{"paper":{"title":"The Impact of Heatwaves on Population Health: A Large Language Model-Enhanced Agent-Based Simulation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"Large language model simulations show heatwave health impacts are mainly psychosocial and hit vulnerable groups hardest.","cross_cats":[],"primary_cat":"q-bio.QM","authors_text":"Hengyang Zhang, Tian Lu, Ying Dai, Yuanfei Liu, Yuanhao Liu, Zuowei Wang","submitted_at":"2026-05-15T12:56:33Z","abstract_excerpt":"Extreme heat events are increasing in frequency and intensity under climate change, but the socio-behavioral mechanisms that shape community resilience remain insufficiently understood. This study uses a Large Language Model-enhanced agent-based model to simulate responses to a prolonged heatwave in a virtual society. One hundred heterogeneous agents were assigned a Heat Vulnerability Index based on demographic risk factors and observed over 13 simulated days covering baseline, heatwave, and recovery periods. The simulation shows that heat-related impacts are primarily psychosocial and unequal"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"The simulation shows that heat-related impacts are primarily psychosocial and unequally distributed. Agents with higher vulnerability experienced larger declines in perceived safety and social connection than agents with lower vulnerability. Vulnerability also shaped adaptive capacity, with highly vulnerable agents showing behavioral constriction marked by reduced engagement in protective actions. At the collective level, risk-information diffusion followed a pattern of complex contagion.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the behaviors and perceptions generated by the large language model for the heterogeneous agents accurately represent real human psychosocial responses to heat stress and social dynamics in a community, without empirical calibration or validation against observed data.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"An LLM-enhanced agent-based model simulates heatwave responses in a virtual society, finding psychosocial impacts are unequally distributed by vulnerability and information spreads via complex contagion.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Large language model simulations show heatwave health impacts are mainly psychosocial and hit vulnerable groups hardest.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"cfb19c6ce2dc5a1f0a5b4f973b679074a265f01b1d9d27552dda66c45d3f8f20"},"source":{"id":"2605.15918","kind":"arxiv","version":1},"verdict":{"id":"119c2320-bb22-4b09-b8eb-754d43338ba6","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T17:36:29.979353Z","strongest_claim":"The simulation shows that heat-related impacts are primarily psychosocial and unequally distributed. Agents with higher vulnerability experienced larger declines in perceived safety and social connection than agents with lower vulnerability. Vulnerability also shaped adaptive capacity, with highly vulnerable agents showing behavioral constriction marked by reduced engagement in protective actions. At the collective level, risk-information diffusion followed a pattern of complex contagion.","one_line_summary":"An LLM-enhanced agent-based model simulates heatwave responses in a virtual society, finding psychosocial impacts are unequally distributed by vulnerability and information spreads via complex contagion.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the behaviors and perceptions generated by the large language model for the heterogeneous agents accurately represent real human psychosocial responses to heat stress and social dynamics in a community, without empirical calibration or validation against observed data.","pith_extraction_headline":"Large language model simulations show heatwave health impacts are mainly psychosocial and hit vulnerable groups hardest."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.15918/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T18:01:18.550612Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T17:50:27.455866Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T17:33:46.553841Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T17:01:55.754593Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"267a05524fc967b71f5068e5c56c9a17b200ef6cff55efef14f0cb8abcda5278"},"references":{"count":16,"sample":[{"doi":"","year":2023,"title":"Llm social simulations are a promising research method","work_id":"9e9c31eb-56ec-4efe-b587-4ee3e9c22a53","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Can Generative AI Improve Social Science?","work_id":"b7acc857-5a61-4f7a-8781-94a9f08554ed","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Brian JL Berry, L Douglas Kiel, and Euel Elliott","work_id":"f7ece74f-1f07-4706-9822-476b8e007d34","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1016/j.scitotenv.2021.149417","year":2021,"title":"Complex Contagions and the Weakness of Long Ties","work_id":"ed0d9441-512f-4ebc-ab3e-0815621dfe1c","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1371/journal.pone.0162464","year":2016,"title":"Beyond Static Responses: Multi-Agent LLM Systems as a New Paradigm for Social Science Research","work_id":"b6c0ee40-1b45-4e71-b69b-c1ccc16a42f1","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":16,"snapshot_sha256":"cb5d1b32a5c83653b591db6833b68c653be968a8b3538c766796ad9c1838518f","internal_anchors":2},"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"}