{"id":"W4389988541","doi":"10.1109/scam59687.2023.00015","title":"Calibrating Deep Learning-based Code Smell Detection using Human Feedback","year":2023,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Code smell; Computer science; Code (set theory); Baseline (sea); Context (archaeology); Deep learning; Artificial intelligence; Container (type theory); Software; Software quality; Machine learning; Human–computer interaction; Software development; Engineering; Programming language","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":[],"consensus_categories":[],"category_scores_codex":[0.003081152,0.001621558,0.0007051888,0.00105272,0.0002361417,0.0008191742,0.000972473,0.001040281,0.0009976166],"category_scores_gemma":[0.01842039,0.0004050643,0.0004153011,0.0004504148,0.0004457539,0.001394679,0.001097626,0.001390311,0.0009290981],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006379155,"about_ca_system_score_gemma":0.0008003245,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003283654,"about_ca_topic_score_gemma":0.005460295,"domain_scores_codex":[0.9976289,0.0007121389,0.0001546074,0.0007407206,0.000589001,0.000174658],"domain_scores_gemma":[0.990704,0.004864648,0.001076103,0.0008849513,0.002033183,0.0004370552],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00184837,0.002857637,0.1326817,0.001142156,0.0003704447,0.0004706351,0.001154453,0.1329277,0.1143481,0.0006144693,0.01036331,0.601221],"study_design_scores_gemma":[0.00006006804,0.0007672104,0.02205059,0.00008006174,0.00005526528,0.0001231736,0.0001772083,0.9384587,0.03519015,0.001117141,0.001863029,0.00005746045],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7890688,0.0009327932,0.1962299,0.0005714782,0.000204132,0.0002637853,0.0007225129,0.008935903,0.003070633],"genre_scores_gemma":[0.9504057,0.0001375073,0.0465143,0.0002009914,0.00002565467,0.0001145648,0.0009429744,0.0001537078,0.001504683],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003283654,"threshold_uncertainty_score":0.0162949,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03823697101359752,"score_gpt":0.2976199262223461,"score_spread":0.2593829552087485,"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."}}