{"id":"W4417076522","doi":"10.1038/s41586-025-09771-9","title":"Persuading voters using human–artificial intelligence dialogues","year":2025,"lang":"en","type":"article","venue":"Nature","topic":"AI in Service Interactions","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Regina","funders":"","keywords":"Persuasion; Conversation; Ballot; Context (archaeology); Presidential system; Preference; Politics; Public opinion","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001266468,0.0001095922,0.0001038222,0.0001945781,0.0002974339,0.000222712,0.0008935958,0.000430021,0.00001975354],"category_scores_gemma":[0.00007411038,0.0001092255,0.00006843527,0.0006295017,0.00003537394,0.0004868903,0.0002675952,0.001337534,0.0000332003],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001226673,"about_ca_system_score_gemma":0.00005632725,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007403554,"about_ca_topic_score_gemma":0.00007740682,"domain_scores_codex":[0.9990976,0.00003742711,0.000176765,0.0003155278,0.0001657465,0.0002068893],"domain_scores_gemma":[0.9992967,0.0001027256,0.00005346896,0.000399079,0.0001117639,0.00003621229],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000007856047,0.00008705638,0.0005558111,0.00003742312,0.00005843502,0.00002914515,0.0028491,0.001165869,0.03734165,0.9153885,0.002905406,0.03957377],"study_design_scores_gemma":[0.0001464128,0.00009725714,0.002151117,0.0005897861,0.0000780144,0.00005303815,0.002200244,0.4905812,0.127625,0.3485347,0.02687969,0.001063598],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09984359,0.0004455699,0.8783865,0.007516432,0.005426339,0.0001756196,0.000003571973,0.0003822549,0.007820149],"genre_scores_gemma":[0.9747993,0.000002525533,0.02273106,0.002102861,0.0001599298,0.000003385821,0.00000225503,0.000005569693,0.000193067],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8749558,"threshold_uncertainty_score":0.5810995,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04879900520946044,"score_gpt":0.360122640421447,"score_spread":0.3113236352119865,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}