{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.15890", "kind": "paper", "url": "https://arxiv.org/abs/2606.15890"}, {"id": "gh:axin1301/urbanwell-benchmark", "kind": "repo", "url": "https://github.com/axin1301/UrbanWell-Benchmark"}], "authors": ["Yanxin Xi", "Xiang Su", "Jie Feng", "Yu Liu", "Sasu Tarkoma", "Pan Hui"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.15890", "source_url": "https://arxiv.org/abs/2606.15890"}, "categories": ["General AI", "Multimodal", "Reasoning"], "description": {"en": "UrbanWell provides a dataset and evaluation protocol for assessing spatio-temporal reasoning in multimodal large language models using satellite and street view imagery across 38 cities, covering environmental, accessibility, urban form, vitality, and subjective perception indicators with tasks in static prediction, forecasting, and trend classification."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.15890", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.15890", "title": "UrbanWell"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2606.15890", "modality": null, "name": "UrbanWell", "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_urbanwell_81901465", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "abef71e73dc18df8ac5d7982fc2eec40fdc62b172cdba4b04eec02be66e929ee", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.15890"}, "publisher": null, "released": "2026-06-14", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.15890", "source_url": "https://arxiv.org/abs/2606.15890"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-15890", "source": "claire_radar", "source_benchmark_id": "2606.15890", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Multimodal", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/axin1301/UrbanWell-Benchmark", "githubScope": "benchmark_repo", "githubStars": 5, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 1, "hfPaperUrl": "https://huggingface.co/papers/2606.15890", "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": "2026-10-01", "state": "stale"}}, "status": "fresh"}, "capabilities": ["Reasoning"], "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": "38d41b8df9c86e25edea6a2ba6336fb02203463e7bf4f1b501b2881ba9dd8ec0", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "UrbanWell provides a dataset and evaluation protocol for assessing spatio-temporal reasoning in multimodal large language models using satellite and street view imagery across 38 cities, covering environmental, accessibility, urban form, vitality, and subjective perception indicators with tasks in static prediction, forecasting, and trend classification.", "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 UrbanWell, a large-scale benchmark designed to systematically evaluate the spatio-temporal reasoning capabilities of MLLMs for urban wellbeing analytics through joint modeling of satellite and street view imagery."}, "familyId": "bmf_a905172c1364", "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/axin1301/UrbanWell-Benchmark", "url": "https://github.com/axin1301/UrbanWell-Benchmark"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/axin1301/UrbanWell-Benchmark", "url": "https://huggingface.co/papers/2606.15890"}, {"basis": "linked-from-report", "linkedUrl": "https://github.com/axin1301/UrbanWell-Benchmark", "url": "https://arxiv.org/abs/2606.15890"}, {"basis": "linked-from-report", "linkedUrl": "https://github.com/axin1301/UrbanWell-Benchmark.", "url": "https://arxiv.org/abs/2606.15890"}], "scope": "benchmark_repo", "url": "https://github.com/axin1301/UrbanWell-Benchmark", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_urbanwell_81901465", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/axin1301/UrbanWell-Benchmark", "data": null, "hfPaper": "https://huggingface.co/papers/2606.15890", "paper": "https://arxiv.org/abs/2606.15890", "pdf": "https://arxiv.org/pdf/2606.15890", "project": null, "report": "https://arxiv.org/abs/2606.15890"}, "metrics": [], "motivation": "Understanding urban wellbeing from multimodal data requires integrating heterogeneous spatial and temporal signals, posing significant challenges for current multimodal large language models (MLLMs).", "name": "UrbanWell", "oneLine": "UrbanWell provides a dataset and evaluation protocol for assessing spatio-temporal reasoning in multimodal large language models using satellite and street view imagery across 38 cities, covering environmental, accessibility, urban form, vitality, and subjective perception indicators with tasks in static prediction, forecasting, and trend classification.", "paperTitle": "UrbanWell: Benchmarking Multimodal Large Language Models for Spatio-Temporal Urban Wellbeing Analytics", "primaryDomain": "General AI", "publication": {"evidence": "accepted by KDD Datasets and Benchmarks Track 2026", "evidenceLevel": "author-claim", "evidenceUrl": "https://arxiv.org/abs/2606.15890", "source": "arxiv-comments", "status": "acceptance_claimed", "venue": "KDD Datasets and Benchmarks Track 2026", "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-14", "source": {"authors": ["Yanxin Xi", "Xiang Su", "Jie Feng", "Yu Liu", "Sasu Tarkoma", "Pan Hui"], "categories": ["cs.AI"], "id": "2606.15890", "title": "UrbanWell: Benchmarking Multimodal Large Language Models for Spatio-Temporal Urban Wellbeing Analytics", "type": "arxiv", "url": "https://arxiv.org/abs/2606.15890"}, "sourceUpdatedAt": "2026-06-14T16:19:21Z", "topics": ["Multimodal", "Reasoning"], "venueAttempts": [{"decisionRaw": "accepted by KDD Datasets and Benchmarks Track 2026", "evidence": [{"level": "author-claim", "observedAt": "2026-10-14T01:46:58.058199Z", "rawValue": "accepted by KDD Datasets and Benchmarks Track 2026", "sourceType": "arxiv-comments", "sourceUrl": "https://arxiv.org/abs/2606.15890"}], "reviewStatus": "accepted", "venueName": "KDD Datasets and Benchmarks Track 2026"}], "whyItMatters": "UrbanWell addresses the lack of standardized benchmarks for multimodal urban wellbeing analytics, enabling consistent comparison of MLLMs on tasks requiring joint spatial and temporal understanding. This supports progress in urban intelligence applications such as planning and policy evaluation."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
