{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00524672,0.002367879,0.001060298,0.001623714,0.0004100419,0.001618708,0.001978723,0.001648478,0.00111858],"category_scores_gemma":[0.03553505,0.0008693297,0.0012511,0.0006359069,0.002415115,0.003529882,0.004789027,0.004480078,0.0005099883],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001670647,"about_ca_system_score_gemma":0.001235491,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002377302,"about_ca_topic_score_gemma":0.001531787,"domain_scores_codex":[0.9962649,0.001206971,0.0002335091,0.0008226912,0.001151233,0.0003207424],"domain_scores_gemma":[0.98503,0.0083828,0.001909354,0.002945339,0.001400329,0.0003322997],"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":[0.0002911279,0.00008787291,0.002591654,0.0001439549,0.0001129201,0.000100618,0.0001061132,0.873813,0.01431172,0.01134868,0.001205969,0.09588628],"study_design_scores_gemma":[0.000002939987,0.00004600545,0.0001666824,0.000008947631,0.00000908053,0.00002187996,0.00000530084,0.9908401,0.004503388,0.004197934,0.0001909204,0.000006708653],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02578893,0.0003586019,0.9708238,0.0004226537,0.00003440436,0.00004438612,0.0000750671,0.001698513,0.0007536971],"genre_scores_gemma":[0.8357656,0.0005593926,0.1608645,0.0004845276,0.0001104856,0.0001443258,0.0003504708,0.0004299195,0.001290735],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00524672,"threshold_uncertainty_score":0.02774763,"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."}}