{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.25984", "kind": "paper", "url": "https://arxiv.org/abs/2606.25984"}], "authors": ["Mingguang Chen", "Bo Qu"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.25984", "source_url": "https://arxiv.org/abs/2606.25984"}, "categories": ["Finance", "Language & Knowledge", "Reasoning"], "description": {"en": "InvestPhilBench is a multi-layer benchmark for evaluating procedural reasoning in investment philosophy, spanning eight cognitive tiers from principle identification to novel framework extrapolation. It includes principle cards, decision-framework cards, and QA questions, with an automated scoring pipeline (BASP) and five algorithmic metrics."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.25984", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.25984", "title": "InvestPhilBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["University of California, Riverside", "IIT Research Institute", "Illinois Institute of Technology"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.25984", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.25984", "source_url": "https://openalex.org/W7165900792"}, "key": "claire-radar:2606.25984", "modality": null, "name": "InvestPhilBench", "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_investphilbench_547d0c00", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "b2701c7eeef6f7147d0476a9ad95a8b75e52dadcea6b858ac35673a611dc785c", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.25984"}, "publisher": null, "released": "2026-06-24", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.25984", "source_url": "https://arxiv.org/abs/2606.25984"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-25984", "source": "claire_radar", "source_benchmark_id": "2606.25984", "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/2606.25984", "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": ["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": "40867a345cfe01336a8ae3495be03bad7db765cf78bb971da89c034bca5b94ef", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "InvestPhilBench is a multi-layer benchmark for evaluating procedural reasoning in investment philosophy, spanning eight cognitive tiers from principle identification to novel framework extrapolation. It includes principle cards, decision-framework cards, and QA questions, with an automated scoring pipeline (BASP) and five algorithmic metrics.", "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 introduce InvestPhilBench, a multi-layer benchmark spanning eight cognitive tiers, from principle identification (L1) to novel framework extrapolation (L8)."}, "familyId": "bmf_2ef9232fbd60", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_investphilbench_547d0c00", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": ["Financial Services"], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.25984", "paper": "https://arxiv.org/abs/2606.25984", "pdf": "https://arxiv.org/pdf/2606.25984", "project": null, "report": "https://arxiv.org/abs/2606.25984"}, "metrics": [], "motivation": "Large language models are increasingly deployed as investment research assistants, yet no benchmark tests whether they can accurately reconstruct and apply the specific procedural decision frameworks of expert investors.", "name": "InvestPhilBench", "oneLine": "InvestPhilBench is a multi-layer benchmark for evaluating procedural reasoning in investment philosophy, spanning eight cognitive tiers from principle identification to novel framework extrapolation. It includes principle cards, decision-framework cards, and QA questions, with an automated scoring pipeline (BASP) and five algorithmic metrics.", "paperTitle": "InvestPhilBench: A Multi-Layer Benchmark for Evaluating Large Language Model Procedural Reasoning in Expert Investment Philosophy", "primaryDomain": "Finance", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.25984", "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/2606.25984"}], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-24", "source": {"authors": ["Mingguang Chen", "Bo Qu"], "categories": ["cs.AI", "cs.LG"], "id": "2606.25984", "title": "InvestPhilBench: A Multi-Layer Benchmark for Evaluating Large Language Model Procedural Reasoning in Expert Investment Philosophy", "type": "arxiv", "url": "https://arxiv.org/abs/2606.25984"}, "sourceUpdatedAt": "2026-07-08T19:50:29Z", "topics": ["Reasoning"], "venueAttempts": [], "whyItMatters": "Fills the gap in testing whether LLMs can accurately reconstruct and apply expert procedural decision frameworks. Provides a reproducible method for scoring procedural reasoning, with a metric (GRA) that exposes deficits hidden by composite scores."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
