{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005020731,0.000470023,0.0003983328,0.0005097256,0.0001406062,0.0008228761,0.001630411,0.000188507,0.0002804873],"category_scores_gemma":[0.001646697,0.0004857932,0.0001025031,0.0003977705,0.00005943618,0.0008991365,0.0009528688,0.0006338677,0.0006544009],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001985721,"about_ca_system_score_gemma":0.0001220496,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003095912,"about_ca_topic_score_gemma":0.000011555,"domain_scores_codex":[0.9965465,0.00006076237,0.0005801706,0.0009011069,0.00115041,0.0007610324],"domain_scores_gemma":[0.997026,0.0007105049,0.000118355,0.0008416577,0.0007336141,0.0005698578],"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":[0.0001328332,0.0009630431,0.2014125,0.0008685886,0.0006225812,0.0001529831,0.003783596,0.08831225,0.004672391,0.06060233,0.04127346,0.5972035],"study_design_scores_gemma":[0.001433451,0.001315963,0.3624291,0.0007254923,0.00001667078,0.0001287873,0.00007468574,0.5716856,0.001355704,0.000503775,0.05811292,0.00221785],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2031834,0.00005932923,0.7918229,0.0008987443,0.001031761,0.0007448389,0.00002714838,0.002167262,0.00006465844],"genre_scores_gemma":[0.6681411,0.00003446424,0.3302526,0.0003648884,0.000172736,0.0003401306,0.00005323504,0.00007182387,0.000569021],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5949856,"threshold_uncertainty_score":0.9997594,"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."}}