{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GMYHVE7RPZPY5D2FR4QWOJFHYH","short_pith_number":"pith:GMYHVE7R","schema_version":"1.0","canonical_sha256":"33307a93f17e5f8e8f458f216724a7c1e5c5987fb5530fbb7a81b5d87e595f0b","source":{"kind":"arxiv","id":"2606.04184","version":1},"attestation_state":"computed","paper":{"title":"GroupToM-Bench: Benchmarking Group Theory of Mind and Nonlinear Social Emergence in MLLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Can Zhang, Jierui Li, Pengfei Zhou, Wangbo Zhao, Weidong Tang, Xinyan Wan, Yang You, Yueling Hou, Zhiyuan Liang, Zihan Mei","submitted_at":"2026-06-02T20:06:32Z","abstract_excerpt":"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. Despite notable progress in individual-level Theory of Mind (ToM) reasoning, existing multimodal large language models fail at this broader task. Collective behavior emerges non-linearly from social tensions, conformity dynamics, and structural constraints, meaning it cannot be recovered by merely summing individual intentions. We present GroupToM-Bench, the first multimodal benchmark for "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.04184","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-02T20:06:32Z","cross_cats_sorted":[],"title_canon_sha256":"7e300f7657f3b5afd5a604e6eaac200fcb767679a8163bdef98d1a9101fb5d92","abstract_canon_sha256":"78085a1fccf6a58d5b96c78f28a06cf36fe8e8dd4bc5e9b05a4fe4144e20b8c8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:08:19.404864Z","signature_b64":"cd7oW480K47dnZiV5meuPhOeAjVwa8tdugFMp/haBjQbw++3TGb6Sxr2LjAY/UHfMAuQ671VHNXZeFh4cm8lBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"33307a93f17e5f8e8f458f216724a7c1e5c5987fb5530fbb7a81b5d87e595f0b","last_reissued_at":"2026-06-04T01:08:19.404047Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:08:19.404047Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GroupToM-Bench: Benchmarking Group Theory of Mind and Nonlinear Social Emergence in MLLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Can Zhang, Jierui Li, Pengfei Zhou, Wangbo Zhao, Weidong Tang, Xinyan Wan, Yang You, Yueling Hou, Zhiyuan Liang, Zihan Mei","submitted_at":"2026-06-02T20:06:32Z","abstract_excerpt":"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. Despite notable progress in individual-level Theory of Mind (ToM) reasoning, existing multimodal large language models fail at this broader task. Collective behavior emerges non-linearly from social tensions, conformity dynamics, and structural constraints, meaning it cannot be recovered by merely summing individual intentions. We present GroupToM-Bench, the first multimodal benchmark for "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04184","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.04184/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.04184","created_at":"2026-06-04T01:08:19.404139+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.04184v1","created_at":"2026-06-04T01:08:19.404139+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04184","created_at":"2026-06-04T01:08:19.404139+00:00"},{"alias_kind":"pith_short_12","alias_value":"GMYHVE7RPZPY","created_at":"2026-06-04T01:08:19.404139+00:00"},{"alias_kind":"pith_short_16","alias_value":"GMYHVE7RPZPY5D2F","created_at":"2026-06-04T01:08:19.404139+00:00"},{"alias_kind":"pith_short_8","alias_value":"GMYHVE7R","created_at":"2026-06-04T01:08:19.404139+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GMYHVE7RPZPY5D2FR4QWOJFHYH","json":"https://pith.science/pith/GMYHVE7RPZPY5D2FR4QWOJFHYH.json","graph_json":"https://pith.science/api/pith-number/GMYHVE7RPZPY5D2FR4QWOJFHYH/graph.json","events_json":"https://pith.science/api/pith-number/GMYHVE7RPZPY5D2FR4QWOJFHYH/events.json","paper":"https://pith.science/paper/GMYHVE7R"},"agent_actions":{"view_html":"https://pith.science/pith/GMYHVE7RPZPY5D2FR4QWOJFHYH","download_json":"https://pith.science/pith/GMYHVE7RPZPY5D2FR4QWOJFHYH.json","view_paper":"https://pith.science/paper/GMYHVE7R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.04184&json=true","fetch_graph":"https://pith.science/api/pith-number/GMYHVE7RPZPY5D2FR4QWOJFHYH/graph.json","fetch_events":"https://pith.science/api/pith-number/GMYHVE7RPZPY5D2FR4QWOJFHYH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GMYHVE7RPZPY5D2FR4QWOJFHYH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GMYHVE7RPZPY5D2FR4QWOJFHYH/action/storage_attestation","attest_author":"https://pith.science/pith/GMYHVE7RPZPY5D2FR4QWOJFHYH/action/author_attestation","sign_citation":"https://pith.science/pith/GMYHVE7RPZPY5D2FR4QWOJFHYH/action/citation_signature","submit_replication":"https://pith.science/pith/GMYHVE7RPZPY5D2FR4QWOJFHYH/action/replication_record"}},"created_at":"2026-06-04T01:08:19.404139+00:00","updated_at":"2026-06-04T01:08:19.404139+00:00"}