{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.04184", "kind": "paper", "url": "https://arxiv.org/abs/2606.04184"}], "authors": ["Weidong Tang", "Jierui Li", "Yueling Hou", "Zihan Mei", "Can Zhang", "Xinyan Wan", "Zhiyuan Liang", "Pengfei Zhou", "Yang You", "Wangbo Zhao"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.04184", "source_url": "https://arxiv.org/abs/2606.04184"}, "categories": ["General AI", "Multimodal"], "description": {"en": "GroupToM-Bench is a multimodal benchmark for evaluating group-level theory of mind through a seven-level cognitive audit framework."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.04184", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.04184", "title": "GroupToM-Bench"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "institutions": ["Xidian University", "National University of Singapore", "University of Electronic Science and Technology of China", "University of Science and Technology of China"], "institutions_reference": {"basis": "openalex_linked_institutions", "doi": "10.48550/arxiv.2606.04184", "retrieved_at": "2026-11-04", "source_key": "claire-radar:2606.04184", "source_url": "https://openalex.org/W7163534005"}, "key": "claire-radar:2606.04184", "modality": null, "name": "GroupToM-Bench", "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_grouptom-bench_12e21c5f", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "dffdfacfbeb1f8a428128196fbb41f580203786cd00641ba22a0da7d5b7206d6", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.04184"}, "publisher": null, "released": "2026-06-02", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.04184", "source_url": "https://arxiv.org/abs/2606.04184"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-04184", "source": "claire_radar", "source_benchmark_id": "2606.04184", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Unknown", "applicationDomains": ["General AI"], "area": "Multimodal", "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/2606.04184", "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": "9680814c9d1989b4a3c300d553df134a3700805fa2927ed01bc46dfaacb3f9f7", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "GroupToM-Bench is a multimodal benchmark for evaluating group-level theory of mind through a seven-level cognitive audit framework.", "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 present GroupToM-Bench, the first multimodal benchmark for group-level ToM, built around a causal chain spanning micro-level BDI states (belief, desire, intention), meso-level group tension and structural constraints, and macro-level outcome prediction and mechanistic attribution."}, "familyId": "bmf_e0f69bf1e272", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_grouptom-bench_12e21c5f", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.04184", "paper": "https://arxiv.org/abs/2606.04184", "pdf": "https://arxiv.org/pdf/2606.04184", "project": null, "report": "https://arxiv.org/abs/2606.04184"}, "metrics": [], "motivation": "True general intelligence requires not only a model of the physical world but also a social world model: the capacity to infer how individual mental states interact and crystallize into group-level outcomes.", "name": "GroupToM-Bench", "oneLine": "GroupToM-Bench is a multimodal benchmark for evaluating group-level theory of mind through a seven-level cognitive audit framework.", "paperTitle": "GroupToM-Bench: Benchmarking Group Theory of Mind and Nonlinear Social Emergence in MLLMs", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.04184", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-02", "source": {"authors": ["Weidong Tang", "Jierui Li", "Yueling Hou", "Zihan Mei", "Can Zhang", "Xinyan Wan", "Zhiyuan Liang", "Pengfei Zhou", "Yang You", "Wangbo Zhao"], "categories": ["cs.CV"], "id": "2606.04184", "title": "GroupToM-Bench: Benchmarking Group Theory of Mind and Nonlinear Social Emergence in MLLMs", "type": "arxiv", "url": "https://arxiv.org/abs/2606.04184"}, "sourceUpdatedAt": "2026-06-15T07:53:28Z", "topics": ["Multimodal"], "venueAttempts": [], "whyItMatters": "It probes a gap in social cognition capabilities of multimodal LLMs, with implications for understanding emergent group behavior."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
