{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001176097,0.00008843641,0.0001357402,0.00005837254,0.0006347311,0.00004339502,0.001109367,0.00001483435,0.00007868839],"category_scores_gemma":[0.00001987549,0.00005269919,0.00006865411,0.0004941036,0.00005413215,0.0003376098,0.0007720499,0.0001924919,0.00001557687],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000449533,"about_ca_system_score_gemma":0.00004955375,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001134844,"about_ca_topic_score_gemma":0.000001225593,"domain_scores_codex":[0.9987862,0.0001115948,0.0002585595,0.000228412,0.0004097626,0.0002055146],"domain_scores_gemma":[0.9990069,0.0001351045,0.0001081041,0.0006704841,0.00005340176,0.00002597876],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001497235,0.0002026416,0.879973,0.0001534996,0.00006803713,0.000004747001,0.007567529,0.009174231,0.0007293134,0.003966879,0.007597449,0.09054771],"study_design_scores_gemma":[0.001331051,0.0008774148,0.6771062,0.00006272303,0.00003709878,0.0001638479,0.004953253,0.2545026,0.02682094,0.001078038,0.03222277,0.0008440586],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9786326,0.0001555088,0.01678127,0.0005824535,0.0006817121,0.0002359506,0.000001334758,0.0001421068,0.002787036],"genre_scores_gemma":[0.9973419,0.00001793195,0.001966975,0.0001617008,0.00003545313,0.00005216707,3.528235e-7,0.00000450982,0.0004190296],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2453284,"threshold_uncertainty_score":0.4881903,"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."}}