{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CSMOOQQRLPKTJKMZPCH6WMEBFH","short_pith_number":"pith:CSMOOQQR","schema_version":"1.0","canonical_sha256":"1498e742115bd534a999788feb308129ec5a702b4863ec47747c7e8aa2a442de","source":{"kind":"arxiv","id":"2503.16527","version":1},"attestation_state":"computed","paper":{"title":"LLM Generated Persona is a Promise with a Catch","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CY","cs.SI"],"primary_cat":"cs.CL","authors_text":"Ang Li, Haozhe Chen, Hongseok Namkoong, Tianyi Peng","submitted_at":"2025-03-18T03:11:27Z","abstract_excerpt":"The use of large language models (LLMs) to simulate human behavior has gained significant attention, particularly through personas that approximate individual characteristics. Persona-based simulations hold promise for transforming disciplines that rely on population-level feedback, including social science, economic analysis, marketing research, and business operations. Traditional methods to collect realistic persona data face significant challenges. They are prohibitively expensive and logistically challenging due to privacy constraints, and often fail to capture multi-dimensional attribute"},"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":"2503.16527","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-18T03:11:27Z","cross_cats_sorted":["cs.AI","cs.CY","cs.SI"],"title_canon_sha256":"49e80a3cb60ea334eee45f17d17f709f9403a1175db5ea93249655560ec7ab1e","abstract_canon_sha256":"4785a6df5e8272467839d462acdab22c5df0761a3b28a32a0c24a2bc3e3c5a3f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:36:43.080408Z","signature_b64":"Oob3UOIU75CjdA9q+RHLCrAK6/bz58CbqQ6nd3tDLc/Xw+Y0hDveSKTehvDwxnlZyqxFq80JU3MppaEUVAESBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1498e742115bd534a999788feb308129ec5a702b4863ec47747c7e8aa2a442de","last_reissued_at":"2026-07-05T10:36:43.079785Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:36:43.079785Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM Generated Persona is a Promise with a Catch","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CY","cs.SI"],"primary_cat":"cs.CL","authors_text":"Ang Li, Haozhe Chen, Hongseok Namkoong, Tianyi Peng","submitted_at":"2025-03-18T03:11:27Z","abstract_excerpt":"The use of large language models (LLMs) to simulate human behavior has gained significant attention, particularly through personas that approximate individual characteristics. Persona-based simulations hold promise for transforming disciplines that rely on population-level feedback, including social science, economic analysis, marketing research, and business operations. Traditional methods to collect realistic persona data face significant challenges. They are prohibitively expensive and logistically challenging due to privacy constraints, and often fail to capture multi-dimensional attribute"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.16527","kind":"arxiv","version":1},"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/2503.16527/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":"2503.16527","created_at":"2026-07-05T10:36:43.079853+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.16527v1","created_at":"2026-07-05T10:36:43.079853+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.16527","created_at":"2026-07-05T10:36:43.079853+00:00"},{"alias_kind":"pith_short_12","alias_value":"CSMOOQQRLPKT","created_at":"2026-07-05T10:36:43.079853+00:00"},{"alias_kind":"pith_short_16","alias_value":"CSMOOQQRLPKTJKMZ","created_at":"2026-07-05T10:36:43.079853+00:00"},{"alias_kind":"pith_short_8","alias_value":"CSMOOQQR","created_at":"2026-07-05T10:36:43.079853+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":15,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00937","citing_title":"Persona Non Grata: LLM Persona-Driven Generations in MCQA are Unstable in Distinct Dimensions","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30801","citing_title":"Using AI Agents to Automate Black-Box Audits of Personalization Algorithms at Scale","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00696","citing_title":"Adaptive Querying with AI Persona Priors","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29793","citing_title":"Fund2Persona: A Framework for Building and Refining Financial Advisor Personas from Fund Disclosure Data","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29793","citing_title":"Fund2Persona: A Framework for Building and Refining Financial Advisor Personas from Fund Disclosure Data","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19640","citing_title":"Creating Multilingual Mental Health Dialogue Datasets: Limits of Persona-Based Localization via Nationality and Language","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18890","citing_title":"Stop Drawing Scientific Claims from LLM Social Simulations Without Robustness Audits","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2507.11198","citing_title":"Temperature and Persona Shape LLM Agent Consensus With Minimal Accuracy Gains in Qualitative Coding","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2509.11295","citing_title":"The Prompt Engineering Report Distilled: Quick Start Guide for Life Sciences","ref_index":77,"is_internal_anchor":false},{"citing_arxiv_id":"2509.11295","citing_title":"The Prompt Engineering Report Distilled: Quick Start Guide for Life Sciences","ref_index":78,"is_internal_anchor":false},{"citing_arxiv_id":"2511.02135","citing_title":"Graph-Based Alternatives to LLMs for Human Simulation","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2601.18027","citing_title":"Sentipolis: Emotion-Aware Agents for Social Simulations","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00696","citing_title":"Adaptive Querying with AI Persona Priors","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00197","citing_title":"The $\\textit{Silicon Society}$ Cookbook: Design Space of LLM-based Social Simulations","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17267","citing_title":"Rectification Difficulty and Optimal Sample Allocation in LLM-Augmented Surveys","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CSMOOQQRLPKTJKMZPCH6WMEBFH","json":"https://pith.science/pith/CSMOOQQRLPKTJKMZPCH6WMEBFH.json","graph_json":"https://pith.science/api/pith-number/CSMOOQQRLPKTJKMZPCH6WMEBFH/graph.json","events_json":"https://pith.science/api/pith-number/CSMOOQQRLPKTJKMZPCH6WMEBFH/events.json","paper":"https://pith.science/paper/CSMOOQQR"},"agent_actions":{"view_html":"https://pith.science/pith/CSMOOQQRLPKTJKMZPCH6WMEBFH","download_json":"https://pith.science/pith/CSMOOQQRLPKTJKMZPCH6WMEBFH.json","view_paper":"https://pith.science/paper/CSMOOQQR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.16527&json=true","fetch_graph":"https://pith.science/api/pith-number/CSMOOQQRLPKTJKMZPCH6WMEBFH/graph.json","fetch_events":"https://pith.science/api/pith-number/CSMOOQQRLPKTJKMZPCH6WMEBFH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CSMOOQQRLPKTJKMZPCH6WMEBFH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CSMOOQQRLPKTJKMZPCH6WMEBFH/action/storage_attestation","attest_author":"https://pith.science/pith/CSMOOQQRLPKTJKMZPCH6WMEBFH/action/author_attestation","sign_citation":"https://pith.science/pith/CSMOOQQRLPKTJKMZPCH6WMEBFH/action/citation_signature","submit_replication":"https://pith.science/pith/CSMOOQQRLPKTJKMZPCH6WMEBFH/action/replication_record"}},"created_at":"2026-07-05T10:36:43.079853+00:00","updated_at":"2026-07-05T10:36:43.079853+00:00"}