{"id":"W3133722238","doi":"10.1007/s11334-021-00388-5","title":"On the use of textual feature extraction techniques to support the automated detection of refactoring documentation","year":2021,"lang":"en","type":"article","venue":"Innovations in Systems and Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"ca_institutions":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"","keywords":"Code refactoring; Computer science; Documentation; Maintainability; Commit; Artificial intelligence; Machine learning; Naive Bayes classifier; Software; Process (computing); Software documentation; Data mining; Software engineering; Programming language; Software development; Software development process; Database","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":[],"consensus_categories":[],"category_scores_codex":[0.000448925,0.00009186823,0.0001197777,0.0002996638,0.00005733859,0.0001188639,0.0001673226,0.00006390279,0.000001226799],"category_scores_gemma":[0.002089406,0.00006771716,0.0000187629,0.001677583,0.00001198142,0.0003421941,0.00007550202,0.0002089362,5.624918e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008590706,"about_ca_system_score_gemma":0.00003890506,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006733364,"about_ca_topic_score_gemma":0.000005936696,"domain_scores_codex":[0.999116,0.00003890005,0.0002901023,0.0001656286,0.0002624466,0.0001268917],"domain_scores_gemma":[0.9980238,0.001262591,0.0000745068,0.0003502159,0.0002705996,0.00001830279],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002165137,0.0001412129,0.01754879,0.0006488364,0.0001421608,0.00003498472,0.004322249,0.3626272,0.4940822,0.06535183,0.00229047,0.0527885],"study_design_scores_gemma":[0.0005097751,0.000491465,0.2734662,0.001383162,0.00001704052,0.0002150403,0.0006541536,0.2505358,0.4542369,0.00007734617,0.0176897,0.0007234274],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3492234,0.00003007938,0.6498483,0.0001413722,0.0002453365,0.0002304795,0.00000427999,0.0002737238,0.000003009309],"genre_scores_gemma":[0.9847346,0.00000591052,0.01509168,0.00001982197,0.00002330618,0.00008013375,0.000003299618,0.00001050468,0.00003075328],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6355112,"threshold_uncertainty_score":0.2761426,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03321997824429876,"score_gpt":0.2960819489872761,"score_spread":0.2628619707429773,"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."}}