{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6JTDYLNA37EKXSURIB52DXSTIM","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":"25497c30c429eb0ceb1cdb70ee85d2150cadf50ce856c1656ecf8f84b20e57d7","cross_cats_sorted":["cs.CY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-23T09:27:40Z","title_canon_sha256":"9953770764125ed60cdac3d886839540646466f2dd520019ddc13cfb2d18e158"},"schema_version":"1.0","source":{"id":"2505.17663","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.17663","created_at":"2026-07-05T11:17:45Z"},{"alias_kind":"arxiv_version","alias_value":"2505.17663v2","created_at":"2026-07-05T11:17:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17663","created_at":"2026-07-05T11:17:45Z"},{"alias_kind":"pith_short_12","alias_value":"6JTDYLNA37EK","created_at":"2026-07-05T11:17:45Z"},{"alias_kind":"pith_short_16","alias_value":"6JTDYLNA37EKXSUR","created_at":"2026-07-05T11:17:45Z"},{"alias_kind":"pith_short_8","alias_value":"6JTDYLNA","created_at":"2026-07-05T11:17:45Z"}],"graph_snapshots":[{"event_id":"sha256:faeef4aba66853c27d3377b113017cabd70959623299fba44e8050074b8fa468","target":"graph","created_at":"2026-07-05T11:17:45Z","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/2505.17663/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As Large Language Models (LLMs) increasingly participate in human-AI interactions, evaluating their Theory of Mind (ToM) capabilities - particularly their ability to track dynamic mental states - becomes crucial. While existing benchmarks assess basic ToM abilities, they predominantly focus on static snapshots of mental states, overlooking the temporal evolution that characterizes real-world social interactions. We present \\textsc{DynToM}, a novel benchmark specifically designed to evaluate LLMs' ability to understand and track the temporal progression of mental states across interconnected sc","authors_text":"Changhe Song, Chunpu Xu, Jiashuo Wang, Pengfei Liu, Qiancheng Xu, Wenjie Li, Yang Xiao, Yi Cheng","cross_cats":["cs.CY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-23T09:27:40Z","title":"Towards Dynamic Theory of Mind: Evaluating LLM Adaptation to Temporal Evolution of Human States"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17663","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":"sha256:55c54f9561855c0adad9cbe03bb8df9f1806f84b50f6e161ffde64c03baa3646","target":"record","created_at":"2026-07-05T11:17:45Z","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":"25497c30c429eb0ceb1cdb70ee85d2150cadf50ce856c1656ecf8f84b20e57d7","cross_cats_sorted":["cs.CY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-23T09:27:40Z","title_canon_sha256":"9953770764125ed60cdac3d886839540646466f2dd520019ddc13cfb2d18e158"},"schema_version":"1.0","source":{"id":"2505.17663","kind":"arxiv","version":2}},"canonical_sha256":"f2663c2da0dfc8abca91407ba1de53432f1409d904d3c73e87bd8f0b1edcae76","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f2663c2da0dfc8abca91407ba1de53432f1409d904d3c73e87bd8f0b1edcae76","first_computed_at":"2026-07-05T11:17:45.772922Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:17:45.772922Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zwuyWDvQejmJBivm4Y61SraSqkUks7XIhhPXrqcm3pey2zyVwdC4qs805m6qKcVrHQ1yLf5WvSiWKxmVFlXsDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:17:45.773400Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.17663","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:55c54f9561855c0adad9cbe03bb8df9f1806f84b50f6e161ffde64c03baa3646","sha256:faeef4aba66853c27d3377b113017cabd70959623299fba44e8050074b8fa468"],"state_sha256":"a9e6c9378c90caef2a30908f99ae011b7bac1da6f830ab3b7d54e8ab4ade6156"}