{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.08459", "kind": "paper", "url": "https://arxiv.org/abs/2608.08459"}, {"id": "gh:setonliang/doc2db-bench", "kind": "repo", "url": "https://github.com/SetonLiang/Doc2DB-Bench"}], "authors": ["Zhuowen Liang", "Zhengxuan Zhang", "Jiayang Wang", "Jiazhuo Chen", "Nan Tang"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.08459", "source_url": "https://arxiv.org/abs/2608.08459"}, "categories": ["General AI", "Language & Knowledge", "cs.CL"], "description": {"en": "Doc2DB-Bench evaluates document-to-database construction, converting long heterogeneous documents into normalized relational databases with entity identities, keys, cross-table links, and integrity constraints. It includes 203 document instances across 42 schemas and 7 domains, with fine-grained capability annotations for intra-table extraction and inter-table reasoning."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.08459", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.08459", "title": "Doc2DB-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["The Hong Kong University of Science and Technology (Guangzhou)"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2608.08459", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2608.08459", "source_url": "https://openalex.org/W7202201989"}, "key": "claire-radar:2608.08459", "modality": null, "name": "Doc2DB-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_doc2db-bench_2f955ada", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "420b86728452f205761f4da1395a16e020fc351921250258a1a760576e9380c5", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2608.08459"}, "publisher": null, "released": "2026-08-09", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.08459", "source_url": "https://arxiv.org/abs/2608.08459"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-08459", "source": "claire_radar", "source_benchmark_id": "2608.08459", "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": "https://github.com/SetonLiang/Doc2DB-Bench", "githubScope": "benchmark_repo", "githubStars": 3, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2608.08459", "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", "state": "unavailable"}}, "status": "fresh"}, "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": "1a30e1a1267c2ee86ee536f5d0089979d7489042c158d140a7974e1c3b2d2840", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Doc2DB-Bench evaluates document-to-database construction, converting long heterogeneous documents into normalized relational databases with entity identities, keys, cross-table links, and integrity constraints. It includes 203 document instances across 42 schemas and 7 domains, with fine-grained capability annotations for intra-table extraction and inter-table reasoning.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact named benchmark artifact released in abstract", "benchmark release stated in one sentence", "evaluation protocol evidence", "public artifact URL"], "snippet": "We introduce Doc2DB-Bench, a benchmark for Document-to-Database construction, containing 203 long-document instances across 42 schemas and seven domain groups, with 117 entity tables, 132 relationship tables, 7,341 rows, and 41,935 cells."}, "familyId": "bmf_589f2dd26eba", "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/SetonLiang/Doc2DB-Bench", "url": "https://github.com/SetonLiang/Doc2DB-Bench"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/SetonLiang/Doc2DB-Bench", "url": "https://huggingface.co/papers/2608.08459"}, {"basis": "linked-from-report", "linkedUrl": "https://github.com/SetonLiang/Doc2DB-Bench.", "url": "https://arxiv.org/abs/2608.08459"}, {"basis": "linked-from-report", "linkedUrl": "https://github.com/SetonLiang/Doc2DB-Bench", "url": "https://arxiv.org/abs/2608.08459"}], "scope": "benchmark_repo", "url": "https://github.com/SetonLiang/Doc2DB-Bench", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_doc2db-bench_2f955ada", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/SetonLiang/Doc2DB-Bench", "data": null, "hfPaper": "https://huggingface.co/papers/2608.08459", "paper": "https://arxiv.org/abs/2608.08459", "pdf": "https://arxiv.org/pdf/2608.08459", "project": null, "report": "https://arxiv.org/abs/2608.08459"}, "metrics": [], "motivation": "Practical AI systems increasingly need to turn long, heterogeneous documents into queryable relational databases, not isolated spreadsheets.", "name": "Doc2DB-Bench", "oneLine": "Doc2DB-Bench evaluates document-to-database construction, converting long heterogeneous documents into normalized relational databases with entity identities, keys, cross-table links, and integrity constraints. It includes 203 document instances across 42 schemas and 7 domains, with fine-grained capability annotations for intra-table extraction and inter-table reasoning.", "paperTitle": "Beyond Tables: Doc2DB-Bench for Relationally Faithful Document-to-Database Construction", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.08459", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "Doc2DB-Bench Team", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://github.com/SetonLiang/Doc2DB-Bench"}], "ranking": {"90d": {"confidence": "Low", "coverage": 0.55, "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": 0.18504537701418716, "value": 3}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.55, "rank": 227, "score": 33}, "method": "attention-ranking-v13", "rank": 227, "score": 33}}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-08-09", "source": {"authors": ["Zhuowen Liang", "Zhengxuan Zhang", "Jiayang Wang", "Jiazhuo Chen", "Nan Tang"], "categories": ["cs.CL", "cs.AI", "cs.DB"], "id": "2608.08459", "title": "Beyond Tables: Doc2DB-Bench for Relationally Faithful Document-to-Database Construction", "type": "arxiv", "url": "https://arxiv.org/abs/2608.08459"}, "sourceUpdatedAt": "2026-08-09T03:58:39Z", "topics": ["cs.CL"], "venueAttempts": [], "whyItMatters": "Existing document-to-table benchmarks overlook relational database requirements such as normalization, entity resolution, and cross-table consistency. Doc2DB-Bench addresses this gap by providing a testbed for assessing LLM-based systems in realistic database construction, supporting analytics, compliance, and decision-making applications."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
