{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MVOAYAL4J4U6R3KXB3GZDHL32P","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":"2440b4325cde45d851075fa9344b7b85fbf152bdef97b0a468e7a386588f1dc8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-30T20:09:37Z","title_canon_sha256":"8be5971cbb2bbdb7c63ad474f2f071a894230eb95825df50bd34f9240c038556"},"schema_version":"1.0","source":{"id":"2410.23426","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.23426","created_at":"2026-07-05T09:29:00Z"},{"alias_kind":"arxiv_version","alias_value":"2410.23426v1","created_at":"2026-07-05T09:29:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.23426","created_at":"2026-07-05T09:29:00Z"},{"alias_kind":"pith_short_12","alias_value":"MVOAYAL4J4U6","created_at":"2026-07-05T09:29:00Z"},{"alias_kind":"pith_short_16","alias_value":"MVOAYAL4J4U6R3KX","created_at":"2026-07-05T09:29:00Z"},{"alias_kind":"pith_short_8","alias_value":"MVOAYAL4","created_at":"2026-07-05T09:29:00Z"}],"graph_snapshots":[{"event_id":"sha256:f8e322ea0c63e3c1ae093c61c547f1ce7ba35ae5662a13296339a174c74a1d4c","target":"graph","created_at":"2026-07-05T09:29:00Z","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/2410.23426/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Haomin Zhuang, Jindong Wang, Kehan Guo, Lichao Sun, Weixiang Sun, Xiangliang Zhang, Xiangqi Wang, Yanfang Ye, Yue Huang, Yujun Zhou, Zhengqing Yuan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-30T20:09:37Z","title":"Social Science Meets LLMs: How Reliable Are Large Language Models in Social Simulations?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.23426","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":"sha256:438a4a10fda91187464968958bc38010370edeb4acc43d421b36266cf3ab61a7","target":"record","created_at":"2026-07-05T09:29:00Z","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":"2440b4325cde45d851075fa9344b7b85fbf152bdef97b0a468e7a386588f1dc8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-30T20:09:37Z","title_canon_sha256":"8be5971cbb2bbdb7c63ad474f2f071a894230eb95825df50bd34f9240c038556"},"schema_version":"1.0","source":{"id":"2410.23426","kind":"arxiv","version":1}},"canonical_sha256":"655c0c017c4f29e8ed570ecd919d7bd3f6f1f29212edf3b83dcea87eac88688c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"655c0c017c4f29e8ed570ecd919d7bd3f6f1f29212edf3b83dcea87eac88688c","first_computed_at":"2026-07-05T09:29:00.384407Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:29:00.384407Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YqRFWcdQtEu+ESIsJOgvOLgbjLuWw1IhQT/abskjt9lV7GcgGIbtnJXrdLlYG4lDnbb+K6xD3UonA0uQYGBQDA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:29:00.384862Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.23426","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:438a4a10fda91187464968958bc38010370edeb4acc43d421b36266cf3ab61a7","sha256:f8e322ea0c63e3c1ae093c61c547f1ce7ba35ae5662a13296339a174c74a1d4c"],"state_sha256":"9187c8509d66e0c0783ec2581c34925288bd044a861048c6888ccb2d9367d414"}