{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.27442", "kind": "paper", "url": "https://arxiv.org/abs/2608.27442"}], "authors": ["Dewu Zheng", "Yanlin Wang", "Xiwen Wang", "Kefeng Duan", "Hongyu Zhang", "Xilin Liu", "Yuchi Ma", "Zibin Zheng"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.27442", "source_url": "https://arxiv.org/abs/2608.27442"}, "categories": ["Code & Software", "General AI", "cs.SE"], "description": {"en": "In real-world software development, code review typically involves iterative interactions between developers and reviewers to improve software quality, making the process costly and time-consuming."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.27442", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.27442", "title": "MCR-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.27442", "modality": null, "name": "MCR-Bench", "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_mcr-bench_7a6da290", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "a5870026054272aaf5f758acee0b5a3de5f4a635a5eb8da835c963f5d77ab7b6", "relation": "introduces", "review_state": "rule-auto-admitted", "reviewed_at": "2026-08-31T04:05:24.949457Z", "source_url": "https://arxiv.org/abs/2608.27442"}, "publisher": null, "released": "2026-08-27", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.27442", "source_url": "https://arxiv.org/abs/2608.27442"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-27442", "source": "claire_radar", "source_benchmark_id": "2608.27442", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "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/2608.27442", "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": [], "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": "2026-08-31T04:05:24.949457Z", "state": "rule-auto-admitted"}, "dataStatus": "primary-source-indexed", "demo": false, "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["exact named benchmark artifact released in abstract", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "To bridge this gap, we introduce MCR-Bench, the first defect state-aware benchmark designed for realistic multi-round code review."}, "familyId": "bmf_0ade0c7988a9", "firstSeenAt": "2026-08-30", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_mcr-bench_7a6da290", "indexedAt": "2026-08-30T06:59:55.242506Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2608.27442", "paper": "https://arxiv.org/abs/2608.27442", "pdf": "https://arxiv.org/pdf/2608.27442", "project": null, "report": "https://arxiv.org/abs/2608.27442"}, "metrics": [], "motivation": "In real-world software development, code review typically involves iterative interactions between developers and reviewers to improve software quality, making the process costly and time-consuming.", "name": "MCR-Bench", "oneLine": "In real-world software development, code review typically involves iterative interactions between developers and reviewers to improve software quality, making the process costly and time-consuming.", "paperTitle": "From Static to Dynamic: Benchmarking Real-World Code Review with MCR-Bench", "primaryDomain": "General AI", "publication": {"evidence": "Accepted at ISSTA 2026", "evidenceLevel": "author-claim", "evidenceUrl": "https://arxiv.org/abs/2608.27442", "source": "arxiv-comments", "status": "acceptance_claimed", "venue": "ISSTA 2026", "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "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": "2026-08-27", "source": {"authors": ["Dewu Zheng", "Yanlin Wang", "Xiwen Wang", "Kefeng Duan", "Hongyu Zhang", "Xilin Liu", "Yuchi Ma", "Zibin Zheng"], "categories": ["cs.SE", "cs.AI", "cs.CL"], "id": "2608.27442", "title": "From Static to Dynamic: Benchmarking Real-World Code Review with MCR-Bench", "type": "arxiv", "url": "https://arxiv.org/abs/2608.27442"}, "sourceUpdatedAt": "2026-08-27T17:56:24Z", "topics": ["cs.SE"], "venueAttempts": [{"decisionRaw": "Accepted at ISSTA 2026", "evidence": [{"level": "author-claim", "observedAt": "2026-10-14T01:46:58.058199Z", "rawValue": "Accepted at ISSTA 2026", "sourceType": "arxiv-comments", "sourceUrl": "https://arxiv.org/abs/2608.27442"}], "reviewStatus": "accepted", "venueName": "ISSTA 2026"}]}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
