{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.24162", "kind": "paper", "url": "https://arxiv.org/abs/2606.24162"}, {"id": "gh:umich-foreseer/behaviorbench_eval", "kind": "repo", "url": "https://github.com/umich-foreseer/behaviorbench_eval"}, {"kind": "website", "url": "https://umich-foreseer.github.io/behaviorbench/"}], "authors": ["Jin Huang", "Yutong Xie", "Wanli Song", "Xingjian Zhang", "Owen Yang", "Walter Yuan", "Matthew O. Jackson", "Qiaozhu Mei"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.24162", "source_url": "https://arxiv.org/abs/2606.24162"}, "categories": ["Factuality", "General AI", "Language & Knowledge", "cs.CL"], "description": {"en": "Evaluates foundation models on four behavioral science capabilities: behavior prediction and simulation, strategic decision-making, subject-trait inference, and behavioral knowledge application, assessing both individual-level and distributional alignment."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.24162", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.24162", "title": "BehaviorBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["University of Michigan", "Samjin Pharm (South Korea)", "ILJIN Group (South Korea)", "Santa Fe Institute", "Stanford University"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.24162", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.24162", "source_url": "https://openalex.org/W7165780472"}, "key": "claire-radar:2606.24162", "modality": null, "name": "BehaviorBench", "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_behaviorbench_01c04f85", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "e1c7f9b84eddf43942dfcbfeb795e74ee90ed4c502075399160edf2b72f57542", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.24162"}, "publisher": null, "released": "2026-06-23", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.24162", "source_url": "https://arxiv.org/abs/2606.24162"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-24162", "source": "claire_radar", "source_benchmark_id": "2606.24162", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Language & Knowledge", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": "https://github.com/umich-foreseer/behaviorbench_eval", "githubScope": "benchmark_repo", "githubStars": 1, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": 0, "hfPaperUrl": "https://huggingface.co/papers/2606.24162", "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": {"checkedAt": "2026-10-04T15:31:48.030916Z", "lastSuccessfulDate": "2026-10-04", "state": "stale"}}, "status": "fresh"}, "capabilities": ["Factuality"], "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": "d6eff0c3c37a7bb9add1c0946432270af6262242cf25f20be88b1394976141e9", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "Evaluates foundation models on four behavioral science capabilities: behavior prediction and simulation, strategic decision-making, subject-trait inference, and behavioral knowledge application, assessing both individual-level and distributional alignment.", "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", "public artifact URL"], "snippet": "We introduce BehaviorBench, a comprehensive benchmark that evaluates foundation models along four core capabilities: (1) behavior prediction and simulation, (2) strategic decision-making, (3) subject-trait inference, and (4) behavioral knowledge application."}, "familyId": "bmf_2d286f1be0d2", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [{"evidence": [{"basis": "linked-from-project", "linkedUrl": "https://github.com/umich-foreseer/behaviorbench_eval", "url": "https://umich-foreseer.github.io/behaviorbench/"}], "scope": "benchmark_repo", "url": "https://github.com/umich-foreseer/behaviorbench_eval", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_behaviorbench_01c04f85", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/umich-foreseer/behaviorbench_eval", "data": null, "hfPaper": "https://huggingface.co/papers/2606.24162", "paper": "https://arxiv.org/abs/2606.24162", "pdf": "https://arxiv.org/pdf/2606.24162", "project": "https://umich-foreseer.github.io/behaviorbench/", "report": "https://arxiv.org/abs/2606.24162"}, "metrics": [], "motivation": "Foundation models have been increasingly applied to behavioral science domains such as psychology, sociology, and economics.", "name": "BehaviorBench", "oneLine": "Evaluates foundation models on four behavioral science capabilities: behavior prediction and simulation, strategic decision-making, subject-trait inference, and behavioral knowledge application, assessing both individual-level and distributional alignment.", "paperTitle": "BehaviorBench: Benchmarking Foundation Models for Behavioral Science Tasks", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.24162", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "publishers": [{"name": "University of Michigan Foreseer Lab", "organizationType": "academic-lab", "role": "benchmark-publisher", "sourceUrl": "https://umich-foreseer.github.io/behaviorbench/"}], "ranking": {}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-23", "source": {"authors": ["Jin Huang", "Yutong Xie", "Wanli Song", "Xingjian Zhang", "Walter Yuan", "Matthew O. Jackson", "Qiaozhu Mei"], "categories": ["cs.CL", "cs.LG"], "id": "2606.24162", "title": "BehaviorBench: Benchmarking Foundation Models for Behavioral Science Tasks", "type": "arxiv", "url": "https://arxiv.org/abs/2606.24162"}, "sourceUpdatedAt": "2026-06-23T05:30:54Z", "topics": ["cs.CL"], "venueAttempts": [], "whyItMatters": "Addresses the lack of systematic evaluation of foundation models in behavioral science, providing a standardized benchmark that captures population-level validity, helping researchers and practitioners choose models for behavioral simulation and analysis."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
