{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:T7RMH2T3SGRUZEDC3HW6TGPJRG","short_pith_number":"pith:T7RMH2T3","schema_version":"1.0","canonical_sha256":"9fe2c3ea7b91a34c9062d9ede999e98991757854ba58c8e1b879a08145483ded","source":{"kind":"arxiv","id":"2310.03051","version":1},"attestation_state":"computed","paper":{"title":"How FaR Are Large Language Models From Agents with Theory-of-Mind?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aditya Gupta, Aida Nematzadeh, Aman Madaan, Ari Holtzman, Jay Pujara, Kevin R. McKee, Manaal Faruqui, Pei Zhou, Shyam Upadhyay, Srividya Pranavi Potharaju, Swaroop Mishra, Xiang Ren","submitted_at":"2023-10-04T06:47:58Z","abstract_excerpt":"\"Thinking is for Doing.\" Humans can infer other people's mental states from observations--an ability called Theory-of-Mind (ToM)--and subsequently act pragmatically on those inferences. Existing question answering benchmarks such as ToMi ask models questions to make inferences about beliefs of characters in a story, but do not test whether models can then use these inferences to guide their actions. We propose a new evaluation paradigm for large language models (LLMs): Thinking for Doing (T4D), which requires models to connect inferences about others' mental states to actions in social scenari"},"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":"2310.03051","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-04T06:47:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f82e8407a9d9c13603e48e95a93a6aad9f964dd76551332776898f1e5c8de739","abstract_canon_sha256":"593788663157b252b6a57a3d5b576199cf37090f2be2fba594d1cb18a1ff72a4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:57:28.270959Z","signature_b64":"dYJCzY7rcQTAMvaigLqcKtUd2jQTU6eYMxTP6VA+94AiZk4zALQw5aQiiWWfqzuKejzos/ByPw1oQZcrros5AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9fe2c3ea7b91a34c9062d9ede999e98991757854ba58c8e1b879a08145483ded","last_reissued_at":"2026-07-05T06:57:28.270469Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:57:28.270469Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How FaR Are Large Language Models From Agents with Theory-of-Mind?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aditya Gupta, Aida Nematzadeh, Aman Madaan, Ari Holtzman, Jay Pujara, Kevin R. McKee, Manaal Faruqui, Pei Zhou, Shyam Upadhyay, Srividya Pranavi Potharaju, Swaroop Mishra, Xiang Ren","submitted_at":"2023-10-04T06:47:58Z","abstract_excerpt":"\"Thinking is for Doing.\" Humans can infer other people's mental states from observations--an ability called Theory-of-Mind (ToM)--and subsequently act pragmatically on those inferences. Existing question answering benchmarks such as ToMi ask models questions to make inferences about beliefs of characters in a story, but do not test whether models can then use these inferences to guide their actions. We propose a new evaluation paradigm for large language models (LLMs): Thinking for Doing (T4D), which requires models to connect inferences about others' mental states to actions in social scenari"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.03051","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/2310.03051/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":"2310.03051","created_at":"2026-07-05T06:57:28.270528+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.03051v1","created_at":"2026-07-05T06:57:28.270528+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.03051","created_at":"2026-07-05T06:57:28.270528+00:00"},{"alias_kind":"pith_short_12","alias_value":"T7RMH2T3SGRU","created_at":"2026-07-05T06:57:28.270528+00:00"},{"alias_kind":"pith_short_16","alias_value":"T7RMH2T3SGRUZEDC","created_at":"2026-07-05T06:57:28.270528+00:00"},{"alias_kind":"pith_short_8","alias_value":"T7RMH2T3","created_at":"2026-07-05T06:57:28.270528+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.31916","citing_title":"Theory of Mind and Persuasion Beyond Conversation: Assessing the Capacity of LLMs to Induce Belief States via Planning and Action","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2507.21035","citing_title":"GenoMAS: A Multi-Agent Framework for Scientific Discovery via Code-Driven Gene Expression Analysis","ref_index":165,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09826","citing_title":"EnactToM: An Evolving Benchmark for Functional Theory of Mind in Embodied Agents","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15205","citing_title":"Does Theory of Mind Improvement Really Benefit Human-AI Interactions? Empirical Findings from Interactive Evaluations","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09826","citing_title":"EnactToM: An Evolving Benchmark for Functional Theory of Mind in Embodied Agents","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20833","citing_title":"AVISE: Framework for Evaluating the Security of AI Systems","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T7RMH2T3SGRUZEDC3HW6TGPJRG","json":"https://pith.science/pith/T7RMH2T3SGRUZEDC3HW6TGPJRG.json","graph_json":"https://pith.science/api/pith-number/T7RMH2T3SGRUZEDC3HW6TGPJRG/graph.json","events_json":"https://pith.science/api/pith-number/T7RMH2T3SGRUZEDC3HW6TGPJRG/events.json","paper":"https://pith.science/paper/T7RMH2T3"},"agent_actions":{"view_html":"https://pith.science/pith/T7RMH2T3SGRUZEDC3HW6TGPJRG","download_json":"https://pith.science/pith/T7RMH2T3SGRUZEDC3HW6TGPJRG.json","view_paper":"https://pith.science/paper/T7RMH2T3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.03051&json=true","fetch_graph":"https://pith.science/api/pith-number/T7RMH2T3SGRUZEDC3HW6TGPJRG/graph.json","fetch_events":"https://pith.science/api/pith-number/T7RMH2T3SGRUZEDC3HW6TGPJRG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T7RMH2T3SGRUZEDC3HW6TGPJRG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T7RMH2T3SGRUZEDC3HW6TGPJRG/action/storage_attestation","attest_author":"https://pith.science/pith/T7RMH2T3SGRUZEDC3HW6TGPJRG/action/author_attestation","sign_citation":"https://pith.science/pith/T7RMH2T3SGRUZEDC3HW6TGPJRG/action/citation_signature","submit_replication":"https://pith.science/pith/T7RMH2T3SGRUZEDC3HW6TGPJRG/action/replication_record"}},"created_at":"2026-07-05T06:57:28.270528+00:00","updated_at":"2026-07-05T06:57:28.270528+00:00"}