{"id":"W4414472674","doi":"10.21105/joss.08497","title":"fairmetrics: An R package for group fairness evaluation","year":2025,"lang":"en","type":"article","venue":"The Journal of Open Source Software","topic":"Ethics and Social Impacts of AI","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"R package; Set (abstract data type); Independence (probability theory); Fairness measure; Group (periodic table); Interval (graph theory); Function (biology); Point (geometry)","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":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.01827183,0.00009300786,0.0002354531,0.0001390995,0.001490087,0.0007729119,0.001610965,0.0001404636,0.00008700008],"category_scores_gemma":[0.009364505,0.00006569688,0.0001197537,0.0005964019,0.000230229,0.00125075,0.0001391769,0.0003274399,0.000002979468],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001949742,"about_ca_system_score_gemma":0.000822942,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001335604,"about_ca_topic_score_gemma":0.001449888,"domain_scores_codex":[0.9976727,0.00098087,0.0003459253,0.00009608621,0.0006495851,0.0002548598],"domain_scores_gemma":[0.9959375,0.00159858,0.0004109953,0.0002137855,0.001711045,0.0001281232],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0007840334,0.0006060948,0.01094376,0.00008513204,0.0004353629,0.000004261653,0.2341746,0.0005393896,0.0002395496,0.09266332,0.05321957,0.6063049],"study_design_scores_gemma":[0.003050535,0.0008160989,0.01310862,0.0002732869,0.0006827555,0.000004634785,0.166351,0.0001589772,0.0001704765,0.6071112,0.2078756,0.0003968595],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5263031,0.001993588,0.392258,0.05076977,0.002546225,0.003829055,0.00003647765,0.00009651738,0.02216725],"genre_scores_gemma":[0.9934117,0.0001587866,0.002576394,0.001639931,0.0004152176,0.000009820586,0.000003879177,0.00001574778,0.001768505],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6059081,"threshold_uncertainty_score":0.9998099,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09663177106547788,"score_gpt":0.457888780070179,"score_spread":0.3612570090047011,"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."}}