{"record": {"aliases": ["Bootstrapping Niche Multilingual Code Translation via Reinforcement Learning with Execution-Based Verifiable Supervision"], "artifacts": [{"id": "arxiv:2608.13854", "kind": "paper", "url": "https://arxiv.org/abs/2608.13854"}], "authors": ["Kouki Yuki", "Jie Zeng", "Kyoko Ogawa", "Ryunosuke Ikeda", "Yohei Kobashi", "Takeshi Kojima", "Ikuya Yamada", "Yusuke Iwasawa", "Yutaka Matsuo"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.13854", "source_url": "https://arxiv.org/abs/2608.13854"}, "categories": ["General AI", "Language & Knowledge", "cs.CL"], "description": {"en": "HumanEval-X++ is an execution-based benchmark extending HumanEval-X to a broad many-to-many language space for code translation evaluation."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.13854", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.13854", "title": "HumanEval-X++"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["National Institute of Technology, Numazu College", "Seikei University", "Osaka Metropolitan University", "The University of Tokyo", "Tokyo University of Science"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2608.13854", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2608.13854", "source_url": "https://openalex.org/W7203652254"}, "key": "claire-radar:2608.13854", "modality": null, "name": "HumanEval-X++", "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": "true", "origin_record_id": "bm_bootstrapping-niche-multilingual-code-tran_de25b8dd", "origin_source": "arxiv", "recognition_confidence": "0.45", "record_sha256": "d523bdc39ba0b90d3029fe83a0e49b488688b72dd06b517ce467f22ef357eb14", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-08-26T06:10:57.123445Z", "source_url": "https://arxiv.org/abs/2608.13854"}, "publisher": null, "released": "2026-08-14", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.13854", "source_url": "https://arxiv.org/abs/2608.13854"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-13854", "source": "claire_radar", "source_benchmark_id": "2608.13854", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": ["Bootstrapping Niche Multilingual Code Translation via Reinforcement Learning with Execution-Based Verifiable Supervision"], "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": null, "hfPaperUrl": "https://huggingface.co/papers/2608.13854", "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"}, "attentionForecast": {"confidence": "Low", "horizon": "7d", "reason": "The benchmark extends an existing known suite but lacks explicit public release details, making early attention uncertain.", "score": 40}, "capabilities": [], "confidence": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-26T06:10:57.123445Z", "inputHash": "b7deaa5a4d844955c4a953a082ef2c4b75d009a9f52dfdfbee6b2d3c5abd40fc", "model": "deepseek-v4-pro"}, "curation": {"canonicalNameEvidence": "we introduce HumanEval-X++, an execution-based benchmark that extends HumanEval-X to a broad many-to-many language space", "canonicalNameSource": "abstract", "decisionReason": "The abstract formally names the benchmark and describes an execution-based scoring contract.", "model": "deepseek-v4-pro", "reviewedAt": "2026-08-26T06:10:57.123445Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "HumanEval-X++ is an execution-based benchmark extending HumanEval-X to a broad many-to-many language space for code translation evaluation.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["benchmark term in abstract", "benchmark release stated in one sentence"], "snippet": "To evaluate the niche translation capability, we introduce HumanEval-X++, an execution-based benchmark that extends HumanEval-X to a broad many-to-many language space."}, "familyId": "bmf_30c196f82c84", "firstSeenAt": "2026-08-19", "heat": null, "id": "bm_bootstrapping-niche-multilingual-code-tran_de25b8dd", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "paper": "https://arxiv.org/abs/2608.13854", "pdf": "https://arxiv.org/pdf/2608.13854", "project": null, "report": "https://arxiv.org/abs/2608.13854"}, "metrics": [], "motivation": "Code translation must preserve executable behavior across many programming languages, yet neural code translation has largely focused on a few popular languages such as C++, Java, and Python.", "name": "HumanEval-X++", "oneLine": "HumanEval-X++ is an execution-based benchmark extending HumanEval-X to a broad many-to-many language space for code translation evaluation.", "paperTitle": "Bootstrapping Niche Multilingual Code Translation via Reinforcement Learning with Execution-Based Verifiable Supervision", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.13854", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-08-19T11:05:13.395391Z"}, "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": 0.45, "relation": "introduces", "releasedAt": "2026-08-14", "source": {"authors": ["Kouki Yuki", "Jie Zeng", "Kyoko Ogawa", "Ryunosuke Ikeda", "Yohei Kobashi", "Takeshi Kojima", "Ikuya Yamada", "Yusuke Iwasawa", "Yutaka Matsuo"], "categories": ["cs.CL"], "id": "2608.13854", "title": "Bootstrapping Niche Multilingual Code Translation via Reinforcement Learning with Execution-Based Verifiable Supervision", "type": "arxiv", "url": "https://arxiv.org/abs/2608.13854"}, "sourceUpdatedAt": "2026-08-14T00:56:41Z", "topics": ["cs.CL"], "venueAttempts": [], "whyItMatters": "It provides execution-validated evaluation for niche many-to-many code translation, where parallel supervision is sparse."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
