{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.31522", "kind": "paper", "url": "https://arxiv.org/abs/2606.31522"}], "authors": ["Muhammad Usman Safder", "Ayesha Gull", "Rania Elbadry", "Fan Zhang", "Yankai Chen", "Xueqing Peng", "Xue", "Liu", "Preslav Nakov", "Zhuohan Xie"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.31522", "source_url": "https://arxiv.org/abs/2606.31522"}, "categories": ["Agents & Tool Use", "Finance", "cs.CL"], "description": {"en": "Evaluates the longitudinal stability of behavioral mandates in LLM-based financial agents using a synthetic market simulation that decouples observable price from hidden fundamental value, scoring mandate adherence across calm, crash, and bubble market regimes."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.31522", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.31522", "title": "FinPersona-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2606.31522", "modality": null, "name": "FinPersona-Bench", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "Medium", "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_finpersona-bench_6543120b", "origin_source": "arxiv", "recognition_confidence": "0.85", "record_sha256": "cd18f929e3395b68329aa64031d75a8a64f23f430cc77078383baadddfb32ca9", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.31522"}, "publisher": null, "released": "2026-06-30", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.31522", "source_url": "https://arxiv.org/abs/2606.31522"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-31522", "source": "claire_radar", "source_benchmark_id": "2606.31522", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Machine Generated", "applicationDomains": ["Finance"], "area": "Agents & Tool Use", "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/2606.31522", "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": "Medium", "construction": "Original Synthetic", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "4dcfae791689a136b0d677536f5d291ecc206f601cbad44aa895d432c954ac8c", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates the longitudinal stability of behavioral mandates in LLM-based financial agents using a synthetic market simulation that decouples observable price from hidden fundamental value, scoring mandate adherence across calm, crash, and bubble market regimes.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["coined title prefix ending in Bench or Benchmark", "benchmark release stated in one sentence"], "snippet": "To measure MSD objectively, we introduce FinPersona-Bench, a simulation benchmark in which a synthetic market decouples observable price from hidden fundamental value, enabling falsifiable evaluation across three failure modes: trading without signal in calm markets, panic-selling during crashes, and ignoring fundamental value during speculative bubbles."}, "familyId": "bmf_47d6e24194de", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_finpersona-bench_6543120b", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Financial Services"], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.31522", "paper": "https://arxiv.org/abs/2606.31522", "pdf": "https://arxiv.org/pdf/2606.31522", "project": null, "report": "https://arxiv.org/abs/2606.31522"}, "metrics": [], "motivation": "Large Language Models (LLMs) are increasingly deployed as autonomous financial agents initialized with explicit behavioral mandates such as \"preserve capital\" or \"avoid speculative bets\" that are meant to govern every decision throughout deployment.", "name": "FinPersona-Bench", "oneLine": "Evaluates the longitudinal stability of behavioral mandates in LLM-based financial agents using a synthetic market simulation that decouples observable price from hidden fundamental value, scoring mandate adherence across calm, crash, and bubble market regimes.", "paperTitle": "FinPersona-Bench: A Benchmark for Longitudinal Psychometric Stability of Autonomous Financial Agents", "primaryDomain": "Finance", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.31522", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "arXiv", "organizationType": "community", "role": "benchmark-publisher", "sourceUrl": "https://arxiv.org/abs/2606.31522"}], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 0.85, "relation": "introduces", "releasedAt": "2026-06-30", "source": {"authors": ["Muhammad Usman Safder", "Ayesha Gull", "Rania Elbadry", "Fan Zhang", "Yankai Chen", "Xueqing Peng", "Xue (Steve) Liu", "Preslav Nakov", "Zhuohan Xie"], "categories": ["cs.CL", "cs.AI"], "id": "2606.31522", "title": "FinPersona-Bench: A Benchmark for Longitudinal Psychometric Stability of Autonomous Financial Agents", "type": "arxiv", "url": "https://arxiv.org/abs/2606.31522"}, "sourceUpdatedAt": "2026-07-01T13:27:11Z", "topics": ["cs.CL"], "venueAttempts": [], "whyItMatters": "It addresses the gap in evaluating long-horizon behavioral consistency of autonomous financial agents, providing a falsifiable method to measure mandate salience decay and informing deployment decisions for mandate-aware re-grounding strategies."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
