{"id":"W4403511313","doi":"10.1109/tse.2024.3482984","title":"TEASMA: A Practical Methodology for Test Adequacy Assessment of Deep Neural Networks","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Huawei Technologies (Canada); University of Ottawa","funders":"Huawei Technologies; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Science Foundation Ireland","keywords":"Computer science; Artificial neural network; Test (biology); Artificial intelligence; Machine learning; Reliability engineering; Software engineering; Engineering","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":[0.009175902,0.002085042,0.0008224024,0.005572263,0.000497136,0.001497759,0.002151222,0.00133964,0.003737168],"category_scores_gemma":[0.05491425,0.0006274105,0.001174168,0.001473314,0.001095715,0.001809771,0.002387099,0.001622208,0.0006819736],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001122662,"about_ca_system_score_gemma":0.002133674,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003428783,"about_ca_topic_score_gemma":0.00435533,"domain_scores_codex":[0.9927362,0.002350373,0.0009995585,0.0008892016,0.002749078,0.0002756199],"domain_scores_gemma":[0.970574,0.01765461,0.0036254,0.002913863,0.004874863,0.0003572478],"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":[0.000633751,0.0003211325,0.02846076,0.0009581574,0.0004461146,0.0005411379,0.0006365847,0.3790287,0.0246005,0.02062055,0.01127854,0.532474],"study_design_scores_gemma":[0.00005748684,0.0002890337,0.00343499,0.0001103041,0.00004040356,0.0002224847,0.0001051998,0.9627237,0.01842987,0.01113873,0.003395347,0.00005251947],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03425392,0.0002613081,0.9498095,0.0001441375,0.00005231846,0.0003962715,0.0009006629,0.01242154,0.001760362],"genre_scores_gemma":[0.2663891,0.0001262162,0.7287574,0.0001513179,0.0000320143,0.001163001,0.001699452,0.0007950743,0.0008864205],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009175902,"threshold_uncertainty_score":0.04852736,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03694737320835111,"score_gpt":0.3424103154514501,"score_spread":0.3054629422430989,"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."}}