{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.14718", "kind": "paper", "url": "https://arxiv.org/abs/2608.14718"}, {"id": "gh:zfkarl/videogaia", "kind": "repo", "url": "https://github.com/zfkarl/VideoGAIA"}], "authors": ["Fan Zhang", "Guangming Yao", "Jinyang Wu", "Hao Wu", "Zheng Lian", "Xinyu Geng", "Jingdong Chen", "Yi Yuan", "Pheng-Ann Heng"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.14718", "source_url": "https://arxiv.org/abs/2608.14718"}, "categories": ["General AI", "Vision & 3D", "cs.CV"], "description": {"en": "VideoGAIA evaluates agentic video understanding through multi-turn, tool-augmented interactions where models must iteratively perceive videos, invoke external tools, and integrate multimodal evidence. It contains 271 human-verified tasks across diverse real-world scenarios."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.14718", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.14718", "title": "VideoGAIA"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.14718", "modality": null, "name": "VideoGAIA", "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_videogaia_c89526e7", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "1b0864ab81fcc245fc627de2068e20ed365c425b490ccafd9f51afe74554563e", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2608.14718"}, "publisher": null, "released": "2026-08-12", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.14718", "source_url": "https://arxiv.org/abs/2608.14718"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-14718", "source": "claire_radar", "source_benchmark_id": "2608.14718", "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/zfkarl/VideoGAIA", "githubScope": "benchmark_repo", "githubStars": 105, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 11, "hfPaperUrl": "https://huggingface.co/papers/2608.14718", "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": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "7d365d3edbf1067bad146b71b70188fdbdf07060e1d52b2a5e61a2de2f371938", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "VideoGAIA evaluates agentic video understanding through multi-turn, tool-augmented interactions where models must iteratively perceive videos, invoke external tools, and integrate multimodal evidence. It contains 271 human-verified tasks across diverse real-world scenarios.", "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": "Towards this end, we introduce VideoGAIA, an agentic video understanding benchmark for general artificial intelligence (AI) assistants."}, "familyId": "bmf_be79630d2651", "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/zfkarl/VideoGAIA", "url": "https://github.com/zfkarl/VideoGAIA"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/zfkarl/VideoGAIA", "url": "https://huggingface.co/papers/2608.14718"}], "scope": "benchmark_repo", "url": "https://github.com/zfkarl/VideoGAIA", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_videogaia_c89526e7", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/zfkarl/VideoGAIA", "data": null, "hfPaper": "https://huggingface.co/papers/2608.14718", "paper": "https://arxiv.org/abs/2608.14718", "pdf": "https://arxiv.org/pdf/2608.14718", "project": null, "report": "https://arxiv.org/abs/2608.14718"}, "metrics": [], "motivation": "Video understanding is a fundamental task for evaluating the capabilities of multimodal large language models (MLLMs).", "name": "VideoGAIA", "oneLine": "VideoGAIA evaluates agentic video understanding through multi-turn, tool-augmented interactions where models must iteratively perceive videos, invoke external tools, and integrate multimodal evidence. It contains 271 human-verified tasks across diverse real-world scenarios.", "paperTitle": "VideoGAIA: A Benchmark for General AI Assistants on Agentic Video Understanding", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.14718", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "Karl28", "organizationType": "community", "role": "benchmark-publisher", "sourceUrl": "https://github.com/zfkarl/VideoGAIA"}], "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": 0.6224852885180543, "value": 105}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": 0.4390696100905538, "value": 11}}, "confidence": "Medium", "coverage": 0.7, "rank": 27, "score": 56}, "method": "attention-ranking-v13", "rank": 27, "score": 56}}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-08-12", "source": {"authors": ["Fan Zhang", "Guangming Yao", "Jinyang Wu", "Hao Wu", "Zheng Lian", "Xinyu Geng", "Jingdong Chen", "Yi Yuan", "Pheng-Ann Heng"], "categories": ["cs.CV", "cs.CL"], "id": "2608.14718", "title": "VideoGAIA: A Benchmark for General AI Assistants on Agentic Video Understanding", "type": "arxiv", "url": "https://arxiv.org/abs/2608.14718"}, "sourceUpdatedAt": "2026-08-12T03:24:44Z", "topics": ["cs.CV"], "venueAttempts": [], "whyItMatters": "Conventional single-turn video understanding benchmarks are becoming saturated; VideoGAIA moves beyond to assess advanced MLLMs' ability to act as general AI assistants, using tools to gather complementary information across turns. It provides a timely, challenging benchmark for next-generation video understanding."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
