{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2605.25784", "kind": "paper", "url": "https://arxiv.org/abs/2605.25784"}], "authors": ["Jing Huang", "Duanchu Wang", "Junjie Yang", "Zihang Cheng", "Cheng Li", "Lin Cui", "Zhouyi Wu", "Di Wang"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2605.25784", "source_url": "https://arxiv.org/abs/2605.25784"}, "categories": ["General AI", "Reasoning", "Vision & 3D"], "description": {"en": "VertiCue-Bench evaluates multimodal large language models on geospatial reasoning using canopy height models to resolve 2D ambiguity in remote sensing natural scenes. It includes 1,534 instances across 17 tasks, testing height perception and semantic reasoning."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2605.25784", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2605.25784", "title": "VertiCue-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2605.25784", "modality": null, "name": "VertiCue-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_verticue-bench_6f5c5a90", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "e01402fa62215fb4175ae9f172e3e942c5ff762ef4f82d2bacc3058f23ed981d", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2605.25784"}, "publisher": null, "released": "2026-05-25", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2605.25784", "source_url": "https://arxiv.org/abs/2605.25784"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2605-25784", "source": "claire_radar", "source_benchmark_id": "2605.25784", "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": null, "hfPaperUrl": "https://huggingface.co/papers/2605.25784", "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"}, "capabilities": ["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": "e43330584dc237458c09f246ff95527fc3ae128e63af3a1dc78cbe71fd7b585d", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "VertiCue-Bench evaluates multimodal large language models on geospatial reasoning using canopy height models to resolve 2D ambiguity in remote sensing natural scenes. It includes 1,534 instances across 17 tasks, testing height perception and semantic reasoning.", "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"], "snippet": "To address this gap, we introduce VertiCue-Bench, the first diagnostic benchmark for CHM-grounded geospatial reasoning."}, "familyId": "bmf_fabfbf0a5160", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_verticue-bench_6f5c5a90", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2605.25784", "paper": "https://arxiv.org/abs/2605.25784", "pdf": "https://arxiv.org/pdf/2605.25784", "project": null, "report": "https://arxiv.org/abs/2605.25784"}, "metrics": [], "motivation": "Multimodal Large Language Models (MLLMs) have recently shown promising progress in geospatial reasoning.", "name": "VertiCue-Bench", "oneLine": "VertiCue-Bench evaluates multimodal large language models on geospatial reasoning using canopy height models to resolve 2D ambiguity in remote sensing natural scenes. It includes 1,534 instances across 17 tasks, testing height perception and semantic reasoning.", "paperTitle": "VertiCue-Bench: Diagnosing Whether MLLMs Use Height Cues to Resolve 2D Ambiguity in Remote Sensing Natural Scenes", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2605.25784", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-05-25", "source": {"authors": ["Jing Huang", "Duanchu Wang", "Junjie Yang", "Zihang Cheng", "Cheng Li", "Lin Cui", "Zhouyi Wu", "Di Wang"], "categories": ["cs.CV", "cs.MM"], "id": "2605.25784", "title": "VertiCue-Bench: Diagnosing Whether MLLMs Use Height Cues to Resolve 2D Ambiguity in Remote Sensing Natural Scenes", "type": "arxiv", "url": "https://arxiv.org/abs/2605.25784"}, "sourceUpdatedAt": "2026-05-25T12:30:33Z", "topics": ["Reasoning"], "venueAttempts": [], "whyItMatters": "Current remote sensing benchmarks are mostly 2D-centric, failing in environments with spectral confusion. This benchmark addresses the gap of whether models can leverage vertical cues for semantic disambiguation, providing insights into geometry-to-semantics reasoning in MLLMs."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
