{"id":"W4404520567","doi":"10.1109/access.2024.3502164","title":"Beyond the Seeds: Fairness Testing via Counterfactual Analysis of Non-Seed Instances","year":2024,"lang":"en","type":"article","venue":"IEEE Access","topic":"Ethics and Social Impacts of AI","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Ministry of Higher Education, Malaysia","keywords":"Counterfactual thinking; Computer science; Psychology; Social psychology","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":[0.07727624,0.002004353,0.002145091,0.003446977,0.001993841,0.004168441,0.005452876,0.003237084,0.00232249],"category_scores_gemma":[0.2664037,0.0009419781,0.003105891,0.002073534,0.006089917,0.007120613,0.005220445,0.005231191,0.0004464094],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002604407,"about_ca_system_score_gemma":0.004017238,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002323083,"about_ca_topic_score_gemma":0.002993913,"domain_scores_codex":[0.937426,0.04562643,0.001972775,0.007651532,0.006361824,0.000961564],"domain_scores_gemma":[0.564391,0.3759506,0.01228426,0.03869682,0.006861144,0.001816208],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003116812,0.001754343,0.1013633,0.0008434692,0.001688512,0.001624807,0.002306592,0.3960901,0.005872429,0.2350852,0.008422924,0.2418315],"study_design_scores_gemma":[0.0002109209,0.0001767917,0.002228626,0.0000761891,0.00008864502,0.0001668483,0.0001608709,0.8396659,0.004740421,0.1507147,0.001724507,0.00004565693],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.125985,0.000385623,0.8673232,0.001322337,0.0001437664,0.000664681,0.0004709156,0.001592101,0.002112349],"genre_scores_gemma":[0.6651488,0.00007549193,0.3317205,0.0006413614,0.0001256124,0.0006051274,0.000934125,0.000291073,0.0004579636],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.07727624,"threshold_uncertainty_score":0.4086807,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06902802798576814,"score_gpt":0.4110211090537495,"score_spread":0.3419930810679814,"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."}}