{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2609.01056", "kind": "paper", "url": "https://arxiv.org/abs/2609.01056"}], "authors": ["Leonardo Ranaldi", "Sherrie Shen", "Jushi Kai", "Alexandra Birch"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2609.01056", "source_url": "https://arxiv.org/abs/2609.01056"}, "categories": ["General AI", "Language & Knowledge", "cs.AI"], "description": {"en": "A multilingual benchmark of persona-grounded everyday workflows for agents, evaluated via sandbox actions."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2609.01056", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2609.01056", "title": "WorldBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Shanghai Jiao Tong University", "University of Edinburgh"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2609.01056", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2609.01056", "source_url": "https://openalex.org/W7206175763"}, "key": "claire-radar:2609.01056", "modality": null, "name": "WorldBench", "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": "false", "origin_record_id": "bm_worldbench_7c7f4e1b", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "7701cb0219d412248626be071f10d90c4af86ef64ff0d794c31cc99c3e010a88", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-name-audit-deferred", "reviewed_at": "2026-09-03T00:59:34.317835Z", "source_url": "https://arxiv.org/abs/2609.01056"}, "publisher": null, "released": "2026-09-01", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2609.01056", "source_url": "https://arxiv.org/abs/2609.01056"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2609-01056", "source": "claire_radar", "source_benchmark_id": "2609.01056", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Language & Knowledge", "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": null, "hfPaperUrl": "https://huggingface.co/papers/2609.01056", "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", "state": "unavailable"}}, "status": "unavailable"}, "attentionForecast": {"confidence": "Low", "horizon": "7d", "reason": "The broad multilingual focus may generate interest, but unclear availability and evaluation specifics limit forecast confidence.", "score": 15}, "capabilities": [], "confidence": "High", "construction": "Transform Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-03T00:59:34.317835Z", "inputHash": "cbcb0e41a33372e7974580d87a75bbee3362fb51499be7e4be608a4aaf3a7fdc", "model": "deepseek-v4-pro"}, "curation": {"canonicalNameEvidence": "WorldBench: Culturally Grounded Benchmark for Multilingual Agents", "canonicalNameSource": "paper_title", "decisionReason": "Abstract announces a benchmark but lacks clear scoring contract or public artifact links; deferred pending further evidence.", "model": "deepseek-v4-pro", "reviewedAt": "2026-09-03T00:59:34.317835Z", "state": "ai-name-audit-deferred"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "A multilingual benchmark of persona-grounded everyday workflows for agents, evaluated via sandbox actions.", "displayEligible": false, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "To address these concerns, we present WorldBench: a comprehensive, multilingual benchmark of genuine, persona-grounded everyday workflows, where agents can act in a sandbox via structured actions."}, "familyId": "bmf_365c8ee11b3d", "firstSeenAt": "2026-09-02", "heat": null, "id": "bm_worldbench_7c7f4e1b", "indexedAt": "2026-09-02T05:21:06.631990Z", "industrySectors": [], "links": {"code": null, "data": null, "paper": "https://arxiv.org/abs/2609.01056", "pdf": "https://arxiv.org/pdf/2609.01056", "project": null, "report": "https://arxiv.org/abs/2609.01056"}, "metrics": [], "motivation": "Despite the growing use of LLM-powered agents to solve multi-step tasks in complex environments, existing benchmarks rarely test state preservation, performance across languages, and application to realistic, grounded scenarios.", "name": "WorldBench", "oneLine": "A multilingual benchmark of persona-grounded everyday workflows for agents, evaluated via sandbox actions.", "paperTitle": "WorldBench: Culturally Grounded Benchmark for Multilingual Agents", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2609.01056", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-09-02T05:21:06.631990Z"}, "publications": [], "ranking": {"90d": {"confidence": "Low", "coverage": 0.0, "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": null, "value": null}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": null}, "method": "attention-ranking-v13", "rank": null, "score": null}}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-09-01", "source": {"authors": ["Leonardo Ranaldi", "Sherrie Shen", "Jushi Kai", "Alexandra Birch"], "categories": ["cs.AI", "cs.CL"], "id": "2609.01056", "title": "WorldBench: Culturally Grounded Benchmark for Multilingual Agents", "type": "arxiv", "url": "https://arxiv.org/abs/2609.01056"}, "sourceUpdatedAt": "2026-09-01T10:53:07Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "Aims to cover culturally diverse agent workflows, but requires more evaluation details."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
