{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DYNXSEUIJKAIVN47UBW7T5Z7MV","short_pith_number":"pith:DYNXSEUI","schema_version":"1.0","canonical_sha256":"1e1b7912884a808ab79fa06df9f73f6570c59167c720acb302a29cd8236f6214","source":{"kind":"arxiv","id":"2409.02601","version":3},"attestation_state":"computed","paper":{"title":"ChatGPT vs Social Surveys: Probing Objective and Subjective Silicon Population","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CY","authors_text":"Lan Luo, Lu Yu, Muzhi Zhou, Xiaomin Geng","submitted_at":"2024-09-04T10:33:37Z","abstract_excerpt":"Recent discussions about Large Language Models (LLMs) indicate that they have the potential to simulate human responses in social surveys and generate reliable predictions, such as those found in political polls. However, the existing findings are highly inconsistent, leaving us uncertain about the population characteristics of data generated by LLMs. In this paper, we employ repeated random sampling to create sampling distributions that identify the population parameters of silicon samples generated by GPT. Our findings show that GPT's demographic distribution aligns with the 2020 U.S. popula"},"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":"2409.02601","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2024-09-04T10:33:37Z","cross_cats_sorted":[],"title_canon_sha256":"390130deecad0c8ef579d0739ea12303a1f6bfe7bd6159d2e8f2255b15461111","abstract_canon_sha256":"1a156836b969ecb005917d39554d937a8f03c293aa8a5f54857c2084df289d68"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:25:09.555849Z","signature_b64":"+SWyvZ3owXtEOEQYg7L0w4kgzwPpFshiF05xvL+ekR69jBkUtBZf+M75Fgv7UyZoYO6AkQMn/ExnUsa1c6r0BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e1b7912884a808ab79fa06df9f73f6570c59167c720acb302a29cd8236f6214","last_reissued_at":"2026-07-05T10:25:09.555289Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:25:09.555289Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ChatGPT vs Social Surveys: Probing Objective and Subjective Silicon Population","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CY","authors_text":"Lan Luo, Lu Yu, Muzhi Zhou, Xiaomin Geng","submitted_at":"2024-09-04T10:33:37Z","abstract_excerpt":"Recent discussions about Large Language Models (LLMs) indicate that they have the potential to simulate human responses in social surveys and generate reliable predictions, such as those found in political polls. However, the existing findings are highly inconsistent, leaving us uncertain about the population characteristics of data generated by LLMs. In this paper, we employ repeated random sampling to create sampling distributions that identify the population parameters of silicon samples generated by GPT. Our findings show that GPT's demographic distribution aligns with the 2020 U.S. popula"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.02601","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/2409.02601/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":"2409.02601","created_at":"2026-07-05T10:25:09.555366+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.02601v3","created_at":"2026-07-05T10:25:09.555366+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.02601","created_at":"2026-07-05T10:25:09.555366+00:00"},{"alias_kind":"pith_short_12","alias_value":"DYNXSEUIJKAI","created_at":"2026-07-05T10:25:09.555366+00:00"},{"alias_kind":"pith_short_16","alias_value":"DYNXSEUIJKAIVN47","created_at":"2026-07-05T10:25:09.555366+00:00"},{"alias_kind":"pith_short_8","alias_value":"DYNXSEUI","created_at":"2026-07-05T10:25:09.555366+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"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":16,"is_internal_anchor":false},{"citing_arxiv_id":"2509.06337","citing_title":"Large Language Models as Virtual Survey Respondents: Evaluating Sociodemographic Response Generation","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DYNXSEUIJKAIVN47UBW7T5Z7MV","json":"https://pith.science/pith/DYNXSEUIJKAIVN47UBW7T5Z7MV.json","graph_json":"https://pith.science/api/pith-number/DYNXSEUIJKAIVN47UBW7T5Z7MV/graph.json","events_json":"https://pith.science/api/pith-number/DYNXSEUIJKAIVN47UBW7T5Z7MV/events.json","paper":"https://pith.science/paper/DYNXSEUI"},"agent_actions":{"view_html":"https://pith.science/pith/DYNXSEUIJKAIVN47UBW7T5Z7MV","download_json":"https://pith.science/pith/DYNXSEUIJKAIVN47UBW7T5Z7MV.json","view_paper":"https://pith.science/paper/DYNXSEUI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.02601&json=true","fetch_graph":"https://pith.science/api/pith-number/DYNXSEUIJKAIVN47UBW7T5Z7MV/graph.json","fetch_events":"https://pith.science/api/pith-number/DYNXSEUIJKAIVN47UBW7T5Z7MV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DYNXSEUIJKAIVN47UBW7T5Z7MV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DYNXSEUIJKAIVN47UBW7T5Z7MV/action/storage_attestation","attest_author":"https://pith.science/pith/DYNXSEUIJKAIVN47UBW7T5Z7MV/action/author_attestation","sign_citation":"https://pith.science/pith/DYNXSEUIJKAIVN47UBW7T5Z7MV/action/citation_signature","submit_replication":"https://pith.science/pith/DYNXSEUIJKAIVN47UBW7T5Z7MV/action/replication_record"}},"created_at":"2026-07-05T10:25:09.555366+00:00","updated_at":"2026-07-05T10:25:09.555366+00:00"}