{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2605.25461", "kind": "paper", "url": "https://arxiv.org/abs/2605.25461"}, {"id": "gh:icip-cas/metaphorvu", "kind": "repo", "url": "https://github.com/icip-cas/MetaphorVU"}], "authors": ["Zhuoqun Li", "Boxi Cao", "Guiping Jiang", "Fangrui Lv", "Ruotong Pan", "Jianan Wang", "Xiangyu Wu", "Hongyu Lin", "Yaojie Lu", "Yong Du", "Ruyin Jia", "Liyan", "Tingting Gao", "Han Li", "Xianpei Han", "Le Sun"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2605.25461", "source_url": "https://arxiv.org/abs/2605.25461"}, "categories": ["General AI", "Vision & 3D", "cs.CV"], "description": {"en": "MetaphorVU-Bench evaluates metaphorical video understanding in multimodal LLMs through tasks requiring cross-domain mapping, with a benchmark dataset and evaluation code publicly available."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2605.25461", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2605.25461", "title": "MetaphorVU-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2605.25461", "modality": null, "name": "MetaphorVU-Bench", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "Medium", "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_metaphorvu-bench_ab9e08cf", "origin_source": "arxiv", "recognition_confidence": "0.85", "record_sha256": "57818977d6b98431f1ee98b92f502af5d4d750484d1afb20592e72043968a639", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2605.25461"}, "publisher": null, "released": "2026-05-25", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2605.25461", "source_url": "https://arxiv.org/abs/2605.25461"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2605-25461", "source": "claire_radar", "source_benchmark_id": "2605.25461", "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/icip-cas/MetaphorVU", "githubScope": "benchmark_repo", "githubStars": 10, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 5, "hfPaperUrl": "https://huggingface.co/papers/2605.25461", "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": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "d8c0f822677392ee51b5ed37bebe65731cf5117faab044fd4dd0e314e22ce090", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "MetaphorVU-Bench evaluates metaphorical video understanding in multimodal LLMs through tasks requiring cross-domain mapping, with a benchmark dataset and evaluation code publicly available.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact named benchmark artifact released in abstract", "benchmark release stated in one sentence"], "snippet": "To bridge this gap, we propose MetaphorVU-Bench, the first systematic and comprehensive benchmark dedicated to metaphorical video understanding."}, "familyId": "bmf_2f1827922297", "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/icip-cas/MetaphorVU", "url": "https://github.com/icip-cas/MetaphorVU"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/icip-cas/MetaphorVU", "url": "https://huggingface.co/papers/2605.25461"}], "scope": "benchmark_repo", "url": "https://github.com/icip-cas/MetaphorVU", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_metaphorvu-bench_ab9e08cf", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/icip-cas/MetaphorVU", "data": null, "hfPaper": "https://huggingface.co/papers/2605.25461", "paper": "https://arxiv.org/abs/2605.25461", "pdf": "https://arxiv.org/pdf/2605.25461", "project": null, "report": "https://arxiv.org/abs/2605.25461"}, "metrics": [], "motivation": "Metaphorical videos are prevalent across various real-world scenarios to convey complex ideas, and understanding them typically requires high-order cognitive capabilities.", "name": "MetaphorVU-Bench", "oneLine": "MetaphorVU-Bench evaluates metaphorical video understanding in multimodal LLMs through tasks requiring cross-domain mapping, with a benchmark dataset and evaluation code publicly available.", "paperTitle": "MetaphorVU: Towards Metaphorical Video Understanding", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2605.25461", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "MetaphorVU team", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://github.com/icip-cas/MetaphorVU"}], "ranking": {}, "readiness": "Runnable", "recognitionConfidence": 0.85, "relation": "introduces", "releasedAt": "2026-05-25", "source": {"authors": ["Zhuoqun Li", "Boxi Cao", "Guiping Jiang", "Fangrui Lv", "Ruotong Pan", "Jianan Wang", "Xiangyu Wu", "Hongyu Lin", "Yaojie Lu", "Yong Du", "Ruyin Jia", "Liyan", "Tingting Gao", "Han Li", "Xianpei Han", "Le Sun"], "categories": ["cs.CV"], "id": "2605.25461", "title": "MetaphorVU: Towards Metaphorical Video Understanding", "type": "arxiv", "url": "https://arxiv.org/abs/2605.25461"}, "sourceUpdatedAt": "2026-05-25T06:12:19Z", "topics": ["cs.CV"], "venueAttempts": [], "whyItMatters": "It fills the gap of systematic evaluation of high-order cognitive capabilities in video understanding, revealing defects in cross-domain mapping and enabling future improvements."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
