{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.09573", "kind": "paper", "url": "https://arxiv.org/abs/2608.09573"}], "authors": ["Jiajun Xu", "Yanghao Zhou", "Jingyun Liao", "Yu Bai", "Jinxing Zhou", "Chengliang Liu", "Changsen Yuan", "Bo Wang", "Qian Liu"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.09573", "source_url": "https://arxiv.org/abs/2608.09573"}, "categories": ["General AI", "Vision & 3D", "cs.CV"], "description": {"en": "Evaluates video-grounded diagnostic understanding of one-shot website generation. Approximately 1.7K Video QA instances from 6,338 verified failures across semantic-logical, visual-motion, structural-temporal, and functional categories. Scoring is based on model accuracy in multi-agent system V2Lens compared against baseline Video MLLMs."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.09573", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.09573", "title": "VideoVIBE"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.09573", "modality": null, "name": "VideoVIBE", "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_videovibe_8a828619", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "ea87b908ebeacf88d608adb79d43df96f9d3d9749b91105888771ad97a684ad6", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2608.09573"}, "publisher": null, "released": "2026-08-10", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.09573", "source_url": "https://arxiv.org/abs/2608.09573"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-09573", "source": "claire_radar", "source_benchmark_id": "2608.09573", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Mixed", "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/2608.09573", "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": "Aggregate Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "d727bd676b33f4f6bb5b9b1547b0e4dad2f8f56b84ca9144f2ef0d368c35acd7", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates video-grounded diagnostic understanding of one-shot website generation. Approximately 1.7K Video QA instances from 6,338 verified failures across semantic-logical, visual-motion, structural-temporal, and functional categories. Scoring is based on model accuracy in multi-agent system V2Lens compared against baseline Video MLLMs.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "We introduce VideoVIBE, a video-grounded benchmark that transforms human-operated webpage recordings into fine-grained diagnostic tasks."}, "familyId": "bmf_58daaf002b88", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_videovibe_8a828619", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2608.09573", "paper": "https://arxiv.org/abs/2608.09573", "pdf": "https://arxiv.org/pdf/2608.09573", "project": null, "report": "https://arxiv.org/abs/2608.09573"}, "metrics": [], "motivation": "Natural-language-driven \"vibe coding\" enables the one-shot generation of visually rich and interactive web applications, yet reliable assessment of their quality has not kept pace.", "name": "VideoVIBE", "oneLine": "Evaluates video-grounded diagnostic understanding of one-shot website generation. Approximately 1.7K Video QA instances from 6,338 verified failures across semantic-logical, visual-motion, structural-temporal, and functional categories. Scoring is based on model accuracy in multi-agent system V2Lens compared against baseline Video MLLMs.", "paperTitle": "VideoVIBE: A Video-Grounded Diagnostic Benchmark for One-Shot Interactive Website Generation", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.09573", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "arXiv", "organizationType": "community", "role": "benchmark-publisher", "sourceUrl": "https://arxiv.org/abs/2608.09573"}], "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": "2026-08-10", "source": {"authors": ["Jiajun Xu", "Yanghao Zhou", "Jingyun Liao", "Yu Bai", "Jinxing Zhou", "Chengliang Liu", "Changsen Yuan", "Bo Wang", "Qian Liu"], "categories": ["cs.CV"], "id": "2608.09573", "title": "VideoVIBE: A Video-Grounded Diagnostic Benchmark for One-Shot Interactive Website Generation", "type": "arxiv", "url": "https://arxiv.org/abs/2608.09573"}, "sourceUpdatedAt": "2026-08-10T13:07:40Z", "topics": ["cs.CV"], "venueAttempts": [], "whyItMatters": "Existing benchmarks often score isolated artifacts or final outcomes, lacking diagnostic insight. This benchmark provides a repeatable protocol to assess failure modes in generated webpages, enabling targeted model improvements for interactive website generation."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
