{"id":"W4391614764","doi":"10.1145/3644388","title":"DeepGD: A Multi-Objective Black-Box Test Selection Approach for Deep Neural Networks","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"École de Technologie Supérieure; University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Selection (genetic algorithm); Black box; Artificial neural network; Artificial intelligence; Deep neural networks; Machine learning; Test (biology)","routes":{"ca_aff":true,"ca_fund":true,"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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007457686,0.0002631775,0.0002825395,0.0003564174,0.0001871995,0.0001264572,0.0003562629,0.0002244402,0.00000156437],"category_scores_gemma":[0.002091928,0.0002567524,0.0001265354,0.000579446,0.00005345903,0.0002052219,0.00002175413,0.0004898547,0.000001157351],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000643727,"about_ca_system_score_gemma":0.00002617555,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002551863,"about_ca_topic_score_gemma":0.0000027973,"domain_scores_codex":[0.998518,0.0001256203,0.0002219317,0.0006458594,0.00009242849,0.0003961535],"domain_scores_gemma":[0.9921411,0.007251,0.00003239884,0.0003897458,0.00007945255,0.0001063261],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001934977,0.0001158676,0.0002542373,0.0001981033,0.0001133565,0.000008329506,0.0009808593,0.449801,0.0001525208,0.0006748072,0.0001240089,0.5475575],"study_design_scores_gemma":[0.0002095718,0.0003096733,0.0002531728,0.00003457642,0.00004708979,0.0002009075,0.000008963939,0.9966417,0.0007251789,0.001092836,0.0002089649,0.0002673716],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002063585,0.0005937684,0.9861279,0.00008165612,0.0006214374,0.0003022855,0.00000645115,0.01205796,0.000002150909],"genre_scores_gemma":[0.1553794,0.00002920832,0.8440926,0.00008989801,0.00008365029,0.000236933,0.00000465238,0.00004022201,0.00004348699],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5472901,"threshold_uncertainty_score":0.9999885,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0672593941211773,"score_gpt":0.3148195756862651,"score_spread":0.2475601815650877,"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."}}