{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XVENKOBM3YDUPSP22LEXABKWTH","short_pith_number":"pith:XVENKOBM","schema_version":"1.0","canonical_sha256":"bd48d5382cde0747c9fad2c970055699cc95662c2f3ec7934d5821e7c0064c57","source":{"kind":"arxiv","id":"2505.21997","version":1},"attestation_state":"computed","paper":{"title":"Leveraging Interview-Informed LLMs to Model Survey Responses: Comparative Insights from AI-Generated and Human Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anqi Deng, Jihong Zhang, Ling Zhang, Lin Tan, Nicole Bonge, Nicole Zarrett, Xinya Liang","submitted_at":"2025-05-28T05:57:26Z","abstract_excerpt":"Mixed methods research integrates quantitative and qualitative data but faces challenges in aligning their distinct structures, particularly in examining measurement characteristics and individual response patterns. Advances in large language models (LLMs) offer promising solutions by generating synthetic survey responses informed by qualitative data. This study investigates whether LLMs, guided by personal interviews, can reliably predict human survey responses, using the Behavioral Regulations in Exercise Questionnaire (BREQ) and interviews from after-school program staff as a case study. Re"},"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":"2505.21997","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-28T05:57:26Z","cross_cats_sorted":[],"title_canon_sha256":"186ffec40a4e47fbd90f45ac377a723e50bd4c3670ea159a57b79278e75a6974","abstract_canon_sha256":"482c2a3bc6871dda9ee753e647b5fb78ac82fc4569ac42b14a01b179c565afe4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:07.604858Z","signature_b64":"I3I8Pt++uV16T0n/6KWRg1smqb4glYG+ihfe0OuEUBIRqpNLEqHckEk/1XogBI6G4rJOUJQcAMLamPuwQIgiCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd48d5382cde0747c9fad2c970055699cc95662c2f3ec7934d5821e7c0064c57","last_reissued_at":"2026-07-05T11:11:07.604201Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:07.604201Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Leveraging Interview-Informed LLMs to Model Survey Responses: Comparative Insights from AI-Generated and Human Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anqi Deng, Jihong Zhang, Ling Zhang, Lin Tan, Nicole Bonge, Nicole Zarrett, Xinya Liang","submitted_at":"2025-05-28T05:57:26Z","abstract_excerpt":"Mixed methods research integrates quantitative and qualitative data but faces challenges in aligning their distinct structures, particularly in examining measurement characteristics and individual response patterns. Advances in large language models (LLMs) offer promising solutions by generating synthetic survey responses informed by qualitative data. This study investigates whether LLMs, guided by personal interviews, can reliably predict human survey responses, using the Behavioral Regulations in Exercise Questionnaire (BREQ) and interviews from after-school program staff as a case study. Re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.21997","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/2505.21997/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":"2505.21997","created_at":"2026-07-05T11:11:07.604270+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.21997v1","created_at":"2026-07-05T11:11:07.604270+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.21997","created_at":"2026-07-05T11:11:07.604270+00:00"},{"alias_kind":"pith_short_12","alias_value":"XVENKOBM3YDU","created_at":"2026-07-05T11:11:07.604270+00:00"},{"alias_kind":"pith_short_16","alias_value":"XVENKOBM3YDUPSP2","created_at":"2026-07-05T11:11:07.604270+00:00"},{"alias_kind":"pith_short_8","alias_value":"XVENKOBM","created_at":"2026-07-05T11:11:07.604270+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.16991","citing_title":"Response-free item difficulty modelling for multiple-choice items with fine-tuned transformers: Component-wise representation and multi-task learning","ref_index":190,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XVENKOBM3YDUPSP22LEXABKWTH","json":"https://pith.science/pith/XVENKOBM3YDUPSP22LEXABKWTH.json","graph_json":"https://pith.science/api/pith-number/XVENKOBM3YDUPSP22LEXABKWTH/graph.json","events_json":"https://pith.science/api/pith-number/XVENKOBM3YDUPSP22LEXABKWTH/events.json","paper":"https://pith.science/paper/XVENKOBM"},"agent_actions":{"view_html":"https://pith.science/pith/XVENKOBM3YDUPSP22LEXABKWTH","download_json":"https://pith.science/pith/XVENKOBM3YDUPSP22LEXABKWTH.json","view_paper":"https://pith.science/paper/XVENKOBM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.21997&json=true","fetch_graph":"https://pith.science/api/pith-number/XVENKOBM3YDUPSP22LEXABKWTH/graph.json","fetch_events":"https://pith.science/api/pith-number/XVENKOBM3YDUPSP22LEXABKWTH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XVENKOBM3YDUPSP22LEXABKWTH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XVENKOBM3YDUPSP22LEXABKWTH/action/storage_attestation","attest_author":"https://pith.science/pith/XVENKOBM3YDUPSP22LEXABKWTH/action/author_attestation","sign_citation":"https://pith.science/pith/XVENKOBM3YDUPSP22LEXABKWTH/action/citation_signature","submit_replication":"https://pith.science/pith/XVENKOBM3YDUPSP22LEXABKWTH/action/replication_record"}},"created_at":"2026-07-05T11:11:07.604270+00:00","updated_at":"2026-07-05T11:11:07.604270+00:00"}