{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.20517", "kind": "paper", "url": "https://arxiv.org/abs/2606.20517"}, {"id": "gh:multi-lcb/multi-lcb", "kind": "repo", "url": "https://github.com/Multi-LCB/Multi-LCB"}], "authors": ["Maria Ivanova", "Pavel Zadorozhny", "Rodion Levichev", "Ivan Petrov", "Adamenko Pavel", "Ivan Lopatin", "Alexey Kutalev", "Dmitrii Babaev"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.20517", "source_url": "https://arxiv.org/abs/2606.20517"}, "categories": ["Code & Software", "Code generation", "Software & AI Compute", "cs.AI"], "description": {"en": "Multi-LCB evaluates code generation across twelve programming languages (C++, C#, Python, Java, Rust, Go, TypeScript, JavaScript, Ruby, Kotlin, Scala, PHP) by transforming Python tasks from LiveCodeBench while preserving its contamination controls and evaluation protocol."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.20517", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.20517", "title": "Multi-LCB"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2606.20517", "modality": null, "name": "Multi-LCB", "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_multi-lcb_028b5b88", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "e5c542aa58a507d7cbb2067dce556d1dfc5c7d849f045acb161f70e1aa27d7a9", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.20517"}, "publisher": null, "released": "2026-06-18", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.20517", "source_url": "https://arxiv.org/abs/2606.20517"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-20517", "source": "claire_radar", "source_benchmark_id": "2606.20517", "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/Multi-LCB/Multi-LCB", "githubScope": "benchmark_repo", "githubStars": 29, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 60, "hfPaperUrl": "https://huggingface.co/papers/2606.20517", "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", "lastSuccessfulDate": "2026-10-02", "state": "stale"}}, "status": "fresh"}, "capabilities": ["Code generation"], "confidence": "High", "construction": "Transform Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "f648ab30e00c8861c6e20a2507217f1d4853a08596d77d744506b2efe8608d6f", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Multi-LCB evaluates code generation across twelve programming languages (C++, C#, Python, Java, Rust, Go, TypeScript, JavaScript, Ruby, Kotlin, Scala, PHP) by transforming Python tasks from LiveCodeBench while preserving its contamination controls and evaluation protocol.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "We introduce Multi-LCB, a benchmark for evaluating LLMs across twelve programming languages, including Python."}, "familyId": "bmf_d210c1214987", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [{"evidence": [{"basis": "existing-code-link", "linkedUrl": "https://github.com/Multi-LCB/Multi-LCB", "url": "https://github.com/Multi-LCB/Multi-LCB"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/Multi-LCB/Multi-LCB", "url": "https://huggingface.co/papers/2606.20517"}], "scope": "benchmark_repo", "url": "https://github.com/Multi-LCB/Multi-LCB", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_multi-lcb_028b5b88", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Software & Cloud"], "links": {"code": "https://github.com/Multi-LCB/Multi-LCB", "data": null, "hfPaper": "https://huggingface.co/papers/2606.20517", "paper": "https://arxiv.org/abs/2606.20517", "pdf": "https://arxiv.org/pdf/2606.20517", "project": null, "report": "https://arxiv.org/abs/2606.20517"}, "metrics": [], "motivation": "LiveCodeBench (LCB) has recently become a widely adopted benchmark for evaluating large language models (LLMs) on code-generation tasks.", "name": "Multi-LCB", "oneLine": "Multi-LCB evaluates code generation across twelve programming languages (C++, C#, Python, Java, Rust, Go, TypeScript, JavaScript, Ruby, Kotlin, Scala, PHP) by transforming Python tasks from LiveCodeBench while preserving its contamination controls and evaluation protocol.", "paperTitle": "Multi-LCB: Extending LiveCodeBench to Multiple Programming Languages", "primaryDomain": "Software & AI Compute", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.20517", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "Multi-LCB Team", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://github.com/Multi-LCB/Multi-LCB"}], "ranking": {}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-18", "source": {"authors": ["Maria Ivanova", "Pavel Zadorozhny", "Rodion Levichev", "Ivan Petrov", "Adamenko Pavel", "Ivan Lopatin", "Alexey Kutalev", "Dmitrii Babaev"], "categories": ["cs.AI", "cs.PL"], "id": "2606.20517", "title": "Multi-LCB: Extending LiveCodeBench to Multiple Programming Languages", "type": "arxiv", "url": "https://arxiv.org/abs/2606.20517"}, "sourceUpdatedAt": "2026-06-18T17:35:57Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "LiveCodeBench restricted code evaluation to Python; Multi-LCB addresses the gap by enabling cross-language assessment, revealing Python overfitting and language-specific contamination in LLMs, and supporting robust multilingual code evaluation for real-world software engineering."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
