{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.12342", "kind": "paper", "url": "https://arxiv.org/abs/2608.12342"}, {"id": "gh:hedyhe/fined-bench", "kind": "repo", "url": "https://github.com/hedyHe/FinED-Bench"}], "authors": ["Ying He", "Zhouhong Gu", "Zhecheng Hu", "Yubo Zhou", "Hao Shen", "Jiaqing Liang", "Zhaoqian Dai", "Shuguang Ma", "Fei Yu", "Yanghua Xiao", "Zhixu Li"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.12342", "source_url": "https://arxiv.org/abs/2608.12342"}, "categories": ["Finance", "Vision & 3D", "cs.CL"], "description": {"en": "FinED-Bench evaluates error detection in financial documents across nine real-world financial scenarios, covering three cognitive complexity levels. It includes over 900 documents from 2025, with data and code publicly available."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.12342", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.12342", "title": "FinED-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.12342", "modality": null, "name": "FinED-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_fined-bench_3f021fe1", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "0febbc0c9392c6649ce095000d46a8e91811922508370fae0a76bebd19738940", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2608.12342"}, "publisher": null, "released": "2026-06-03", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.12342", "source_url": "https://arxiv.org/abs/2608.12342"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-12342", "source": "claire_radar", "source_benchmark_id": "2608.12342", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Finance"], "area": "Vision & 3D", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/hedyHe/FinED-Bench", "githubScope": "benchmark_repo", "githubStars": 0, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2608.12342", "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": "2da8f6491aa3abc07def0529966ba75d6325cace9d4c664e4f88fc61fa987abf", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "FinED-Bench evaluates error detection in financial documents across nine real-world financial scenarios, covering three cognitive complexity levels. It includes over 900 documents from 2025, with data and code publicly available.", "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": "In this paper, we introduce \\textbf{FinED-Bench}, the first publicly \\textbf{Bench}mark for \\textbf{Fin}ancial \\textbf{E}rror \\textbf{D}etection across three levels of cognitive complexity."}, "familyId": "bmf_e5c0a8628ba8", "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/hedyHe/FinED-Bench", "url": "https://github.com/hedyHe/FinED-Bench"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/hedyHe/FinED-Bench", "url": "https://huggingface.co/papers/2608.12342"}, {"basis": "linked-from-report", "linkedUrl": "https://github.com/hedyHe/FinED-Bench.", "url": "https://arxiv.org/abs/2608.12342"}, {"basis": "linked-from-report", "linkedUrl": "https://github.com/hedyHe/FinED-Bench", "url": "https://arxiv.org/abs/2608.12342"}], "scope": "benchmark_repo", "url": "https://github.com/hedyHe/FinED-Bench", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_fined-bench_3f021fe1", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Financial Services"], "links": {"code": "https://github.com/hedyHe/FinED-Bench", "data": null, "hfPaper": "https://huggingface.co/papers/2608.12342", "paper": "https://arxiv.org/abs/2608.12342", "pdf": "https://arxiv.org/pdf/2608.12342", "project": null, "report": "https://arxiv.org/abs/2608.12342"}, "metrics": [], "motivation": "Ensuring the accuracy of financial documents is critical for economic analysis, regulatory compliance, and corporate decision-making.", "name": "FinED-Bench", "oneLine": "FinED-Bench evaluates error detection in financial documents across nine real-world financial scenarios, covering three cognitive complexity levels. It includes over 900 documents from 2025, with data and code publicly available.", "paperTitle": "Are Large Language Models Reliable Reviewers? A Benchmark for Error Detection in Financial Documents", "primaryDomain": "Finance", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.12342", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "FinED-Bench Team", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://github.com/hedyHe/FinED-Bench"}], "ranking": {}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-03", "source": {"authors": ["Ying He", "Zhouhong Gu", "Zhecheng Hu", "Yubo Zhou", "Hao Shen", "Jiaqing Liang", "Zhaoqian Dai", "Shuguang Ma", "Fei Yu", "Yanghua Xiao", "Zhixu Li"], "categories": ["cs.CL", "cs.LG"], "id": "2608.12342", "title": "Are Large Language Models Reliable Reviewers? A Benchmark for Error Detection in Financial Documents", "type": "arxiv", "url": "https://arxiv.org/abs/2608.12342"}, "sourceUpdatedAt": "2026-06-03T12:41:31Z", "topics": ["cs.CL"], "venueAttempts": [], "whyItMatters": "Financial document accuracy is critical for compliance and decision-making, yet current LLMs struggle with error detection. FinED-Bench provides a fixed protocol to assess and improve model reliability in this domain."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
