{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2607.19409", "kind": "paper", "url": "https://arxiv.org/abs/2607.19409"}], "authors": ["Wolfgang M. Pauli", "Sarah Panda", "Kidus Admassu", "Said Bleik", "Ademola Okerinde", "Jeremy Reynolds"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2607.19409", "source_url": "https://arxiv.org/abs/2607.19409"}, "categories": ["Finance", "Language & Knowledge", "cs.AI"], "description": {"en": "FORCE-Bench evaluates agentic AI systems in enterprise finance across three task types: financial obligation research, financial entity performance research, and business brief generation. It includes 251 expert-annotated queries and a rubric-based scoring framework across eight dimensions: accuracy, citations, clarity, depth, groundedness, recency, relevance, and structure."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.19409", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.19409", "title": "FORCE-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Microsoft (United States)"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2607.19409", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2607.19409", "source_url": "https://openalex.org/W7170179132"}, "key": "claire-radar:2607.19409", "modality": null, "name": "FORCE-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_force-bench_be1ccc66", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "0006fc5333da8c03ec6e62066115ddc8700dd750579a5e17629f2542aec46d4f", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2607.19409"}, "publisher": null, "released": "2026-07-11", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.19409", "source_url": "https://arxiv.org/abs/2607.19409"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-19409", "source": "claire_radar", "source_benchmark_id": "2607.19409", "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": null, "hfPaperUrl": "https://huggingface.co/papers/2607.19409", "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", "state": "unavailable"}}, "status": "unavailable"}, "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": "23431856bd791d1004934d5b3e7a259a952219e0989a2d3e6faf7295842eb1a5", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "FORCE-Bench evaluates agentic AI systems in enterprise finance across three task types: financial obligation research, financial entity performance research, and business brief generation. It includes 251 expert-annotated queries and a rubric-based scoring framework across eight dimensions: accuracy, citations, clarity, depth, groundedness, recency, relevance, and structure.", "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 FORCE-Bench, which contains 251 expert-annotated queries and evaluates responses using a rubric-based framework calibrated to the requirements of the operational finance domain, across eight dimensions: accuracy, citations, clarity, depth, groundedness, recency, relevance, and structure."}, "familyId": "bmf_3be86d47de12", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_force-bench_be1ccc66", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Financial Services"], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2607.19409", "paper": "https://arxiv.org/abs/2607.19409", "pdf": "https://arxiv.org/pdf/2607.19409", "project": null, "report": "https://arxiv.org/abs/2607.19409"}, "metrics": [], "motivation": "Recent advances in large language models have accelerated deployment of agentic systems in operational finance.", "name": "FORCE-Bench", "oneLine": "FORCE-Bench evaluates agentic AI systems in enterprise finance across three task types: financial obligation research, financial entity performance research, and business brief generation. It includes 251 expert-annotated queries and a rubric-based scoring framework across eight dimensions: accuracy, citations, clarity, depth, groundedness, recency, relevance, and structure.", "paperTitle": "FORCE-Bench: A Benchmark, Dataset, and Evaluation Harness for Agentic AI in Enterprise Finance", "primaryDomain": "Finance", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2607.19409", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "FORCE-Bench team", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://arxiv.org/abs/2607.19409"}], "ranking": {"90d": {"confidence": "Low", "coverage": 0.0, "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": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": null}, "method": "attention-ranking-v13", "rank": null, "score": null}}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-07-11", "source": {"authors": ["Wolfgang M. Pauli", "Sarah Panda", "Kidus Admassu", "Said Bleik", "Ademola Okerinde", "Jeremy Reynolds"], "categories": ["cs.AI"], "id": "2607.19409", "title": "FORCE-Bench: A Benchmark, Dataset, and Evaluation Harness for Agentic AI in Enterprise Finance", "type": "arxiv", "url": "https://arxiv.org/abs/2607.19409"}, "sourceUpdatedAt": "2026-07-11T01:16:31Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "Existing benchmarks focus on general capabilities rather than operational finance workflows. FORCE-Bench provides a domain-specific evaluation tool that measures rule adherence, verifiability, and groundedness, which are critical for real-world deployment of agentic systems in finance. It enables comparable assessment of agent performance under operational constraints."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
