{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.03882", "kind": "paper", "url": "https://arxiv.org/abs/2608.03882"}], "authors": ["Martin Böckling", "Elizaveta Nosova", "Heiko Paulheim", "Andreea Iana"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.03882", "source_url": "https://arxiv.org/abs/2608.03882"}, "categories": ["Factuality", "Language & Knowledge", "Logistics & Operations", "Reasoning"], "description": {"en": "MultiGlobeQA evaluates geospatial reasoning in large language models across 46,060 question-answer pairs in 17 languages, covering 14 spatial-function families and 15 answer formats, with ground truth from three knowledge graphs."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.03882", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.03882", "title": "MultiGlobeQA"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.03882", "modality": null, "name": "MultiGlobeQA", "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_multiglobeqa_73949294", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "0fbdb38a2c7f586f29807b61b0abd6d7c2ca00d33238e8f4025968bd69f071c1", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2608.03882"}, "publisher": null, "released": "2026-08-04", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.03882", "source_url": "https://arxiv.org/abs/2608.03882"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-03882", "source": "claire_radar", "source_benchmark_id": "2608.03882", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Machine Generated", "applicationDomains": ["Logistics & Operations"], "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": 0, "hfPaperUrl": "https://huggingface.co/papers/2608.03882", "observedAt": "2026-10-04T15:31:48.030916Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}}, "status": "fresh"}, "capabilities": ["Reasoning", "Factuality"], "confidence": "High", "construction": "Original Synthetic", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "c80cca706fd7ab8e85516160919e62f76cce7721f812ffcf4b00855bed45ae84", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "MultiGlobeQA evaluates geospatial reasoning in large language models across 46,060 question-answer pairs in 17 languages, covering 14 spatial-function families and 15 answer formats, with ground truth from three knowledge graphs.", "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"], "snippet": "We introduce MultiGlobeQA, a multilingual benchmark of 46,060 question-answer pairs spanning 14 spatial-function families and 15 answer formats, with execution-based ground truth over three knowledge graphs."}, "familyId": "bmf_6185f11d15a8", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_multiglobeqa_73949294", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Logistics"], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2608.03882", "paper": "https://arxiv.org/abs/2608.03882", "pdf": "https://arxiv.org/pdf/2608.03882", "project": null, "report": "https://arxiv.org/abs/2608.03882"}, "metrics": [], "motivation": "Geospatial reasoning, i.e., computing distances, containment, and other spatial relations over real-world entities, is central to navigation and logistics, yet large language models (LLMs) struggle with the required geometric and topological computation despite storing considerable geographic knowledge.", "name": "MultiGlobeQA", "oneLine": "MultiGlobeQA evaluates geospatial reasoning in large language models across 46,060 question-answer pairs in 17 languages, covering 14 spatial-function families and 15 answer formats, with ground truth from three knowledge graphs.", "paperTitle": "MultiGlobeQA: A Multilingual and Globally Diverse Benchmark for Geospatial Reasoning", "primaryDomain": "Logistics & Operations", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.03882", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {"90d": {"confidence": "Low", "coverage": 0.15, "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": 0.0, "value": 0}}, "confidence": "Low", "coverage": 0.15, "rank": null, "score": 43}, "method": "attention-ranking-v13", "rank": null, "score": 43}}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-08-04", "source": {"authors": ["Martin B\\\"ockling", "Elizaveta Nosova", "Heiko Paulheim", "Andreea Iana"], "categories": ["cs.CL", "cs.AI", "cs.IR"], "id": "2608.03882", "title": "MultiGlobeQA: A Multilingual and Globally Diverse Benchmark for Geospatial Reasoning", "type": "arxiv", "url": "https://arxiv.org/abs/2608.03882"}, "sourceUpdatedAt": "2026-08-04T16:18:52Z", "topics": ["Reasoning"], "venueAttempts": [], "whyItMatters": "Current geospatial benchmarks are limited in language coverage and geographic control. This benchmark aims to provide a broader, multilingual evaluation to identify specific failures in computational reasoning over geographic knowledge."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
