{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:2ZKJYJY7QE3OB2VKLSCNV7JIKG","short_pith_number":"pith:2ZKJYJY7","schema_version":"1.0","canonical_sha256":"d6549c271f8136e0eaaa5c84dafd2851a4c4206f7dd71a4d947535cd2de8ee7b","source":{"kind":"arxiv","id":"2208.10264","version":5},"attestation_state":"computed","paper":{"title":"Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Adam Tauman Kalai, Gati Aher, Rosa I. Arriaga","submitted_at":"2022-08-18T17:54:49Z","abstract_excerpt":"We introduce a new type of test, called a Turing Experiment (TE), for evaluating to what extent a given language model, such as GPT models, can simulate different aspects of human behavior. A TE can also reveal consistent distortions in a language model's simulation of a specific human behavior. Unlike the Turing Test, which involves simulating a single arbitrary individual, a TE requires simulating a representative sample of participants in human subject research. We carry out TEs that attempt to replicate well-established findings from prior studies. We design a methodology for simulating TE"},"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":"2208.10264","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-08-18T17:54:49Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"82c4862018f37507422e0ddbdadadef6a0af960c0eae5f89dd01fac37214a172","abstract_canon_sha256":"79396852b20699ae42cda018a62eac4c1b2c6d2431a89c05d8bae7291dbc7095"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:28:55.450410Z","signature_b64":"KiPqTM30CfTMt8wgjtoHUsvAZNeX582+ZhypD/rhwT5UlXMzXq3uy+8QTm1OtJIIawZohlqcKtbeepToFcYXAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d6549c271f8136e0eaaa5c84dafd2851a4c4206f7dd71a4d947535cd2de8ee7b","last_reissued_at":"2026-07-05T06:28:55.449949Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:28:55.449949Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Adam Tauman Kalai, Gati Aher, Rosa I. Arriaga","submitted_at":"2022-08-18T17:54:49Z","abstract_excerpt":"We introduce a new type of test, called a Turing Experiment (TE), for evaluating to what extent a given language model, such as GPT models, can simulate different aspects of human behavior. A TE can also reveal consistent distortions in a language model's simulation of a specific human behavior. Unlike the Turing Test, which involves simulating a single arbitrary individual, a TE requires simulating a representative sample of participants in human subject research. We carry out TEs that attempt to replicate well-established findings from prior studies. We design a methodology for simulating TE"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.10264","kind":"arxiv","version":5},"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/2208.10264/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":"2208.10264","created_at":"2026-07-05T06:28:55.450007+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.10264v5","created_at":"2026-07-05T06:28:55.450007+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.10264","created_at":"2026-07-05T06:28:55.450007+00:00"},{"alias_kind":"pith_short_12","alias_value":"2ZKJYJY7QE3O","created_at":"2026-07-05T06:28:55.450007+00:00"},{"alias_kind":"pith_short_16","alias_value":"2ZKJYJY7QE3OB2VK","created_at":"2026-07-05T06:28:55.450007+00:00"},{"alias_kind":"pith_short_8","alias_value":"2ZKJYJY7","created_at":"2026-07-05T06:28:55.450007+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":16,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21037","citing_title":"Honeyquest for LLMs: Rethinking Cyber Deception for AI Attackers","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30036","citing_title":"Teaching Values to Machines: Simulating Human-Like Behavior in LLMs","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29874","citing_title":"Evolutionary Dynamics of Cooperation in Next-Generation LLM Agent Systems: A Cross-Provider Empirical Extension","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11678","citing_title":"Can AI Reason Like an Urban Planner? Benchmarking Large Language Models Against Professional Judgment","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2305.09620","citing_title":"AI-Augmented Surveys: Leveraging Large Language Models and Surveys for Opinion Prediction","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2504.09662","citing_title":"AgentDynEx: Nudging the Mechanics and Dynamics of Multi-Agent Simulations","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2509.12626","citing_title":"DoubleAgents: Human-Agent Alignment in a Socially Embedded Workflow","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2603.03295","citing_title":"Language Model Goal Selection Differs from Humans' in a Self-Directed Learning Task","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09581","citing_title":"Avenir-UX: Automated UX Evaluation via Simulated Human Web Interaction with GUI Grounding","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27271","citing_title":"Frame Entrepreneurs in an AI Agent Community: Concentrated Identity-Claim Production on Moltbook","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11789","citing_title":"Beyond Inefficiency: Systemic Costs of Incivility in Multi-Agent Monte Carlo Simulations","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2404.04475","citing_title":"Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27271","citing_title":"Frame Entrepreneurs in an AI Agent Community: Concentrated Identity-Claim Production on Moltbook","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06524","citing_title":"Process Matters more than Output for Distinguishing Humans from Machines","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27271","citing_title":"Frame Entrepreneurs in an AI Agent Community: Concentrated Identity-Claim Production on Moltbook","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06524","citing_title":"Process Matters more than Output for Distinguishing Humans from Machines","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2ZKJYJY7QE3OB2VKLSCNV7JIKG","json":"https://pith.science/pith/2ZKJYJY7QE3OB2VKLSCNV7JIKG.json","graph_json":"https://pith.science/api/pith-number/2ZKJYJY7QE3OB2VKLSCNV7JIKG/graph.json","events_json":"https://pith.science/api/pith-number/2ZKJYJY7QE3OB2VKLSCNV7JIKG/events.json","paper":"https://pith.science/paper/2ZKJYJY7"},"agent_actions":{"view_html":"https://pith.science/pith/2ZKJYJY7QE3OB2VKLSCNV7JIKG","download_json":"https://pith.science/pith/2ZKJYJY7QE3OB2VKLSCNV7JIKG.json","view_paper":"https://pith.science/paper/2ZKJYJY7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.10264&json=true","fetch_graph":"https://pith.science/api/pith-number/2ZKJYJY7QE3OB2VKLSCNV7JIKG/graph.json","fetch_events":"https://pith.science/api/pith-number/2ZKJYJY7QE3OB2VKLSCNV7JIKG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2ZKJYJY7QE3OB2VKLSCNV7JIKG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2ZKJYJY7QE3OB2VKLSCNV7JIKG/action/storage_attestation","attest_author":"https://pith.science/pith/2ZKJYJY7QE3OB2VKLSCNV7JIKG/action/author_attestation","sign_citation":"https://pith.science/pith/2ZKJYJY7QE3OB2VKLSCNV7JIKG/action/citation_signature","submit_replication":"https://pith.science/pith/2ZKJYJY7QE3OB2VKLSCNV7JIKG/action/replication_record"}},"created_at":"2026-07-05T06:28:55.450007+00:00","updated_at":"2026-07-05T06:28:55.450007+00:00"}