{"record": {"aliases": [], "artifacts": [{"id": "gh:msavdert/mandate-bench", "kind": "repo", "url": "https://github.com/msavdert/mandate-bench"}, {"kind": "website", "url": "https://msavdert.github.io/mandate-bench/"}], "categories": ["Finance", "Language & Knowledge", "Reasoning"], "description": {"en": "Evaluates LLM agents' compliance with portfolio-rebalancing mandates through frozen market snapshots and pre-registered metrics."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://github.com/msavdert/mandate-bench", "source": "claire_radar", "source_url": "https://github.com/msavdert/mandate-bench", "title": "Mandate Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:github:msavdert/mandate-bench", "modality": null, "name": "Mandate 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-candidate", "display_eligible": "false", "origin_record_id": "bm_mandate-bench_a638082e", "origin_source": "github", "recognition_confidence": "0.4", "record_sha256": "f63858b3699e2d672630dfb9d11d354b0ecc9a297dc2e6449cb7d820b6df978c", "relation": "unclear", "review_model": "deepseek-v4-pro", "review_state": "ai-name-audit-deferred", "reviewed_at": "2026-08-27T04:18:56.318436Z", "source_url": "https://github.com/msavdert/mandate-bench"}, "publisher": null, "released": "2026-08-22", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:github:msavdert/mandate-bench", "source_url": "https://github.com/msavdert/mandate-bench"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-github-msavdert-mandate-bench", "source": "claire_radar", "source_benchmark_id": "github:msavdert/mandate-bench", "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/msavdert/mandate-bench", "githubScope": "benchmark_repo", "githubStars": 0, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": null, "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": {"state": "not_applicable"}}, "status": "fresh"}, "attentionForecast": {"confidence": "Medium", "horizon": "7d", "reason": "The benchmark addresses a timely gap in AI trading agent evaluation with reproducible methodology and public leaderboard.", "score": 55}, "capabilities": ["Reasoning"], "confidence": "Medium", "construction": "Unknown", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-27T04:18:56.318436Z", "inputHash": "07600f11c57ab5436a033651399aabbfed3990969d927aab771360e6a25643a9", "model": "deepseek-v4-pro"}, "curation": {"decisionReason": "The formal benchmark name is source-grounded, but the public release does not yet meet the independent evidence or adoption threshold.", "model": "deepseek-v4-pro", "reviewedAt": "2026-08-27T04:18:56.318436Z", "state": "ai-name-audit-deferred"}, "dataStatus": "primary-source-candidate", "demo": false, "description": "Evaluates LLM agents' compliance with portfolio-rebalancing mandates through frozen market snapshots and pre-registered metrics.", "discoverySources": [{"id": "github:msavdert/mandate-bench", "type": "github", "url": "https://github.com/msavdert/mandate-bench"}], "displayEligible": false, "domainCuration": {"method": "rules-v1", "state": "auto"}, "evaluationMode": "public_reusable", "evidence": {"reasonCodes": ["discovered via github", "benchmark term in abstract", "evaluation protocol evidence", "public artifact URL", "no explicit benchmark release evidence"], "snippet": "mandate-bench Behavioral benchmarking of LLM agents on a fixed portfolio-rebalancing task: mandate compliance, decision consistency, reasoning-action agreement agents benchmark instruction-following llm reproducibility # Mandate Bench Behavioral benchmarking of LLM agents on a fixed portfolio-rebalancing task: mandate compliance, decision consistency, and reasoning-action agreement."}, "familyId": "bmf_692dbb1815c5", "firstSeenAt": "2026-08-23", "heat": null, "id": "bm_mandate-bench_a638082e", "indexedAt": "2026-08-23T05:46:57.857309Z", "industrySectors": ["Financial Services"], "links": {"code": "https://github.com/msavdert/mandate-bench", "project": "https://msavdert.github.io/mandate-bench/"}, "metrics": [], "motivation": "mandate-bench Behavioral benchmarking of LLM agents on a fixed portfolio-rebalancing task: mandate compliance, decision consistency, reasoning-action agreement agents benchmark instruction-following llm reproducibility # Mandate Bench Behavioral benchmarking of LLM agents on a fixed portfolio-rebalancing task: mandate compliance, decision consistency, and reasoning-action agreement.", "name": "Mandate Bench", "oneLine": "Evaluates LLM agents' compliance with portfolio-rebalancing mandates through frozen market snapshots and pre-registered metrics.", "paperTitle": "mandate-bench", "primaryDomain": "Finance", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://github.com/msavdert/mandate-bench", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-08-23T05:46:57.857309Z"}, "publications": [], "publishers": [{"name": "Mandate Bench Team", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://github.com/msavdert/mandate-bench"}], "ranking": {"90d": {"confidence": "Low", "coverage": 0.55, "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": 0.0, "value": 0}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.55, "rank": 496, "score": 23}, "method": "attention-ranking-v13", "rank": 496, "score": 23}}, "readiness": "Runnable", "recognitionConfidence": 0.4, "relation": "unclear", "releasedAt": "2026-08-22", "source": {"authors": ["msavdert"], "categories": [], "id": "github:msavdert/mandate-bench", "title": "mandate-bench", "type": "github", "url": "https://github.com/msavdert/mandate-bench"}, "sourceUpdatedAt": "2026-08-23T02:03:49Z", "topics": ["Reasoning"], "venueAttempts": [], "whyItMatters": "Shifts agent evaluation from noisy profit metrics to behavioral consistency and rule adherence, offering a reproducible standard for financial agents."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
