{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.3753355,0.001645428,0.001656846,0.0200226,0.005989393,0.02178783,0.006769165,0.004398885,0.004994636],"category_scores_gemma":[0.7109536,0.001456121,0.002033612,0.01117863,0.01204001,0.0338046,0.01524761,0.006287894,0.00136217],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01325089,"about_ca_system_score_gemma":0.03136253,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003231383,"about_ca_topic_score_gemma":0.003695045,"domain_scores_codex":[0.5669849,0.3221608,0.02718939,0.01350249,0.0652977,0.004864786],"domain_scores_gemma":[0.1632205,0.6787729,0.03653133,0.0379475,0.07888623,0.004641541],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.0003935054,0.0008221486,0.0418531,0.007729952,0.0002636276,0.0009611438,0.09877839,0.002431869,0.001881699,0.0572588,0.01361545,0.7740104],"study_design_scores_gemma":[0.0008850123,0.003603184,0.04689484,0.1115311,0.001121037,0.002946497,0.1827014,0.03638019,0.01558055,0.3310501,0.2662954,0.001010726],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3092439,0.02623742,0.4785145,0.1039442,0.001819414,0.005886563,0.0007640825,0.00375944,0.06983051],"genre_scores_gemma":[0.6732413,0.004891002,0.3071568,0.007988444,0.0003342342,0.00391657,0.0004485352,0.0007728783,0.001250264],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.3753355,"threshold_uncertainty_score":0.7703226,"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."}}