{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.18595", "kind": "paper", "url": "https://arxiv.org/abs/2608.18595"}], "authors": ["Bang Xie", "Hao Liu", "Zhiyuan Peng", "Xin Yin", "Senjian Zhang", "Yuan Luo", "Chenhao Ying", "Haiming Jin", "Wei Chen", "Shaocong Long", "Zhenyu Shi"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.18595", "source_url": "https://arxiv.org/abs/2608.18595"}, "categories": ["Code & Software", "Code generation", "Software & AI Compute", "cs.SE"], "description": {"en": "OdinEval is a benchmark for program repair in the Odin programming language, built from documented defects, with issue-to-commit bindings, regression tests, and execution records."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.18595", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.18595", "title": "OdinEval"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Shanghai Jiao Tong University", "Zhejiang University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2608.18595", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2608.18595", "source_url": "https://openalex.org/W7203865598"}, "key": "claire-radar:2608.18595", "modality": null, "name": "OdinEval", "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_odineval_a7103a7e", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "4df5027e355c815e56eff61c9be15ae33e21b71d8707c63e9dd9d911d4d5725f", "relation": "introduces", "review_model": "deepseek-v4-flash", "review_state": "ai-reviewed", "reviewed_at": "2026-08-20T09:45:58.504563Z", "source_url": "https://arxiv.org/abs/2608.18595"}, "publisher": null, "released": "2026-08-19", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.18595", "source_url": "https://arxiv.org/abs/2608.18595"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-18595", "source": "claire_radar", "source_benchmark_id": "2608.18595", "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": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2608.18595", "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": "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": "6618ab0cd023268560fb59d1e91e20569a6dddb7e88ba6a6565cae82d884a0dd", "model": "deepseek-v4-flash"}, "curation": {"decisionReason": "Named benchmark with clear release artifacts and reproducible protocol, including frozen data and containers.", "model": "deepseek-v4-flash", "reviewedAt": "2026-08-20T09:45:58.504563Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "OdinEval is a benchmark for program repair in the Odin programming language, built from documented defects, with issue-to-commit bindings, regression tests, and execution records.", "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", "evaluation protocol evidence"], "snippet": "We present OdinEval, a reproducible benchmark built from documented defects in public Odin repositories."}, "familyId": "bmf_3047befaf9e9", "firstSeenAt": "2026-08-20", "heat": null, "id": "bm_odineval_a7103a7e", "indexedAt": "2026-08-20T09:44:47.308583Z", "industrySectors": ["Software & Cloud"], "links": {"code": null, "data": null, "paper": "https://arxiv.org/abs/2608.18595", "pdf": "https://arxiv.org/pdf/2608.18595", "project": null, "report": "https://arxiv.org/abs/2608.18595"}, "metrics": [], "motivation": "Repository-level repair benchmarks still center on a few mainstream languages, leaving systems languages such as Odin largely untested.", "name": "OdinEval", "oneLine": "OdinEval is a benchmark for program repair in the Odin programming language, built from documented defects, with issue-to-commit bindings, regression tests, and execution records.", "paperTitle": "OdinEval: A Reproducible Benchmark for LLM-Based Program Repair in the Odin Programming Language", "primaryDomain": "Software & AI Compute", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.18595", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-08-20T09:44:47.308583Z"}, "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": 1.0, "relation": "introduces", "releasedAt": "2026-08-19", "source": {"authors": ["Bang Xie", "Hao Liu", "Zhiyuan Peng", "Xin Yin", "Senjian Zhang", "Yuan Luo", "Chenhao Ying", "Haiming Jin", "Wei Chen", "Shaocong Long", "Zhenyu Shi"], "categories": ["cs.SE"], "id": "2608.18595", "title": "OdinEval: A Reproducible Benchmark for LLM-Based Program Repair in the Odin Programming Language", "type": "arxiv", "url": "https://arxiv.org/abs/2608.18595"}, "sourceUpdatedAt": "2026-08-19T06:38:32Z", "topics": ["cs.SE"], "venueAttempts": [], "whyItMatters": "Existing repair benchmarks focus on mainstream languages, leaving systems languages like Odin untested. OdinEval provides a reproducible benchmark for a less-covered language."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
