{"id":"W4393477082","doi":"10.5281/zenodo.5361068","title":"How Do I Refactor This? An Empirical Study on Refactoring Trends and Topics in Stack Overflow","year":2021,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec","funders":"","keywords":"Code refactoring; Stack (abstract data type); Computer science; Empirical research; Programming language; Software engineering; Mathematics; Statistics; 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","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007188126,0.0002711456,0.0003544097,0.0007116027,0.0008023015,0.004278203,0.002172275,0.0001470713,0.001163521],"category_scores_gemma":[0.0005818621,0.0002641206,0.00005378523,0.001218227,0.00005803091,0.0006358689,0.002701696,0.0007340875,0.0003251366],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001815095,"about_ca_system_score_gemma":0.000010412,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004736333,"about_ca_topic_score_gemma":0.00000753735,"domain_scores_codex":[0.9967753,0.0008106332,0.0002861483,0.001075481,0.0006667787,0.0003856521],"domain_scores_gemma":[0.9976414,0.00003887059,0.0001465455,0.001727544,0.0002138572,0.0002318097],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001248434,0.0004197957,0.00003709866,0.00003058047,0.00004811358,0.0001442037,0.000823497,0.000004357817,0.00001849643,0.00004048459,0.9478471,0.05057375],"study_design_scores_gemma":[0.0003700421,0.0005886586,0.002779684,0.00005219044,0.00002116003,0.000019791,0.0003554677,0.0002109731,0.000009000077,0.000006691726,0.9953098,0.0002765672],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.01968686,0.0001916484,0.0009799661,0.003041541,0.0005116786,0.0004937855,0.9705266,0.0008305256,0.003737432],"genre_scores_gemma":[0.01643939,0.0001996798,0.000388251,0.0001608179,0.0004085529,9.971384e-8,0.9803306,0.0005916145,0.001481028],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.05029719,"threshold_uncertainty_score":0.9999811,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0732749163253318,"score_gpt":0.311746874508511,"score_spread":0.2384719581831792,"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."}}