{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2607.19235", "kind": "paper", "url": "https://arxiv.org/abs/2607.19235"}], "authors": ["Ziyi Wang", "Yuhang Wu", "Dongxu Piao", "Xingyu Liu", "Tianhui Zhou", "Miao Liu"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2607.19235", "source_url": "https://arxiv.org/abs/2607.19235"}, "categories": ["General AI", "Multimodal", "Reasoning"], "description": {"en": "MeetingToM evaluates multimodal LLMs on theory-of-mind reasoning in multi-party meetings, including pseudo-consensus detection, across three levels: subject, dyad, and group. It provides a unified evaluation protocol."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2607.19235", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2607.19235", "title": "MeetingToM"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2607.19235", "modality": null, "name": "MeetingToM", "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_meetingtom_9e241987", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "ae42fab699dc51f19aae3f2b8e1e4e01700924c6f3abebe7546037559dfd9b02", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2607.19235"}, "publisher": null, "released": "2026-07-21", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2607.19235", "source_url": "https://arxiv.org/abs/2607.19235"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2607-19235", "source": "claire_radar", "source_benchmark_id": "2607.19235", "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": 0, "hfPaperUrl": "https://huggingface.co/papers/2607.19235", "observedAt": "2026-10-04T15:31:48.030916Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"observedAt": "2026-10-04T15:31:48.030916Z", "state": "fresh"}}, "status": "fresh"}, "capabilities": ["Reasoning"], "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": "68b984db09633bd4ed37499e16247e584a24a1785d41080dc103e8dc04511726", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "MeetingToM evaluates multimodal LLMs on theory-of-mind reasoning in multi-party meetings, including pseudo-consensus detection, across three levels: subject, dyad, and group. It provides a unified evaluation protocol.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "We introduce MeetingToM, a benchmark for complex social behavior reasoning in naturalistic multi-party meetings."}, "familyId": "bmf_69648c95f671", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_meetingtom_9e241987", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2607.19235", "paper": "https://arxiv.org/abs/2607.19235", "pdf": "https://arxiv.org/pdf/2607.19235", "project": null, "report": "https://arxiv.org/abs/2607.19235"}, "metrics": [], "motivation": "Theory of Mind (ToM), the ability to infer other's beliefs, intentions, and states of knowledge, is central to social interaction, yet remains challenging for current Multimodal Large Language Models (MLLMs), especially in multi-party meetings where cues are distributed across speech and behavior.", "name": "MeetingToM", "oneLine": "MeetingToM evaluates multimodal LLMs on theory-of-mind reasoning in multi-party meetings, including pseudo-consensus detection, across three levels: subject, dyad, and group. It provides a unified evaluation protocol.", "paperTitle": "MeetingToM: Evaluating Multimodal LLMs on Theory-of-Mind Reasoning in Multi-Party Meetings", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2607.19235", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {"90d": {"confidence": "Low", "coverage": 0.15, "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": 0.0, "value": 0}}, "confidence": "Low", "coverage": 0.15, "rank": null, "score": 43}, "method": "attention-ranking-v13", "rank": null, "score": 43}}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-07-21", "source": {"authors": ["Ziyi Wang", "Yuhang Wu", "Dongxu Piao", "Xingyu Liu", "Tianhui Zhou", "Miao Liu"], "categories": ["cs.CL", "cs.CV"], "id": "2607.19235", "title": "MeetingToM: Evaluating Multimodal LLMs on Theory-of-Mind Reasoning in Multi-Party Meetings", "type": "arxiv", "url": "https://arxiv.org/abs/2607.19235"}, "sourceUpdatedAt": "2026-07-21T16:05:49Z", "topics": ["Multimodal", "Reasoning"], "venueAttempts": [], "whyItMatters": "It covers latent social states and group dynamics often missing in existing ToM benchmarks, revealing limitations in integrating non-verbal cues and inferring hidden attitudes."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
