{"id":"W4389068312","doi":"10.1016/j.jss.2023.111907","title":"Software engineering practices for machine learning — Adoption, effects, and team assessment","year":2023,"lang":"en","type":"article","venue":"Journal of Systems and Software","topic":"Software Engineering Research","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Software engineering; Software; Computer science; Engineering management; Knowledge management; Artificial intelligence; Engineering; Operating system","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":[0.001630933,0.0001510962,0.0003148089,0.0003332132,0.0001636626,0.0003763293,0.0002746523,0.00007870694,4.990707e-7],"category_scores_gemma":[0.006442004,0.0001261049,0.00006035362,0.0003306209,0.00001473814,0.0006383818,0.0001542142,0.0003829836,0.000001514113],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006287841,"about_ca_system_score_gemma":0.00008187458,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002370724,"about_ca_topic_score_gemma":6.843683e-7,"domain_scores_codex":[0.9986688,0.00006513406,0.0003535293,0.0002112665,0.0004195278,0.0002817581],"domain_scores_gemma":[0.995162,0.003822661,0.0004015475,0.0001633634,0.000274448,0.000176055],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00003934287,0.0000859401,0.8770204,0.007899649,0.0004540361,0.000295145,0.002243854,0.05398541,0.0009138273,0.001656457,0.00377352,0.05163238],"study_design_scores_gemma":[0.003128526,0.002120536,0.4775205,0.002474809,0.00009661822,0.001913102,0.0004663762,0.448322,0.0001183159,0.0001584839,0.06284762,0.0008330739],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1507863,0.004694479,0.8429882,0.0001348325,0.0007965445,0.0002875803,0.000003849289,0.0003068271,0.000001389392],"genre_scores_gemma":[0.8213429,0.0008770403,0.1768081,0.00001951675,0.0004799858,0.0000594406,0.000004996825,0.00005328466,0.0003547287],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6705566,"threshold_uncertainty_score":0.7712146,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0184189781801899,"score_gpt":0.2924588079169577,"score_spread":0.2740398297367678,"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."}}