{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2607.00711", "kind": "paper", "url": "https://arxiv.org/abs/2607.00711"}, {"id": "gh:fangz-cs/clarifycodebench", "kind": "repo", "url": "https://github.com/fangz-cs/ClarifyCodeBench"}], "authors": ["Zheng Fang", "Dongming Jin", "Yihong dong", "Yongmin Li", "Kechi Zhang", "Zhi Jin", "Ge Li"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2607.00711", "source_url": "https://arxiv.org/abs/2607.00711"}, "categories": ["Code", "Code & Software", "Code generation", "Software & AI Compute"], "description": {"en": "ClarifyCodeBench evaluates LLMs on clarifying ambiguous requirements for code generation through interactive dialogues. It includes manual annotations of ambiguity types, clarification questions, and ground-truth answers, with metrics for interaction quality."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.00711", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.00711", "title": "ClarifyCodeBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Peking University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2607.00711", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2607.00711", "source_url": "https://openalex.org/W7167033509"}, "key": "claire-radar:2607.00711", "modality": null, "name": "ClarifyCodeBench", "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_clarifycodebench_aa8d2946", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "1dfb9932e697167667782d1a44cae506c026765614fec6f87632cefe1e867b5c", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2607.00711"}, "publisher": null, "released": "2026-07-01", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.00711", "source_url": "https://arxiv.org/abs/2607.00711"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-00711", "source": "claire_radar", "source_benchmark_id": "2607.00711", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Software & AI Compute"], "area": "Code & Software", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/fangz-cs/ClarifyCodeBench", "githubScope": "benchmark_repo", "githubStars": 1, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2607.00711", "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": ["Code generation"], "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": "58ded43d2b3f7996b63a9725c4d6d88976d54d37f9a558b36f34b6a3ab737f7c", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "ClarifyCodeBench evaluates LLMs on clarifying ambiguous requirements for code generation through interactive dialogues. It includes manual annotations of ambiguity types, clarification questions, and ground-truth answers, with metrics for interaction quality.", "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 bridge this gap, we introduce ClarifyCodeBench, a novel interactive benchmark for evaluating LLMs' capability in resolving requirement ambiguity."}, "familyId": "bmf_76530bd5505f", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [{"evidence": [{"basis": "linked-from-report", "linkedUrl": "https://github.com/fangz-cs/ClarifyCodeBench", "url": "https://arxiv.org/abs/2607.00711"}], "scope": "benchmark_repo", "url": "https://github.com/fangz-cs/ClarifyCodeBench", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_clarifycodebench_aa8d2946", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Software & Cloud"], "links": {"code": "https://github.com/fangz-cs/ClarifyCodeBench", "data": null, "hfPaper": "https://huggingface.co/papers/2607.00711", "paper": "https://arxiv.org/abs/2607.00711", "pdf": "https://arxiv.org/pdf/2607.00711", "project": null, "report": "https://arxiv.org/abs/2607.00711"}, "metrics": [], "motivation": "Large Language Models have emerged as programming assistants.", "name": "ClarifyCodeBench", "oneLine": "ClarifyCodeBench evaluates LLMs on clarifying ambiguous requirements for code generation through interactive dialogues. It includes manual annotations of ambiguity types, clarification questions, and ground-truth answers, with metrics for interaction quality.", "paperTitle": "ClarifyCodeBench: Evaluating LLMs on Clarifying Ambiguous Requirements for Code Generation", "primaryDomain": "Software & AI Compute", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2607.00711", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-07-01", "source": {"authors": ["Zheng Fang", "Dongming Jin", "Yihong dong", "Yongmin Li", "Kechi Zhang", "Zhi Jin", "Ge Li"], "categories": ["cs.SE"], "id": "2607.00711", "title": "ClarifyCodeBench: Evaluating LLMs on Clarifying Ambiguous Requirements for Code Generation", "type": "arxiv", "url": "https://arxiv.org/abs/2607.00711"}, "sourceUpdatedAt": "2026-07-01T09:58:59Z", "topics": ["Code"], "venueAttempts": [], "whyItMatters": "Code generation in practice involves underspecified requirements, but existing benchmarks assume perfect prompts. ClarifyCodeBench addresses this by measuring a critical yet underexplored capability, revealing that strong code generation does not imply effective requirement clarification."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
