{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.002430853,0.0003831572,0.0004477152,0.001273687,0.000205043,0.0001786378,0.0006182449,0.0002524414,0.000007998499],"category_scores_gemma":[0.00635265,0.0003871871,0.0001169745,0.001444637,0.00003968083,0.0002889769,0.00006458018,0.002570606,0.000007564236],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001886385,"about_ca_system_score_gemma":0.00008906121,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000211776,"about_ca_topic_score_gemma":0.00001871517,"domain_scores_codex":[0.9972098,0.0005644956,0.0003725726,0.0008599495,0.0003054464,0.0006877513],"domain_scores_gemma":[0.9893489,0.009818781,0.00003935858,0.0005766914,0.00004862553,0.0001675656],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002962831,0.00005900138,0.004084145,0.0005845258,0.00007310582,0.00008963839,0.001562662,0.83466,0.0009795774,0.0001045314,0.000001499191,0.1577717],"study_design_scores_gemma":[0.000539499,0.0003471283,0.001509479,0.000279929,0.00002113292,0.0001718362,0.00004363076,0.9884415,0.004006806,0.00004592101,0.004108745,0.0004843985],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02168046,0.002148782,0.9722483,0.0001224486,0.0006381862,0.000243428,0.00000475976,0.002908154,0.000005509974],"genre_scores_gemma":[0.4644929,0.0000793092,0.5351058,0.00001637096,0.00003785971,0.0001019849,0.000005643038,0.00006641117,0.0000937147],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4428125,"threshold_uncertainty_score":0.999858,"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."}}