{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:P7UU72CPKS7Y6FBFLCCJTOI6PH","short_pith_number":"pith:P7UU72CP","schema_version":"1.0","canonical_sha256":"7fe94fe84f54bf8f1425588499b91e79f90f06a04464a620f8825b503c309f07","source":{"kind":"arxiv","id":"2304.11490","version":3},"attestation_state":"computed","paper":{"title":"Boosting Theory-of-Mind Performance in Large Language Models via Prompting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Christopher J. Honey, Shima Rahimi Moghaddam","submitted_at":"2023-04-22T22:50:50Z","abstract_excerpt":"Large language models (LLMs) excel in many tasks in 2023, but they still face challenges in complex reasoning. Theory-of-mind (ToM) tasks, which require understanding agents' beliefs, goals, and mental states, are essential for common-sense reasoning involving humans, making it crucial to enhance LLM performance in this area. This study measures the ToM performance of GPT-4 and three GPT-3.5 variants (Davinci-2, Davinci-3, GPT-3.5-Turbo), and investigates the effectiveness of in-context learning in improving their ToM comprehension. We evaluated prompts featuring two-shot chain of thought reas"},"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":"2304.11490","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-04-22T22:50:50Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"72c18173d42c0054a73f0ee2e7727f9324ea32d27d0375432a843a8488f92ab8","abstract_canon_sha256":"602cdb46ee929c4948f383a18000aaecc8312a638cfaea9070ea5c60bc9c976d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:04:38.570801Z","signature_b64":"+177H2rFxzOd10WjaasNZP+1sSQSDus3DrpoCjZg+1rxcUx8QK7ONhKo0nh0xgrZ6AISMQ6hmUNzVX/V39kRAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7fe94fe84f54bf8f1425588499b91e79f90f06a04464a620f8825b503c309f07","last_reissued_at":"2026-07-05T06:04:38.570405Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:04:38.570405Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Boosting Theory-of-Mind Performance in Large Language Models via Prompting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Christopher J. Honey, Shima Rahimi Moghaddam","submitted_at":"2023-04-22T22:50:50Z","abstract_excerpt":"Large language models (LLMs) excel in many tasks in 2023, but they still face challenges in complex reasoning. Theory-of-mind (ToM) tasks, which require understanding agents' beliefs, goals, and mental states, are essential for common-sense reasoning involving humans, making it crucial to enhance LLM performance in this area. This study measures the ToM performance of GPT-4 and three GPT-3.5 variants (Davinci-2, Davinci-3, GPT-3.5-Turbo), and investigates the effectiveness of in-context learning in improving their ToM comprehension. We evaluated prompts featuring two-shot chain of thought reas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.11490","kind":"arxiv","version":3},"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/2304.11490/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":"2304.11490","created_at":"2026-07-05T06:04:38.570456+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.11490v3","created_at":"2026-07-05T06:04:38.570456+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.11490","created_at":"2026-07-05T06:04:38.570456+00:00"},{"alias_kind":"pith_short_12","alias_value":"P7UU72CPKS7Y","created_at":"2026-07-05T06:04:38.570456+00:00"},{"alias_kind":"pith_short_16","alias_value":"P7UU72CPKS7Y6FBF","created_at":"2026-07-05T06:04:38.570456+00:00"},{"alias_kind":"pith_short_8","alias_value":"P7UU72CP","created_at":"2026-07-05T06:04:38.570456+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20603","citing_title":"A Survey of Large Language Models for Perception and Measurement of Human Psychology","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2507.04005","citing_title":"Exploring a Gamified Personality Assessment Method through Interaction with LLM Agents Embodying Different Personalities","ref_index":85,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P7UU72CPKS7Y6FBFLCCJTOI6PH","json":"https://pith.science/pith/P7UU72CPKS7Y6FBFLCCJTOI6PH.json","graph_json":"https://pith.science/api/pith-number/P7UU72CPKS7Y6FBFLCCJTOI6PH/graph.json","events_json":"https://pith.science/api/pith-number/P7UU72CPKS7Y6FBFLCCJTOI6PH/events.json","paper":"https://pith.science/paper/P7UU72CP"},"agent_actions":{"view_html":"https://pith.science/pith/P7UU72CPKS7Y6FBFLCCJTOI6PH","download_json":"https://pith.science/pith/P7UU72CPKS7Y6FBFLCCJTOI6PH.json","view_paper":"https://pith.science/paper/P7UU72CP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.11490&json=true","fetch_graph":"https://pith.science/api/pith-number/P7UU72CPKS7Y6FBFLCCJTOI6PH/graph.json","fetch_events":"https://pith.science/api/pith-number/P7UU72CPKS7Y6FBFLCCJTOI6PH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P7UU72CPKS7Y6FBFLCCJTOI6PH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P7UU72CPKS7Y6FBFLCCJTOI6PH/action/storage_attestation","attest_author":"https://pith.science/pith/P7UU72CPKS7Y6FBFLCCJTOI6PH/action/author_attestation","sign_citation":"https://pith.science/pith/P7UU72CPKS7Y6FBFLCCJTOI6PH/action/citation_signature","submit_replication":"https://pith.science/pith/P7UU72CPKS7Y6FBFLCCJTOI6PH/action/replication_record"}},"created_at":"2026-07-05T06:04:38.570456+00:00","updated_at":"2026-07-05T06:04:38.570456+00:00"}