{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.00931", "kind": "paper", "url": "https://arxiv.org/abs/2606.00931"}], "authors": ["Fangzhou Lin", "Peiran Li", "Lingyu Xu", "Wenjing Chen", "Qianwen Ge", "Shuo Xing", "Mingyang Wu", "Xiangbo Gao", "Siyuan Yang", "Kazunori Yamada", "Ziming Zhang", "Haichong Zhang", "Zhen Dong", "Ming-Hsuan Yang", "Zhengzhong Tu"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.00931", "source_url": "https://arxiv.org/abs/2606.00931"}, "categories": ["General AI", "Vision & 3D", "cs.CV"], "description": {"en": "CV-Arena is a benchmark of 12K high-resolution image instruction pairs across 16 task types, with a human-AI collaborative preference protocol (Active Elo) for evaluating instructional computer vision problem solving."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.00931", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.00931", "title": "CV-Arena"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2606.00931", "modality": null, "name": "CV-Arena", "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_cv-arena_3558dfa5", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "b92c0124c856a7712fef05ca5d34138e9e5df143d7f17ef5bf2a88a5fcebf2d7", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.00931"}, "publisher": null, "released": "2026-05-30", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.00931", "source_url": "https://arxiv.org/abs/2606.00931"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-00931", "source": "claire_radar", "source_benchmark_id": "2606.00931", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Mixed", "applicationDomains": ["General AI"], "area": "Vision & 3D", "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": 0, "hfPaperUrl": "https://huggingface.co/papers/2606.00931", "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", "lastSuccessfulDate": "2026-09-30", "state": "stale"}}, "status": "stale"}, "capabilities": [], "confidence": "High", "construction": "Aggregate Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "5c20d7f13a506c6bcd4b096345171b0301000890ae3bb6d3c9fa6b1f4d0bbb93", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "CV-Arena is a benchmark of 12K high-resolution image instruction pairs across 16 task types, with a human-AI collaborative preference protocol (Active Elo) for evaluating instructional computer vision problem solving.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "We introduce CV-Arena, an open benchmark designed to evaluate this capability at professional scales."}, "familyId": "bmf_cc2f478af1d0", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_cv-arena_3558dfa5", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.00931", "paper": "https://arxiv.org/abs/2606.00931", "pdf": "https://arxiv.org/pdf/2606.00931", "project": null, "report": "https://arxiv.org/abs/2606.00931"}, "metrics": [], "motivation": "Instruction-guided image editing is becoming a general interface for visual work, yet existing benchmarks still focus largely on narrow appearance edits and do not fully capture the diversity of real-image tasks in professional workflows.", "name": "CV-Arena", "oneLine": "CV-Arena is a benchmark of 12K high-resolution image instruction pairs across 16 task types, with a human-AI collaborative preference protocol (Active Elo) for evaluating instructional computer vision problem solving.", "paperTitle": "CV-Arena: An Open Benchmark for Instructional Computer Vision Problem Solving with Human-AI Collaborative Preferences", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.00931", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-05-30", "source": {"authors": ["Fangzhou Lin", "Peiran Li", "Lingyu Xu", "Wenjing Chen", "Qianwen Ge", "Shuo Xing", "Mingyang Wu", "Xiangbo Gao", "Siyuan Yang", "Kazunori Yamada", "Ziming Zhang", "Haichong Zhang", "Zhen Dong", "Ming-Hsuan Yang", "Zhengzhong Tu"], "categories": ["cs.CV", "cs.AI"], "id": "2606.00931", "title": "CV-Arena: An Open Benchmark for Instructional Computer Vision Problem Solving with Human-AI Collaborative Preferences", "type": "arxiv", "url": "https://arxiv.org/abs/2606.00931"}, "sourceUpdatedAt": "2026-05-30T23:37:55Z", "topics": ["cs.CV"], "venueAttempts": [], "whyItMatters": "Addresses the gap in evaluating diverse real-image editing tasks with professional constraints, providing a scalable and traceable evaluation resource for model comparison."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
