{"id":"W4241100723","doi":"10.1109/icse.2013.6606723","title":"Normalizing source code vocabulary to support program comprehension and software quality","year":2013,"lang":"en","type":"article","venue":"2013 35th International Conference on Software Engineering (ICSE)","topic":"Software Engineering Research","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Program comprehension; Computer science; Source code; Identifier; Normalization (sociology); Vocabulary; Software maintenance; Natural language processing; Static program analysis; Software quality; Information retrieval; Software; Artificial intelligence; Programming language; Software development; Software system; Linguistics","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":[0.00349296,0.00102036,0.0009552895,0.003192713,0.0006503995,0.002141964,0.001589301,0.0007372961,0.001644291],"category_scores_gemma":[0.04414978,0.0005078607,0.0008040629,0.002596616,0.00102471,0.005288298,0.002756119,0.001415863,0.0009929513],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001135253,"about_ca_system_score_gemma":0.002409029,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002923683,"about_ca_topic_score_gemma":0.002959775,"domain_scores_codex":[0.9946331,0.001250444,0.0007809167,0.001313113,0.001804725,0.0002177531],"domain_scores_gemma":[0.9733894,0.01054565,0.004239269,0.005797343,0.005683578,0.0003446508],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0004162097,0.0003891279,0.01342909,0.001300146,0.0001111065,0.00021861,0.00376943,0.01122505,0.1751803,0.009189625,0.005129607,0.7796417],"study_design_scores_gemma":[0.0002224734,0.0008522446,0.03625889,0.0006390993,0.0006010238,0.001480773,0.002744728,0.3030332,0.5348104,0.04030768,0.07868753,0.0003620376],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1716085,0.001619421,0.7898248,0.0004970203,0.0001056715,0.0006731546,0.0007354515,0.03060301,0.004332993],"genre_scores_gemma":[0.4709885,0.0006303929,0.5189561,0.0002625597,0.00007318403,0.0006028397,0.002996236,0.003878098,0.001612238],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00349296,"threshold_uncertainty_score":0.01847279,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05326241694142796,"score_gpt":0.3216025145088108,"score_spread":0.2683400975673829,"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."}}