{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FAFXNX734S6Q2NZOG3JHZ3SMSK","short_pith_number":"pith:FAFXNX73","schema_version":"1.0","canonical_sha256":"280b76dffbe4bd0d372e36d27cee4c92a27a9c42f6cd811a8846ad1bb26284d4","source":{"kind":"arxiv","id":"2508.06950","version":3},"attestation_state":"computed","paper":{"title":"Large Language Models Do Not Simulate Human Psychology","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Benjamin Paa{\\ss}en, Sarah Schr\\\"oder, Thekla Morgenroth, Ulrike Kuhl, Valerie Vaquet","submitted_at":"2025-08-09T11:56:59Z","abstract_excerpt":"Large Language Models (LLMs),such as ChatGPT, are increasingly used in research, ranging from simple writing assistance to complex data annotation tasks. Recently, some research has suggested that LLMs may even be able to simulate human psychology and can, hence, replace human participants in psychological studies. We caution against this approach. We provide conceptual arguments against the hypothesis that LLMs simulate human psychology. We then present empiric evidence illustrating our arguments by demonstrating that slight changes to wording that correspond to large changes in meaning lead "},"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":"2508.06950","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-08-09T11:56:59Z","cross_cats_sorted":[],"title_canon_sha256":"80254ad82092677dc25a9e80dd62b72921341a0eeebeb591b5ce23a50dc017d8","abstract_canon_sha256":"985e71806e4533ef693e83c53b554a46349839f8f58e4293c84ae59236f5845d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:53:07.339716Z","signature_b64":"xdu5qOrHZd38U3uCOASiAEr3l8U0/x0tzy/P5UnbxwRY5zjbbPmUaF6b4biMs10nJ3yCgQUDdFj9HihofC74Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"280b76dffbe4bd0d372e36d27cee4c92a27a9c42f6cd811a8846ad1bb26284d4","last_reissued_at":"2026-07-05T11:53:07.339099Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:53:07.339099Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Language Models Do Not Simulate Human Psychology","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Benjamin Paa{\\ss}en, Sarah Schr\\\"oder, Thekla Morgenroth, Ulrike Kuhl, Valerie Vaquet","submitted_at":"2025-08-09T11:56:59Z","abstract_excerpt":"Large Language Models (LLMs),such as ChatGPT, are increasingly used in research, ranging from simple writing assistance to complex data annotation tasks. Recently, some research has suggested that LLMs may even be able to simulate human psychology and can, hence, replace human participants in psychological studies. We caution against this approach. We provide conceptual arguments against the hypothesis that LLMs simulate human psychology. We then present empiric evidence illustrating our arguments by demonstrating that slight changes to wording that correspond to large changes in meaning lead "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.06950","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/2508.06950/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":"2508.06950","created_at":"2026-07-05T11:53:07.339175+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.06950v3","created_at":"2026-07-05T11:53:07.339175+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.06950","created_at":"2026-07-05T11:53:07.339175+00:00"},{"alias_kind":"pith_short_12","alias_value":"FAFXNX734S6Q","created_at":"2026-07-05T11:53:07.339175+00:00"},{"alias_kind":"pith_short_16","alias_value":"FAFXNX734S6Q2NZO","created_at":"2026-07-05T11:53:07.339175+00:00"},{"alias_kind":"pith_short_8","alias_value":"FAFXNX73","created_at":"2026-07-05T11:53:07.339175+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.27153","citing_title":"Building an Atlas of Social Experiments to Link Studies, Reconcile Conflicts, and Bridge Gaps","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2508.15503","citing_title":"Guidelines for Empirical Studies in Software Engineering involving Large Language Models","ref_index":119,"is_internal_anchor":false},{"citing_arxiv_id":"2508.15503","citing_title":"Guidelines for Empirical Studies in Software Engineering involving Large Language Models","ref_index":119,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FAFXNX734S6Q2NZOG3JHZ3SMSK","json":"https://pith.science/pith/FAFXNX734S6Q2NZOG3JHZ3SMSK.json","graph_json":"https://pith.science/api/pith-number/FAFXNX734S6Q2NZOG3JHZ3SMSK/graph.json","events_json":"https://pith.science/api/pith-number/FAFXNX734S6Q2NZOG3JHZ3SMSK/events.json","paper":"https://pith.science/paper/FAFXNX73"},"agent_actions":{"view_html":"https://pith.science/pith/FAFXNX734S6Q2NZOG3JHZ3SMSK","download_json":"https://pith.science/pith/FAFXNX734S6Q2NZOG3JHZ3SMSK.json","view_paper":"https://pith.science/paper/FAFXNX73","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.06950&json=true","fetch_graph":"https://pith.science/api/pith-number/FAFXNX734S6Q2NZOG3JHZ3SMSK/graph.json","fetch_events":"https://pith.science/api/pith-number/FAFXNX734S6Q2NZOG3JHZ3SMSK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FAFXNX734S6Q2NZOG3JHZ3SMSK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FAFXNX734S6Q2NZOG3JHZ3SMSK/action/storage_attestation","attest_author":"https://pith.science/pith/FAFXNX734S6Q2NZOG3JHZ3SMSK/action/author_attestation","sign_citation":"https://pith.science/pith/FAFXNX734S6Q2NZOG3JHZ3SMSK/action/citation_signature","submit_replication":"https://pith.science/pith/FAFXNX734S6Q2NZOG3JHZ3SMSK/action/replication_record"}},"created_at":"2026-07-05T11:53:07.339175+00:00","updated_at":"2026-07-05T11:53:07.339175+00:00"}