{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.00793", "kind": "paper", "url": "https://arxiv.org/abs/2606.00793"}, {"id": "gh:study-overflow/mbench", "kind": "repo", "url": "https://github.com/study-overflow/MBench"}, {"kind": "website", "url": "https://peanutup.github.io/MBench-project/"}], "authors": ["Shengjun Zhang", "Zhang Zhang", "Simin Huang", "Zhenyu Tang", "Hanyang Wang", "Chensheng Dai", "Min Chen", "Yifan Li", "Yuxin Li", "Yingjie Chen", "Hao Liu", "Chen Li", "Jing Lyu", "Yueqi Duan"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.00793", "source_url": "https://arxiv.org/abs/2606.00793"}, "categories": ["General AI", "Vision & 3D", "cs.CV"], "description": {"en": "MBench is a benchmark for memory capability of video world models, decomposing into entity, environment, and causal consistency with 12 sub-dimensions. Includes code, dataset, and leaderboard."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.00793", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.00793", "title": "MBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2606.00793", "modality": null, "name": "MBench", "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_mbench_6b4d0471", "origin_source": "arxiv", "recognition_confidence": "0.95", "record_sha256": "9228587f00eb373c1b43aa0d3a022f09eb120fab534e22ebc7ed665f934b0ff5", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.00793"}, "publisher": null, "released": "2026-05-30", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.00793", "source_url": "https://arxiv.org/abs/2606.00793"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-00793", "source": "claire_radar", "source_benchmark_id": "2606.00793", "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/study-overflow/MBench", "githubScope": "benchmark_repo", "githubStars": 117, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 11, "hfPaperUrl": "https://huggingface.co/papers/2606.00793", "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": "Transform Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "4dd57fe4a8e34045c4559d47bf92d0d04c3fa4113f3cf8c0d5a3442c3930d75b", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "MBench is a benchmark for memory capability of video world models, decomposing into entity, environment, and causal consistency with 12 sub-dimensions. Includes code, dataset, and leaderboard.", "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": "To address this gap, we present \\textbf{MBench}, a comprehensive benchmark dedicated to quantifying and evaluating the memory capability of video world models."}, "familyId": "bmf_5facad24d801", "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/study-overflow/MBench", "url": "https://github.com/study-overflow/MBench"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/study-overflow/MBench", "url": "https://huggingface.co/papers/2606.00793"}, {"basis": "linked-from-project", "linkedUrl": "https://github.com/study-overflow/MBench", "url": "https://peanutup.github.io/MBench-project/"}, {"basis": "linked-from-project", "linkedUrl": "https://github.com/study-overflow/MBench.git", "url": "https://peanutup.github.io/MBench-project/"}], "scope": "benchmark_repo", "url": "https://github.com/study-overflow/MBench", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_mbench_6b4d0471", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/study-overflow/MBench", "data": null, "hfPaper": "https://huggingface.co/papers/2606.00793", "paper": "https://arxiv.org/abs/2606.00793", "pdf": "https://arxiv.org/pdf/2606.00793", "project": "https://peanutup.github.io/MBench-project/", "report": "https://arxiv.org/abs/2606.00793"}, "metrics": [], "motivation": "Recent advancements in video-based world models have demonstrated an unprecedented ability to synthesize high-fidelity visual sequences.", "name": "MBench", "oneLine": "MBench is a benchmark for memory capability of video world models, decomposing into entity, environment, and causal consistency with 12 sub-dimensions. Includes code, dataset, and leaderboard.", "paperTitle": "MBench: A Comprehensive Benchmark on Memory Capability for Video World Models", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.00793", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Runnable", "recognitionConfidence": 0.95, "relation": "introduces", "releasedAt": "2026-05-30", "source": {"authors": ["Shengjun Zhang", "Zhang Zhang", "Simin Huang", "Zhenyu Tang", "Hanyang Wang", "Chensheng Dai", "Min Chen", "Yifan Li", "Yuxin Li", "Yingjie Chen", "Hao Liu", "Chen Li", "Jing Lyu", "Yueqi Duan"], "categories": ["cs.CV"], "id": "2606.00793", "title": "MBench: A Comprehensive Benchmark on Memory Capability for Video World Models", "type": "arxiv", "url": "https://arxiv.org/abs/2606.00793"}, "sourceUpdatedAt": "2026-06-08T08:58:38Z", "topics": ["cs.CV"], "venueAttempts": [], "whyItMatters": "Fills the gap in evaluating long-term state retention in video world models, providing a standardized benchmark to advance the field."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
