{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01256534,0.0006475001,0.0003611207,0.001513433,0.001106529,0.004317272,0.0004192689,0.001779406,0.002473265],"category_scores_gemma":[0.07024354,0.0003759882,0.0006251869,0.0004660071,0.002748352,0.003525557,0.001772848,0.001552497,0.0004090838],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008524789,"about_ca_system_score_gemma":0.0006158832,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002154667,"about_ca_topic_score_gemma":0.001780569,"domain_scores_codex":[0.9854653,0.008798212,0.0007003676,0.0009497167,0.003630084,0.0004562948],"domain_scores_gemma":[0.9449515,0.03082717,0.01329405,0.003871556,0.005467749,0.001587898],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.003001504,0.0008393109,0.5687092,0.001143308,0.001222445,0.0009954752,0.1050319,0.01484125,0.04137255,0.04793498,0.007500133,0.207408],"study_design_scores_gemma":[0.0006317564,0.003795502,0.6062893,0.00112797,0.001314382,0.001957603,0.08671993,0.05979862,0.01747747,0.1625703,0.0571537,0.001163446],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9535909,0.0005019191,0.02520675,0.001915337,0.0001002464,0.00007108503,0.00008427045,0.000126084,0.01840337],"genre_scores_gemma":[0.9933221,0.0001242882,0.005604032,0.0004560895,0.00003636386,0.0000194395,0.00004709865,0.00002046534,0.0003701724],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01256534,"threshold_uncertainty_score":0.06645268,"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."}}