{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.29711", "kind": "paper", "url": "https://arxiv.org/abs/2608.29711"}, {"kind": "website", "url": "https://bomiaowang.github.io/DVBench/"}], "authors": ["Bomiao Wang", "Zekai Shao", "Jiexiang Lan", "Xiaoliang Fu", "Xingchen Zeng", "Siming Chen"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.29711", "source_url": "https://arxiv.org/abs/2608.29711"}, "categories": ["General AI", "Language & Knowledge", "cs.CL"], "description": {"en": "Evaluates multimodal large language models on data videos that combine dynamic charts and structured narratives."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.29711", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.29711", "title": "DVBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.29711", "modality": null, "name": "DVBench", "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": "false", "origin_record_id": "bm_dvbench_8df5362a", "origin_source": "arxiv", "recognition_confidence": "0.95", "record_sha256": "ef54caa0cb5554b9910acee1822ede707ea156783517dcfb355be93bb0976518", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-name-audit-deferred", "reviewed_at": "2026-09-03T00:59:34.317835Z", "source_url": "https://arxiv.org/abs/2608.29711"}, "publisher": null, "released": "2026-08-30", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.29711", "source_url": "https://arxiv.org/abs/2608.29711"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-29711", "source": "claire_radar", "source_benchmark_id": "2608.29711", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Language & Knowledge", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/BomiaoWang/DVBench", "githubScope": "benchmark_repo", "githubStars": 1, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 0, "hfPaperUrl": "https://huggingface.co/papers/2608.29711", "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": "2026-10-01", "state": "stale"}}, "status": "fresh"}, "attentionForecast": {"confidence": "Low", "horizon": "7d", "reason": "The benchmark targets an emerging niche of data video understanding for MLLMs, which may attract moderate interest in the multimodal benchmark community.", "score": 35}, "capabilities": [], "confidence": "High", "construction": "Transform Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-03T00:59:34.317835Z", "inputHash": "64808908f76a8f9104412a5b7da4586b9f134476ae081314470d23d471dccb42", "model": "deepseek-v4-pro"}, "curation": {"canonicalNameEvidence": "We introduce DVBench, a benchmark for evaluating MLLMs on data videos", "canonicalNameSource": "abstract", "decisionReason": "Artifact evidence is empty and no stable scoring contract or public reuse path is described, so the benchmark cannot be confirmed as formally released.", "model": "deepseek-v4-pro", "reviewedAt": "2026-09-03T00:59:34.317835Z", "state": "ai-name-audit-deferred"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates multimodal large language models on data videos that combine dynamic charts and structured narratives.", "displayEligible": false, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "score_submission", "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence", "public artifact URL"], "snippet": "To address this gap, we introduce DVBench, a benchmark for evaluating MLLMs on data videos, a storytelling medium that integrates dynamic charts with structured narratives."}, "familyId": "bmf_d3ece561af98", "firstSeenAt": "2026-09-01", "heat": null, "id": "bm_dvbench_8df5362a", "indexedAt": "2026-09-01T06:28:29.895112Z", "industrySectors": [], "links": {"code": null, "data": null, "paper": "https://arxiv.org/abs/2608.29711", "pdf": "https://arxiv.org/pdf/2608.29711", "project": "https://bomiaowang.github.io/DVBench/", "report": "https://arxiv.org/abs/2608.29711"}, "metrics": [], "motivation": "While MLLMs have made significant strides in chart comprehension and video understanding, current evaluations largely isolate these capabilities, leaving a critical gap in understanding temporally evolving structured visual information.", "name": "DVBench", "oneLine": "Evaluates multimodal large language models on data videos that combine dynamic charts and structured narratives.", "paperTitle": "DVBench: Benchmarking MLLMs for Understanding Dynamic Charts and Narratives in Data Videos", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.29711", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-09-01T06:28:29.895112Z"}, "publications": [], "ranking": {"90d": {"confidence": "Medium", "coverage": 0.7, "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": 0.09252268850709358, "value": 1}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": 0.0, "value": 0}}, "confidence": "Medium", "coverage": 0.7, "rank": 553, "score": 20}, "method": "attention-ranking-v13", "rank": 553, "score": 20}}, "readiness": "Paper only", "recognitionConfidence": 0.95, "relation": "introduces", "releasedAt": "2026-08-30", "source": {"authors": ["Bomiao Wang", "Zekai Shao", "Jiexiang Lan", "Xiaoliang Fu", "Xingchen Zeng", "Siming Chen"], "categories": ["cs.CL"], "id": "2608.29711", "title": "DVBench: Benchmarking MLLMs for Understanding Dynamic Charts and Narratives in Data Videos", "type": "arxiv", "url": "https://arxiv.org/abs/2608.29711"}, "sourceUpdatedAt": "2026-08-30T10:38:29Z", "topics": ["cs.CL"], "venueAttempts": [], "whyItMatters": "Addresses the lack of evaluation resources for video-based data storytelling comprehension by multimodal models."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
