{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MVOAYAL4J4U6R3KXB3GZDHL32P","short_pith_number":"pith:MVOAYAL4","schema_version":"1.0","canonical_sha256":"655c0c017c4f29e8ed570ecd919d7bd3f6f1f29212edf3b83dcea87eac88688c","source":{"kind":"arxiv","id":"2410.23426","version":1},"attestation_state":"computed","paper":{"title":"Social Science Meets LLMs: How Reliable Are Large Language Models in Social Simulations?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Haomin Zhuang, Jindong Wang, Kehan Guo, Lichao Sun, Weixiang Sun, Xiangliang Zhang, Xiangqi Wang, Yanfang Ye, Yue Huang, Yujun Zhou, Zhengqing Yuan","submitted_at":"2024-10-30T20:09:37Z","abstract_excerpt":"Large Language Models (LLMs) are increasingly employed for simulations, enabling applications in role-playing agents and Computational Social Science (CSS). However, the reliability of these simulations is under-explored, which raises concerns about the trustworthiness of LLMs in these applications. In this paper, we aim to answer ``How reliable is LLM-based simulation?'' To address this, we introduce TrustSim, an evaluation dataset covering 10 CSS-related topics, to systematically investigate the reliability of the LLM simulation. We conducted experiments on 14 LLMs and found that inconsisten"},"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":"2410.23426","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-30T20:09:37Z","cross_cats_sorted":[],"title_canon_sha256":"8be5971cbb2bbdb7c63ad474f2f071a894230eb95825df50bd34f9240c038556","abstract_canon_sha256":"2440b4325cde45d851075fa9344b7b85fbf152bdef97b0a468e7a386588f1dc8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:29:00.384862Z","signature_b64":"YqRFWcdQtEu+ESIsJOgvOLgbjLuWw1IhQT/abskjt9lV7GcgGIbtnJXrdLlYG4lDnbb+K6xD3UonA0uQYGBQDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"655c0c017c4f29e8ed570ecd919d7bd3f6f1f29212edf3b83dcea87eac88688c","last_reissued_at":"2026-07-05T09:29:00.384407Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:29:00.384407Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Social Science Meets LLMs: How Reliable Are Large Language Models in Social Simulations?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Haomin Zhuang, Jindong Wang, Kehan Guo, Lichao Sun, Weixiang Sun, Xiangliang Zhang, Xiangqi Wang, Yanfang Ye, Yue Huang, Yujun Zhou, Zhengqing Yuan","submitted_at":"2024-10-30T20:09:37Z","abstract_excerpt":"Large Language Models (LLMs) are increasingly employed for simulations, enabling applications in role-playing agents and Computational Social Science (CSS). However, the reliability of these simulations is under-explored, which raises concerns about the trustworthiness of LLMs in these applications. In this paper, we aim to answer ``How reliable is LLM-based simulation?'' To address this, we introduce TrustSim, an evaluation dataset covering 10 CSS-related topics, to systematically investigate the reliability of the LLM simulation. We conducted experiments on 14 LLMs and found that inconsisten"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.23426","kind":"arxiv","version":1},"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/2410.23426/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":"2410.23426","created_at":"2026-07-05T09:29:00.384465+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.23426v1","created_at":"2026-07-05T09:29:00.384465+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.23426","created_at":"2026-07-05T09:29:00.384465+00:00"},{"alias_kind":"pith_short_12","alias_value":"MVOAYAL4J4U6","created_at":"2026-07-05T09:29:00.384465+00:00"},{"alias_kind":"pith_short_16","alias_value":"MVOAYAL4J4U6R3KX","created_at":"2026-07-05T09:29:00.384465+00:00"},{"alias_kind":"pith_short_8","alias_value":"MVOAYAL4","created_at":"2026-07-05T09:29:00.384465+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2412.19363","citing_title":"Large Language Models for Market Research: A Data-augmentation Approach","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2502.08691","citing_title":"AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Society","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2502.17773","citing_title":"How Many Human Survey Respondents is a Large Language Model Worth? An Uncertainty Quantification Perspective","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2509.18052","citing_title":"The PIMMUR Principles: Ensuring Validity in Collective Behavior of LLM Societies","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MVOAYAL4J4U6R3KXB3GZDHL32P","json":"https://pith.science/pith/MVOAYAL4J4U6R3KXB3GZDHL32P.json","graph_json":"https://pith.science/api/pith-number/MVOAYAL4J4U6R3KXB3GZDHL32P/graph.json","events_json":"https://pith.science/api/pith-number/MVOAYAL4J4U6R3KXB3GZDHL32P/events.json","paper":"https://pith.science/paper/MVOAYAL4"},"agent_actions":{"view_html":"https://pith.science/pith/MVOAYAL4J4U6R3KXB3GZDHL32P","download_json":"https://pith.science/pith/MVOAYAL4J4U6R3KXB3GZDHL32P.json","view_paper":"https://pith.science/paper/MVOAYAL4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.23426&json=true","fetch_graph":"https://pith.science/api/pith-number/MVOAYAL4J4U6R3KXB3GZDHL32P/graph.json","fetch_events":"https://pith.science/api/pith-number/MVOAYAL4J4U6R3KXB3GZDHL32P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MVOAYAL4J4U6R3KXB3GZDHL32P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MVOAYAL4J4U6R3KXB3GZDHL32P/action/storage_attestation","attest_author":"https://pith.science/pith/MVOAYAL4J4U6R3KXB3GZDHL32P/action/author_attestation","sign_citation":"https://pith.science/pith/MVOAYAL4J4U6R3KXB3GZDHL32P/action/citation_signature","submit_replication":"https://pith.science/pith/MVOAYAL4J4U6R3KXB3GZDHL32P/action/replication_record"}},"created_at":"2026-07-05T09:29:00.384465+00:00","updated_at":"2026-07-05T09:29:00.384465+00:00"}