{"id":"W4396629499","doi":"10.1109/ms.2024.3395616","title":"How Trustworthy Is Your Continuous Integration (CI) Accelerator?: A Comparison of the Trustworthiness of CI Acceleration Products","year":2024,"lang":"en","type":"article","venue":"IEEE Software","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal; University of Waterloo","funders":"","keywords":"Trustworthiness; Acceleration; Computer science; Software engineering; Computer security; Physics","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":[0.002243764,0.000201403,0.0004336121,0.0003168593,0.0002843496,0.000950493,0.001243214,0.00008458033,0.00009959909],"category_scores_gemma":[0.002574801,0.000121059,0.0001868487,0.002604616,0.0001545702,0.0005751515,0.0003393934,0.0002235705,0.00003727469],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003866266,"about_ca_system_score_gemma":0.0001574192,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005253393,"about_ca_topic_score_gemma":0.00007029428,"domain_scores_codex":[0.9962098,0.0001921409,0.0008674145,0.0008217583,0.001679368,0.0002295354],"domain_scores_gemma":[0.9966975,0.0004182572,0.0004894819,0.001412522,0.0009292408,0.00005294024],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00006287017,0.0002700598,0.04037958,0.0002030511,0.00009638951,0.000005295889,0.01320719,0.000962278,0.00574879,0.0008077079,0.3400036,0.5982531],"study_design_scores_gemma":[0.001587444,0.0004821315,0.07511165,0.001506895,0.0004050299,0.00002346847,0.0158101,0.1314291,0.3754337,0.01122389,0.3855464,0.001440202],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9261911,0.0006804477,0.06179855,0.003131565,0.006984178,0.0006363165,0.0002267592,0.0001625392,0.0001885811],"genre_scores_gemma":[0.9950182,0.000004448759,0.001316885,0.00008311588,0.0002281833,0.00001284143,0.00002178046,0.00001511269,0.003299415],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.596813,"threshold_uncertainty_score":0.9165626,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1816990682329545,"score_gpt":0.3961308599928329,"score_spread":0.2144317917598785,"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."}}