{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YMGRICRUQJF24MQBV5DYZ2VGZQ","short_pith_number":"pith:YMGRICRU","schema_version":"1.0","canonical_sha256":"c30d140a34824bae3201af478ceaa6cc0bddc43daa841c94701b6007105a437a","source":{"kind":"arxiv","id":"2501.08579","version":3},"attestation_state":"computed","paper":{"title":"LLM-based Human Simulations Have Not Yet Been Reliable","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bingqiao Luo, Bingsheng He, Huacan Wang, Jiaying Wu, Nuo Chen, Qian Wang, Wei Chen, Zhenheng Tang, Zichen Jiang","submitted_at":"2025-01-15T04:59:49Z","abstract_excerpt":"Large Language Models (LLMs) are increasingly employed for simulating human behaviors across diverse domains. However, our position is that current LLM-based human simulations remain insufficiently reliable, as evidenced by significant discrepancies between their outcomes and authentic human actions. Our investigation begins with a systematic review of LLM-based human simulations in social, economic, policy, and psychological contexts, identifying their common frameworks, recent advances, and persistent limitations. This review reveals that such discrepancies primarily stem from inherent limit"},"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":"2501.08579","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-15T04:59:49Z","cross_cats_sorted":[],"title_canon_sha256":"107c5e0cdeed8a640f9d253ebacc1b506a1973d7743c1ad2b5917f6d254c197c","abstract_canon_sha256":"b14f07a59f8a94efa29e2e7534f293ff8472cbf75a710e1bd04e639becfa02a4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:18:23.579971Z","signature_b64":"0R3/+xJ3DSvKR7ys++b5vx8Cbro0XUP/CIyfJGc6eE58BleEs3RXPJyBaeS31MoSkQ5rba+jLWG0t9siF/D7Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c30d140a34824bae3201af478ceaa6cc0bddc43daa841c94701b6007105a437a","last_reissued_at":"2026-07-07T02:18:23.578914Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:18:23.578914Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM-based Human Simulations Have Not Yet Been Reliable","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bingqiao Luo, Bingsheng He, Huacan Wang, Jiaying Wu, Nuo Chen, Qian Wang, Wei Chen, Zhenheng Tang, Zichen Jiang","submitted_at":"2025-01-15T04:59:49Z","abstract_excerpt":"Large Language Models (LLMs) are increasingly employed for simulating human behaviors across diverse domains. However, our position is that current LLM-based human simulations remain insufficiently reliable, as evidenced by significant discrepancies between their outcomes and authentic human actions. Our investigation begins with a systematic review of LLM-based human simulations in social, economic, policy, and psychological contexts, identifying their common frameworks, recent advances, and persistent limitations. This review reveals that such discrepancies primarily stem from inherent limit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.08579","kind":"arxiv","version":3},"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/2501.08579/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":"2501.08579","created_at":"2026-07-07T02:18:23.579045+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.08579v3","created_at":"2026-07-07T02:18:23.579045+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.08579","created_at":"2026-07-07T02:18:23.579045+00:00"},{"alias_kind":"pith_short_12","alias_value":"YMGRICRUQJF2","created_at":"2026-07-07T02:18:23.579045+00:00"},{"alias_kind":"pith_short_16","alias_value":"YMGRICRUQJF24MQB","created_at":"2026-07-07T02:18:23.579045+00:00"},{"alias_kind":"pith_short_8","alias_value":"YMGRICRU","created_at":"2026-07-07T02:18:23.579045+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":7,"sample":[{"citing_arxiv_id":"2606.09013","citing_title":"Beyond Averages: Evaluating LLMs on Human Survey Replication at the Distributional Level","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2607.00010","citing_title":"Prompt Optimization for User Simulation in Conversational Recommender Systems: A Multi-Objective Framework","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2605.25680","citing_title":"Simulating Human Memory with Language Models","ref_index":63,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17079","citing_title":"Can LLMs Think Like Consumers? Benchmarking Crowd-Level Reaction Reconstruction with ConsumerSimBench","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2509.18052","citing_title":"The PIMMUR Principles: Ensuring Validity in Collective Behavior of LLM Societies","ref_index":41,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06196","citing_title":"The Granularity Axis: A Micro-to-Macro Latent Direction for Social Roles in Language Models","ref_index":66,"is_internal_anchor":true},{"citing_arxiv_id":"2604.07838","citing_title":"We Need Strong Preconditions For Using Simulations In Policy","ref_index":57,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YMGRICRUQJF24MQBV5DYZ2VGZQ","json":"https://pith.science/pith/YMGRICRUQJF24MQBV5DYZ2VGZQ.json","graph_json":"https://pith.science/api/pith-number/YMGRICRUQJF24MQBV5DYZ2VGZQ/graph.json","events_json":"https://pith.science/api/pith-number/YMGRICRUQJF24MQBV5DYZ2VGZQ/events.json","paper":"https://pith.science/paper/YMGRICRU"},"agent_actions":{"view_html":"https://pith.science/pith/YMGRICRUQJF24MQBV5DYZ2VGZQ","download_json":"https://pith.science/pith/YMGRICRUQJF24MQBV5DYZ2VGZQ.json","view_paper":"https://pith.science/paper/YMGRICRU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.08579&json=true","fetch_graph":"https://pith.science/api/pith-number/YMGRICRUQJF24MQBV5DYZ2VGZQ/graph.json","fetch_events":"https://pith.science/api/pith-number/YMGRICRUQJF24MQBV5DYZ2VGZQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YMGRICRUQJF24MQBV5DYZ2VGZQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YMGRICRUQJF24MQBV5DYZ2VGZQ/action/storage_attestation","attest_author":"https://pith.science/pith/YMGRICRUQJF24MQBV5DYZ2VGZQ/action/author_attestation","sign_citation":"https://pith.science/pith/YMGRICRUQJF24MQBV5DYZ2VGZQ/action/citation_signature","submit_replication":"https://pith.science/pith/YMGRICRUQJF24MQBV5DYZ2VGZQ/action/replication_record"}},"created_at":"2026-07-07T02:18:23.579045+00:00","updated_at":"2026-07-07T02:18:23.579045+00:00"}