{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AKRIN4L5OWCSSMLZPA7UN67BYB","short_pith_number":"pith:AKRIN4L5","schema_version":"1.0","canonical_sha256":"02a286f17d7585293179783f46fbe1c0603fc2cba0a9ad50949713b898cf3e16","source":{"kind":"arxiv","id":"2506.02461","version":1},"attestation_state":"computed","paper":{"title":"XToM: Exploring the Multilingual Theory of Mind for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Cheng Jiayang, Chunkit Chan, Ercong Nie, Ginny Y. Wong, Helmut Schmid, Hinrich Sch\\\"utze, Hongchuan Zeng, Kawai Chung, Simon See, Xinyuan Cheng, Yangqiu Song, Yauwai Yim, Yixiang Fan, Yuzhuo Ao, Zheye Deng, Zhifan Sun, Zhiying Zou","submitted_at":"2025-06-03T05:23:25Z","abstract_excerpt":"Theory of Mind (ToM), the ability to infer mental states in others, is pivotal for human social cognition. Existing evaluations of ToM in LLMs are largely limited to English, neglecting the linguistic diversity that shapes human cognition. This limitation raises a critical question: can LLMs exhibit Multilingual Theory of Mind, which is the capacity to reason about mental states across diverse linguistic contexts? To address this gap, we present XToM, a rigorously validated multilingual benchmark that evaluates ToM across five languages and incorporates diverse, contextually rich task scenario"},"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":"2506.02461","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-03T05:23:25Z","cross_cats_sorted":[],"title_canon_sha256":"3c8c4285511ada4e27b3055becf86660b87c68ebbf1af0ae6bdaa08f4b5835c8","abstract_canon_sha256":"96dcd54773407df883c9cab2d91085d6a8ed59a8f9d58fdb7a4ea6a9cd145f9f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:02.477873Z","signature_b64":"fGVLlSZ5boMs9DhjdLhzy6rEiwYgDD4zHnNGkjtzUwSz5SVtBR+px3NaKq7onc1Zq/ZFpvryRHHEO1e0OCH7Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"02a286f17d7585293179783f46fbe1c0603fc2cba0a9ad50949713b898cf3e16","last_reissued_at":"2026-07-05T11:15:02.477445Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:02.477445Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"XToM: Exploring the Multilingual Theory of Mind for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Cheng Jiayang, Chunkit Chan, Ercong Nie, Ginny Y. Wong, Helmut Schmid, Hinrich Sch\\\"utze, Hongchuan Zeng, Kawai Chung, Simon See, Xinyuan Cheng, Yangqiu Song, Yauwai Yim, Yixiang Fan, Yuzhuo Ao, Zheye Deng, Zhifan Sun, Zhiying Zou","submitted_at":"2025-06-03T05:23:25Z","abstract_excerpt":"Theory of Mind (ToM), the ability to infer mental states in others, is pivotal for human social cognition. Existing evaluations of ToM in LLMs are largely limited to English, neglecting the linguistic diversity that shapes human cognition. This limitation raises a critical question: can LLMs exhibit Multilingual Theory of Mind, which is the capacity to reason about mental states across diverse linguistic contexts? To address this gap, we present XToM, a rigorously validated multilingual benchmark that evaluates ToM across five languages and incorporates diverse, contextually rich task scenario"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02461","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/2506.02461/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":"2506.02461","created_at":"2026-07-05T11:15:02.477507+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.02461v1","created_at":"2026-07-05T11:15:02.477507+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02461","created_at":"2026-07-05T11:15:02.477507+00:00"},{"alias_kind":"pith_short_12","alias_value":"AKRIN4L5OWCS","created_at":"2026-07-05T11:15:02.477507+00:00"},{"alias_kind":"pith_short_16","alias_value":"AKRIN4L5OWCSSMLZ","created_at":"2026-07-05T11:15:02.477507+00:00"},{"alias_kind":"pith_short_8","alias_value":"AKRIN4L5","created_at":"2026-07-05T11:15:02.477507+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.24635","citing_title":"HiMed: Incentivizing Hindi Reasoning in Medical LLMs","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AKRIN4L5OWCSSMLZPA7UN67BYB","json":"https://pith.science/pith/AKRIN4L5OWCSSMLZPA7UN67BYB.json","graph_json":"https://pith.science/api/pith-number/AKRIN4L5OWCSSMLZPA7UN67BYB/graph.json","events_json":"https://pith.science/api/pith-number/AKRIN4L5OWCSSMLZPA7UN67BYB/events.json","paper":"https://pith.science/paper/AKRIN4L5"},"agent_actions":{"view_html":"https://pith.science/pith/AKRIN4L5OWCSSMLZPA7UN67BYB","download_json":"https://pith.science/pith/AKRIN4L5OWCSSMLZPA7UN67BYB.json","view_paper":"https://pith.science/paper/AKRIN4L5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.02461&json=true","fetch_graph":"https://pith.science/api/pith-number/AKRIN4L5OWCSSMLZPA7UN67BYB/graph.json","fetch_events":"https://pith.science/api/pith-number/AKRIN4L5OWCSSMLZPA7UN67BYB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AKRIN4L5OWCSSMLZPA7UN67BYB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AKRIN4L5OWCSSMLZPA7UN67BYB/action/storage_attestation","attest_author":"https://pith.science/pith/AKRIN4L5OWCSSMLZPA7UN67BYB/action/author_attestation","sign_citation":"https://pith.science/pith/AKRIN4L5OWCSSMLZPA7UN67BYB/action/citation_signature","submit_replication":"https://pith.science/pith/AKRIN4L5OWCSSMLZPA7UN67BYB/action/replication_record"}},"created_at":"2026-07-05T11:15:02.477507+00:00","updated_at":"2026-07-05T11:15:02.477507+00:00"}