{"id":"W4229000353","doi":"10.1145/3477314.3507053","title":"Fighting evil is not enough when refactoring metamodels","year":2022,"lang":"en","type":"article","venue":"Proceedings of the 37th ACM/SIGAPP Symposium on Applied Computing","topic":"Software Engineering Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Code refactoring; Correctness; Computer science; Context (archaeology); Quality (philosophy); Task (project management); Process (computing); Set (abstract data type); Domain (mathematical analysis); Metamodeling; Software engineering; Heuristic; Artificial intelligence; Programming language; Systems engineering; Engineering; Software","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":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.002010276,0.0004637394,0.0005487502,0.0003585235,0.001128649,0.0003688512,0.007083626,0.00009724531,0.00002573747],"category_scores_gemma":[0.0004610422,0.0004111228,0.0002572753,0.001372037,0.00007353237,0.0003303782,0.00787738,0.001269172,0.00001804949],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004270958,"about_ca_system_score_gemma":0.0001155893,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002334338,"about_ca_topic_score_gemma":7.428983e-8,"domain_scores_codex":[0.9950069,0.0000313466,0.0007438808,0.001151468,0.002048683,0.001017679],"domain_scores_gemma":[0.9968638,0.001025977,0.0005948438,0.00107696,0.0002505374,0.0001879277],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002040672,0.0004697145,0.00514106,0.0009604626,0.0003964699,0.000007863945,0.03493141,0.07252056,0.6589575,0.1969846,0.007806432,0.02161987],"study_design_scores_gemma":[0.001741576,0.0003994453,0.001611426,0.000307753,0.0000758561,0.00007308817,0.0006574042,0.2101156,0.760366,0.009930665,0.0131139,0.00160731],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9464803,0.0001608837,0.02336453,0.009345314,0.001869314,0.002012523,0.00001809032,0.0019421,0.01480691],"genre_scores_gemma":[0.9677861,0.000003163401,0.03079654,0.0007472072,0.0002380288,0.0001030139,0.000001038399,0.00007683149,0.0002480404],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.187054,"threshold_uncertainty_score":0.9998341,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0277705031316424,"score_gpt":0.2476717664792831,"score_spread":0.2199012633476407,"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."}}