{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Y4YLMDJMNBTMP2DIXKHKXNQGR2","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":"7f6a9266c89cdf9cf94a72a24b159eee455a3f6946c254b9c8bba1f88df3d102","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-08T18:13:27Z","title_canon_sha256":"5dd85d75d344ee3f9489a87c0d4f5df0f89d5a68c7f4496646c85ad2ddb22b06"},"schema_version":"1.0","source":{"id":"2410.06271","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.06271","created_at":"2026-07-05T09:17:59Z"},{"alias_kind":"arxiv_version","alias_value":"2410.06271v1","created_at":"2026-07-05T09:17:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.06271","created_at":"2026-07-05T09:17:59Z"},{"alias_kind":"pith_short_12","alias_value":"Y4YLMDJMNBTM","created_at":"2026-07-05T09:17:59Z"},{"alias_kind":"pith_short_16","alias_value":"Y4YLMDJMNBTMP2DI","created_at":"2026-07-05T09:17:59Z"},{"alias_kind":"pith_short_8","alias_value":"Y4YLMDJM","created_at":"2026-07-05T09:17:59Z"}],"graph_snapshots":[{"event_id":"sha256:9475db244cfa70dc84ea1508c7f47f49d566dd17a8cc71d5a8fb4bb809c8ddfa","target":"graph","created_at":"2026-07-05T09:17:59Z","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/2410.06271/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the success of ChatGPT and other similarly sized SotA LLMs, claims of emergent human like social reasoning capabilities, especially Theory of Mind (ToM), in these models have appeared in the scientific literature. On the one hand those ToM-capabilities have been successfully tested using tasks styled similar to those used in psychology (Kosinski, 2023). On the other hand, follow up studies showed that those capabilities vanished when the tasks were slightly altered (Ullman, 2023). In this work we introduce a novel dataset of 68 tasks for probing ToM in LLMs, including potentially challeng","authors_text":"Christian Nickel, Laura Schrewe, Lucie Flek","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-08T18:13:27Z","title":"Probing the Robustness of Theory of Mind in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.06271","kind":"arxiv","version":1},"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":"sha256:48653501df6d3d47a07f9ebae9438b746961743d1741656c6f5e16f27d32d351","target":"record","created_at":"2026-07-05T09:17:59Z","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":"7f6a9266c89cdf9cf94a72a24b159eee455a3f6946c254b9c8bba1f88df3d102","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-08T18:13:27Z","title_canon_sha256":"5dd85d75d344ee3f9489a87c0d4f5df0f89d5a68c7f4496646c85ad2ddb22b06"},"schema_version":"1.0","source":{"id":"2410.06271","kind":"arxiv","version":1}},"canonical_sha256":"c730b60d2c6866c7e868ba8eabb6068e9a431f058de05e6aedbca7fe4a9f9bf2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c730b60d2c6866c7e868ba8eabb6068e9a431f058de05e6aedbca7fe4a9f9bf2","first_computed_at":"2026-07-05T09:17:59.139933Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:17:59.139933Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kW6d1dFHlyuL8GTKLr2gxL3WHZNewaE+bXSiztmKrTlZ+54AbfwKLB9DlB7Y4tG9LjS8PeLpcG0yH4TtuawXBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:17:59.140415Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.06271","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:48653501df6d3d47a07f9ebae9438b746961743d1741656c6f5e16f27d32d351","sha256:9475db244cfa70dc84ea1508c7f47f49d566dd17a8cc71d5a8fb4bb809c8ddfa"],"state_sha256":"4d5b13ce36d63e799709745917388d8530419c21fba20c2b57ffc1b7fac5e55c"}