{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.07570", "kind": "paper", "url": "https://arxiv.org/abs/2608.07570"}], "authors": ["Rui Yang", "Wei Zhou", "Dingyong Gou", "Xiaohui Cui", "Cong Li", "Yinyin Gong", "Yipo Huang", "Jiliang Zhao"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.07570", "source_url": "https://arxiv.org/abs/2608.07570"}, "categories": ["General AI", "Vision & 3D", "cs.CV"], "description": {"en": "COMEX is a benchmark for explainable aesthetic image cropping containing 33,161 quadruples of expanded image, crop box, composition category, and composition-grounded explanation. It supports joint evaluation of crop localization, composition understanding, and explanation generation."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.07570", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.07570", "title": "COMEX"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["ZTE (China)", "State Key Laboratory of Mobile Networks and Mobile Multimedia Technology", "Chang'an University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2608.07570", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2608.07570", "source_url": "https://openalex.org/W7202185131"}, "key": "claire-radar:2608.07570", "modality": null, "name": "COMEX", "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_comex_9077da26", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "105a2537f3c45e108df099d2316736be1cc470692f2b75365ad7b6c8575fabac", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2608.07570"}, "publisher": null, "released": "2026-08-04", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.07570", "source_url": "https://arxiv.org/abs/2608.07570"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-07570", "source": "claire_radar", "source_benchmark_id": "2608.07570", "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": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2608.07570", "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.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "778832c8b2ffa61e32f6c420cf2ecdbb70d67cbeb9fdd63b3a78b3fc98a3f1ed", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "COMEX is a benchmark for explainable aesthetic image cropping containing 33,161 quadruples of expanded image, crop box, composition category, and composition-grounded explanation. It supports joint evaluation of crop localization, composition understanding, and explanation generation.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence"], "snippet": "To support this setting, we introduce COMEX, a new benchmark built through image expansion and an IO-reversal pipeline."}, "familyId": "bmf_34d8cbd69dec", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_comex_9077da26", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2608.07570", "paper": "https://arxiv.org/abs/2608.07570", "pdf": "https://arxiv.org/pdf/2608.07570", "project": null, "report": "https://arxiv.org/abs/2608.07570"}, "metrics": [], "motivation": "Explainable aesthetic image cropping requires not only localizing a visually pleasing crop but also explaining why it is preferred.", "name": "COMEX", "oneLine": "COMEX is a benchmark for explainable aesthetic image cropping containing 33,161 quadruples of expanded image, crop box, composition category, and composition-grounded explanation. It supports joint evaluation of crop localization, composition understanding, and explanation generation.", "paperTitle": "COMEX: A Composition-Grounded Benchmark and Learning Framework for Explainable Aesthetic Image Cropping", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.07570", "source": "arxiv-metadata", "status": "unverified", "venue": null, "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": "2026-08-04", "source": {"authors": ["Rui Yang", "Wei Zhou", "Dingyong Gou", "Xiaohui Cui", "Cong Li", "Yinyin Gong", "Yipo Huang", "Jiliang Zhao"], "categories": ["cs.CV", "cs.AI"], "id": "2608.07570", "title": "COMEX: A Composition-Grounded Benchmark and Learning Framework for Explainable Aesthetic Image Cropping", "type": "arxiv", "url": "https://arxiv.org/abs/2608.07570"}, "sourceUpdatedAt": "2026-08-04T03:02:22Z", "topics": ["cs.CV"], "venueAttempts": [], "whyItMatters": "Provides a structured evaluation of crop-and-explain methods, enabling comparison across models on composition-grounded reasoning and explanation generation, addressing the gap of evaluating explainability in image cropping."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
