{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.05485", "kind": "paper", "url": "https://arxiv.org/abs/2608.05485"}, {"kind": "website", "url": "https://zzzmyyzeng.github.io/VideoArgus"}], "categories": ["General AI", "Vision & 3D", "cs.CV"], "description": {"en": "Evaluates video generation and editing across five settings using agent-generated rubrics that score candidates with criterion-specific evidence and diagnostic reports."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.05485", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.05485", "title": "VideoArgus-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.05485", "modality": null, "name": "VideoArgus-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": "true", "origin_record_id": "bm_videoargus-bench_f3e24463", "origin_source": "arxiv", "recognition_confidence": "0.55", "record_sha256": "88421545477d84be112a16a728019ca474ef075b1a31a5ad196c99368fc6f8aa", "relation": "evaluates_only", "review_model": "deepseek-v4-pro", "review_state": "ai-reviewed", "reviewed_at": "2026-09-06T08:45:23.913416Z", "source_url": "https://arxiv.org/abs/2608.05485"}, "publisher": null, "released": "2026-08-06", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.05485", "source_url": "https://arxiv.org/abs/2608.05485"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-05485", "source": "claire_radar", "source_benchmark_id": "2608.05485", "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/zzzmyyzeng/VideoArgus", "githubScope": "benchmark_repo", "githubStars": 9, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 3, "hfPaperUrl": "https://huggingface.co/papers/2608.05485", "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": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}}, "status": "fresh"}, "attentionForecast": {"confidence": "Medium", "horizon": "7d", "reason": "The unified video generation and editing scope with released artifacts likely attracts moderate attention from multimodal evaluation researchers.", "score": 62}, "capabilities": [], "confidence": "Medium", "construction": "Transform Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-06T08:45:23.913416Z", "inputHash": "bc7bec8887f9de1416f231bcf8c59f2a7e7b27f5078be2138e4109a1f9678ff0", "model": "deepseek-v4-pro"}, "curation": {"canonicalNameEvidence": "We further construct VideoArgus-Bench, containing 1,026 curated input instances", "canonicalNameSource": "abstract", "decisionReason": "Explicitly releases frozen benchmark rubrics and all code/data, providing a reusable evaluation protocol for five video tasks.", "model": "deepseek-v4-pro", "reviewedAt": "2026-09-06T08:45:23.913416Z", "state": "ai-reviewed"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates video generation and editing across five settings using agent-generated rubrics that score candidates with criterion-specific evidence and diagnostic reports.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["exact named benchmark artifact released in abstract", "evaluation protocol evidence", "public artifact URL", "named entity is a model, method, framework, or dataset used in evaluation"], "snippet": "We further construct VideoArgus-Bench, containing 1,026 curated input instances built from 653 high-quality images and 416 high-quality videos, with all benchmark rubrics pre-generated, frozen, and released."}, "familyId": "bmf_6e9794b854e8", "firstSeenAt": "2026-08-19", "heat": null, "id": "bm_videoargus-bench_f3e24463", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "paper": "https://arxiv.org/abs/2608.05485", "pdf": "https://arxiv.org/pdf/2608.05485", "project": "https://zzzmyyzeng.github.io/VideoArgus", "report": "https://arxiv.org/abs/2608.05485"}, "metrics": [], "motivation": "Evaluating generated videos remains challenging because existing benchmarks rely on fixed evaluation content, cover only a subset of generation and editing settings, and provide limited evidence for their scores.", "name": "VideoArgus-Bench", "oneLine": "Evaluates video generation and editing across five settings using agent-generated rubrics that score candidates with criterion-specific evidence and diagnostic reports.", "paperTitle": "VideoArgus: Agentic Rubric-Grounded Unified Evaluation for Video Generation and Editing", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.05485", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-08-19T11:05:13.395391Z"}, "publications": [], "publishers": [{"name": "VideoArgus project team", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://zzzmyyzeng.github.io/VideoArgus"}], "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": 0.30735371836622627, "value": 9}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": 0.24495074076910422, "value": 3}}, "confidence": "Medium", "coverage": 0.7, "rank": 183, "score": 36}, "method": "attention-ranking-v13", "rank": 183, "score": 36}}, "readiness": "Paper only", "recognitionConfidence": 0.55, "relation": "evaluates_only", "releasedAt": "2026-08-06", "source": {"authors": ["Ziyun Zeng and Zixuan Wang and Yongsheng Yu and Hang Hua and Jiebo Luo"], "categories": ["cs.CV"], "id": "2608.05485", "title": "VideoArgus: Agentic Rubric-Grounded Unified Evaluation for Video Generation and Editing", "type": "arxiv", "url": "https://arxiv.org/abs/2608.05485"}, "sourceUpdatedAt": "2026-08-06T00:28:38Z", "topics": ["cs.CV"], "venueAttempts": [], "whyItMatters": "Supplies a frozen rubric set and released code/data, enabling comparable, evidence-grounded evaluation beyond fixed content benchmarks."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
