{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:D7SN7U2G64BZL7Q356WN47KVYA","short_pith_number":"pith:D7SN7U2G","schema_version":"1.0","canonical_sha256":"1fe4dfd346f70395fe1befacde7d55c02a2e4882a03f90ffa6c7243480189c58","source":{"kind":"arxiv","id":"2310.20320","version":1},"attestation_state":"computed","paper":{"title":"Theory of Mind in Large Language Models: Examining Performance of 11 State-of-the-Art models vs. Children Aged 7-10 on Advanced Tests","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bram M.A. van Dijk, Marco R. Spruit, Max J. van Duijn, Peter van der Putten, Tom Kouwenhoven, Werner de Valk","submitted_at":"2023-10-31T09:55:07Z","abstract_excerpt":"To what degree should we ascribe cognitive capacities to Large Language Models (LLMs), such as the ability to reason about intentions and beliefs known as Theory of Mind (ToM)? Here we add to this emerging debate by (i) testing 11 base- and instruction-tuned LLMs on capabilities relevant to ToM beyond the dominant false-belief paradigm, including non-literal language usage and recursive intentionality; (ii) using newly rewritten versions of standardized tests to gauge LLMs' robustness; (iii) prompting and scoring for open besides closed questions; and (iv) benchmarking LLM performance against "},"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":"2310.20320","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-31T09:55:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"71325aea13f713a8a658825cf59099f6543c66e79eb3946585b58ea3c78ec054","abstract_canon_sha256":"85f438cb64628ac6191e107c31614f99cb0cc1bd29e4c9a8c0aba520ea305d4d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:07:28.419219Z","signature_b64":"3GbqsbdZMJbRxMkttwKYke0JBEj+RSCh/R1zoGifReQqe58sK+26p0ekMq3prI4g6d8YEN0rfFOwvlxofiR8Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1fe4dfd346f70395fe1befacde7d55c02a2e4882a03f90ffa6c7243480189c58","last_reissued_at":"2026-07-05T07:07:28.418748Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:07:28.418748Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Theory of Mind in Large Language Models: Examining Performance of 11 State-of-the-Art models vs. Children Aged 7-10 on Advanced Tests","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bram M.A. van Dijk, Marco R. Spruit, Max J. van Duijn, Peter van der Putten, Tom Kouwenhoven, Werner de Valk","submitted_at":"2023-10-31T09:55:07Z","abstract_excerpt":"To what degree should we ascribe cognitive capacities to Large Language Models (LLMs), such as the ability to reason about intentions and beliefs known as Theory of Mind (ToM)? Here we add to this emerging debate by (i) testing 11 base- and instruction-tuned LLMs on capabilities relevant to ToM beyond the dominant false-belief paradigm, including non-literal language usage and recursive intentionality; (ii) using newly rewritten versions of standardized tests to gauge LLMs' robustness; (iii) prompting and scoring for open besides closed questions; and (iv) benchmarking LLM performance against "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.20320","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/2310.20320/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":"2310.20320","created_at":"2026-07-05T07:07:28.418803+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.20320v1","created_at":"2026-07-05T07:07:28.418803+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.20320","created_at":"2026-07-05T07:07:28.418803+00:00"},{"alias_kind":"pith_short_12","alias_value":"D7SN7U2G64BZ","created_at":"2026-07-05T07:07:28.418803+00:00"},{"alias_kind":"pith_short_16","alias_value":"D7SN7U2G64BZL7Q3","created_at":"2026-07-05T07:07:28.418803+00:00"},{"alias_kind":"pith_short_8","alias_value":"D7SN7U2G","created_at":"2026-07-05T07:07:28.418803+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01006","citing_title":"Understanding Large Language Models","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D7SN7U2G64BZL7Q356WN47KVYA","json":"https://pith.science/pith/D7SN7U2G64BZL7Q356WN47KVYA.json","graph_json":"https://pith.science/api/pith-number/D7SN7U2G64BZL7Q356WN47KVYA/graph.json","events_json":"https://pith.science/api/pith-number/D7SN7U2G64BZL7Q356WN47KVYA/events.json","paper":"https://pith.science/paper/D7SN7U2G"},"agent_actions":{"view_html":"https://pith.science/pith/D7SN7U2G64BZL7Q356WN47KVYA","download_json":"https://pith.science/pith/D7SN7U2G64BZL7Q356WN47KVYA.json","view_paper":"https://pith.science/paper/D7SN7U2G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.20320&json=true","fetch_graph":"https://pith.science/api/pith-number/D7SN7U2G64BZL7Q356WN47KVYA/graph.json","fetch_events":"https://pith.science/api/pith-number/D7SN7U2G64BZL7Q356WN47KVYA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D7SN7U2G64BZL7Q356WN47KVYA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D7SN7U2G64BZL7Q356WN47KVYA/action/storage_attestation","attest_author":"https://pith.science/pith/D7SN7U2G64BZL7Q356WN47KVYA/action/author_attestation","sign_citation":"https://pith.science/pith/D7SN7U2G64BZL7Q356WN47KVYA/action/citation_signature","submit_replication":"https://pith.science/pith/D7SN7U2G64BZL7Q356WN47KVYA/action/replication_record"}},"created_at":"2026-07-05T07:07:28.418803+00:00","updated_at":"2026-07-05T07:07:28.418803+00:00"}