{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.01869", "kind": "paper", "url": "https://arxiv.org/abs/2606.01869"}, {"kind": "website", "url": "https://anonymous.4open.science/r/WorldCoder-Bench/"}], "authors": ["Shuo Lu", "Yinuo Xu", "Kecheng Yu", "Siru Jiang", "Yongcan Yu", "Yubin Wang", "Haitao Yang", "Yuxiang Zhang", "Bin Wang", "Ran He", "Jian Liang"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.01869", "source_url": "https://arxiv.org/abs/2606.01869"}, "categories": ["General AI", "Geometric reasoning", "Vision & 3D", "cs.AI"], "description": {"en": "Evaluates autonomous physically grounded 3D world synthesis from natural language, with 2,026 expert-curated tasks across Simulation, Rendering, and Application scenarios, using execution-based verification via StateProbe to check hidden behavioral contracts over runtime states."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.01869", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.01869", "title": "WorldCoder-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Huawei Technologies (China)"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.01869", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.01869", "source_url": "https://openalex.org/W7163197567"}, "key": "claire-radar:2606.01869", "modality": null, "name": "WorldCoder-Bench", "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_worldcoder-bench_8f868de5", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "64d78574e6c41ca7707211ae8ede6bf97a898526e31c480e3d1dfd5c2223ff74", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.01869"}, "publisher": null, "released": "2026-06-01", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.01869", "source_url": "https://arxiv.org/abs/2606.01869"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-01869", "source": "claire_radar", "source_benchmark_id": "2606.01869", "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": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 2, "hfPaperUrl": "https://huggingface.co/papers/2606.01869", "observedAt": "2026-10-04T03:02:42.754940Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "lastSuccessfulDate": "2026-09-30", "state": "stale"}}, "status": "stale"}, "capabilities": ["Geometric reasoning"], "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": "3227ed109d8f98090ac73e1e2cd973521870dd9ffe97c2ac2216641c779ad4bb", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates autonomous physically grounded 3D world synthesis from natural language, with 2,026 expert-curated tasks across Simulation, Rendering, and Application scenarios, using execution-based verification via StateProbe to check hidden behavioral contracts over runtime states.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence", "evaluation protocol evidence", "public artifact URL"], "snippet": "We introduce WorldCoder-Bench, a benchmark for autonomous, physically grounded 3D world synthesis."}, "familyId": "bmf_46b10b77b482", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_worldcoder-bench_8f868de5", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.01869", "paper": "https://arxiv.org/abs/2606.01869", "pdf": "https://arxiv.org/pdf/2606.01869", "project": "https://anonymous.4open.science/r/WorldCoder-Bench/", "report": "https://arxiv.org/abs/2606.01869"}, "metrics": [], "motivation": "Large language models (LLMs) are increasingly asked not only to write static interfaces, but to construct executable interactive worlds from natural language.", "name": "WorldCoder-Bench", "oneLine": "Evaluates autonomous physically grounded 3D world synthesis from natural language, with 2,026 expert-curated tasks across Simulation, Rendering, and Application scenarios, using execution-based verification via StateProbe to check hidden behavioral contracts over runtime states.", "paperTitle": "WorldCoder-Bench: Benchmarking Physically Grounded 3D World Synthesis", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.01869", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "WorldCoder-Bench team", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://anonymous.4open.science/r/WorldCoder-Bench/"}], "ranking": {}, "readiness": "Inspectable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-01", "source": {"authors": ["Shuo Lu", "Yinuo Xu", "Kecheng Yu", "Siru Jiang", "Yongcan Yu", "Yubin Wang", "Haitao Yang", "Yuxiang Zhang", "Bin Wang", "Ran He", "Jian Liang"], "categories": ["cs.AI"], "id": "2606.01869", "title": "WorldCoder-Bench: Benchmarking Physically Grounded 3D World Synthesis", "type": "arxiv", "url": "https://arxiv.org/abs/2606.01869"}, "sourceUpdatedAt": "2026-06-08T11:47:41Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "Existing web-generation benchmarks observe only pixels or DOM nodes, missing the mechanics of Three.js worlds inside canvas elements. This benchmark provides a protocol for verifying hidden contracts, enabling assessment of correctness-adjusted cost and time efficiency for 3D world synthesis."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
