{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CZ2QS2QN5YCAVOYYNLAJSK5SYR","short_pith_number":"pith:CZ2QS2QN","schema_version":"1.0","canonical_sha256":"1675096a0dee040abb186ac0992bb2c468d8ca3730874b8b70f60ba9fd912699","source":{"kind":"arxiv","id":"2402.01908","version":3},"attestation_state":"computed","paper":{"title":"Large language models that replace human participants can harmfully misportray and flatten identity groups","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CY","authors_text":"Angelina Wang, Jamie Morgenstern, John P. Dickerson","submitted_at":"2024-02-02T21:21:06Z","abstract_excerpt":"Large language models (LLMs) are increasing in capability and popularity, propelling their application in new domains -- including as replacements for human participants in computational social science, user testing, annotation tasks, and more. In many settings, researchers seek to distribute their surveys to a sample of participants that are representative of the underlying human population of interest. This means in order to be a suitable replacement, LLMs will need to be able to capture the influence of positionality (i.e., relevance of social identities like gender and race). However, we s"},"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":"2402.01908","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2024-02-02T21:21:06Z","cross_cats_sorted":[],"title_canon_sha256":"2a7181cea54c64c01d14ef8b69646fd540f5069dd502d14ccc25cda1fb10a87c","abstract_canon_sha256":"76a171a62f6d5d33792c582db4dd85fc6cf41f546302d8e6ed79f442508635a8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:08:52.390034Z","signature_b64":"rrVcWBy0vmdxLGcDm0wPGgtbhW0bP4rNwlr5pUS3zduYpOmqYvgFN2HBOD6hHtT598B4x+ykdLxiXZ6Ev9RDBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1675096a0dee040abb186ac0992bb2c468d8ca3730874b8b70f60ba9fd912699","last_reissued_at":"2026-07-05T10:08:52.389631Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:08:52.389631Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large language models that replace human participants can harmfully misportray and flatten identity groups","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CY","authors_text":"Angelina Wang, Jamie Morgenstern, John P. Dickerson","submitted_at":"2024-02-02T21:21:06Z","abstract_excerpt":"Large language models (LLMs) are increasing in capability and popularity, propelling their application in new domains -- including as replacements for human participants in computational social science, user testing, annotation tasks, and more. In many settings, researchers seek to distribute their surveys to a sample of participants that are representative of the underlying human population of interest. This means in order to be a suitable replacement, LLMs will need to be able to capture the influence of positionality (i.e., relevance of social identities like gender and race). However, we s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.01908","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/2402.01908/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":"2402.01908","created_at":"2026-07-05T10:08:52.389688+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.01908v3","created_at":"2026-07-05T10:08:52.389688+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.01908","created_at":"2026-07-05T10:08:52.389688+00:00"},{"alias_kind":"pith_short_12","alias_value":"CZ2QS2QN5YCA","created_at":"2026-07-05T10:08:52.389688+00:00"},{"alias_kind":"pith_short_16","alias_value":"CZ2QS2QN5YCAVOYY","created_at":"2026-07-05T10:08:52.389688+00:00"},{"alias_kind":"pith_short_8","alias_value":"CZ2QS2QN","created_at":"2026-07-05T10:08:52.389688+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19816","citing_title":"Challenges to Grassroots Organization Engagement with AI Policy","ref_index":87,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28963","citing_title":"Beyond the Mean: Three-Axis Fidelity for Aligning LLM-Based Survey Simulators from Small Pilot Data","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2411.10915","citing_title":"Bias in Large Language Models: Origin, Evaluation, and Mitigation","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2507.00439","citing_title":"Improving the Distributional Alignment of LLMs using Supervision","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CZ2QS2QN5YCAVOYYNLAJSK5SYR","json":"https://pith.science/pith/CZ2QS2QN5YCAVOYYNLAJSK5SYR.json","graph_json":"https://pith.science/api/pith-number/CZ2QS2QN5YCAVOYYNLAJSK5SYR/graph.json","events_json":"https://pith.science/api/pith-number/CZ2QS2QN5YCAVOYYNLAJSK5SYR/events.json","paper":"https://pith.science/paper/CZ2QS2QN"},"agent_actions":{"view_html":"https://pith.science/pith/CZ2QS2QN5YCAVOYYNLAJSK5SYR","download_json":"https://pith.science/pith/CZ2QS2QN5YCAVOYYNLAJSK5SYR.json","view_paper":"https://pith.science/paper/CZ2QS2QN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.01908&json=true","fetch_graph":"https://pith.science/api/pith-number/CZ2QS2QN5YCAVOYYNLAJSK5SYR/graph.json","fetch_events":"https://pith.science/api/pith-number/CZ2QS2QN5YCAVOYYNLAJSK5SYR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CZ2QS2QN5YCAVOYYNLAJSK5SYR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CZ2QS2QN5YCAVOYYNLAJSK5SYR/action/storage_attestation","attest_author":"https://pith.science/pith/CZ2QS2QN5YCAVOYYNLAJSK5SYR/action/author_attestation","sign_citation":"https://pith.science/pith/CZ2QS2QN5YCAVOYYNLAJSK5SYR/action/citation_signature","submit_replication":"https://pith.science/pith/CZ2QS2QN5YCAVOYYNLAJSK5SYR/action/replication_record"}},"created_at":"2026-07-05T10:08:52.389688+00:00","updated_at":"2026-07-05T10:08:52.389688+00:00"}