{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.02603", "kind": "paper", "url": "https://arxiv.org/abs/2608.02603"}, {"id": "gh:yuxueyang1204/worldexam", "kind": "repo", "url": "https://github.com/YuxueYang1204/worldexam"}, {"kind": "website", "url": "https://WorldExam.github.io"}], "authors": ["Yuxue Yang", "Shuyao Shang", "Jiahe Wang", "Zitong Zhou", "Liang Tan", "Junhan Zeng", "Ruizhi Li", "Junyan Li", "Yu Liu", "Xiao Yang", "Yong Li", "Jun Zhu", "Hongsheng Li", "Tieniu Tan", "Lue Fan", "Zhaoxiang Zhang"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.02603", "source_url": "https://arxiv.org/abs/2608.02603"}, "categories": ["General AI", "Vision & 3D", "cs.CV"], "description": {"en": "WorldExam evaluates controllable video generation models as world models across four levels: Visual Quality, Control Adherence, Spatial Consistency, and World Reactivity, with 1,474 cases across eight tasks."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.02603", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.02603", "title": "WorldExam"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.02603", "modality": null, "name": "WorldExam", "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_worldexam_7f2f166e", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "16f0d81316ca6d357b97c44d6788a5e1cd117d7497c229de053f11102baed03f", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2608.02603"}, "publisher": null, "released": "2026-08-03", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.02603", "source_url": "https://arxiv.org/abs/2608.02603"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-02603", "source": "claire_radar", "source_benchmark_id": "2608.02603", "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/YuxueYang1204/worldexam", "githubScope": "benchmark_repo", "githubStars": 23, "hfDailySubmittedAt": "2026-08-04T00:00:00.000Z", "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 33, "hfPaperUrl": "https://huggingface.co/papers/2608.02603", "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"}, "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": "ad6f7e1c7fa7d00cdeb16255b1471a37c16e556e55fa1f1cef5b11b412f7da0e", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "WorldExam evaluates controllable video generation models as world models across four levels: Visual Quality, Control Adherence, Spatial Consistency, and World Reactivity, with 1,474 cases across eight tasks.", "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", "public artifact URL"], "snippet": "We introduce WorldExam, a hierarchical diagnostic benchmark spanning four levels: Visual Quality, Control Adherence, Spatial Consistency, and World Reactivity."}, "familyId": "bmf_3931c2ca2952", "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/YuxueYang1204/worldexam", "url": "https://github.com/YuxueYang1204/worldexam"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/YuxueYang1204/worldexam", "url": "https://huggingface.co/papers/2608.02603"}, {"basis": "linked-from-project", "linkedUrl": "https://github.com/YuxueYang1204/worldexam", "url": "https://WorldExam.github.io"}], "scope": "benchmark_repo", "url": "https://github.com/YuxueYang1204/worldexam", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_worldexam_7f2f166e", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/YuxueYang1204/worldexam", "data": null, "hfPaper": "https://huggingface.co/papers/2608.02603", "paper": "https://arxiv.org/abs/2608.02603", "pdf": "https://arxiv.org/pdf/2608.02603", "project": "https://WorldExam.github.io", "report": "https://arxiv.org/abs/2608.02603"}, "metrics": [], "motivation": "Controllable video generation models are increasingly being developed as world models.", "name": "WorldExam", "oneLine": "WorldExam evaluates controllable video generation models as world models across four levels: Visual Quality, Control Adherence, Spatial Consistency, and World Reactivity, with 1,474 cases across eight tasks.", "paperTitle": "WorldExam: Benchmarking World Models from Apparent Appearance to Inherent Reactivity", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.02603", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "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": 0.4242130572709284, "value": 23}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": 0.6230888957997812, "value": 33}}, "confidence": "Medium", "coverage": 0.7, "rank": 84, "score": 48}, "method": "attention-ranking-v13", "rank": 84, "score": 48}}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-08-03", "source": {"authors": ["Yuxue Yang", "Shuyao Shang", "Jiahe Wang", "Zitong Zhou", "Liang Tan", "Junhan Zeng", "Ruizhi Li", "Junyan Li", "Yu Liu", "Xiao Yang", "Yong Li", "Jun Zhu", "Hongsheng Li", "Tieniu Tan", "Lue Fan", "Zhaoxiang Zhang"], "categories": ["cs.CV"], "id": "2608.02603", "title": "WorldExam: Benchmarking World Models from Apparent Appearance to Inherent Reactivity", "type": "arxiv", "url": "https://arxiv.org/abs/2608.02603"}, "sourceUpdatedAt": "2026-08-03T17:59:54Z", "topics": ["cs.CV"], "venueAttempts": [], "whyItMatters": "Fills the gap in evaluating inherent world reactivity beyond visual quality and instruction fulfillment, providing a hierarchical diagnostic for model comparison."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
