{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.10460", "kind": "paper", "url": "https://arxiv.org/abs/2606.10460"}], "authors": ["Haonan Wang", "Jiaxiang Liu", "Yurong Liu", "Austin Senna Wijaya", "Tianle Zhou", "Eden Wu", "Yijia Chen", "Wanting You", "Reya Vir", "Daniela Pinto", "Grace Fan", "Yusen Zhang", "Juliana Freire", "Eugene Wu"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.10460", "source_url": "https://arxiv.org/abs/2606.10460"}, "categories": ["General AI", "Language & Knowledge", "Reasoning"], "description": {"en": "LakeQA evaluates search-centric question answering over a 9.5 TB data lake of Wikipedia and government data. Tasks require multi-hop reasoning across heterogeneous structured and unstructured sources, with expert-annotated answers."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.10460", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.10460", "title": "LakeQA"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Columbia International University", "University of Missouri", "Columbia University", "Barnard College", "New York University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.10460", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.10460", "source_url": "https://openalex.org/W7164159198"}, "key": "claire-radar:2606.10460", "modality": null, "name": "LakeQA", "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_lakeqa_b77b7993", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "22142bd9869226c6b5ab1bb48e7d463f7d835469dcbf3a4ab8bb0e052072799c", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.10460"}, "publisher": null, "released": "2026-06-09", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.10460", "source_url": "https://arxiv.org/abs/2606.10460"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-10460", "source": "claire_radar", "source_benchmark_id": "2606.10460", "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/2606.10460", "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": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "b3684db45f5e76dcb55cae665a8c38bf62640d81127db03fd9d426e64b9d8c86", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "LakeQA evaluates search-centric question answering over a 9.5 TB data lake of Wikipedia and government data. Tasks require multi-hop reasoning across heterogeneous structured and unstructured sources, with expert-annotated answers.", "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": "To this end, we introduce LakeQA, a comprehensive benchmark for search-centric question answering over data lakes that jointly emphasizes searching and reasoning capabilities."}, "familyId": "bmf_dfc10241a16b", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_lakeqa_b77b7993", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.10460", "paper": "https://arxiv.org/abs/2606.10460", "pdf": "https://arxiv.org/pdf/2606.10460", "project": null, "report": "https://arxiv.org/abs/2606.10460"}, "metrics": [], "motivation": "Recent large language models (LLMs) have shown rapid progress in reading-based question answering (QA), where evidence is explicitly provided or can be trivially retrieved.", "name": "LakeQA", "oneLine": "LakeQA evaluates search-centric question answering over a 9.5 TB data lake of Wikipedia and government data. Tasks require multi-hop reasoning across heterogeneous structured and unstructured sources, with expert-annotated answers.", "paperTitle": "LakeQA: An Exploratory QA Benchmark over a Million-Scale Data Lake", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.10460", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "arXiv", "organizationType": "community", "role": "benchmark-publisher", "sourceUrl": "https://arxiv.org/abs/2606.10460"}], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-09", "source": {"authors": ["Haonan Wang", "Jiaxiang Liu", "Yurong Liu", "Austin Senna Wijaya", "Tianle Zhou", "Eden Wu", "Yijia Chen", "Wanting You", "Reya Vir", "Daniela Pinto", "Grace Fan", "Yusen Zhang", "Juliana Freire and Eugene Wu"], "categories": ["cs.CL", "cs.AI"], "id": "2606.10460", "title": "LakeQA: An Exploratory QA Benchmark over a Million-Scale Data Lake", "type": "arxiv", "url": "https://arxiv.org/abs/2606.10460"}, "sourceUpdatedAt": "2026-06-09T06:15:36Z", "topics": ["Reasoning"], "venueAttempts": [], "whyItMatters": "Existing QA benchmarks provide explicit evidence or trivial retrieval, missing the challenge of locating and composing evidence in large-scale data lakes. LakeQA fills this gap, supporting development and assessment of agents that can search and reason over massive heterogeneous data."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
