{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FFWBTUFHLNYTYOIZPEJTYCCHDR","short_pith_number":"pith:FFWBTUFH","schema_version":"1.0","canonical_sha256":"296c19d0a75b713c391979133c08471c799980982b9f9a1e93f54d52ced39ca4","source":{"kind":"arxiv","id":"2506.09450","version":1},"attestation_state":"computed","paper":{"title":"UniToMBench: Integrating Perspective-Taking to Improve Theory of Mind in LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chris Kim, Kevin Zhu, Nitin Yarlagadda, Prameshwar Thiyagarajan, Shamant Sai, Soumil Garg, Vaishnavi Parimi, Zhangir Meirbek","submitted_at":"2025-06-11T06:55:40Z","abstract_excerpt":"Theory of Mind (ToM), the ability to understand the mental states of oneself and others, remains a challenging area for large language models (LLMs), which often fail to predict human mental states accurately. In this paper, we introduce UniToMBench, a unified benchmark that integrates the strengths of SimToM and TOMBENCH to systematically improve and assess ToM capabilities in LLMs by integrating multi-interaction task designs and evolving story scenarios. Supported by a custom dataset of over 1,000 hand-written scenarios, UniToMBench combines perspective-taking techniques with diverse evalua"},"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":"2506.09450","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-11T06:55:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"23cbc1d2949f073db4f74a14194a94e6d8a3796f02b37e519b53e02b5254b795","abstract_canon_sha256":"8f465b8381aacdb691ddbba2e21fd33e76175e72c6daef88d36c7faa19cb631a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:37.652495Z","signature_b64":"cH9+4HP3wEqKvBZ6GP+fPkLjtN3OpGHGXFif/JUkrVnZ1y9gqqH/MxGEZAhQOn3AhPZ2FL45KSnRwO/eEmOIDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"296c19d0a75b713c391979133c08471c799980982b9f9a1e93f54d52ced39ca4","last_reissued_at":"2026-07-05T11:19:37.651890Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:37.651890Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UniToMBench: Integrating Perspective-Taking to Improve Theory of Mind in LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chris Kim, Kevin Zhu, Nitin Yarlagadda, Prameshwar Thiyagarajan, Shamant Sai, Soumil Garg, Vaishnavi Parimi, Zhangir Meirbek","submitted_at":"2025-06-11T06:55:40Z","abstract_excerpt":"Theory of Mind (ToM), the ability to understand the mental states of oneself and others, remains a challenging area for large language models (LLMs), which often fail to predict human mental states accurately. In this paper, we introduce UniToMBench, a unified benchmark that integrates the strengths of SimToM and TOMBENCH to systematically improve and assess ToM capabilities in LLMs by integrating multi-interaction task designs and evolving story scenarios. Supported by a custom dataset of over 1,000 hand-written scenarios, UniToMBench combines perspective-taking techniques with diverse evalua"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.09450","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/2506.09450/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":"2506.09450","created_at":"2026-07-05T11:19:37.651965+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.09450v1","created_at":"2026-07-05T11:19:37.651965+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.09450","created_at":"2026-07-05T11:19:37.651965+00:00"},{"alias_kind":"pith_short_12","alias_value":"FFWBTUFHLNYT","created_at":"2026-07-05T11:19:37.651965+00:00"},{"alias_kind":"pith_short_16","alias_value":"FFWBTUFHLNYTYOIZ","created_at":"2026-07-05T11:19:37.651965+00:00"},{"alias_kind":"pith_short_8","alias_value":"FFWBTUFH","created_at":"2026-07-05T11:19:37.651965+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/FFWBTUFHLNYTYOIZPEJTYCCHDR","json":"https://pith.science/pith/FFWBTUFHLNYTYOIZPEJTYCCHDR.json","graph_json":"https://pith.science/api/pith-number/FFWBTUFHLNYTYOIZPEJTYCCHDR/graph.json","events_json":"https://pith.science/api/pith-number/FFWBTUFHLNYTYOIZPEJTYCCHDR/events.json","paper":"https://pith.science/paper/FFWBTUFH"},"agent_actions":{"view_html":"https://pith.science/pith/FFWBTUFHLNYTYOIZPEJTYCCHDR","download_json":"https://pith.science/pith/FFWBTUFHLNYTYOIZPEJTYCCHDR.json","view_paper":"https://pith.science/paper/FFWBTUFH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.09450&json=true","fetch_graph":"https://pith.science/api/pith-number/FFWBTUFHLNYTYOIZPEJTYCCHDR/graph.json","fetch_events":"https://pith.science/api/pith-number/FFWBTUFHLNYTYOIZPEJTYCCHDR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FFWBTUFHLNYTYOIZPEJTYCCHDR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FFWBTUFHLNYTYOIZPEJTYCCHDR/action/storage_attestation","attest_author":"https://pith.science/pith/FFWBTUFHLNYTYOIZPEJTYCCHDR/action/author_attestation","sign_citation":"https://pith.science/pith/FFWBTUFHLNYTYOIZPEJTYCCHDR/action/citation_signature","submit_replication":"https://pith.science/pith/FFWBTUFHLNYTYOIZPEJTYCCHDR/action/replication_record"}},"created_at":"2026-07-05T11:19:37.651965+00:00","updated_at":"2026-07-05T11:19:37.651965+00:00"}