{"id":"W4220742105","doi":"10.1145/3489525.3511683","title":"Studying the Performance Risks of Upgrading Docker Hub Images","year":2022,"lang":"en","type":"article","venue":"","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Image (mathematics); Test (biology); Work (physics); Computer security; Artificial intelligence; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01121629,0.0009102096,0.000422494,0.003006799,0.0009143284,0.001415598,0.001514285,0.001340351,0.001060853],"category_scores_gemma":[0.1100539,0.000574666,0.0006595433,0.002066134,0.001244736,0.003164509,0.001233416,0.002109065,0.0003104643],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002201959,"about_ca_system_score_gemma":0.001608584,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007805335,"about_ca_topic_score_gemma":0.006604291,"domain_scores_codex":[0.9856361,0.004343071,0.0009395599,0.001543308,0.00625321,0.001284872],"domain_scores_gemma":[0.8269643,0.1184311,0.02401924,0.01202275,0.01650077,0.002061832],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.002852063,0.003346693,0.5598504,0.0008488467,0.0006384384,0.00210916,0.0043634,0.1941957,0.04396732,0.005942835,0.005843867,0.1760412],"study_design_scores_gemma":[0.0001854814,0.007913023,0.5272741,0.0002158688,0.0007698092,0.001789227,0.003896134,0.3778691,0.06759568,0.005384364,0.006821689,0.0002854234],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9920043,0.0001725556,0.004478331,0.0002858916,0.00002345294,0.00009719528,0.0001646993,0.0002313308,0.00254226],"genre_scores_gemma":[0.9931474,0.00009182921,0.005644989,0.00005768482,0.00001906244,0.00006381323,0.000241941,0.00008565188,0.0006475701],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01121629,"threshold_uncertainty_score":0.05931818,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05026386954125298,"score_gpt":0.2910728953215878,"score_spread":0.2408090257803348,"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."}}