{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.25325", "kind": "paper", "url": "https://arxiv.org/abs/2608.25325"}], "authors": ["Suyang Zhong", "Jingzhe Zhu", "Qi Xu", "Liyao Sun", "Yin Wang", "Qingqing Sun", "Shuai Chen", "Tianyi Zhang"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.25325", "source_url": "https://arxiv.org/abs/2608.25325"}, "categories": ["Finance", "Language & Knowledge", "cs.AI"], "description": {"en": "Evaluates Chinese financial LLMs on static operation execution across 9,742 instances and evidence-state control via FinRisk-Ask using pre-action trajectory states."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.25325", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.25325", "title": "FinRiskAtlas"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Xiamen University", "Ant Group (China)", "Shanghai University", "Tongji University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2608.25325", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2608.25325", "source_url": "https://openalex.org/W7204468731"}, "key": "claire-radar:2608.25325", "modality": null, "name": "FinRiskAtlas", "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": "true", "origin_record_id": "bm_finriskatlas_4424cb99", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "d81a4f59fbc18b3583c41a0e7172d0421e6c80eb83537c9626eca93a154bf94d", "relation": "introduces", "review_state": "rule-auto-admitted", "reviewed_at": "2026-08-31T04:05:24.949457Z", "source_url": "https://arxiv.org/abs/2608.25325"}, "publisher": null, "released": "2026-08-26", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.25325", "source_url": "https://arxiv.org/abs/2608.25325"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-25325", "source": "claire_radar", "source_benchmark_id": "2608.25325", "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/2608.25325", "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"}, "attentionForecast": {"confidence": "Low", "horizon": "7d", "reason": "The paper targets a professional financial domain and introduces two complementary evaluation dimensions, which may attract attention despite missing artifact links.", "score": 55}, "capabilities": [], "confidence": "High", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-27T04:12:36.511123Z", "inputHash": "15c61651b4320250333dcdecf5e8f161bf9b01fb42dcf4fad412f79e682d63ec", "model": "deepseek-v4-pro"}, "curation": {"decisionReason": "Automatically admitted from an explicit named benchmark release with evaluation-protocol evidence at or above the configured publication-confidence threshold.", "policy": "source-evidence-v2", "reviewedAt": "2026-08-31T04:05:24.949457Z", "state": "rule-auto-admitted"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates Chinese financial LLMs on static operation execution across 9,742 instances and evidence-state control via FinRisk-Ask using pre-action trajectory states.", "displayEligible": true, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "We introduce FinRiskAtlas, a Chinese-language benchmark that evaluates financial LLMs along two complementary dimensions: operation execution under fixed evidence states and evidence-state control under evolving review conditions."}, "familyId": "bmf_11eb05bab140", "firstSeenAt": "2026-08-29", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_finriskatlas_4424cb99", "indexedAt": "2026-08-29T08:02:23.506802Z", "industrySectors": ["Financial Services"], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2608.25325", "paper": "https://arxiv.org/abs/2608.25325", "pdf": "https://arxiv.org/pdf/2608.25325", "project": null, "report": "https://arxiv.org/abs/2608.25325"}, "metrics": [], "motivation": "Deploying large language models for professional financial review requires more than measuring general financial competence: models must perform the specific review operation required by a workflow and determine whether available evidence is sufficient for a defensible decision.", "name": "FinRiskAtlas", "oneLine": "Evaluates Chinese financial LLMs on static operation execution across 9,742 instances and evidence-state control via FinRisk-Ask using pre-action trajectory states.", "paperTitle": "FinRiskAtlas: Decision-Aligned Evaluation of Large Language Models for Financial Risk Review", "primaryDomain": "Finance", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.25325", "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": "2026-08-26", "source": {"authors": ["Suyang Zhong", "Jingzhe Zhu", "Qi Xu", "Liyao Sun", "Yin Wang", "Qingqing Sun", "Shuai Chen", "Tianyi Zhang"], "categories": ["cs.AI", "cs.CL"], "id": "2608.25325", "title": "FinRiskAtlas: Decision-Aligned Evaluation of Large Language Models for Financial Risk Review", "type": "arxiv", "url": "https://arxiv.org/abs/2608.25325"}, "sourceUpdatedAt": "2026-08-26T03:13:15Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "Addresses the gap between broad financial benchmarks and workflow-specific decisions, showing that knowledge scores do not predict operational reliability."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
