{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2609.37216", "kind": "paper", "url": "https://arxiv.org/abs/2609.37216"}, {"id": "hf:dcloud347/crjudgebenchmark", "kind": "dataset", "url": "https://huggingface.co/datasets/dcloud347/CRJudgeBenchmark"}], "authors": ["Yue Pan", "Jiawei Li", "Ziyuan Zhang", "Xiangxin Zhao", "He Ye"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2609.37216", "source_url": "https://arxiv.org/abs/2609.37216"}, "categories": ["Code & Software", "Software & AI Compute", "cs.SE"], "description": {"en": "Large language models can generate plausible code-review comments, but such comments may contain technically incorrect claims that mislead developers."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2609.37216", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2609.37216", "title": "CRJudgeBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["University College London", "Amazon (United States)", "Zhejiang University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2609.37216", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2609.37216", "source_url": "https://openalex.org/W7214897648"}, "key": "claire-radar:2609.37216", "modality": null, "name": "CRJudgeBench", "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_crjudgebench_6a81b5fc", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "256ba67f8624629e6410d221372f3e586a3bee1b8deabd715835d42227154e9a", "relation": "introduces", "review_state": "rule-auto-admitted", "reviewed_at": "2026-10-01T07:28:29.742921Z", "source_url": "https://arxiv.org/abs/2609.37216"}, "publisher": null, "released": "2026-09-29", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2609.37216", "source_url": "https://arxiv.org/abs/2609.37216"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2609-37216", "source": "claire_radar", "source_benchmark_id": "2609.37216", "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": "dcloud347/CRJudgeBenchmark", "hfDatasetDownloads": 122, "hfDatasetLikes": 1, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2609.37216", "observedAt": "2026-10-04T15:31:48.030916Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}, "hfDatasetLikes": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}, "hfPaperUpvotes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "state": "unavailable"}}, "status": "fresh"}, "capabilities": [], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "curation": {"decisionReason": "Automatically admitted from an explicit named benchmark release with evaluation-protocol evidence at or above the configured publication-confidence threshold.", "policy": "source-evidence-v2", "reviewedAt": "2026-10-01T07:28:29.742921Z", "state": "rule-auto-admitted"}, "dataStatus": "primary-source-indexed", "demo": false, "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence", "evaluation protocol evidence", "public artifact URL"], "snippet": "To fill this gap, we introduce CRJudgeBench, a benchmark of 1199 instances constructed from real pull requests and expert-verified perturbations, covering both trustworthy and plausible but untrustworthy comments."}, "familyId": "bmf_7a5b752b5bd7", "firstSeenAt": "2026-09-30", "heat": null, "id": "bm_crjudgebench_6a81b5fc", "indexedAt": "2026-10-01T07:27:53.594997Z", "industrySectors": ["Software & Cloud"], "links": {"code": null, "data": "https://huggingface.co/datasets/dcloud347/CRJudgeBenchmark", "hfPaper": "https://huggingface.co/papers/2609.37216", "paper": "https://arxiv.org/abs/2609.37216", "pdf": "https://arxiv.org/pdf/2609.37216", "project": null, "report": "https://arxiv.org/abs/2609.37216"}, "metrics": [], "motivation": "Large language models can generate plausible code-review comments, but such comments may contain technically incorrect claims that mislead developers.", "name": "CRJudgeBench", "oneLine": "Large language models can generate plausible code-review comments, but such comments may contain technically incorrect claims that mislead developers.", "paperTitle": "CRJudgeBench: Can AI Detect Plausible but Invalid Code Reviews?", "primaryDomain": "Software & AI Compute", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2609.37216", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {"30d": {"confidence": "Low", "coverage": 0.15, "datasetDownloadRank": 24, "datasetRankPopulation": 34, "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": 30, "historyDate": "2026-09-05", "rank": null, "score": null, "windowDays": 30}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": null, "value": null}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": 0.5794847005233054, "value": 122}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.15, "rank": 25, "score": 51}, "method": "attention-ranking-v13", "rank": 25, "score": 51}, "90d": {"confidence": "Low", "coverage": 0.3, "datasetDownloadRank": 53, "datasetRankPopulation": 85, "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": 0.4955583738172231, "value": 122}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.3, "rank": 66, "score": 50}, "method": "attention-ranking-v13", "rank": 66, "score": 50}}, "readiness": "Inspectable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-09-29", "source": {"authors": ["Yue Pan", "Jiawei Li", "Ziyuan Zhang", "Xiangxin Zhao", "He Ye"], "categories": ["cs.SE", "cs.AI"], "id": "2609.37216", "title": "CRJudgeBench: Can AI Detect Plausible but Invalid Code Reviews?", "type": "arxiv", "url": "https://arxiv.org/abs/2609.37216"}, "sourceUpdatedAt": "2026-09-29T10:31:16Z", "topics": ["cs.SE"], "venueAttempts": []}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
