{"id":"W1997588820","doi":"10.5555/2486788.2487012","title":"Normalizing source code vocabulary to support program comprehension and software quality","year":2013,"lang":"en","type":"article","venue":"International Conference on Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Program comprehension; Source code; Identifier; Normalization (sociology); Vocabulary; Software quality; Software maintenance; Natural language processing; Information retrieval; Static program analysis; Software; Artificial intelligence; Software development; Programming language; 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":[0.00334363,0.0009987982,0.0009398633,0.003154688,0.0006365879,0.002065493,0.001549808,0.0007148263,0.001617006],"category_scores_gemma":[0.04100724,0.0004918794,0.0008044465,0.002547479,0.0009676131,0.005123929,0.002674358,0.001366351,0.0009827932],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001076428,"about_ca_system_score_gemma":0.002382082,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003022281,"about_ca_topic_score_gemma":0.002979153,"domain_scores_codex":[0.9948385,0.001198546,0.0007567836,0.001258532,0.001733196,0.0002144159],"domain_scores_gemma":[0.9752837,0.009687783,0.003918441,0.005343705,0.00543732,0.0003291503],"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":[0.0004058115,0.0003807355,0.01319412,0.001300006,0.0001106419,0.0002204556,0.003613893,0.01102462,0.1738502,0.008666522,0.005120216,0.7821129],"study_design_scores_gemma":[0.0002222223,0.0008557528,0.03701678,0.0006545227,0.0006155427,0.001465634,0.002820156,0.3080306,0.5279115,0.0381943,0.08185083,0.0003622093],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1685513,0.001641939,0.7933109,0.0004730197,0.0001074601,0.0006815457,0.000754106,0.03020254,0.00427714],"genre_scores_gemma":[0.4747864,0.0006606153,0.5150175,0.0002558573,0.00007241165,0.0006315631,0.003157396,0.003762095,0.001656212],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00334363,"threshold_uncertainty_score":0.01768303,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05035563521686575,"score_gpt":0.3253980243126402,"score_spread":0.2750423890957744,"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."}}