{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.14546", "kind": "paper", "url": "https://arxiv.org/abs/2608.14546"}, {"id": "gh:zqyzzz/cpi-benchmark", "kind": "repo", "url": "https://github.com/zqyzzz/CPI-benchmark"}], "authors": ["Qinye Zhou", "Jun Zheng", "Yongchao Du", "Yuan Wang", "Zhengrui Chen", "Zuan Gao", "Taihang Hu", "Chao Lin", "Yefeng Shen", "Xingjian Wang", "Zhao Wang", "Zhengtao Wu", "Xiaoli Xu", "Zhengze Xu", "Hao Yan", "Denghui Yang", "Yuhang Yu", "Huayu Zhang", "Mingzhou Zhang", "Mengting Chen"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.14546", "source_url": "https://arxiv.org/abs/2608.14546"}, "categories": ["General AI", "Vision & 3D", "cs.CV"], "description": {"en": "CPI-Bench evaluates image editing models across general, practical, and intelligent tasks with VLM-as-Judge scoring, including multi-image and reasoning-based editing."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.14546", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.14546", "title": "CPI-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.14546", "modality": null, "name": "CPI-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_cpi-bench_2cecc896", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "4201c9e8037aacb100f1adc4ca0b489d8f7546e5b8ee33fe9f4ad050462c694b", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2608.14546"}, "publisher": null, "released": "2026-08-14", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.14546", "source_url": "https://arxiv.org/abs/2608.14546"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-14546", "source": "claire_radar", "source_benchmark_id": "2608.14546", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Vision & 3D", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/zqyzzz/CPI-benchmark", "githubScope": "benchmark_repo", "githubStars": 7, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 16, "hfPaperUrl": "https://huggingface.co/papers/2608.14546", "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", "lastSuccessfulDate": "2026-09-30", "state": "stale"}}, "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": "0604b1a0b8824409d44a66b794d09d481d64bc8fb557dd3a42663a95ffe1b6e3", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "CPI-Bench evaluates image editing models across general, practical, and intelligent tasks with VLM-as-Judge scoring, including multi-image and reasoning-based editing.", "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"], "snippet": "To address these limitations, we propose CPI-Bench, a Comprehensive, Practical and Intelligent benchmark for real-world image editing."}, "familyId": "bmf_6f391349d28c", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [{"evidence": [{"basis": "existing-code-link", "linkedUrl": "https://github.com/zqyzzz/CPI-benchmark", "url": "https://github.com/zqyzzz/CPI-benchmark"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/zqyzzz/CPI-benchmark", "url": "https://huggingface.co/papers/2608.14546"}, {"basis": "huggingface-paper-association", "linkedUrl": "https://github.com/zqyzzz/CPI-benchmark", "url": "https://huggingface.co/api/papers/2608.14546"}], "scope": "benchmark_repo", "url": "https://github.com/zqyzzz/CPI-benchmark", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_cpi-bench_2cecc896", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/zqyzzz/CPI-benchmark", "data": null, "hfPaper": "https://huggingface.co/papers/2608.14546", "paper": "https://arxiv.org/abs/2608.14546", "pdf": "https://arxiv.org/pdf/2608.14546", "project": null, "report": "https://arxiv.org/abs/2608.14546"}, "metrics": [], "motivation": "With the rapid advancement of image editing models and their widespread application across various domains, there is an increasingly urgent need to deploy these model capabilities directly into real-world scenarios.", "name": "CPI-Bench", "oneLine": "CPI-Bench evaluates image editing models across general, practical, and intelligent tasks with VLM-as-Judge scoring, including multi-image and reasoning-based editing.", "paperTitle": "CPI-Bench: A Comprehensive, Practical and Intelligent Benchmark for Real-World Image Editing", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.14546", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "TaobaoTmall-AlgorithmProducts", "organizationType": "company-research-lab", "role": "benchmark-publisher", "sourceUrl": "https://github.com/zqyzzz/CPI-benchmark"}], "ranking": {"90d": {"confidence": "Medium", "coverage": 0.7, "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": 0.2775680655212807, "value": 7}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": 0.5006135254152291, "value": 16}}, "confidence": "Medium", "coverage": 0.7, "rank": 157, "score": 38}, "method": "attention-ranking-v13", "rank": 157, "score": 38}}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-08-14", "source": {"authors": ["Qinye Zhou", "Jun Zheng", "Yongchao Du", "Yuan Wang", "Zhengrui Chen", "Zuan Gao", "Taihang Hu", "Chao Lin", "Yefeng Shen", "Xingjian Wang", "Zhao Wang", "Zhengtao Wu", "Xiaoli Xu", "Zhengze Xu", "Hao Yan", "Denghui Yang", "Yuhang Yu", "Huayu Zhang", "Mingzhou Zhang", "Mengting Chen"], "categories": ["cs.CV"], "id": "2608.14546", "title": "CPI-Bench: A Comprehensive, Practical and Intelligent Benchmark for Real-World Image Editing", "type": "arxiv", "url": "https://arxiv.org/abs/2608.14546"}, "sourceUpdatedAt": "2026-08-18T07:27:55Z", "topics": ["cs.CV"], "venueAttempts": [], "whyItMatters": "It provides a comprehensive benchmark that captures real-world deployment scenarios and reasoning demands, with scoring aligned to human preferences for reliable model comparison."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
