{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.06041", "kind": "paper", "url": "https://arxiv.org/abs/2608.06041"}], "authors": ["Lukas Twist", "Twm Stone", "Helen Yannakoudakis", "Jie M. Zhang"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.06041", "source_url": "https://arxiv.org/abs/2608.06041"}, "categories": ["Code & Software", "Code generation", "General AI", "cs.SE"], "description": {"en": "LangChoiceBench measures Python preference in project-level code generation across 28 projects and seven software areas, assessing language choice, recommendation-implementation consistency, and language diversity."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.06041", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.06041", "title": "LangChoiceBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["King's College London"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2608.06041", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2608.06041", "source_url": "https://openalex.org/W7201854194"}, "key": "claire-radar:2608.06041", "modality": null, "name": "LangChoiceBench", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "Medium", "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_langchoicebench_33a5b10b", "origin_source": "arxiv", "recognition_confidence": "0.85", "record_sha256": "63f72025db0eee6d960ac3d2ca087fb016e4ee98f0ea8f64a2941725f7563104", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2608.06041"}, "publisher": null, "released": "2026-08-06", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.06041", "source_url": "https://arxiv.org/abs/2608.06041"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-06041", "source": "claire_radar", "source_benchmark_id": "2608.06041", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Code & Software", "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": null, "hfPaperUrl": "https://huggingface.co/papers/2608.06041", "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", "state": "unavailable"}}, "status": "unavailable"}, "capabilities": ["Code generation"], "confidence": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "6ed3bea83cd13cb456ef17e28687d706519bcad6fee3d73d79d6082555c6a14c", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "LangChoiceBench measures Python preference in project-level code generation across 28 projects and seven software areas, assessing language choice, recommendation-implementation consistency, and language diversity.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence"], "snippet": "To bridge this gap, we introduce LangChoiceBench, a project-level code-generation benchmark for measuring Python preference, recommendation-implementation consistency, and language diversity."}, "familyId": "bmf_81dd6396539d", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_langchoicebench_33a5b10b", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2608.06041", "paper": "https://arxiv.org/abs/2608.06041", "pdf": "https://arxiv.org/pdf/2608.06041", "project": null, "report": "https://arxiv.org/abs/2608.06041"}, "metrics": [], "motivation": "Large language models (LLMs) have been shown to exhibit strong Python preferences when generating project-level code, but there is currently no systematic way to measure this behaviour across new models.", "name": "LangChoiceBench", "oneLine": "LangChoiceBench measures Python preference in project-level code generation across 28 projects and seven software areas, assessing language choice, recommendation-implementation consistency, and language diversity.", "paperTitle": "LangChoiceBench: Measuring and Explaining Programming-Language Choice in LLMs", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.06041", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {"90d": {"confidence": "Low", "coverage": 0.0, "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": null, "value": null}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": null}, "method": "attention-ranking-v13", "rank": null, "score": null}}, "readiness": "Paper only", "recognitionConfidence": 0.85, "relation": "introduces", "releasedAt": "2026-08-06", "source": {"authors": ["Lukas Twist", "Twm Stone", "Helen Yannakoudakis", "Jie M. Zhang"], "categories": ["cs.SE", "cs.CL"], "id": "2608.06041", "title": "LangChoiceBench: Measuring and Explaining Programming-Language Choice in LLMs", "type": "arxiv", "url": "https://arxiv.org/abs/2608.06041"}, "sourceUpdatedAt": "2026-08-06T13:52:16Z", "topics": ["cs.SE"], "venueAttempts": [], "whyItMatters": "Addresses the lack of systematic evaluation of language preference in LLMs, providing a way to compare models on code generation beyond correctness."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
