{"id":"W4403413460","doi":"10.1145/3674805.3695404","title":"From Literature to Practice: Exploring Fairness Testing Tools for the Software Industry Adoption","year":2024,"lang":"en","type":"article","venue":"","topic":"Ethics and Social Impacts of AI","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Software testing; Software engineering; Software; Knowledge management; Operating system","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","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001390961,0.00008439364,0.00007986731,0.00002576613,0.0008644216,0.003021125,0.0002130444,0.0003080996,0.00004978954],"category_scores_gemma":[0.02752775,0.00005945689,0.00005397947,0.0005486128,0.00005531945,0.002740256,0.00004933813,0.0006699572,0.00002119339],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008808709,"about_ca_system_score_gemma":0.0002787069,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003048683,"about_ca_topic_score_gemma":0.0003809461,"domain_scores_codex":[0.9990145,0.00008414145,0.0001233737,0.0002003252,0.0003222818,0.0002553941],"domain_scores_gemma":[0.9900725,0.009191778,0.00003061591,0.0001171184,0.00047032,0.0001176845],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001795582,0.00002627781,0.0001025589,0.00003878332,0.0000658265,0.00001379412,0.1974422,0.0001185251,0.0001121473,0.1067649,0.01924872,0.6760483],"study_design_scores_gemma":[0.00009615697,0.00007163228,0.0007458749,0.0006565211,0.00007308769,7.997158e-7,0.186159,0.0002352348,0.00008776112,0.03526155,0.7763251,0.0002872522],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.1627248,0.008127837,0.07589966,0.6765531,0.01465509,0.003294393,0.000287889,0.002280889,0.05617631],"genre_scores_gemma":[0.9323086,0.0004857403,0.04653213,0.006003638,0.008737092,0.0002970373,0.00002098905,0.00004413569,0.00557066],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7695838,"threshold_uncertainty_score":0.9980139,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2655213578436426,"score_gpt":0.4429523532059585,"score_spread":0.1774309953623159,"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."}}