{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.03918", "kind": "paper", "url": "https://arxiv.org/abs/2606.03918"}, {"id": "gh:trata-inc/trata-hedge-bench", "kind": "repo", "url": "https://github.com/Trata-Inc/trata-hedge-bench"}], "authors": ["Mahesh Ramesh", "Eric Cho", "Alice Lu", "Shawn Huang", "Baiqing Lyu"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.03918", "source_url": "https://arxiv.org/abs/2606.03918"}, "categories": ["Finance", "Language & Knowledge", "Reasoning"], "description": {"en": "Hedge-Bench 1.0 evaluates agents on 102 financial reasoning tasks with deterministic grading against expert reasoning traces."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.03918", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.03918", "title": "Hedge-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Brigham Young University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.03918", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.03918", "source_url": "https://openalex.org/W7163355642"}, "key": "claire-radar:2606.03918", "modality": null, "name": "Hedge-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_hedge-bench_8e798fcd", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "28b3b1c7a349bcc36c5a9cc6e9aff5e550fb361d2b86ea05d6c74c7fa286dfa1", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.03918"}, "publisher": null, "released": "2026-06-02", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.03918", "source_url": "https://arxiv.org/abs/2606.03918"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-03918", "source": "claire_radar", "source_benchmark_id": "2606.03918", "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/Trata-Inc/trata-hedge-bench", "githubScope": "benchmark_repo", "githubStars": 100, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 2, "hfPaperUrl": "https://huggingface.co/papers/2606.03918", "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", "lastSuccessfulDate": "2026-09-25", "state": "stale"}}, "status": "fresh"}, "capabilities": ["Reasoning"], "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": "244e330fede2224ae02d72cf1808c09c427087d1524f93275d02bf8d436e8111", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Hedge-Bench 1.0 evaluates agents on 102 financial reasoning tasks with deterministic grading against expert reasoning traces.", "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 present Hedge-Bench 1.0: a benchmark of 102 actual, on-the-job tasks grounded in the explicit reasoning traces of professional hedge fund analysts working with relevant information sources."}, "familyId": "bmf_9e742fdac1fd", "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/Trata-Inc/trata-hedge-bench", "url": "https://github.com/Trata-Inc/trata-hedge-bench"}, {"basis": "existing-metric-association", "linkedUrl": "https://github.com/Trata-Inc/trata-hedge-bench", "url": "https://huggingface.co/papers/2606.03918"}, {"basis": "linked-from-report", "linkedUrl": "http://github.com/Trata-Inc/trata-hedge-bench", "url": "https://arxiv.org/abs/2606.03918"}], "scope": "benchmark_repo", "url": "https://github.com/Trata-Inc/trata-hedge-bench", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_hedge-bench_8e798fcd", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Financial Services"], "links": {"code": "https://github.com/Trata-Inc/trata-hedge-bench", "data": null, "hfPaper": "https://huggingface.co/papers/2606.03918", "paper": "https://arxiv.org/abs/2606.03918", "pdf": "https://arxiv.org/pdf/2606.03918", "project": null, "report": "https://arxiv.org/abs/2606.03918"}, "metrics": [], "motivation": "AI agents can increasingly handle the mechanical tasks of financial analysis: retrieving documents, calculating formulas, updating spreadsheets.", "name": "Hedge-Bench", "oneLine": "Hedge-Bench 1.0 evaluates agents on 102 financial reasoning tasks with deterministic grading against expert reasoning traces.", "paperTitle": "Hedge-Bench: Benchmarking Agents on Hard, Realistic Tasks Pertaining to Financial Reasoning", "primaryDomain": "Finance", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.03918", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "Trata Inc.", "organizationType": "company-research-lab", "role": "benchmark-publisher", "sourceUrl": "https://github.com/Trata-Inc/trata-hedge-bench"}], "ranking": {}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-02", "source": {"authors": ["Eric Cho", "Shawn Huang", "Alice Lu", "Andy Lyu"], "categories": ["cs.AI"], "id": "2606.03918", "title": "Hedge-Bench: Benchmarking Agents on Hard, Realistic Tasks Pertaining to Financial Reasoning", "type": "arxiv", "url": "https://arxiv.org/abs/2606.03918"}, "sourceUpdatedAt": "2026-06-02T17:11:56Z", "topics": ["Reasoning"], "venueAttempts": [], "whyItMatters": "It provides a reproducible benchmark for open-ended financial analysis, addressing the lack of hard, realistic tasks with verified grading."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
