{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003626484,0.002410131,0.001857306,0.00183162,0.0004428301,0.0008325569,0.003096046,0.001694469,0.002704586],"category_scores_gemma":[0.00862855,0.0009608018,0.001026342,0.000736954,0.001323981,0.001536944,0.002169993,0.002335218,0.0003649089],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002072104,"about_ca_system_score_gemma":0.002679602,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006510997,"about_ca_topic_score_gemma":0.009148479,"domain_scores_codex":[0.997768,0.0009385434,0.0001112188,0.0004166767,0.000522778,0.0002427777],"domain_scores_gemma":[0.993494,0.004433055,0.0004658075,0.000358524,0.0009673928,0.0002812823],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000260118,0.0002203846,0.00375635,0.0001557348,0.0001365619,0.0001989252,0.00006972935,0.8263527,0.004157284,0.003359018,0.002566647,0.1587666],"study_design_scores_gemma":[0.0000224347,0.00006834147,0.0001812957,0.000007921684,0.000009743893,0.00001974039,0.000007552403,0.9961738,0.001241416,0.00206919,0.0001930483,0.000005542646],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04987395,0.000682421,0.9437127,0.0004627037,0.00005114451,0.0002323177,0.0002311965,0.00346572,0.001287887],"genre_scores_gemma":[0.6452636,0.0001868236,0.3493707,0.0007682182,0.0000613251,0.0005431295,0.001014924,0.0004020612,0.002389224],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006510997,"threshold_uncertainty_score":0.01917887,"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."}}