{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2607.23740", "kind": "paper", "url": "https://arxiv.org/abs/2607.23740"}], "authors": ["ZenGen Team", "Ao Xiang", "Bi Jingping", "Chen Jiahui", "Chen Lehan", "Chen Yilin", "Cheng Xueqi", "Fan Yixing", "Gan Kairong", "Gao Haowen", "Gao Jinhua", "Gao Shuxuan", "Gong Chang", "Guo Jiafeng", "Guo Ruijie", "Han Zhouyu", "He Guangfu", "He Yichun", "Jiang Shuo", "Jing Shaoling", "Jing Ya", "Lei Chenhao", "Lei Yan", "Li Anqi", "Li Chengao", "Li Haoyu", "Li Shitian", "Liang Xinjian", "Liu Zhaoge", "Lyu Xingyu", "Nie Zhuwei", "Pang Liang", "Quan Zeping", "Shan Shiguang", "Shen Huawei", "Tang Xinran", "Tian Feng", "Wang Qian", "Wang Ruiping", "Wang Xiaohong", "Xia Zaiyu", "Xiao Yi", "Xu Jiayuan", "Xu Kehan", "Xu Qianqian", "Xu Tianyu", "Xu Yongjun", "Xue Yuanhai", "Yang Haoming", "Yang Jun", "Yao Di", "Yu Xiaoming", "Zhang Futong", "Zhang Jie", "Zhang Shixuan", "Zhang Yuxuan", "Zhao Xinyu", "Zhao Zhuoran", "Zhong Yunfei", "Zhu Shengyu"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2607.23740", "source_url": "https://arxiv.org/abs/2607.23740"}, "categories": ["General AI", "Language & Knowledge", "cs.CL"], "description": {"en": "SoMBench evaluates social intelligence in large language models across 3 primary dimensions, 17 secondary dimensions, and 71 task paradigms, with 284 shared scenarios and 3,481 expert-verified instances."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.23740", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.23740", "title": "SoMBench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2607.23740", "modality": null, "name": "SoMBench", "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_sombench_39ae8a74", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "faceb8ab7f7c9f37dcb4def5a0c2c748d2f8ecb0fc249a00d1d0b73b728386b5", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2607.23740"}, "publisher": null, "released": "2026-07-26", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.23740", "source_url": "https://arxiv.org/abs/2607.23740"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-23740", "source": "claire_radar", "source_benchmark_id": "2607.23740", "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": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2607.23740", "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": "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": "f4cb66738e796a59c9a6315c9f98b2ba928dc9b04da86d6947be750a2ca34778", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "SoMBench evaluates social intelligence in large language models across 3 primary dimensions, 17 secondary dimensions, and 71 task paradigms, with 284 shared scenarios and 3,481 expert-verified instances.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact named benchmark artifact released in abstract", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "For measurement, we introduce SoMBench, a psychology-grounded benchmark spanning 3 primary dimensions, 17 secondary dimensions, and 71 task paradigms."}, "familyId": "bmf_06b31d962c2c", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_sombench_39ae8a74", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2607.23740", "paper": "https://arxiv.org/abs/2607.23740", "pdf": "https://arxiv.org/pdf/2607.23740", "project": null, "report": "https://arxiv.org/abs/2607.23740"}, "metrics": [], "motivation": "As large language models move from isolated task solving toward long-term service in human environments, they require social intelligence: the ability to infer mental states, track social relations, reason over norms, and adapt behavior under context.", "name": "SoMBench", "oneLine": "SoMBench evaluates social intelligence in large language models across 3 primary dimensions, 17 secondary dimensions, and 71 task paradigms, with 284 shared scenarios and 3,481 expert-verified instances.", "paperTitle": "Zing: Social Mind for LLMs", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2607.23740", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {"90d": {"confidence": "Low", "coverage": 0.0, "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": null, "value": null}, "hfDatasetDownloads": {"normalization": "log-max", "normalized": null, "value": null}, "hfPaperUpvotes": {"normalization": "log-max", "normalized": null, "value": null}}, "confidence": "Low", "coverage": 0.0, "rank": null, "score": null}, "method": "attention-ranking-v13", "rank": null, "score": null}}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-07-26", "source": {"authors": ["Zing Team", "Ao Xiang", "Bi Jingping", "Chen Jiahui", "Chen Lehan", "Chen Yilin", "Cheng Xueqi", "Fan Yixing", "Gan Kairong", "Gao Haowen", "Gao Jinhua", "Gao Shuxuan", "Gong Chang", "Guo Jiafeng", "Guo Ruijie", "Han Zhouyu", "He Guangfu", "He Yichun", "Jiang Shuo", "Jing Shaoling", "Jing Ya", "Lei Chenhao", "Lei Yan", "Li Anqi", "Li Chengao", "Li Haoyu", "Li Shitian", "Liang Xinjian", "Liu Zhaoge", "Lyu Xingyu", "Nie Zhuwei", "Pang Liang", "Quan Zeping", "Shan Shiguang", "Shen Huawei", "Tang Xinran", "Tian Feng", "Wang Qian", "Wang Ruiping", "Wang Xiaohong", "Xia Zaiyu", "Xiao Yi", "Xu Jiayuan", "Xu Kehan", "Xu Qianqian", "Xu Tianyu", "Xu Yongjun", "Yang Haoming", "Yang Jun", "Yao Di", "Yu Xiaoming", "Zhang Futong", "Zhang Jie", "Zhang Shixuan", "Zhang Yuxuan", "Zhao Xinyu", "Zhao Zhuoran", "Zhong Yunfei", "Zhu Shengyu"], "categories": ["cs.CL"], "id": "2607.23740", "title": "Zing: Social Mind for LLMs", "type": "arxiv", "url": "https://arxiv.org/abs/2607.23740"}, "sourceUpdatedAt": "2026-07-26T16:25:45Z", "topics": ["cs.CL"], "venueAttempts": [], "whyItMatters": "SoMBench targets the gap in evaluating LLMs' social intelligence, providing a structured benchmark to measure capabilities that are increasingly important for long-term deployment in human environments."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
