{"id":"W3208913301","doi":"10.32920/ryerson.14638470.v1","title":"Partially observable Markov Decision Process to prioritize software defects","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Partially observable Markov decision process; Dependency (UML); Dependency graph; Exploit; Software bug; Prioritization; Software; Graph; Process (computing); Software quality; Software regression; Data mining; Risk analysis (engineering); Markov chain; Markov model; Software development; Machine learning; Artificial intelligence; Computer security; Engineering; Theoretical computer science","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":[0.003271496,0.001630185,0.001869381,0.001227595,0.0006799754,0.001409115,0.001494062,0.001445095,0.003793821],"category_scores_gemma":[0.01073742,0.0008337819,0.00152065,0.0009363327,0.001409684,0.001389338,0.001216989,0.002451786,0.0002891143],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002232024,"about_ca_system_score_gemma":0.003568298,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02224345,"about_ca_topic_score_gemma":0.01455428,"domain_scores_codex":[0.9972317,0.001018922,0.0001400516,0.0006196949,0.0005630933,0.0004265114],"domain_scores_gemma":[0.984322,0.01283299,0.001156362,0.0002283228,0.001021155,0.000439172],"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":[0.0001636174,0.00006622217,0.002365075,0.0001339211,0.00006179725,0.0001743431,0.00008719706,0.9740987,0.0005330836,0.01298065,0.0004959079,0.008839363],"study_design_scores_gemma":[0.00002480386,0.00003637149,0.00024555,0.000009639562,0.0000199546,0.00001159661,0.0000116622,0.9936441,0.000157386,0.005691555,0.0001395459,0.000007800476],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0643449,0.0003727982,0.9299793,0.0007130605,0.0000981587,0.000280298,0.0004709335,0.0005499781,0.003190485],"genre_scores_gemma":[0.9039713,0.0003040143,0.09211806,0.000210797,0.00005233215,0.0004752829,0.0004958757,0.00004579539,0.002326605],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02224345,"threshold_uncertainty_score":0.04422796,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02568726536238556,"score_gpt":0.2996946730810493,"score_spread":0.2740074077186637,"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."}}