{"id":"W4224214784","doi":"10.1145/3511598","title":"An Empirical Study on Data Distribution-Aware Test Selection for Deep Learning Enhancement","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Retraining; Computer science; Artificial intelligence; Machine learning; Selection (genetic algorithm); Test data; Artificial neural network; Software deployment; Metric (unit); Data mining; Data set; Test set; Process (computing); Model selection; Deep learning; Distribution (mathematics); Set (abstract data type); Empirical research; Statistics; Mathematics; Engineering","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":[0.0006482058,0.0001516902,0.0001774817,0.00009816579,0.0007210692,0.00002907281,0.0007098849,0.00004242972,0.000009700846],"category_scores_gemma":[0.0005155624,0.0001660358,0.0000301459,0.000440312,0.00001465598,0.0001751802,0.00006345774,0.0004545787,0.000001520375],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009180562,"about_ca_system_score_gemma":0.00001923391,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005230517,"about_ca_topic_score_gemma":0.00000583293,"domain_scores_codex":[0.9985021,0.0002620262,0.000191233,0.0006499662,0.0001434866,0.000251182],"domain_scores_gemma":[0.9956239,0.00339508,0.00005180684,0.0008043034,0.00004067462,0.00008421118],"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":[0.00003667355,0.0006674354,0.001272401,0.00001056054,0.0000418847,0.000001635167,0.0005973113,0.8083981,0.0007216152,0.0001633729,0.0000458294,0.1880432],"study_design_scores_gemma":[0.0009443067,0.005405952,0.00574204,0.000007411038,0.00007191388,0.00007012738,0.0004330742,0.961103,0.001751128,0.0005370359,0.02345196,0.0004820863],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01558045,0.00002343665,0.9829394,0.0002634234,0.0002625925,0.0004342903,0.00005918998,0.0004368734,3.002863e-7],"genre_scores_gemma":[0.4960617,0.0000111286,0.5029699,0.00009045655,0.0000418839,0.0006698741,0.0001085493,0.00001726159,0.00002927749],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4804812,"threshold_uncertainty_score":0.6770745,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1239226798585278,"score_gpt":0.3887620461359517,"score_spread":0.2648393662774238,"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."}}