{"id":"W4389544175","doi":"10.1109/icsme58846.2023.00047","title":"Automatic Refactoring Candidate Identification Leveraging Effective Code Representation","year":2023,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Code refactoring; Computer science; Source code; Identification (biology); Artificial intelligence; Software maintenance; Commit; Machine learning; Code (set theory); Software; Programming language; Software system; Set (abstract data type); 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001397539,0.000842153,0.0008169366,0.00344965,0.0003322857,0.0009507512,0.001021485,0.0007280869,0.0006118037],"category_scores_gemma":[0.009044488,0.0002854817,0.0004979309,0.001331498,0.0003606561,0.001601396,0.0008580646,0.000960056,0.0007358624],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005330533,"about_ca_system_score_gemma":0.001231012,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002643792,"about_ca_topic_score_gemma":0.005145171,"domain_scores_codex":[0.9982729,0.0003426414,0.0001163004,0.0004679892,0.0006767018,0.0001235366],"domain_scores_gemma":[0.9931347,0.00222561,0.001294554,0.001039514,0.002164049,0.0001414636],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000231619,0.0003713797,0.02729791,0.0002088699,0.00006704907,0.0002559166,0.0003053646,0.02186905,0.06112114,0.001644543,0.004504135,0.8821231],"study_design_scores_gemma":[0.00001716359,0.0001296676,0.008052263,0.00004323105,0.00003439066,0.0002529165,0.00007775091,0.9518406,0.03339115,0.003001925,0.003132953,0.00002596436],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2555977,0.0008771047,0.730942,0.0004445662,0.00007255586,0.0002182179,0.0006671223,0.009634985,0.001545832],"genre_scores_gemma":[0.7012854,0.0002694901,0.2927465,0.000115102,0.00004171924,0.0001331768,0.002444059,0.0004073261,0.002557248],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00344965,"threshold_uncertainty_score":0.007390976,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03222432595577605,"score_gpt":0.3270345718379551,"score_spread":0.2948102458821791,"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."}}