{"id":"W3180512116","doi":"10.1007/s10664-021-09969-1","title":"The secret life of test smells - an empirical study on test smell evolution and maintenance","year":2021,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":45,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"","keywords":"Code smell; Test (biology); Code refactoring; Empirical research; Computer science; Reliability engineering; Engineering; Software; Software quality; Software development; Statistics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004780852,0.0001841666,0.0002410323,0.002367683,0.0007194109,0.001529944,0.0007630025,0.0008296825,0.001656294],"category_scores_gemma":[0.06504653,0.0002143839,0.0004089064,0.001887862,0.001447242,0.004139775,0.001699617,0.001306174,0.0003273767],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008239615,"about_ca_system_score_gemma":0.0005698025,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001828132,"about_ca_topic_score_gemma":0.002583406,"domain_scores_codex":[0.9974942,0.0007990228,0.0002590564,0.0002190572,0.001042551,0.0001860485],"domain_scores_gemma":[0.8514193,0.08641453,0.04217948,0.007187969,0.006651992,0.006146668],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003009411,0.0004526151,0.9678226,0.00006115201,0.00006195097,0.000352864,0.005216712,0.0005533021,0.001419418,0.001474625,0.0003333651,0.02195058],"study_design_scores_gemma":[0.00001341827,0.0004279023,0.9861606,0.00005319469,0.00003535335,0.000662176,0.004383836,0.004037641,0.001055251,0.002153627,0.0009839991,0.00003305325],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.998623,0.000155883,0.000392979,0.00007426805,0.000002600425,0.000005237397,0.00006029676,0.0000112282,0.0006744449],"genre_scores_gemma":[0.999557,0.00003114323,0.0001278312,0.00001184709,0.000003798044,0.000003220058,0.00008725509,0.000006584931,0.0001713642],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9952192,"threshold_uncertainty_score":0.02528387,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02457635823879043,"score_gpt":0.294351377688388,"score_spread":0.2697750194495976,"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."}}