{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XSSBVCVBRJB74PMZL2ZIHW6WCJ","short_pith_number":"pith:XSSBVCVB","schema_version":"1.0","canonical_sha256":"bca41a8aa18a43fe3d995eb283dbd6127af447b5c9cb8d9e0da2c44aafa9f07a","source":{"kind":"arxiv","id":"2306.15448","version":2},"attestation_state":"computed","paper":{"title":"Understanding Social Reasoning in Language Models with Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.CL","authors_text":"Jan-Philipp Fr\\\"anken, Kanishk Gandhi, Noah D. Goodman, Tobias Gerstenberg","submitted_at":"2023-06-21T16:42:15Z","abstract_excerpt":"As Large Language Models (LLMs) become increasingly integrated into our everyday lives, understanding their ability to comprehend human mental states becomes critical for ensuring effective interactions. However, despite the recent attempts to assess the Theory-of-Mind (ToM) reasoning capabilities of LLMs, the degree to which these models can align with human ToM remains a nuanced topic of exploration. This is primarily due to two distinct challenges: (1) the presence of inconsistent results from previous evaluations, and (2) concerns surrounding the validity of existing evaluation methodologi"},"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":"2306.15448","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-21T16:42:15Z","cross_cats_sorted":["cs.AI","cs.HC"],"title_canon_sha256":"eaeeead5472e594eaf41d89bd676264d9bac4a713103f43114e569726c822695","abstract_canon_sha256":"170bdc098e3b2503d48acac8dc7438a5b3f6270bb0a34e6bd7a2fa014d8c3ea2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:20:09.244822Z","signature_b64":"BvTsKaXuJfoo23sftozCld+zbapANa6b/YpPXcbbdh+E8cWuZjzT3urs6G0o35PTmo2hfDt+4gtYakZa97t3Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bca41a8aa18a43fe3d995eb283dbd6127af447b5c9cb8d9e0da2c44aafa9f07a","last_reissued_at":"2026-07-05T07:20:09.244246Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:20:09.244246Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Understanding Social Reasoning in Language Models with Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.CL","authors_text":"Jan-Philipp Fr\\\"anken, Kanishk Gandhi, Noah D. Goodman, Tobias Gerstenberg","submitted_at":"2023-06-21T16:42:15Z","abstract_excerpt":"As Large Language Models (LLMs) become increasingly integrated into our everyday lives, understanding their ability to comprehend human mental states becomes critical for ensuring effective interactions. However, despite the recent attempts to assess the Theory-of-Mind (ToM) reasoning capabilities of LLMs, the degree to which these models can align with human ToM remains a nuanced topic of exploration. This is primarily due to two distinct challenges: (1) the presence of inconsistent results from previous evaluations, and (2) concerns surrounding the validity of existing evaluation methodologi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.15448","kind":"arxiv","version":2},"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/2306.15448/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":"2306.15448","created_at":"2026-07-05T07:20:09.244321+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.15448v2","created_at":"2026-07-05T07:20:09.244321+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.15448","created_at":"2026-07-05T07:20:09.244321+00:00"},{"alias_kind":"pith_short_12","alias_value":"XSSBVCVBRJB7","created_at":"2026-07-05T07:20:09.244321+00:00"},{"alias_kind":"pith_short_16","alias_value":"XSSBVCVBRJB74PMZ","created_at":"2026-07-05T07:20:09.244321+00:00"},{"alias_kind":"pith_short_8","alias_value":"XSSBVCVB","created_at":"2026-07-05T07:20:09.244321+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11470","citing_title":"The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes","ref_index":67,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XSSBVCVBRJB74PMZL2ZIHW6WCJ","json":"https://pith.science/pith/XSSBVCVBRJB74PMZL2ZIHW6WCJ.json","graph_json":"https://pith.science/api/pith-number/XSSBVCVBRJB74PMZL2ZIHW6WCJ/graph.json","events_json":"https://pith.science/api/pith-number/XSSBVCVBRJB74PMZL2ZIHW6WCJ/events.json","paper":"https://pith.science/paper/XSSBVCVB"},"agent_actions":{"view_html":"https://pith.science/pith/XSSBVCVBRJB74PMZL2ZIHW6WCJ","download_json":"https://pith.science/pith/XSSBVCVBRJB74PMZL2ZIHW6WCJ.json","view_paper":"https://pith.science/paper/XSSBVCVB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.15448&json=true","fetch_graph":"https://pith.science/api/pith-number/XSSBVCVBRJB74PMZL2ZIHW6WCJ/graph.json","fetch_events":"https://pith.science/api/pith-number/XSSBVCVBRJB74PMZL2ZIHW6WCJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XSSBVCVBRJB74PMZL2ZIHW6WCJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XSSBVCVBRJB74PMZL2ZIHW6WCJ/action/storage_attestation","attest_author":"https://pith.science/pith/XSSBVCVBRJB74PMZL2ZIHW6WCJ/action/author_attestation","sign_citation":"https://pith.science/pith/XSSBVCVBRJB74PMZL2ZIHW6WCJ/action/citation_signature","submit_replication":"https://pith.science/pith/XSSBVCVBRJB74PMZL2ZIHW6WCJ/action/replication_record"}},"created_at":"2026-07-05T07:20:09.244321+00:00","updated_at":"2026-07-05T07:20:09.244321+00:00"}