{"id":"W4387700646","doi":"10.1145/3617946.3617953","title":"Summary of the Fourth International Workshop on Deep Learning for Testing and Testing for Deep Learning (DeepTest 2023)","year":2023,"lang":"en","type":"article","venue":"ACM SIGSOFT Software Engineering Notes","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Deep learning; Dependability; Interpretability; Software engineering; Computer science; Verification and validation; Intersection (aeronautics); Correctness; Software testing; Software system; Artificial intelligence; Software; Engineering; Programming language","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":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008553744,0.000313683,0.0003061889,0.0002714517,0.0005114304,0.0001653673,0.001345382,0.0001321579,0.000002502313],"category_scores_gemma":[0.5326059,0.0002922888,0.0001259096,0.001036516,0.00004921801,0.0003341313,0.00107963,0.0006660541,0.000003799814],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000673278,"about_ca_system_score_gemma":0.00004095072,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001556115,"about_ca_topic_score_gemma":0.000003506308,"domain_scores_codex":[0.9980542,0.00005706687,0.000403385,0.0005761166,0.0003638034,0.0005454103],"domain_scores_gemma":[0.8373899,0.1614773,0.0002976388,0.0004653633,0.0002837602,0.00008594611],"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":[0.00000870032,0.000008774183,0.1866018,0.0001083825,0.00003054512,0.000002671361,0.0003174682,0.7013044,0.0007778048,0.0002499774,0.00001684913,0.1105725],"study_design_scores_gemma":[0.0005216623,0.0001453667,0.08946678,0.0005445345,0.00002427458,0.00001074813,0.00005974387,0.9075115,0.000342548,0.0002571085,0.0007513805,0.000364338],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06155213,0.0001518203,0.9352211,0.000409682,0.001033673,0.0004624632,0.000004510908,0.001151051,0.00001352683],"genre_scores_gemma":[0.6173593,0.000005157747,0.3820599,0.00003545651,0.0002736005,0.00008408153,0.00001474568,0.00006253125,0.0001051941],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5558072,"threshold_uncertainty_score":0.9999529,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02896485804727705,"score_gpt":0.2640472140121904,"score_spread":0.2350823559649133,"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."}}