{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TBVBJKTJSKJHUDSOW745GOXBS2","short_pith_number":"pith:TBVBJKTJ","schema_version":"1.0","canonical_sha256":"986a14aa6992927a0e4eb7f9d33ae196be6eb0a87ddafd59643fd21443dbfee8","source":{"kind":"arxiv","id":"2502.21098","version":1},"attestation_state":"computed","paper":{"title":"Re-evaluating Theory of Mind evaluation in large language models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Felix Sosa, Jennifer Hu, Tomer Ullman","submitted_at":"2025-02-28T14:36:57Z","abstract_excerpt":"The question of whether large language models (LLMs) possess Theory of Mind (ToM) -- often defined as the ability to reason about others' mental states -- has sparked significant scientific and public interest. However, the evidence as to whether LLMs possess ToM is mixed, and the recent growth in evaluations has not resulted in a convergence. Here, we take inspiration from cognitive science to re-evaluate the state of ToM evaluation in LLMs. We argue that a major reason for the disagreement on whether LLMs have ToM is a lack of clarity on whether models should be expected to match human behav"},"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":"2502.21098","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-28T14:36:57Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"cecf73f352071d0d7e1352f4a5b3fb2274375dad7e3750a55f93fa8badf81fb7","abstract_canon_sha256":"dc8b53643d683520b46449e0d015fbdc3cf1b3f701da222ae712c3432a327afe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:21:44.283960Z","signature_b64":"oZh3CK898sgEB3lyS7oT6Q2egQoGPf0escZBwnofwc2l6/Le96yh1hp9+IR1RjXN3GNPVOInpczEoPGueQJ5Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"986a14aa6992927a0e4eb7f9d33ae196be6eb0a87ddafd59643fd21443dbfee8","last_reissued_at":"2026-07-05T10:21:44.283448Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:21:44.283448Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Re-evaluating Theory of Mind evaluation in large language models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Felix Sosa, Jennifer Hu, Tomer Ullman","submitted_at":"2025-02-28T14:36:57Z","abstract_excerpt":"The question of whether large language models (LLMs) possess Theory of Mind (ToM) -- often defined as the ability to reason about others' mental states -- has sparked significant scientific and public interest. However, the evidence as to whether LLMs possess ToM is mixed, and the recent growth in evaluations has not resulted in a convergence. Here, we take inspiration from cognitive science to re-evaluate the state of ToM evaluation in LLMs. We argue that a major reason for the disagreement on whether LLMs have ToM is a lack of clarity on whether models should be expected to match human behav"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.21098","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/2502.21098/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":"2502.21098","created_at":"2026-07-05T10:21:44.283515+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.21098v1","created_at":"2026-07-05T10:21:44.283515+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.21098","created_at":"2026-07-05T10:21:44.283515+00:00"},{"alias_kind":"pith_short_12","alias_value":"TBVBJKTJSKJH","created_at":"2026-07-05T10:21:44.283515+00:00"},{"alias_kind":"pith_short_16","alias_value":"TBVBJKTJSKJHUDSO","created_at":"2026-07-05T10:21:44.283515+00:00"},{"alias_kind":"pith_short_8","alias_value":"TBVBJKTJ","created_at":"2026-07-05T10:21:44.283515+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.20664","citing_title":"The Decrypto Benchmark for Multi-Agent Reasoning and Theory of Mind","ref_index":2021,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TBVBJKTJSKJHUDSOW745GOXBS2","json":"https://pith.science/pith/TBVBJKTJSKJHUDSOW745GOXBS2.json","graph_json":"https://pith.science/api/pith-number/TBVBJKTJSKJHUDSOW745GOXBS2/graph.json","events_json":"https://pith.science/api/pith-number/TBVBJKTJSKJHUDSOW745GOXBS2/events.json","paper":"https://pith.science/paper/TBVBJKTJ"},"agent_actions":{"view_html":"https://pith.science/pith/TBVBJKTJSKJHUDSOW745GOXBS2","download_json":"https://pith.science/pith/TBVBJKTJSKJHUDSOW745GOXBS2.json","view_paper":"https://pith.science/paper/TBVBJKTJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.21098&json=true","fetch_graph":"https://pith.science/api/pith-number/TBVBJKTJSKJHUDSOW745GOXBS2/graph.json","fetch_events":"https://pith.science/api/pith-number/TBVBJKTJSKJHUDSOW745GOXBS2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TBVBJKTJSKJHUDSOW745GOXBS2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TBVBJKTJSKJHUDSOW745GOXBS2/action/storage_attestation","attest_author":"https://pith.science/pith/TBVBJKTJSKJHUDSOW745GOXBS2/action/author_attestation","sign_citation":"https://pith.science/pith/TBVBJKTJSKJHUDSOW745GOXBS2/action/citation_signature","submit_replication":"https://pith.science/pith/TBVBJKTJSKJHUDSOW745GOXBS2/action/replication_record"}},"created_at":"2026-07-05T10:21:44.283515+00:00","updated_at":"2026-07-05T10:21:44.283515+00:00"}