{"id":"W4404635154","doi":"10.1145/3705309","title":"Detecting Refactoring Commits in Machine Learning Python Projects: A Machine Learning-Based Approach","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Engineering Research","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal; Queen's University","funders":"","keywords":"Code refactoring; Computer science; Maintainability; Python (programming language); Software engineering; Java; Programming language; Software; Software development; Artificial intelligence; Machine learning","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":[0.004857549,0.001568887,0.001418849,0.01087656,0.001077391,0.002133487,0.002880781,0.001862412,0.001127258],"category_scores_gemma":[0.01867294,0.0005176634,0.001421837,0.004731525,0.0006450117,0.002377339,0.001890033,0.001905318,0.001873443],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001099869,"about_ca_system_score_gemma":0.002463329,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008461891,"about_ca_topic_score_gemma":0.01258229,"domain_scores_codex":[0.9922521,0.000958468,0.0009818639,0.002614689,0.002451739,0.0007411957],"domain_scores_gemma":[0.9791443,0.007110265,0.004693426,0.002404651,0.005622854,0.001024528],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005643325,0.001294233,0.2955238,0.0007988716,0.0003483104,0.00154814,0.000861488,0.02648217,0.01046389,0.001881821,0.02185557,0.6383774],"study_design_scores_gemma":[0.00007068383,0.0003813473,0.08840367,0.0002368431,0.0002673882,0.001201107,0.0007741007,0.8701802,0.01805803,0.00625794,0.01402076,0.0001479195],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4966501,0.003866513,0.439967,0.001406913,0.000501274,0.001508241,0.01315624,0.0362484,0.006695309],"genre_scores_gemma":[0.6836524,0.0006322105,0.2851877,0.0003896836,0.0002009567,0.0006516612,0.02377646,0.0005354983,0.004973387],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01087656,"threshold_uncertainty_score":0.02568954,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09068230133371412,"score_gpt":0.3197279064261304,"score_spread":0.2290456050924163,"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."}}