{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.15300", "kind": "paper", "url": "https://arxiv.org/abs/2606.15300"}, {"id": "gh:ruc-datalab/coda-bench", "kind": "repo", "url": "https://github.com/ruc-datalab/CoDA-Bench"}, {"id": "hf:ruc-datalab/coda-bench", "kind": "dataset", "url": "https://huggingface.co/datasets/RUC-DataLab/CoDA-Bench"}, {"kind": "website", "url": "https://coda-bench.github.io/"}], "authors": ["Yuxin Zhang", "Ju Fan", "Meihao Fan", "Shaolei Zhang", "Xiaoyong Du"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.15300", "source_url": "https://arxiv.org/abs/2606.15300"}, "categories": ["Agents & Tool Use", "General AI", "cs.AI"], "description": {"en": "CODA-Bench is a benchmark for evaluating AI agents on data-intensive analytical tasks in a Linux sandbox with 1,009 tasks across 31 communities, requiring data discovery, code generation, and correct answers."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.15300", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.15300", "title": "CODA-BENCH"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Renmin University of China"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.15300", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.15300", "source_url": "https://openalex.org/W7164906401"}, "key": "claire-radar:2606.15300", "modality": null, "name": "CODA-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": "unknown", "origin_record_id": "bm_coda-bench_a3ad2891", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "b086b36164a9bdd608c404db414730f9387ddb21627700d09c8a5825f1a9f5a0", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.15300"}, "publisher": null, "released": "2026-06-13", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.15300", "source_url": "https://arxiv.org/abs/2606.15300"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-15300", "source": "claire_radar", "source_benchmark_id": "2606.15300", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Agents & Tool Use", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/ruc-datalab/CoDA-Bench", "githubScope": "benchmark_repo", "githubStars": 49, "hfDailySubmittedAt": null, "hfDataset": "RUC-DataLab/CoDA-Bench", "hfDatasetDownloads": 535, "hfDatasetLikes": 3, "hfPaperUpvotes": 13, "hfPaperUrl": "https://huggingface.co/papers/2606.15300", "observedAt": "2026-10-04T15:31:48.030916Z", "signalStatus": {"githubStars": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}, "hfDatasetDownloads": {"checkedAt": "2026-10-04T15:31:48.030916Z", "lastSuccessfulDate": "2026-10-01", "state": "stale"}, "hfDatasetLikes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "lastSuccessfulDate": "2026-10-01", "state": "stale"}, "hfPaperUpvotes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "lastSuccessfulDate": "2026-10-01", "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": "bc53bacf180f2fd3e57bb930c67527a8ab71526a260aaa2104150d7856741a38", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "CODA-Bench is a benchmark for evaluating AI agents on data-intensive analytical tasks in a Linux sandbox with 1,009 tasks across 31 communities, requiring data discovery, code generation, and correct answers.", "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 paper, we bridge this gap by introducing CODA-BENCH, the first benchmark to jointly evaluate code and data intelligence in a data-intensive environment."}, "familyId": "bmf_7e9ed12d69ca", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 1, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [{"evidence": [{"basis": "existing-code-link", "linkedUrl": "https://github.com/ruc-datalab/CoDA-Bench", "url": "https://github.com/ruc-datalab/CoDA-Bench"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/ruc-datalab/CoDA-Bench", "url": "https://huggingface.co/papers/2606.15300"}, {"basis": "huggingface-paper-association", "linkedUrl": "https://github.com/ruc-datalab/CoDA-Bench", "url": "https://huggingface.co/api/papers/2606.15300"}, {"basis": "linked-from-report", "linkedUrl": "https://github.com/ruc-datalab/CoDA-Bench", "url": "https://arxiv.org/abs/2606.15300"}, {"basis": "linked-from-data", "linkedUrl": "https://github.com/ruc-datalab/CoDA-Bench", "url": "https://huggingface.co/datasets/RUC-DataLab/CoDA-Bench"}], "scope": "benchmark_repo", "url": "https://github.com/ruc-datalab/CoDA-Bench", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_coda-bench_a3ad2891", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/ruc-datalab/CoDA-Bench", "data": "https://huggingface.co/datasets/RUC-DataLab/CoDA-Bench", "hfPaper": "https://huggingface.co/papers/2606.15300", "paper": "https://arxiv.org/abs/2606.15300", "pdf": "https://arxiv.org/pdf/2606.15300", "project": "https://coda-bench.github.io/", "report": "https://arxiv.org/abs/2606.15300"}, "metrics": [], "motivation": "Advanced agents are increasingly demonstrating the potential to operate as autonomous engineers, creating a growing demand for evaluation benchmarks that capture the complexity of real-world development.", "name": "CODA-BENCH", "oneLine": "CODA-Bench is a benchmark for evaluating AI agents on data-intensive analytical tasks in a Linux sandbox with 1,009 tasks across 31 communities, requiring data discovery, code generation, and correct answers.", "paperTitle": "CODA-BENCH: Can Code Agents Handle Data-Intensive Tasks?", "primaryDomain": "General AI", "publication": {"evidence": "Accepted at ICML 2026. 37 pages, 11 figures. Project page: https://coda-bench.github.io/ Code: https://github.com/ruc-datalab/CoDA-Bench Data: https://huggingface.co/datasets/RUC-DataLab/CoDA-Bench", "evidenceLevel": "author-claim", "evidenceUrl": "https://arxiv.org/abs/2606.15300", "source": "arxiv-comments", "status": "acceptance_claimed", "venue": "ICML 2026", "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "RUC-DataLab", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://github.com/ruc-datalab/CoDA-Bench"}], "ranking": {}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-13", "source": {"authors": ["Yuxin Zhang", "Ju Fan", "Meihao Fan", "Shaolei Zhang", "Xiaoyong Du"], "categories": ["cs.AI", "cs.CL"], "id": "2606.15300", "title": "CODA-BENCH: Can Code Agents Handle Data-Intensive Tasks?", "type": "arxiv", "url": "https://arxiv.org/abs/2606.15300"}, "sourceUpdatedAt": "2026-06-13T13:46:47Z", "topics": ["cs.AI"], "venueAttempts": [{"decisionRaw": "Accepted at ICML 2026. 37 pages, 11 figures. Project page: https://coda-bench.github.io/ Code: https://github.com/ruc-datalab/CoDA-Bench Data: https://huggingface.co/datasets/RUC-DataLab/CoDA-Bench", "evidence": [{"level": "author-claim", "observedAt": "2026-10-14T01:46:58.058199Z", "rawValue": "Accepted at ICML 2026. 37 pages, 11 figures. Project page: https://coda-bench.github.io/ Code: https://github.com/ruc-datalab/CoDA-Bench Data: https://huggingface.co/datasets/RUC-DataLab/CoDA-Bench", "sourceType": "arxiv-comments", "sourceUrl": "https://arxiv.org/abs/2606.15300"}], "reviewStatus": "accepted", "venueName": "ICML 2026"}], "whyItMatters": "Existing benchmarks evaluate code or data capabilities in isolation. CODA-Bench jointly evaluates both, reflecting real development scenarios with complex file systems and large-scale data, revealing gaps in agentic data intelligence."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
