{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.25939", "kind": "paper", "url": "https://arxiv.org/abs/2608.25939"}, {"id": "gh:solis-team/xrepotest", "kind": "repo", "url": "https://github.com/solis-team/XRepoTest"}], "authors": ["Dung Le Quang", "Dong Cao Van", "Nam Le Hai", "Linh Ngo Van", "Anh M. T. Bui", "Phuong T. Nguyen"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.25939", "source_url": "https://arxiv.org/abs/2608.25939"}, "categories": ["Code & Software", "Software & AI Compute", "cs.SE"], "description": {"en": "Evaluates multilingual repository-level unit test generation across Rust, Go, Julia, PHP, and Ruby using containerized execution and context augmentation strategies."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.25939", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.25939", "title": "XREPOTEST"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.25939", "modality": null, "name": "XREPOTEST", "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": "true", "origin_record_id": "bm_xrepotest_04d9b86c", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "fd10894777bcfd4c8b9212c8c631976c2e07cf5dd893cba861df306c3f1a06cc", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-08-27T04:12:36.511123Z", "source_url": "https://arxiv.org/abs/2608.25939"}, "publisher": null, "released": "2026-08-26", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.25939", "source_url": "https://arxiv.org/abs/2608.25939"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-25939", "source": "claire_radar", "source_benchmark_id": "2608.25939", "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/solis-team/XRepoTest", "githubScope": "benchmark_repo", "githubStars": 167, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 0, "hfPaperUrl": "https://huggingface.co/papers/2608.25939", "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": "2026-09-24", "state": "stale"}}, "status": "fresh"}, "attentionForecast": {"confidence": "Low", "horizon": "7d", "reason": "A multilingual repository-level unit test benchmark with code and data release may attract moderate interest from software engineering and LLM evaluation communities.", "score": 30}, "capabilities": [], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-27T04:12:36.511123Z", "inputHash": "d7bb169362cc6378b688a7f6d7236c7e86dbbaef546418fb523876255343dc15", "model": "deepseek-v4-pro"}, "curation": {"canonicalNameEvidence": "XREPOTEST: Benchmarking Multilingual Repository-Level Unit Test Generation for Large Language Models", "canonicalNameSource": "paper_title", "decisionReason": "Provides a formally named benchmark with a public code repository and dataset on Hugging Face, a containerized evaluation framework, and multiple scoring metrics.", "model": "deepseek-v4-pro", "reviewedAt": "2026-08-27T04:12:36.511123Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates multilingual repository-level unit test generation across Rust, Go, Julia, PHP, and Ruby using containerized execution and context augmentation strategies.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence", "public artifact URL"], "snippet": "We introduce XREPOTEST, a multilingual repository-level benchmark for unit test generation spanning five underexplored languages: Rust, Go, Julia, PHP, and Ruby."}, "familyId": "bmf_2ad2aabdcaba", "firstSeenAt": "2026-08-27", "heat": null, "id": "bm_xrepotest_04d9b86c", "indexedAt": "2026-08-27T04:12:10.575570Z", "industrySectors": ["Software & Cloud"], "links": {"code": "https://github.com/solis-team/XRepoTest", "data": null, "paper": "https://arxiv.org/abs/2608.25939", "pdf": "https://arxiv.org/pdf/2608.25939", "project": null, "report": "https://arxiv.org/abs/2608.25939"}, "metrics": [], "motivation": "Large language models (LLMs) have shown promise for automated unit test generation, but existing evaluations largely rely on standalone settings and a narrow set of programming languages, overestimating real-world readiness.", "name": "XREPOTEST", "oneLine": "Evaluates multilingual repository-level unit test generation across Rust, Go, Julia, PHP, and Ruby using containerized execution and context augmentation strategies.", "paperTitle": "XREPOTEST: Benchmarking Multilingual Repository-Level Unit Test Generation for Large Language Models", "primaryDomain": "Software & AI Compute", "publication": {"evidence": "Accepted to EMNLP Main 2026", "evidenceLevel": "author-claim", "evidenceUrl": "https://arxiv.org/abs/2608.25939", "source": "arxiv-comments", "status": "acceptance_claimed", "venue": "EMNLP Main 2026", "verifiedAt": "2026-08-27T04:12:10.575570Z"}, "publications": [], "publishers": [{"name": "Solis Team", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://github.com/solis-team/XRepoTest"}], "ranking": {"90d": {"confidence": "Medium", "coverage": 0.7, "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": 0.6839570822533201, "value": 167}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": 0.0, "value": 0}}, "confidence": "Medium", "coverage": 0.7, "rank": 44, "score": 53}, "method": "attention-ranking-v13", "rank": 44, "score": 53}}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-08-26", "source": {"authors": ["Dung Le Quang", "Dong Cao Van", "Nam Le Hai", "Linh Ngo Van", "Anh M. T. Bui", "Phuong T. Nguyen"], "categories": ["cs.SE"], "id": "2608.25939", "title": "XREPOTEST: Benchmarking Multilingual Repository-Level Unit Test Generation for Large Language Models", "type": "arxiv", "url": "https://arxiv.org/abs/2608.25939"}, "sourceUpdatedAt": "2026-08-26T15:53:43Z", "topics": ["cs.SE"], "venueAttempts": [{"decisionRaw": "Accepted to EMNLP Main 2026", "evidence": [{"level": "author-claim", "observedAt": "2026-08-27T04:12:10.575570Z", "rawValue": "Accepted to EMNLP Main 2026", "sourceType": "arxiv-comments", "sourceUrl": "https://arxiv.org/abs/2608.25939"}], "reviewStatus": "accepted", "venueName": "EMNLP Main 2026"}], "whyItMatters": "Exposes the gap between standalone and repository-level test generation, providing metrics like invocation rate to measure whether generated tests exercise intended functionality."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
