{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.04374", "kind": "paper", "url": "https://arxiv.org/abs/2608.04374"}, {"id": "gh:misterbrookt/finreportbench", "kind": "repo", "url": "https://github.com/MisterBrookT/finreportbench"}], "authors": ["Yinghao Tang", "Tan Zhenwei", "Yiyao Wang", "Wanli Gu", "Xiaolu Zhang", "Jun Zhou", "Wei Chen"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.04374", "source_url": "https://arxiv.org/abs/2608.04374"}, "categories": ["Finance", "Language & Knowledge", "cs.CL"], "description": {"en": "FinReportBench evaluates institution-grade financial report generation using 244 bilingual tasks sourced from 10,000 financial research records. It uses a 35-item rubric covering deliverability, report identity, and institutional completeness, with three judge families."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.04374", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.04374", "title": "FinReportBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Zhejiang University", "Ant Group (China)"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2608.04374", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2608.04374", "source_url": "https://openalex.org/W7196950233"}, "key": "claire-radar:2608.04374", "modality": null, "name": "FinReportBench", "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_finreportbench_5d3a5df7", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "5119f601c2fe30763f01b058d281b419045dbf2180313dd03253cb8c04bc7614", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2608.04374"}, "publisher": null, "released": "2026-08-05", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.04374", "source_url": "https://arxiv.org/abs/2608.04374"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-04374", "source": "claire_radar", "source_benchmark_id": "2608.04374", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Finance"], "area": "Language & Knowledge", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/MisterBrookT/finreportbench", "githubScope": "benchmark_repo", "githubStars": 3, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2608.04374", "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": "Transform Existing", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "1dd2d50bc647edddfc6fe7ca60b7b3687f351d68dca43bbe2d02a002bd9c4d03", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "FinReportBench evaluates institution-grade financial report generation using 244 bilingual tasks sourced from 10,000 financial research records. It uses a 35-item rubric covering deliverability, report identity, and institutional completeness, with three judge families.", "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", "public artifact URL"], "snippet": "We introduce FinReportBench, an expert-grounded benchmark for measuring and improving institution-grade financial report generation."}, "familyId": "bmf_33ecc6c20ee7", "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/MisterBrookT/finreportbench", "url": "https://github.com/MisterBrookT/finreportbench"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/MisterBrookT/finreportbench", "url": "https://huggingface.co/papers/2608.04374"}, {"basis": "linked-from-report", "linkedUrl": "https://github.com/MisterBrookT/finreportbench", "url": "https://arxiv.org/abs/2608.04374"}, {"basis": "linked-from-report", "linkedUrl": "https://github.com/MisterBrookT/finreportbench.", "url": "https://arxiv.org/abs/2608.04374"}], "scope": "benchmark_repo", "url": "https://github.com/MisterBrookT/finreportbench", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_finreportbench_5d3a5df7", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Financial Services"], "links": {"code": "https://github.com/MisterBrookT/finreportbench", "data": null, "hfPaper": "https://huggingface.co/papers/2608.04374", "paper": "https://arxiv.org/abs/2608.04374", "pdf": "https://arxiv.org/pdf/2608.04374", "project": null, "report": "https://arxiv.org/abs/2608.04374"}, "metrics": [], "motivation": "Large language models can produce fluent financial analysis, but fluency alone does not establish whether a report is suitable for institutional delivery.", "name": "FinReportBench", "oneLine": "FinReportBench evaluates institution-grade financial report generation using 244 bilingual tasks sourced from 10,000 financial research records. It uses a 35-item rubric covering deliverability, report identity, and institutional completeness, with three judge families.", "paperTitle": "FinReportBench: Measuring and Improving Institution-Grade Financial Report Generation", "primaryDomain": "Finance", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.04374", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "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": 228, "score": 33}, "method": "attention-ranking-v13", "rank": 228, "score": 33}}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-08-05", "source": {"authors": ["Yinghao Tang", "Tan Zhenwei", "Yiyao Wang", "Wanli Gu", "Xiaolu Zhang", "Jun Zhou", "Wei Chen"], "categories": ["cs.CL", "cs.AI"], "id": "2608.04374", "title": "FinReportBench: Measuring and Improving Institution-Grade Financial Report Generation", "type": "arxiv", "url": "https://arxiv.org/abs/2608.04374"}, "sourceUpdatedAt": "2026-08-05T02:31:48Z", "topics": ["cs.CL"], "venueAttempts": [], "whyItMatters": "It fills the gap in evaluating long-form financial reports for institutional delivery, providing a reliable rubric and public artifacts to measure and improve report generation."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
