{"id":"W4392772331","doi":"10.37934/araset.40.2.127139","title":"BiasTrap: Runtime Detection of Biased Prediction in Machine Learning Systems","year":2024,"lang":"en","type":"article","venue":"Journal of Advanced Research in Applied Sciences and Engineering Technology","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Universiti Teknologi Petronas","keywords":"Computer science; Artificial intelligence; Machine learning","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":[],"consensus_categories":[],"category_scores_codex":[0.001838888,0.00006707667,0.0001552632,0.002579764,0.00006878368,0.00006576805,0.0003694886,0.00008920112,6.277081e-7],"category_scores_gemma":[0.00005603198,0.00005727889,0.00002060078,0.00353956,0.0001427237,0.0002161621,0.00009728292,0.0007072139,5.976815e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007326376,"about_ca_system_score_gemma":0.00004781667,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001362496,"about_ca_topic_score_gemma":0.000003490974,"domain_scores_codex":[0.998929,0.00002183651,0.0003629026,0.0001963825,0.0002696495,0.0002202202],"domain_scores_gemma":[0.999602,0.0001330589,0.00007178206,0.000103045,0.00005539441,0.00003473827],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001044026,0.00003568467,0.0003327794,0.0001143593,0.000006918624,0.0000178163,0.0001005278,0.1435626,0.6415791,0.06624837,0.000003156708,0.1479883],"study_design_scores_gemma":[0.0002188354,0.0005616121,0.0005639219,0.0003113712,0.000001377364,0.0001405322,0.0002670016,0.9427828,0.04740208,0.005303772,0.002363477,0.00008325301],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4136425,0.002378696,0.5829163,0.0004038146,0.00016423,0.000201139,9.122991e-7,0.000152903,0.0001395257],"genre_scores_gemma":[0.9807165,0.0004453681,0.01878068,7.12572e-7,0.00001760258,0.000026791,7.876885e-8,0.000004534623,0.00000770905],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7992202,"threshold_uncertainty_score":0.3072532,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02593986973159145,"score_gpt":0.3032125516861288,"score_spread":0.2772726819545374,"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."}}