{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.31435", "kind": "paper", "url": "https://arxiv.org/abs/2606.31435"}], "authors": ["Yuchen Huang", "Xiang Li", "Zhenqing Ling", "Sijia Li", "Qianli Shen", "Daoyuan Chen", "Yi R. Fung", "Yaliang Li"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.31435", "source_url": "https://arxiv.org/abs/2606.31435"}, "categories": ["General AI", "Language & Knowledge", "cs.AI"], "description": {"en": "CDR-Bench is a benchmark of 3,462 tasks for evaluating large language models on faithful execution of compositional, order-sensitive data refinement recipes across four domains and 29 operators, with deterministic reference outputs for exact evaluation."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.31435", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.31435", "title": "CDR-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Alibaba Group (Cayman Islands)", "Alibaba Group (China)", "National University of Singapore"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.31435", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.31435", "source_url": "https://openalex.org/W7166798620"}, "key": "claire-radar:2606.31435", "modality": null, "name": "CDR-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_cdr-bench_40384718", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "6df33f3fe0ba305214073fd02fcea60abcac4f27144a6c646b4c7fb70256279b", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.31435"}, "publisher": null, "released": "2026-06-30", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.31435", "source_url": "https://arxiv.org/abs/2606.31435"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-31435", "source": "claire_radar", "source_benchmark_id": "2606.31435", "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": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 0, "hfPaperUrl": "https://huggingface.co/papers/2606.31435", "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", "lastSuccessfulDate": "2026-10-04", "state": "stale"}}, "status": "stale"}, "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": "b1a757d03ed27beb6ebe96b3552827493948e0a11eda8b9d3c56bfe6770ea86b", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "CDR-Bench is a benchmark of 3,462 tasks for evaluating large language models on faithful execution of compositional, order-sensitive data refinement recipes across four domains and 29 operators, with deterministic reference outputs for exact evaluation.", "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"], "snippet": "To fill this gap, we introduce CDR-Bench, a comprehensive benchmark featuring 3,462 high-quality tasks spanning four real-world data refinement domains and 29 distinct operators."}, "familyId": "bmf_11d5499469aa", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_cdr-bench_40384718", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.31435", "paper": "https://arxiv.org/abs/2606.31435", "pdf": "https://arxiv.org/pdf/2606.31435", "project": null, "report": "https://arxiv.org/abs/2606.31435"}, "metrics": [], "motivation": "Data refinement involves executing multi-step recipes over evolving text states, where both composition and execution order of processing operators determine the outcome.", "name": "CDR-Bench", "oneLine": "CDR-Bench is a benchmark of 3,462 tasks for evaluating large language models on faithful execution of compositional, order-sensitive data refinement recipes across four domains and 29 operators, with deterministic reference outputs for exact evaluation.", "paperTitle": "CDR-Bench: Evaluating Faithful Execution of Compositional, Order-Sensitive Data Refinement Recipes", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.31435", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "arXiv", "organizationType": "community", "role": "benchmark-publisher", "sourceUrl": "https://arxiv.org/abs/2606.31435"}], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-30", "source": {"authors": ["Yuchen Huang", "Xiang Li", "Zhenqing Ling", "Sijia Li", "Qianli Shen", "Daoyuan Chen", "Yi R. Fung", "Yaliang Li"], "categories": ["cs.AI", "cs.CL"], "id": "2606.31435", "title": "CDR-Bench: Evaluating Faithful Execution of Compositional, Order-Sensitive Data Refinement Recipes", "type": "arxiv", "url": "https://arxiv.org/abs/2606.31435"}, "sourceUpdatedAt": "2026-06-30T10:08:45Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "Existing benchmarks leave unclear whether LLMs can directly execute multi-step, order-sensitive data refinement tasks; this benchmark provides a reusable, deterministic evaluation protocol to assess procedural faithfulness in compositional text processing."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
