{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.01942", "kind": "paper", "url": "https://arxiv.org/abs/2608.01942"}, {"kind": "website", "url": "https://hanxjing.github.io/CultureVidBench/"}], "authors": ["Xianjing Han", "Yuhan Su", "Yang Deng", "Dong Ma", "Wee Peng Tay", "Bin Zhu"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.01942", "source_url": "https://arxiv.org/abs/2608.01942"}, "categories": ["General AI", "Vision & 3D", "cs.CV"], "description": {"en": "CultureVidBench evaluates cultural understanding in text-to-video generation with 1,000 curated prompts covering 12 countries, 6 continents, and 14 cultural aspects. It assesses cultural faithfulness, multimodal cultural rendering, semantic adherence, and perceptual quality using human studies and MLLM-based automatic assessment."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.01942", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.01942", "title": "CultureVidBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.01942", "modality": null, "name": "CultureVidBench", "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_culturevidbench_541d6118", "origin_source": "arxiv", "recognition_confidence": "0.95", "record_sha256": "22a91124978955fd30cf1bba20a6b29caa78b8d231269db156d5c476f1e47e62", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2608.01942"}, "publisher": null, "released": "2026-08-03", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.01942", "source_url": "https://arxiv.org/abs/2608.01942"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-01942", "source": "claire_radar", "source_benchmark_id": "2608.01942", "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/2608.01942", "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": "Transform Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "dfea5ff7823a68eef3254a2a732074b099e2660dc300cc21629a597a347f64b5", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "CultureVidBench evaluates cultural understanding in text-to-video generation with 1,000 curated prompts covering 12 countries, 6 continents, and 14 cultural aspects. It assesses cultural faithfulness, multimodal cultural rendering, semantic adherence, and perceptual quality using human studies and MLLM-based automatic assessment.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence", "public artifact URL"], "snippet": "We introduce CultureVidBench, a comprehensive benchmark for evaluating cultural understanding in T2V generation."}, "familyId": "bmf_3a418ce01d2a", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 1, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "candidates"}, "heat": null, "id": "bm_culturevidbench_541d6118", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2608.01942", "paper": "https://arxiv.org/abs/2608.01942", "pdf": "https://arxiv.org/pdf/2608.01942", "project": "https://hanxjing.github.io/CultureVidBench/", "report": "https://arxiv.org/abs/2608.01942"}, "metrics": [], "motivation": "Text-to-video (T2V) generation models have advanced rapidly, yet their ability to represent diverse cultural contexts remains underexplored.", "name": "CultureVidBench", "oneLine": "CultureVidBench evaluates cultural understanding in text-to-video generation with 1,000 curated prompts covering 12 countries, 6 continents, and 14 cultural aspects. It assesses cultural faithfulness, multimodal cultural rendering, semantic adherence, and perceptual quality using human studies and MLLM-based automatic assessment.", "paperTitle": "CultureVidBench: Benchmarking Cultural Understanding in Text-to-Video Generation", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.01942", "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": "Inspectable", "recognitionConfidence": 0.95, "relation": "introduces", "releasedAt": "2026-08-03", "source": {"authors": ["Xianjing Han", "Yuhan Su", "Yang Deng", "Dong Ma", "Wee Peng Tay", "Bin Zhu"], "categories": ["cs.CV", "cs.CL", "cs.MM"], "id": "2608.01942", "title": "CultureVidBench: Benchmarking Cultural Understanding in Text-to-Video Generation", "type": "arxiv", "url": "https://arxiv.org/abs/2608.01942"}, "sourceUpdatedAt": "2026-08-03T09:16:06Z", "topics": ["cs.CV"], "venueAttempts": [], "whyItMatters": "Existing T2V benchmarks focus on perceptual quality and alignment but neglect cultural representation. CultureVidBench addresses this gap by providing a benchmark for evaluating whether generated videos capture culturally specific details, which is crucial for diverse deployment."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
