{"record": {"aliases": ["Can LLMs Normalize Databases? A Benchmark and Multi-Agent Framework for Schema Normalization"], "artifacts": [{"id": "arxiv:2609.11141", "kind": "paper", "url": "https://arxiv.org/abs/2609.11141"}], "authors": ["Dong-Jae Koh", "Huisu Kim", "SeongHwan Yoon", "Lasse M. Jantsch", "Chun-Hee Lee", "Seonghyeon Lee", "Young-Kyoon Suh"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2609.11141", "source_url": "https://arxiv.org/abs/2609.11141"}, "categories": ["Agents", "General AI", "Language & Knowledge"], "description": {"en": "A benchmark of 3,275 samples for evaluating LLM-driven database normalization from 1NF to BCNF."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2609.11141", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2609.11141", "title": "DNBENCH"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Kyungpook National University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2609.11141", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2609.11141", "source_url": "https://openalex.org/W7212304441"}, "key": "claire-radar:2609.11141", "modality": null, "name": "DNBENCH", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"admission_policy_version": "2026-09-09.1", "confidence": "Medium", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-10-14T09:44:51Z", "data_status": "primary-source-indexed", "display_eligible": "false", "origin_record_id": "bm_can-llms-normalize-databases-a-benchmark-a_006c394e", "origin_source": "arxiv", "recognition_confidence": "0.6", "record_sha256": "d085991cc3416ba27ef6da86059e94411ff32973bf607e84f783909c275e0a6e", "relation": "introduces", "review_model": "deepseek-v4-pro", "review_state": "ai-name-audit-deferred", "reviewed_at": "2026-09-12T00:56:20.009268Z", "source_url": "https://arxiv.org/abs/2609.11141"}, "publisher": null, "released": "2026-09-10", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2609.11141", "source_url": "https://arxiv.org/abs/2609.11141"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2609-11141", "source": "claire_radar", "source_benchmark_id": "2609.11141", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": ["Can LLMs Normalize Databases? A Benchmark and Multi-Agent Framework for Schema Normalization"], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Language & Knowledge", "attention": {"asOf": "2026-09-11", "attemptedAt": "2026-09-11T01:40:00.759237Z", "githubRepo": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2609.11141", "observedAt": "2026-09-10T12:24:43.080049Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-09-11T01:40:00.759237Z", "state": "unavailable"}}, "status": "unavailable"}, "attentionForecast": {"confidence": "Low", "horizon": "7d", "reason": "The topic is niche and lacks community signals or release artifacts, limiting likely early attention.", "score": 35}, "capabilities": [], "confidence": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-09-12T00:56:20.009268Z", "inputHash": "a28f870bc1088a8a797e9e4a98411b00a8c598804d25ca8918a6dc6e86902ab7", "model": "deepseek-v4-pro"}, "curation": {"admissionPolicyVersion": "2026-09-09.1", "canonicalNameEvidence": "We introduce a Database Normalization Benchmark (DNBENCH)", "canonicalNameSource": "abstract", "decisionReason": "No artifact evidence, code, or public reuse path is supplied, so the benchmark's availability and scoring protocol cannot be verified.", "evaluationEvidence": {"reuse": "All artifacts will be released upon acceptance", "scoring": "DNBENCH uses a three-axis protocol to measure semantic equivalence, structural accuracy, and logical validity", "task": "3,275 samples for evaluating LLM-driven database normalization from 1NF to BCNF"}, "model": "deepseek-v4-pro", "reviewedAt": "2026-09-12T00:56:20.009268Z", "state": "ai-name-audit-deferred"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "A benchmark of 3,275 samples for evaluating LLM-driven database normalization from 1NF to BCNF.", "displayEligible": false, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "score_submission", "evidence": {"reasonCodes": ["benchmark term in abstract", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "We introduce a Database Normalization Benchmark (DNBENCH), comprising 3,275 samples for evaluating LLM-driven database normalization from 1NF to BCNF."}, "familyId": "bmf_2b97562aba8d", "firstSeenAt": "2026-09-11", "heat": null, "id": "bm_can-llms-normalize-databases-a-benchmark-a_006c394e", "indexedAt": "2026-09-11T00:48:15.671466Z", "industrySectors": [], "links": {"code": null, "data": null, "paper": "https://arxiv.org/abs/2609.11141", "pdf": "https://arxiv.org/pdf/2609.11141", "project": null, "report": "https://arxiv.org/abs/2609.11141"}, "metrics": [], "motivation": "Large Language Models (LLMs) are increasingly used to generate structured outputs, but their reliability remains unclear when those outputs must satisfy database-level constraints.", "name": "DNBENCH", "oneLine": "A benchmark of 3,275 samples for evaluating LLM-driven database normalization from 1NF to BCNF.", "paperTitle": "Can LLMs Normalize Databases? A Benchmark and Multi-Agent Framework for Schema Normalization", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2609.11141", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-09-11T00:48:15.671466Z"}, "publications": [], "ranking": {"30d": {"confidence": "Low", "coverage": 0.0, "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": 30}, "level": {"components": {"githubStars": {"normalization": "log-max", "normalized": null, "value": null}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": null}, "method": "attention-ranking-v13", "rank": null, "score": null}, "90d": {"confidence": "Low", "coverage": 0.0, "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": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": null}, "method": "attention-ranking-v13", "rank": null, "score": null}, "today": {"confidence": "Low", "coverage": 0.0, "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": 1, "historyDate": "2026-09-10", "rank": null, "score": null, "windowDays": 1}, "level": {"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}, "llmAttentionForecast": {"maxContribution": 0.25, "percentile": 0.45, "role": "bonus", "value": 45}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": 11}, "method": "attention-ranking-v13", "rank": null, "score": 11}}, "readiness": "Paper only", "recognitionConfidence": 0.6, "relation": "introduces", "releasedAt": "2026-09-10", "source": {"authors": ["Dong-Jae Koh", "Huisu Kim", "SeongHwan Yoon", "Lasse M. Jantsch", "Chun-Hee Lee", "Seonghyeon Lee", "Young-Kyoon Suh"], "categories": ["cs.CL"], "id": "2609.11141", "title": "Can LLMs Normalize Databases? A Benchmark and Multi-Agent Framework for Schema Normalization", "type": "arxiv", "url": "https://arxiv.org/abs/2609.11141"}, "sourceUpdatedAt": "2026-09-10T06:34:35Z", "topics": ["Agents"], "venueAttempts": [], "whyItMatters": "DB normalization is a common structured task, and a public benchmark could enable systematic comparison of LLM capabilities."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
