewed", "reviewed_at": "2026-08-20T09:45:58.504563Z", "source_url": "https://arxiv.org/abs/2608.18726"}, "publisher": null, "released": "2026-08-19", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.18726", "source_url": "https://arxiv.org/abs/2608.18726"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-18726", "source": "claire_radar", "source_benchmark_id": "2608.18726", "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/acodercat/AtmosCoder-Bench", "githubScope": "benchmark_repo", "githubStars": 2, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2608.18726", "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", "state": "unavailable"}}, "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": "024f39fc515d74250d85c364f676811509d1beaf126fe6dc0035b30611fd08e9", "model": "deepseek-v4-flash"}, "curation": {"decisionReason": "The benchmark defines a repeatable evaluation object with a clear scoring contract (execution-grounded, unit-aware grading), publicly available code and result data, and a credible path for other teams to run it.", "model": "deepseek-v4-flash", "reviewedAt": "2026-08-20T09:45:58.504563Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "AtmosCoder-Bench is an execution-grounded benchmark for LLMs on atmospheric science computation, with 436 problems and 3,910 variants, grading by executing code solutions against ground truth.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "score_submission", "evidence": {"reasonCodes": ["exact named benchmark artifact released in abstract", "benchmark release stated in one sentence", "evaluation protocol evidence", "public artifact URL"], "snippet": "Here we introduce AtmosCoder-Bench, an execution-grounded benchmark that makes the calculation process visible."}, "familyId": "bmf_5582793e0564", "firstSeenAt": "2026-08-20", "heat": null, "id": "bm_atmoscoder-bench_24ddfa7c", "indexedAt": "2026-08-20T09:44:47.308583Z", "industrySectors": [], "links": {"code": "https://github.com/acodercat/AtmosCoder-Bench", "data": null, "paper": "https://arxiv.org/abs/2608.18726", "pdf": "https://arxiv.org/pdf/2608.18726", "project": null, "report": "https://arxiv.org/abs/2608.18726"}, "metrics": [], "motivation": "Large language models are increasingly used for quantitative work in the environmental sciences, yet existing evaluations score only final answers, leaving calculation process unobserved.", "name": "AtmosCoder-Bench", "oneLine": "AtmosCoder-Bench is an execution-grounded benchmark for LLMs on atmospheric science computation, with 436 problems and 3,910 variants, grading by executing code solutions against ground truth.", "paperTitle": "Execution-grounded evaluation reveals hidden failures in language-model calculations for environmental science", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.18726", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-08-20T09:44:47.308583Z"}, "publications": [], "publishers": [{"name": "acodercat", "organizationType": "community", "role": "benchmark-publisher", "sourceUrl": "https://github.com/acodercat/AtmosCoder-Bench"}], "ranking": {"90d": {"confidence": "Low", "coverage": 0.55, "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": 0.1466449917496476, "value": 2}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.55, "rank": 263, "score": 31}, "method": "attention-ranking-v13", "rank": 263, "score": 31}}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-08-19", "source": {"authors": ["Maohao Ran", "Chendong Ma", "Yanting Zhang", "Dailing Jiang", "Yusen Huang", "Meng Gao and Jun Song"], "categories": ["cs.CL"], "id": "2608.18726", "title": "Execution-grounded evaluation reveals hidden failures in language-model calculations for environmental science", "type": "arxiv", "url": "https://arxiv.org/abs/2608.18726"}, "sourceUpdatedAt": "2026-08-19T09:28:45Z", "topics": ["cs.CL"], "venueAttempts": [], "whyItMatters": "Existing evaluations score final answers, overlooking calculation process. AtmosCoder-Bench makes process visible, revealing failures in applying formulas and adapting to regimes."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
