{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.03829", "kind": "paper", "url": "https://arxiv.org/abs/2606.03829"}], "authors": ["Alex Wang", "Georg Meinhardt", "Jacob Katz", "Joseph H. Kim", "Pratyush K. Chaudhary", "Chase Blagden", "Eric Xu"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.03829", "source_url": "https://arxiv.org/abs/2606.03829"}, "categories": ["Finance", "Language & Knowledge", "cs.AI"], "description": {"en": "BigFinanceBench evaluates financial-research agents on open-ended tasks with 928 items, each paired with a ground-truth answer and a point-weighted rubric decomposing the derivation into steps. Supports partial-credit scoring across 36,241 rubric points."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.03829", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.03829", "title": "BigFinanceBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2606.03829", "modality": null, "name": "BigFinanceBench", "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_bigfinancebench_c8640763", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "a37e720520b50d86c33b3691ee5d872478a7ccb674f1c9b2d4e36be5fe5638f5", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.03829"}, "publisher": null, "released": "2026-06-02", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.03829", "source_url": "https://arxiv.org/abs/2606.03829"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-03829", "source": "claire_radar", "source_benchmark_id": "2606.03829", "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": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 0, "hfPaperUrl": "https://huggingface.co/papers/2606.03829", "observedAt": "2026-10-04T03:02:42.754940Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "lastSuccessfulDate": "2026-09-30", "state": "stale"}}, "status": "stale"}, "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": "883397bd70250ab65f8b39beec3514a8acdf14a941036f77a5cfae507da703d9", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "BigFinanceBench evaluates financial-research agents on open-ended tasks with 928 items, each paired with a ground-truth answer and a point-weighted rubric decomposing the derivation into steps. Supports partial-credit scoring across 36,241 rubric points.", "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 BigFinanceBench, a 928-item expert-authored benchmark of open-ended financial-research tasks in which each item pairs a ground-truth reference answer with a point-weighted rubric that decomposes the derivation into independently checkable steps."}, "familyId": "bmf_4b9b21faaf9f", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_bigfinancebench_c8640763", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Financial Services"], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.03829", "paper": "https://arxiv.org/abs/2606.03829", "pdf": "https://arxiv.org/pdf/2606.03829", "project": null, "report": "https://arxiv.org/abs/2606.03829"}, "metrics": [], "motivation": "Financial-research answers are decision-relevant only when another analyst can audit how they were produced: which source was chosen, which period and accounting definition were used, which assumptions were made, and how the calculation was performed.", "name": "BigFinanceBench", "oneLine": "BigFinanceBench evaluates financial-research agents on open-ended tasks with 928 items, each paired with a ground-truth answer and a point-weighted rubric decomposing the derivation into steps. Supports partial-credit scoring across 36,241 rubric points.", "paperTitle": "BigFinanceBench: A Workflow-Grounded Benchmark for Financial-Research Agents", "primaryDomain": "Finance", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.03829", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-02", "source": {"authors": ["Alex Wang", "Georg Meinhardt", "Jacob Katz", "Joseph H. Kim", "Pratyush K. Chaudhary", "Chase Blagden", "Eric Xu"], "categories": ["cs.AI"], "id": "2606.03829", "title": "BigFinanceBench: A Workflow-Grounded Benchmark for Financial-Research Agents", "type": "arxiv", "url": "https://arxiv.org/abs/2606.03829"}, "sourceUpdatedAt": "2026-06-02T16:12:34Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "Existing finance benchmarks evaluate subskills or final answers, not the auditable derivation. BigFinanceBench measures workflow quality, allowing localization of failures and better assessment of decision-relevant outputs."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
