{"id":"W4403780126","doi":"10.48550/arxiv.2409.14610","title":"An Empirical Study of Refactoring Engine Bugs","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Hydraulic and Pneumatic Systems","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Code refactoring; Computer science; Empirical research; Programming language; Software engineering; Software; Mathematics; Statistics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001832504,0.000293601,0.0004682513,0.0002570848,0.00002864091,0.00003066627,0.0004713603,0.0002540535,0.00005345149],"category_scores_gemma":[0.000009565643,0.0003198099,0.0001206301,0.0003430787,0.00002383261,0.00006510118,0.0003090974,0.0006064434,0.00007486275],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001639981,"about_ca_system_score_gemma":0.00004131744,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002208394,"about_ca_topic_score_gemma":0.00005840159,"domain_scores_codex":[0.99883,0.00007631396,0.000293625,0.0004805387,0.00009458514,0.0002248939],"domain_scores_gemma":[0.9988848,0.00005977231,0.00006230586,0.0008012119,0.00004724601,0.0001446779],"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":[0.000007840781,0.0001387205,0.008794863,0.000689027,0.000314037,0.0001963742,0.003374207,0.9857352,0.0001060544,0.0002120055,0.0001988068,0.0002328991],"study_design_scores_gemma":[0.0004484625,0.0001902612,0.003390796,0.000355991,0.000282575,0.000004484085,0.002751318,0.9898874,0.0001640849,0.001514871,0.0004504821,0.0005592907],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9872794,0.0001114768,0.006525834,0.000003479827,0.001190349,0.0003315373,0.00001878713,0.0005257091,0.004013472],"genre_scores_gemma":[0.9993665,0.00003667044,0.00002809496,0.00000242339,0.0001587173,0.000001399485,0.00001049593,0.00005560132,0.0003401484],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01208709,"threshold_uncertainty_score":0.9999254,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08149237320390153,"score_gpt":0.2191156387319377,"score_spread":0.1376232655280361,"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."}}