{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.08036", "kind": "paper", "url": "https://arxiv.org/abs/2606.08036"}], "authors": ["Zongrng Li", "Mingzheng Yang", "Lei Zou", "Hongxu Ma", "Hao Tian", "Siqi Zhou", "Wenjing Gong", "Kaili Zhang", "Bingqian Chen", "Mitch Zhang", "Yifan Yang"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.08036", "source_url": "https://arxiv.org/abs/2606.08036"}, "categories": ["General AI", "Language & Knowledge", "cs.IR"], "description": {"en": "GIScholarBench evaluates LLM overconfidence in GIS research across three tasks: metadata retrieval, literature linking, and research direction generation, using 10,865 papers from 25 GIScience journals."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.08036", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.08036", "title": "GIScholarBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Texas A&M University", "Google (United States)", "Texas A&M University System", "Texas College"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.08036", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.08036", "source_url": "https://openalex.org/W7163994139"}, "key": "claire-radar:2606.08036", "modality": null, "name": "GIScholarBench", "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_gischolarbench_a6158b85", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "5fab6a5f5941831d46e607196cf3801e344639fbf01d01bae2df270b9aebc26b", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.08036"}, "publisher": null, "released": "2026-06-06", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.08036", "source_url": "https://arxiv.org/abs/2606.08036"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-08036", "source": "claire_radar", "source_benchmark_id": "2606.08036", "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/2606.08036", "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": [], "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": "1db69c2d5bb190d6d8d9398e0a81157fa3e6add49640ed2634fca67489141dcc", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "GIScholarBench evaluates LLM overconfidence in GIS research across three tasks: metadata retrieval, literature linking, and research direction generation, using 10,865 papers from 25 GIScience journals.", "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 examine this issue, we introduce GIScholarBench, a benchmark built from 10,865 papers published in 25 core GIScience journals between 2020 and 2025."}, "familyId": "bmf_373e6eeda3f2", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_gischolarbench_a6158b85", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.08036", "paper": "https://arxiv.org/abs/2606.08036", "pdf": "https://arxiv.org/pdf/2606.08036", "project": null, "report": "https://arxiv.org/abs/2606.08036"}, "metrics": [], "motivation": "Large language models (LLMs) are increasingly used in academic research workflows, but scholarly tasks require high factual precision and therefore expose a key weakness: overconfidence.", "name": "GIScholarBench", "oneLine": "GIScholarBench evaluates LLM overconfidence in GIS research across three tasks: metadata retrieval, literature linking, and research direction generation, using 10,865 papers from 25 GIScience journals.", "paperTitle": "GIScholarBench: Benchmarking LLM Overconfidence in GIS Research", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.08036", "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": "2026-06-06", "source": {"authors": ["Zongrng Li", "Mingzheng Yang", "Lei Zou", "Hongxu Ma", "Hao Tian", "Siqi Zhou", "Wenjing Gong", "Kaili Zhang", "Bingqian Chen", "Mitch Zhang", "Yifan Yang"], "categories": ["cs.IR", "cs.AI", "cs.CL"], "id": "2606.08036", "title": "GIScholarBench: Benchmarking LLM Overconfidence in GIS Research", "type": "arxiv", "url": "https://arxiv.org/abs/2606.08036"}, "sourceUpdatedAt": "2026-06-06T07:56:40Z", "topics": ["cs.IR"], "venueAttempts": [], "whyItMatters": "It addresses the need for benchmarks that assess factual accuracy and overconfidence in scholarly AI applications, providing a basis for evaluating LLM reliability in research workflows."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
