{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TP3I2DZRY63LQARGO77VNSD6WZ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"cc5e6898eb13d287c912d4bf315d216d28542db2900d5bc8969225f6b1edcef4","cross_cats_sorted":["cs.CL","cs.HC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-05-29T08:31:16Z","title_canon_sha256":"b3ca4c3f32a80c9f090f98ce0ce0944c2716fe0e00fa1530c4dd8e1b958ef8c6"},"schema_version":"1.0","source":{"id":"2405.18870","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.18870","created_at":"2026-07-05T08:25:35Z"},{"alias_kind":"arxiv_version","alias_value":"2405.18870v2","created_at":"2026-07-05T08:25:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.18870","created_at":"2026-07-05T08:25:35Z"},{"alias_kind":"pith_short_12","alias_value":"TP3I2DZRY63L","created_at":"2026-07-05T08:25:35Z"},{"alias_kind":"pith_short_16","alias_value":"TP3I2DZRY63LQARG","created_at":"2026-07-05T08:25:35Z"},{"alias_kind":"pith_short_8","alias_value":"TP3I2DZR","created_at":"2026-07-05T08:25:35Z"}],"graph_snapshots":[{"event_id":"sha256:c8e2aaae04100ae27e61ca77ba613d0d91857a246b23cd65c863f5114f428064","target":"graph","created_at":"2026-07-05T08:25:35Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2405.18870/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper examines the extent to which large language models (LLMs) have developed higher-order theory of mind (ToM); the human ability to reason about multiple mental and emotional states in a recursive manner (e.g. I think that you believe that she knows). This paper builds on prior work by introducing a handwritten test suite -- Multi-Order Theory of Mind Q&A -- and using it to compare the performance of five LLMs to a newly gathered adult human benchmark. We find that GPT-4 and Flan-PaLM reach adult-level and near adult-level performance on ToM tasks overall, and that GPT-4 exceeds adult ","authors_text":"Adrien Baranes, Alison Lentz, Benjamin Barnett, Blaise Aguera y Arcas, Geoff Keeling, John Oliver Siy, Michael McKibben, Robin I. M. Dunbar, Tatenda Kanyere, Winnie Street","cross_cats":["cs.CL","cs.HC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-05-29T08:31:16Z","title":"LLMs achieve adult human performance on higher-order theory of mind tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.18870","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:511987c0b121e3efbd335e9d328eced5473714b1e33d5952d19df1d9350c71b4","target":"record","created_at":"2026-07-05T08:25:35Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"cc5e6898eb13d287c912d4bf315d216d28542db2900d5bc8969225f6b1edcef4","cross_cats_sorted":["cs.CL","cs.HC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-05-29T08:31:16Z","title_canon_sha256":"b3ca4c3f32a80c9f090f98ce0ce0944c2716fe0e00fa1530c4dd8e1b958ef8c6"},"schema_version":"1.0","source":{"id":"2405.18870","kind":"arxiv","version":2}},"canonical_sha256":"9bf68d0f31c7b6b8022677ff56c87eb67d730dd0ef562568b648d020e6570b7d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9bf68d0f31c7b6b8022677ff56c87eb67d730dd0ef562568b648d020e6570b7d","first_computed_at":"2026-07-05T08:25:35.042932Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:25:35.042932Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lx3lUvAXZN/DKdSt6WfgNFW7I+ojHg8v5/ShSvt8isjFt1JqxU7k1N9Ja3eg0VmBMR0URGIORbhGknUiMNCbAw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:25:35.043372Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.18870","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:511987c0b121e3efbd335e9d328eced5473714b1e33d5952d19df1d9350c71b4","sha256:c8e2aaae04100ae27e61ca77ba613d0d91857a246b23cd65c863f5114f428064"],"state_sha256":"bd08b75deb536cb26c74ac90c9eb79438915749bb1a8e1538a6744a3150dcf22"}