{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2607.24889", "kind": "paper", "url": "https://arxiv.org/abs/2607.24889"}], "authors": ["Jiacheng Lu", "Yiming Li", "Sinuo Wang", "Wentao Zhao", "Rui Sun", "Cheng Hua", "Tao Song", "Hui Cai", "Beidi Luan", "Tianyi Ma", "Qixuan Yang", "Zhengze Wu", "Jing Li", "Daxin Jiang", "Zuo Bai", "Haibing Guan"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2607.24889", "source_url": "https://arxiv.org/abs/2607.24889"}, "categories": ["Agents", "Finance", "Language & Knowledge"], "description": {"en": "GAUGE evaluates agent-built financial valuation models against observed analyst practice using 56 facets, eight validity gates, and a failure-aware score over 196 tasks."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.24889", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.24889", "title": "GAUGE"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["StepFun AI (China)", "Tsinghua University", "Shanghai Jiao Tong University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2607.24889", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2607.24889", "source_url": "https://openalex.org/W7171732952"}, "key": "claire-radar:2607.24889", "modality": null, "name": "GAUGE", "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_gauge_c5d48106", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "97db532b512b0bd0c51d7d585020b7800ba2cc3ce93cede6d14a6ec73e954853", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2607.24889"}, "publisher": null, "released": "2026-07-27", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.24889", "source_url": "https://arxiv.org/abs/2607.24889"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-24889", "source": "claire_radar", "source_benchmark_id": "2607.24889", "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/2607.24889", "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": "241f8c88b248e236fca5562ceb58f39ba684b023b452289e162279bcbbb90989", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "GAUGE evaluates agent-built financial valuation models against observed analyst practice using 56 facets, eight validity gates, and a failure-aware score over 196 tasks.", "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 introduce GAUGE, a benchmark for evaluating agent-built valuation models against observed analyst practice rather than a single point answer."}, "familyId": "bmf_a90fd9a9a1e6", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_gauge_c5d48106", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Financial Services"], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2607.24889", "paper": "https://arxiv.org/abs/2607.24889", "pdf": "https://arxiv.org/pdf/2607.24889", "project": null, "report": "https://arxiv.org/abs/2607.24889"}, "metrics": [], "motivation": "Financial models combine public disclosures with analyst assumptions to produce forecasts and valuations.", "name": "GAUGE", "oneLine": "GAUGE evaluates agent-built financial valuation models against observed analyst practice using 56 facets, eight validity gates, and a failure-aware score over 196 tasks.", "paperTitle": "GAUGE: Grading Agent-Built Financial Models Without a Golden Answer", "primaryDomain": "Finance", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2607.24889", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "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": "2026-07-27", "source": {"authors": ["Jiacheng Lu", "Sinuo Wang", "Wentao Zhao", "Rui Sun", "Cheng Hua", "Tao Song", "Hui Cai", "Beidi Luan", "Zhengze Wu", "Lingjing Teng", "Yijia He", "Jing Li", "Daxin Jiang", "Zuo Bai", "Haibing Guan"], "categories": ["cs.LG", "cs.AI", "cs.CE"], "id": "2607.24889", "title": "GAUGE: Grading Agent-Built Financial Models Without a Golden Answer", "type": "arxiv", "url": "https://arxiv.org/abs/2607.24889"}, "sourceUpdatedAt": "2026-07-27T13:03:19Z", "topics": ["Agents"], "venueAttempts": [], "whyItMatters": "Provides a benchmark that avoids penalizing legitimate disagreement, enabling fair comparison of agents on financial modeling and judgment."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
