{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2605.30907", "kind": "paper", "url": "https://arxiv.org/abs/2605.30907"}], "authors": ["Srivatsa Kundurthy", "Clara Na", "Colton Moraine", "Anoushka Mohta", "Case Winter", "George Fang", "John Ling", "Emma Strubell", "Zach Kirshner"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2605.30907", "source_url": "https://arxiv.org/abs/2605.30907"}, "categories": ["Finance", "Robot manipulation", "Robotics", "Robotics & Embodied AI"], "description": {"en": "Evaluates LLM agents on synthesis, manipulation, and comprehension tasks over financial spreadsheet workbooks, with 131 tasks and granular rubric criteria validated by expert annotators."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2605.30907", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2605.30907", "title": "BlueFin"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Cornell University", "Carnegie Mellon University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2605.30907", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2605.30907", "source_url": "https://openalex.org/W7163066580"}, "key": "claire-radar:2605.30907", "modality": null, "name": "BlueFin", "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_bluefin_2fd6c32a", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "9e945b614a353b94d74ca8ec6693d5c489b45a0a5802ea3f5116c5afb35d78c0", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2605.30907"}, "publisher": null, "released": "2026-05-29", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2605.30907", "source_url": "https://arxiv.org/abs/2605.30907"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2605-30907", "source": "claire_radar", "source_benchmark_id": "2605.30907", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["Robotics & Embodied AI", "Finance"], "area": "Robotics & Embodied AI", "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/2605.30907", "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": ["Robot manipulation"], "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": "90d53d7dea828e6760a3774046a5fecedc8289acee860d28ed48ca340160a8ea", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates LLM agents on synthesis, manipulation, and comprehension tasks over financial spreadsheet workbooks, with 131 tasks and granular rubric criteria validated by expert annotators.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "We present BlueFin, a benchmark that tasks large language model (LLM) agents with synthesis, manipulation, and comprehension tasks over spreadsheet workbooks in the professional finance domain."}, "familyId": "bmf_98253ff66ed8", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_bluefin_2fd6c32a", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Robotics", "Financial Services"], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2605.30907", "paper": "https://arxiv.org/abs/2605.30907", "pdf": "https://arxiv.org/pdf/2605.30907", "project": null, "report": "https://arxiv.org/abs/2605.30907"}, "metrics": [], "motivation": "We present BlueFin, a benchmark that tasks large language model (LLM) agents with synthesis, manipulation, and comprehension tasks over spreadsheet workbooks in the professional finance domain.", "name": "BlueFin", "oneLine": "Evaluates LLM agents on synthesis, manipulation, and comprehension tasks over financial spreadsheet workbooks, with 131 tasks and granular rubric criteria validated by expert annotators.", "paperTitle": "BlueFin: Benchmarking LLM Agents on Financial Spreadsheets", "primaryDomain": "Robotics & Embodied AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2605.30907", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "BlueFin Benchmark Team", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://arxiv.org/abs/2605.30907"}], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-05-29", "source": {"authors": ["Srivatsa Kundurthy", "Clara Na", "Colton Moraine", "Anoushka Mohta", "Case Winter", "George Fang", "John Ling", "Emma Strubell", "Zach Kirshner"], "categories": ["cs.SE", "cs.AI", "cs.CL", "cs.LG"], "id": "2605.30907", "title": "BlueFin: Benchmarking LLM Agents on Financial Spreadsheets", "type": "arxiv", "url": "https://arxiv.org/abs/2605.30907"}, "sourceUpdatedAt": "2026-05-29T06:43:23Z", "topics": ["Robotics"], "venueAttempts": [], "whyItMatters": "Fills the gap in evaluating LLMs for spreadsheet tasks relevant to professional finance, where current models perform below 50%, providing a measure for practical deployment."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
