{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6JTDYLNA37EKXSURIB52DXSTIM","short_pith_number":"pith:6JTDYLNA","schema_version":"1.0","canonical_sha256":"f2663c2da0dfc8abca91407ba1de53432f1409d904d3c73e87bd8f0b1edcae76","source":{"kind":"arxiv","id":"2505.17663","version":2},"attestation_state":"computed","paper":{"title":"Towards Dynamic Theory of Mind: Evaluating LLM Adaptation to Temporal Evolution of Human States","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.CL","authors_text":"Changhe Song, Chunpu Xu, Jiashuo Wang, Pengfei Liu, Qiancheng Xu, Wenjie Li, Yang Xiao, Yi Cheng","submitted_at":"2025-05-23T09:27:40Z","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"},"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":"2505.17663","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-23T09:27:40Z","cross_cats_sorted":["cs.CY"],"title_canon_sha256":"9953770764125ed60cdac3d886839540646466f2dd520019ddc13cfb2d18e158","abstract_canon_sha256":"25497c30c429eb0ceb1cdb70ee85d2150cadf50ce856c1656ecf8f84b20e57d7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:45.773400Z","signature_b64":"zwuyWDvQejmJBivm4Y61SraSqkUks7XIhhPXrqcm3pey2zyVwdC4qs805m6qKcVrHQ1yLf5WvSiWKxmVFlXsDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f2663c2da0dfc8abca91407ba1de53432f1409d904d3c73e87bd8f0b1edcae76","last_reissued_at":"2026-07-05T11:17:45.772922Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:45.772922Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Dynamic Theory of Mind: Evaluating LLM Adaptation to Temporal Evolution of Human States","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.CL","authors_text":"Changhe Song, Chunpu Xu, Jiashuo Wang, Pengfei Liu, Qiancheng Xu, Wenjie Li, Yang Xiao, Yi Cheng","submitted_at":"2025-05-23T09:27:40Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17663","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/2505.17663/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":"2505.17663","created_at":"2026-07-05T11:17:45.772977+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.17663v2","created_at":"2026-07-05T11:17:45.772977+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17663","created_at":"2026-07-05T11:17:45.772977+00:00"},{"alias_kind":"pith_short_12","alias_value":"6JTDYLNA37EK","created_at":"2026-07-05T11:17:45.772977+00:00"},{"alias_kind":"pith_short_16","alias_value":"6JTDYLNA37EKXSUR","created_at":"2026-07-05T11:17:45.772977+00:00"},{"alias_kind":"pith_short_8","alias_value":"6JTDYLNA","created_at":"2026-07-05T11:17:45.772977+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.31916","citing_title":"Theory of Mind and Persuasion Beyond Conversation: Assessing the Capacity of LLMs to Induce Belief States via Planning and Action","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2510.05174","citing_title":"Emergent Coordination in Multi-Agent Language Models","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2601.11044","citing_title":"AgencyBench: Benchmarking the Frontiers of Autonomous Agents in 1M-Token Real-World Contexts","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6JTDYLNA37EKXSURIB52DXSTIM","json":"https://pith.science/pith/6JTDYLNA37EKXSURIB52DXSTIM.json","graph_json":"https://pith.science/api/pith-number/6JTDYLNA37EKXSURIB52DXSTIM/graph.json","events_json":"https://pith.science/api/pith-number/6JTDYLNA37EKXSURIB52DXSTIM/events.json","paper":"https://pith.science/paper/6JTDYLNA"},"agent_actions":{"view_html":"https://pith.science/pith/6JTDYLNA37EKXSURIB52DXSTIM","download_json":"https://pith.science/pith/6JTDYLNA37EKXSURIB52DXSTIM.json","view_paper":"https://pith.science/paper/6JTDYLNA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.17663&json=true","fetch_graph":"https://pith.science/api/pith-number/6JTDYLNA37EKXSURIB52DXSTIM/graph.json","fetch_events":"https://pith.science/api/pith-number/6JTDYLNA37EKXSURIB52DXSTIM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6JTDYLNA37EKXSURIB52DXSTIM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6JTDYLNA37EKXSURIB52DXSTIM/action/storage_attestation","attest_author":"https://pith.science/pith/6JTDYLNA37EKXSURIB52DXSTIM/action/author_attestation","sign_citation":"https://pith.science/pith/6JTDYLNA37EKXSURIB52DXSTIM/action/citation_signature","submit_replication":"https://pith.science/pith/6JTDYLNA37EKXSURIB52DXSTIM/action/replication_record"}},"created_at":"2026-07-05T11:17:45.772977+00:00","updated_at":"2026-07-05T11:17:45.772977+00:00"}