{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.02685", "kind": "paper", "url": "https://arxiv.org/abs/2608.02685"}, {"id": "gh:eureka246/bulkpr-bench-release", "kind": "repo", "url": "https://github.com/Eureka246/BulkPR-Bench-Release"}], "authors": ["Zetong Xiong", "Qiao Zhao", "Jun Zhang", "Xueying Lyu", "Zhi Li", "Yixiang Tu", "Xiaowen Yang", "Yunjie Zhang", "Yufeng Wang", "Zhe Zhang", "Kaize Yu", "Hanwen Du", "Zhongkai Sun", "Zhuoxin Liu", "Zekun Lin", "Jianwen Yang", "Ruining Chen", "Ying Zhang", "Tingxuan Pan", "Ke Chen", "Shubin Han", "Chuanhao Sun", "Yehua Yang"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.02685", "source_url": "https://arxiv.org/abs/2608.02685"}, "categories": ["Agents", "Code & Software", "Software & AI Compute"], "description": {"en": "BulkPR-Bench evaluates governance of interacting pull requests. It includes 581 candidate PRs on 18 repositories, with metrics RDS and Global-SGY measuring safe delivery. The benchmark uses executable repository execution with hidden safety checks."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.02685", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.02685", "title": "BulkPR-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Baidu (China)"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2608.02685", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2608.02685", "source_url": "https://openalex.org/W7172529949"}, "key": "claire-radar:2608.02685", "modality": null, "name": "BulkPR-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": "unknown", "origin_record_id": "bm_bulkpr-bench_1253579f", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "cc957cffeb3d7dfc38158f1e5cbea6e36a3a4406a7ad78460521e6a5780b1b20", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2608.02685"}, "publisher": null, "released": "2026-08-03", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.02685", "source_url": "https://arxiv.org/abs/2608.02685"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-02685", "source": "claire_radar", "source_benchmark_id": "2608.02685", "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/Eureka246/BulkPR-Bench-Release", "githubScope": "benchmark_repo", "githubStars": 0, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2608.02685", "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", "state": "unavailable"}}, "status": "fresh"}, "capabilities": [], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "12c3924e5aee28a796c6e54f3bd0c7d13732d61f8f27783829c5fdb4b37cccb6", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "BulkPR-Bench evaluates governance of interacting pull requests. It includes 581 candidate PRs on 18 repositories, with metrics RDS and Global-SGY measuring safe delivery. The benchmark uses executable repository execution with hidden safety checks.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence", "evaluation protocol evidence", "public artifact URL"], "snippet": "We introduce BulkPR-Bench, an executable benchmark in which an agent must recover consequential PR relations and return a large safe subset in executable order under a rolling-release protocol."}, "familyId": "bmf_10e04fc9ee92", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 1, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [{"evidence": [{"basis": "existing-code-link", "linkedUrl": "https://github.com/Eureka246/BulkPR-Bench-Release", "url": "https://github.com/Eureka246/BulkPR-Bench-Release"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/Eureka246/BulkPR-Bench-Release", "url": "https://huggingface.co/papers/2608.02685"}, {"basis": "linked-from-report", "linkedUrl": "https://github.com/Eureka246/BulkPR-Bench-Release", "url": "https://arxiv.org/abs/2608.02685"}], "scope": "benchmark_repo", "url": "https://github.com/Eureka246/BulkPR-Bench-Release", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_bulkpr-bench_1253579f", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Software & Cloud"], "links": {"code": "https://github.com/Eureka246/BulkPR-Bench-Release", "data": null, "hfPaper": "https://huggingface.co/papers/2608.02685", "paper": "https://arxiv.org/abs/2608.02685", "pdf": "https://arxiv.org/pdf/2608.02685", "project": "https://doi.org/10.5281/zenodo.21717780", "report": "https://arxiv.org/abs/2608.02685"}, "metrics": [], "motivation": "Coding-agent benchmarks increasingly cover long-horizon, end-to-end, and interactive development, but typically retain one requested outcome or a fixed change sequence.", "name": "BulkPR-Bench", "oneLine": "BulkPR-Bench evaluates governance of interacting pull requests. It includes 581 candidate PRs on 18 repositories, with metrics RDS and Global-SGY measuring safe delivery. The benchmark uses executable repository execution with hidden safety checks.", "paperTitle": "BulkPR-Bench: Benchmarking Queue-Level Governance of Interacting Pull Requests", "primaryDomain": "Software & AI Compute", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.02685", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "Zenodo", "organizationType": "benchmark-organization", "role": "benchmark-publisher", "sourceUrl": "https://doi.org/10.5281/zenodo.21717780"}, {"name": "GitHub", "organizationType": "community", "role": "benchmark-publisher", "sourceUrl": "https://github.com/Eureka246/BulkPR-Bench-Release"}], "ranking": {"90d": {"confidence": "Low", "coverage": 0.55, "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": 0.0, "value": 0}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.55, "rank": 532, "score": 23}, "method": "attention-ranking-v13", "rank": 532, "score": 23}}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-08-03", "source": {"authors": ["Zetong Xiong", "Qiao Zhao", "Jun Zhang", "Xueying Lyu", "Zhi Li", "Yixiang Tu", "Xiaowen Yang", "Yunjie Zhang", "Yufeng Wang", "Zhe Zhang", "Kaize Yu", "Hanwen Du", "Zhongkai Sun", "Zhuoxin Liu", "Zekun Lin", "Jianwen Yang", "Ruining Chen", "Ying Zhang", "Tingxuan Pan", "Ke Chen", "Shubin Han", "Chuanhao Sun", "Yehua Yang"], "categories": ["cs.SE", "cs.AI"], "id": "2608.02685", "title": "BulkPR-Bench: Benchmarking Queue-Level Governance of Interacting Pull Requests", "type": "arxiv", "url": "https://arxiv.org/abs/2608.02685"}, "sourceUpdatedAt": "2026-08-03T07:24:33Z", "topics": ["Agents"], "venueAttempts": [], "whyItMatters": "Coding-agent benchmarks often assume independent PRs. BulkPR-Bench addresses interactive PR queues, providing a benchmark for evaluating joint decision-making in complex scenarios, with executable validation."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
