{"id":"W4387344927","doi":"10.1145/3610100","title":"People Perceive Algorithmic Assessments as Less Fair and Trustworthy Than Identical Human Assessments","year":2023,"lang":"en","type":"article","venue":"Proceedings of the ACM on Human-Computer Interaction","topic":"Ethics and Social Impacts of AI","field":"Social Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Interpretability; Framing (construction); Risk perception; Perception; Mistake; Psychology; Social psychology; Risk assessment; Computer science; Framing effect; Cognitive psychology; Actuarial science; Artificial intelligence; Computer security; Business; Political science","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.00117455,0.0002034602,0.0002922468,0.0002053947,0.00145077,0.0007326531,0.001102687,0.0001952869,0.00004335026],"category_scores_gemma":[0.000459652,0.0001755808,0.0001614411,0.0004110625,0.0002397198,0.001199882,0.0007003848,0.0005968015,0.00003003463],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002175723,"about_ca_system_score_gemma":0.00005834219,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002341066,"about_ca_topic_score_gemma":0.0005785768,"domain_scores_codex":[0.9978694,0.00006934081,0.000373883,0.0004050958,0.0008842411,0.0003980822],"domain_scores_gemma":[0.9985675,0.000241088,0.0003656763,0.000225745,0.0004631503,0.000136854],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.0003298075,0.001830358,0.1776171,0.0006965919,0.001155406,0.00001689428,0.2412931,0.00004669205,0.03721581,0.4314041,0.05238578,0.05600839],"study_design_scores_gemma":[0.001452212,0.001635927,0.6724159,0.0009553965,0.000193128,0.00001109156,0.06319062,0.001832179,0.002469486,0.2521889,0.002766481,0.0008886639],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9814996,0.000002740059,0.00001663295,0.004643197,0.001033655,0.0003806266,0.000003668646,0.0001377969,0.01228216],"genre_scores_gemma":[0.9970462,0.00004289058,0.0003133733,0.0003115463,0.0007797044,0.00002193465,0.000005957183,0.00002681061,0.001451564],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4947988,"threshold_uncertainty_score":0.9998492,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1163642652367825,"score_gpt":0.4704424882561423,"score_spread":0.3540782230193598,"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."}}