{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2608.04009", "kind": "paper", "url": "https://arxiv.org/abs/2608.04009"}, {"id": "gh:co-minder/societybench-codebase", "kind": "repo", "url": "https://github.com/co-minder/SocietyBench-codebase"}, {"kind": "website", "url": "https://co-minder.github.io/Societybench"}], "authors": ["Zhenran Wang", "Zhonghan Bian", "Jinsong Li", "Zhangyang Qi"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2608.04009", "source_url": "https://arxiv.org/abs/2608.04009"}, "categories": ["Factuality", "General AI", "Language & Knowledge", "cs.CL"], "description": {"en": "SocietyBench is a benchmark for forecasting counterfactual social-world evolution, collecting web news and social-media posts to build timelines and generating forecasting questions scored on probability calibration and temporal accuracy."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2608.04009", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2608.04009", "title": "SocietyBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2608.04009", "modality": null, "name": "SocietyBench", "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_societybench_8a44f535", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "36a176ffc2ceda80133721a803493fa43bf83b0c922a86ae7ea12b43d4468be6", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2608.04009"}, "publisher": null, "released": "2026-08-04", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2608.04009", "source_url": "https://arxiv.org/abs/2608.04009"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2608-04009", "source": "claire_radar", "source_benchmark_id": "2608.04009", "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/co-minder/SocietyBench-codebase", "githubScope": "benchmark_repo", "githubStars": 2, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2608.04009", "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", "state": "unavailable"}}, "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": "c56bd9b46af2a4422d3b738fef97316b2f035d9027b08c18675b5364c001d03e", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "SocietyBench is a benchmark for forecasting counterfactual social-world evolution, collecting web news and social-media posts to build timelines and generating forecasting questions scored on probability calibration and temporal accuracy.", "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 SocietyBench, an end-to-end benchmark that takes a one-line event topic, collects Web news and social-media posts across five platforms, distills them into a date-indexed timeline that keeps factual events and a public-opinion layer separate, and then turns every cutoff date on that timeline into an audited bank of forecasting questions."}, "familyId": "bmf_2d0da2d0dcde", "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/co-minder/SocietyBench-codebase", "url": "https://co-minder.github.io/Societybench"}], "scope": "benchmark_repo", "url": "https://github.com/co-minder/SocietyBench-codebase", "verification": "source-linked"}], "status": "linked"}, "heat": null, "id": "bm_societybench_8a44f535", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": "https://github.com/co-minder/SocietyBench-codebase", "data": null, "hfPaper": "https://huggingface.co/papers/2608.04009", "paper": "https://arxiv.org/abs/2608.04009", "pdf": "https://arxiv.org/pdf/2608.04009", "project": "https://co-minder.github.io/Societybench", "report": "https://arxiv.org/abs/2608.04009"}, "metrics": [], "motivation": "Large language models (LLMs), and the agents built on top of them, are now benchmarked heavily on whether they can finish a task -- fix a bug, drive a browser, operate a GUI.", "name": "SocietyBench", "oneLine": "SocietyBench is a benchmark for forecasting counterfactual social-world evolution, collecting web news and social-media posts to build timelines and generating forecasting questions scored on probability calibration and temporal accuracy.", "paperTitle": "SocietyBench: Forecasting Counterfactual Social-World Evolution", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2608.04009", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "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": 0.1466449917496476, "value": 2}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.55, "rank": 266, "score": 31}, "method": "attention-ranking-v13", "rank": 266, "score": 31}}, "readiness": "Runnable", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-08-04", "source": {"authors": ["Zhenran Wang", "Zhonghan Bian", "Jinsong Li", "Zhangyang Qi"], "categories": ["cs.CL"], "id": "2608.04009", "title": "SocietyBench: Forecasting Counterfactual Social-World Evolution", "type": "arxiv", "url": "https://arxiv.org/abs/2608.04009"}, "sourceUpdatedAt": "2026-08-07T17:15:28Z", "topics": ["cs.CL"], "venueAttempts": [], "whyItMatters": "Current benchmarks focus on task completion, not on social understanding and forecasting. SocietyBench measures how well models understand and predict social events, providing a complementary evaluation axis."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
