{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6A5KJWHT3T6UVRS5EWXDL3OYWU","short_pith_number":"pith:6A5KJWHT","schema_version":"1.0","canonical_sha256":"f03aa4d8f3dcfd4ac65d25ae35edd8b53d7c0f5603fd34bd06d9c93c68ba4740","source":{"kind":"arxiv","id":"2502.17773","version":5},"attestation_state":"computed","paper":{"title":"How Many Human Survey Respondents is a Large Language Model Worth? An Uncertainty Quantification Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ME","authors_text":"Chengpiao Huang, Kaizheng Wang, Yuhang Wu","submitted_at":"2025-02-25T02:07:29Z","abstract_excerpt":"Large language models (LLMs) are increasingly used to simulate survey responses, but synthetic data can be misaligned with the human population, leading to unreliable inference. We develop a general framework that converts LLM-simulated responses into reliable confidence sets for population parameters of human responses, quantifying the uncertainty induced by the human-LLM misalignment. The key design choice is the number of simulated responses: too many produce overly narrow sets with poor coverage, while too few yield overly wide and uninformative sets dominated by stochastic noise. We propo"},"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":"2502.17773","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2025-02-25T02:07:29Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"1b04278b8b6298df7959af833a1b89e87d06af99e4a9474afd07e070cdd237b9","abstract_canon_sha256":"a91af79341673920f1918f0bffce53fd87b99e99043d6b75e39640c9db62337e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T02:04:47.807531Z","signature_b64":"F4QJcL3WII6eDLisQXnM6BIrYqF8x2K57wupzVh3Hgiu7Mp0nSTX4F5YhAjFzC2bsBjGoBps5Vhd4er6TYOVAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f03aa4d8f3dcfd4ac65d25ae35edd8b53d7c0f5603fd34bd06d9c93c68ba4740","last_reissued_at":"2026-05-21T02:04:47.806469Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T02:04:47.806469Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How Many Human Survey Respondents is a Large Language Model Worth? An Uncertainty Quantification Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ME","authors_text":"Chengpiao Huang, Kaizheng Wang, Yuhang Wu","submitted_at":"2025-02-25T02:07:29Z","abstract_excerpt":"Large language models (LLMs) are increasingly used to simulate survey responses, but synthetic data can be misaligned with the human population, leading to unreliable inference. We develop a general framework that converts LLM-simulated responses into reliable confidence sets for population parameters of human responses, quantifying the uncertainty induced by the human-LLM misalignment. The key design choice is the number of simulated responses: too many produce overly narrow sets with poor coverage, while too few yield overly wide and uninformative sets dominated by stochastic noise. We propo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.17773","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/2502.17773/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":"2502.17773","created_at":"2026-05-21T02:04:47.806624+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.17773v5","created_at":"2026-05-21T02:04:47.806624+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.17773","created_at":"2026-05-21T02:04:47.806624+00:00"},{"alias_kind":"pith_short_12","alias_value":"6A5KJWHT3T6U","created_at":"2026-05-21T02:04:47.806624+00:00"},{"alias_kind":"pith_short_16","alias_value":"6A5KJWHT3T6UVRS5","created_at":"2026-05-21T02:04:47.806624+00:00"},{"alias_kind":"pith_short_8","alias_value":"6A5KJWHT","created_at":"2026-05-21T02:04:47.806624+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2604.09606","citing_title":"Evaluating Reliability Gaps in Large Language Model Safety via Repeated Prompt Sampling","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2605.00696","citing_title":"Adaptive Querying with AI Persona Priors","ref_index":45,"is_internal_anchor":true},{"citing_arxiv_id":"2604.17267","citing_title":"Rectification Difficulty and Optimal Sample Allocation in LLM-Augmented Surveys","ref_index":48,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6A5KJWHT3T6UVRS5EWXDL3OYWU","json":"https://pith.science/pith/6A5KJWHT3T6UVRS5EWXDL3OYWU.json","graph_json":"https://pith.science/api/pith-number/6A5KJWHT3T6UVRS5EWXDL3OYWU/graph.json","events_json":"https://pith.science/api/pith-number/6A5KJWHT3T6UVRS5EWXDL3OYWU/events.json","paper":"https://pith.science/paper/6A5KJWHT"},"agent_actions":{"view_html":"https://pith.science/pith/6A5KJWHT3T6UVRS5EWXDL3OYWU","download_json":"https://pith.science/pith/6A5KJWHT3T6UVRS5EWXDL3OYWU.json","view_paper":"https://pith.science/paper/6A5KJWHT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.17773&json=true","fetch_graph":"https://pith.science/api/pith-number/6A5KJWHT3T6UVRS5EWXDL3OYWU/graph.json","fetch_events":"https://pith.science/api/pith-number/6A5KJWHT3T6UVRS5EWXDL3OYWU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6A5KJWHT3T6UVRS5EWXDL3OYWU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6A5KJWHT3T6UVRS5EWXDL3OYWU/action/storage_attestation","attest_author":"https://pith.science/pith/6A5KJWHT3T6UVRS5EWXDL3OYWU/action/author_attestation","sign_citation":"https://pith.science/pith/6A5KJWHT3T6UVRS5EWXDL3OYWU/action/citation_signature","submit_replication":"https://pith.science/pith/6A5KJWHT3T6UVRS5EWXDL3OYWU/action/replication_record"}},"created_at":"2026-05-21T02:04:47.806624+00:00","updated_at":"2026-05-21T02:04:47.806624+00:00"}