{"id":"W4412033360","doi":"10.1145/3747289","title":"Towards Understanding Refactoring Engine Bugs","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Engineering Research","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Code refactoring; Computer science; Software engineering; Programming language; Software","routes":{"ca_aff":true,"ca_fund":true,"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"],"consensus_categories":[],"category_scores_codex":[0.0009204624,0.0002583689,0.0003312267,0.0007738831,0.000176577,0.0000883051,0.0007227584,0.0001940054,0.00001171441],"category_scores_gemma":[0.003606765,0.0002701071,0.00008970408,0.0008831435,0.00004188134,0.0002244414,0.00006540039,0.0006117519,0.000005782042],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002512697,"about_ca_system_score_gemma":0.00008761902,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002929221,"about_ca_topic_score_gemma":0.000001795951,"domain_scores_codex":[0.9983913,0.0001178017,0.0002491845,0.0005360354,0.0002029118,0.0005027744],"domain_scores_gemma":[0.9935248,0.005393257,0.00002506186,0.0008571585,0.00005230075,0.0001474263],"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":[0.00008321276,0.0001817619,0.001941693,0.0007855686,0.000789905,0.0001062191,0.00217015,0.1993255,0.006096728,0.0936762,0.0002212372,0.6946218],"study_design_scores_gemma":[0.01385707,0.003170121,0.09168361,0.003584055,0.0007317005,0.001313367,0.00133555,0.2970541,0.3673528,0.1104296,0.09996594,0.009522083],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005847108,0.0003727427,0.9901332,0.0005404297,0.001562298,0.0001328664,0.000003827141,0.001376096,0.0000314452],"genre_scores_gemma":[0.2570818,0.000121517,0.7423838,0.00008011608,0.00003384969,0.00004493755,0.000001050596,0.00002409841,0.0002287952],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6850997,"threshold_uncertainty_score":0.9999751,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1393592182729809,"score_gpt":0.3511492955049095,"score_spread":0.2117900772319286,"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."}}