{"id":"W4210772589","doi":"10.1145/3511887","title":"Towards Robustness of Deep Program Processing Models—Detection, Estimation, and Enhancement","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Advanced Malware Detection Techniques","field":"Computer Science","cited_by":58,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"JST-Mirai Program; National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Robustness (evolution); Computer science; Source code; Source lines of code; Computer engineering; Machine learning; Artificial intelligence; Data mining; Software; 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":[],"consensus_categories":[],"category_scores_codex":[0.0004968109,0.0001445393,0.0002208801,0.0002794178,0.0002628707,0.00002233235,0.0002482407,0.00005852279,0.000006319774],"category_scores_gemma":[0.0001882959,0.000160342,0.00003492783,0.000430699,0.00004343105,0.0002833786,0.00005120075,0.0002697755,7.789501e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005694312,"about_ca_system_score_gemma":0.00002844656,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001091324,"about_ca_topic_score_gemma":0.000001957633,"domain_scores_codex":[0.998953,0.0001197697,0.0002451559,0.0003445745,0.0001553613,0.0001821436],"domain_scores_gemma":[0.9991738,0.0002747377,0.00008605821,0.0003227002,0.00008525456,0.00005751204],"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":[0.000009043136,0.00003096009,4.435871e-7,0.0000457702,0.000009154267,5.397196e-7,0.000253717,0.4088282,0.0004147949,0.0001295562,3.320485e-7,0.5902776],"study_design_scores_gemma":[0.0002307588,0.0005435452,0.00003834805,0.00001557675,0.00001958914,0.0001407306,0.00006941833,0.9499051,0.04485534,0.003623909,0.0003662766,0.0001913806],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004048022,0.0002912971,0.9942309,0.00007610066,0.0002675002,0.0002520003,0.000002725521,0.0008291482,0.000002336104],"genre_scores_gemma":[0.2885004,0.00003588739,0.7110274,0.0000174076,0.000006588187,0.0003894841,8.121725e-7,0.00001184768,0.0000101377],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5900862,"threshold_uncertainty_score":0.6538556,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04880284229526353,"score_gpt":0.3117413535294528,"score_spread":0.2629385112341893,"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."}}