{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2609.02502", "kind": "paper", "url": "https://arxiv.org/abs/2609.02502"}], "authors": ["Chuer Chen", "Zichen Wang", "Yi He", "Zhengxi Yu", "Nan Cao"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2609.02502", "source_url": "https://arxiv.org/abs/2609.02502"}, "categories": ["General AI", "Vision & 3D", "cs.CV"], "description": {"en": "Evaluates text-to-image models on their ability to generate images that convey visual metaphors, using a set of metaphor prompts and comparative scoring."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2609.02502", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2609.02502", "title": "VMetaphor-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2609.02502", "modality": null, "name": "VMetaphor-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_vmetaphor-bench_19432c0c", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "f33c79a370b768abaa78fd0b09fd602b4468d1b06d934603bf0aadc6d267f709", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-09-04T00:46:59.007339Z", "source_url": "https://arxiv.org/abs/2609.02502"}, "publisher": null, "released": "2026-09-02", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2609.02502", "source_url": "https://arxiv.org/abs/2609.02502"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2609-02502", "source": "claire_radar", "source_benchmark_id": "2609.02502", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Vision & 3D", "attention": {"asOf": "2026-09-03", "attemptedAt": "2026-09-03T06:34:20.331209Z", "githubRepo": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2609.02502", "observedAt": "2026-09-02T06:30:32.214812Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-09-03T06:34:20.331209Z", "state": "unavailable"}}, "status": "unavailable"}, "attentionForecast": {"confidence": "Medium", "horizon": "7d", "reason": "The topic is novel but relatively niche, with moderate appeal to the T2I evaluation community and limited artifact links beyond the paper.", "score": 45}, "capabilities": [], "confidence": "High", "construction": "Transform Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-04T00:46:59.007339Z", "inputHash": "2e88ab68ea37aa4d71281f9a3100098018d91630d2c06b22b8b3529daf870365", "model": "deepseek-v4-pro"}, "curation": {"canonicalNameEvidence": "we introduce VMetaphor-Bench, the first benchmark for evaluating visual metaphor generation in T2I models.", "canonicalNameSource": "abstract", "decisionReason": "The paper explicitly introduces a named benchmark with a defined evaluation objective and implies a scoring protocol, and the arXiv paper itself provides a public path to inspect the benchmark.", "model": "deepseek-v4-pro", "reviewedAt": "2026-09-04T00:46:59.007339Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates text-to-image models on their ability to generate images that convey visual metaphors, using a set of metaphor prompts and comparative scoring.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "score_submission", "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 VMetaphor-Bench, the first benchmark for evaluating visual metaphor generation in T2I models."}, "familyId": "bmf_16825944a476", "firstSeenAt": "2026-09-03", "heat": null, "id": "bm_vmetaphor-bench_19432c0c", "indexedAt": "2026-09-03T00:55:28.123857Z", "industrySectors": [], "links": {"code": null, "data": null, "paper": "https://arxiv.org/abs/2609.02502", "pdf": "https://arxiv.org/pdf/2609.02502", "project": null, "report": "https://arxiv.org/abs/2609.02502"}, "metrics": [], "motivation": "Text-to-image (T2I) models have achieved remarkable success at faithfully rendering specified objects and attributes, yet their ability to produce visual metaphors, images that convey abstract ideas by combining elements from two distinct domains, remains largely unexamined.", "name": "VMetaphor-Bench", "oneLine": "Evaluates text-to-image models on their ability to generate images that convey visual metaphors, using a set of metaphor prompts and comparative scoring.", "paperTitle": "Blending Concepts: Benchmarking Visual Metaphor Generation in Text-to-Image Models", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2609.02502", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-09-03T00:55:28.123857Z"}, "publications": [], "ranking": {"30d": {"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": 30}, "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}, "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}, "today": {"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": 1, "historyDate": "2026-09-02", "rank": null, "score": null, "windowDays": 1}, "level": {"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}, "llmAttentionForecast": {"maxContribution": 0.25, "percentile": 0.2, "role": "bonus", "value": 20}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": 5}, "method": "attention-ranking-v13", "rank": null, "score": 5}}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-09-02", "source": {"authors": ["Chuer Chen", "Zichen Wang", "Yi He", "Zhengxi Yu", "Nan Cao"], "categories": ["cs.CV", "cs.AI"], "id": "2609.02502", "title": "Blending Concepts: Benchmarking Visual Metaphor Generation in Text-to-Image Models", "type": "arxiv", "url": "https://arxiv.org/abs/2609.02502"}, "sourceUpdatedAt": "2026-09-02T12:07:39Z", "topics": ["cs.CV"], "venueAttempts": [], "whyItMatters": "Visual metaphor generation is underexplored in T2I evaluation; this benchmark provides a repeatable way to compare models on creative conceptual blending."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
