{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.00036", "kind": "paper", "url": "https://arxiv.org/abs/2608.00036"}], "authors": ["Hongchen Wei", "Yuanzhe Wang", "Bei Liu", "Yifan Yang", "Qi Dai", "Ruichun Ma", "Kai Qiu", "Yunsheng Li", "Dongdong Chen", "Chong Luo", "Zhenzhong Chen", "Baining Guo"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.00036", "source_url": "https://arxiv.org/abs/2608.00036"}, "categories": ["Biology & Drug Discovery", "Finance", "Language & Knowledge", "cs.CL"], "description": {"en": "XL-DocBench evaluates evidence-grounded long-document understanding with 1,519 human-verified questions from six professional domains, contexts up to 2,303 pages, multi-page evidence, and typed reasoning rules."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.00036", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.00036", "title": "XL-DocBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.00036", "modality": null, "name": "XL-DocBench", "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_xl-docbench_d4b9f759", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "1d93a1e94f0785234244e76a3d366bb477c2f62864c251255ee5cc9418b6b0f4", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2608.00036"}, "publisher": null, "released": "2026-07-21", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.00036", "source_url": "https://arxiv.org/abs/2608.00036"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-00036", "source": "claire_radar", "source_benchmark_id": "2608.00036", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Biology & Drug Discovery", "Finance"], "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": 2, "hfPaperUrl": "https://huggingface.co/papers/2608.00036", "observedAt": "2026-10-04T15:31:48.030916Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}}, "status": "fresh"}, "capabilities": [], "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": "364074b787831af6ba8349ef106978e3cd713d305573340cd522c517978db1d5", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "XL-DocBench evaluates evidence-grounded long-document understanding with 1,519 human-verified questions from six professional domains, contexts up to 2,303 pages, multi-page evidence, and typed reasoning rules.", "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": "We introduce XL-DocBench, a fully human-verified benchmark for extra-long document understanding, with 1,519 retained questions from six professional domains and contexts up to 2,303 pages."}, "familyId": "bmf_7ec798d59d5d", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_xl-docbench_d4b9f759", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Pharma & Biotech", "Financial Services"], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2608.00036", "paper": "https://arxiv.org/abs/2608.00036", "pdf": "https://arxiv.org/pdf/2608.00036", "project": null, "report": "https://arxiv.org/abs/2608.00036"}, "metrics": [], "motivation": "Real-world document tasks often ask professionals to answer questions from annual reports, regulations, clinical guidelines, and technical manuals that span hundreds or thousands of pages.", "name": "XL-DocBench", "oneLine": "XL-DocBench evaluates evidence-grounded long-document understanding with 1,519 human-verified questions from six professional domains, contexts up to 2,303 pages, multi-page evidence, and typed reasoning rules.", "paperTitle": "XL-DocBench: Benchmarking Evidence-Grounded Extra-Long Document Understanding", "primaryDomain": "Biology & Drug Discovery", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.00036", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {"90d": {"confidence": "Low", "coverage": 0.15, "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": 0.19411886932144953, "value": 2}}, "confidence": "Low", "coverage": 0.15, "rank": null, "score": 45}, "method": "attention-ranking-v13", "rank": null, "score": 45}}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-07-21", "source": {"authors": ["Hongchen Wei", "Yuanzhe Wang", "Bei Liu", "Yifan Yang", "Qi Dai", "Ruichun Ma", "Kai Qiu", "Yunsheng Li", "Dongdong Chen", "Chong Luo", "Zhenzhong Chen", "Baining Guo"], "categories": ["cs.CL", "cs.AI"], "id": "2608.00036", "title": "XL-DocBench: Benchmarking Evidence-Grounded Extra-Long Document Understanding", "type": "arxiv", "url": "https://arxiv.org/abs/2608.00036"}, "sourceUpdatedAt": "2026-07-21T09:38:24Z", "topics": ["cs.CL"], "venueAttempts": [], "whyItMatters": "Professional workflows require traceable answers from long documents; this benchmark fills a gap in multi-page and structured reasoning evaluation, enabling failure attribution."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
