{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003371036,0.0003323589,0.0002828787,0.0004061255,0.00009796209,0.0006536858,0.001236323,0.0001182498,0.0001493616],"category_scores_gemma":[0.001740782,0.0003485451,0.0000732292,0.0003331593,0.00003548637,0.0007482964,0.0007582979,0.0004353952,0.0003163536],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001472312,"about_ca_system_score_gemma":0.00007753288,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001203505,"about_ca_topic_score_gemma":0.000004953227,"domain_scores_codex":[0.9974135,0.00003848836,0.0004176183,0.000688749,0.0008840265,0.00055769],"domain_scores_gemma":[0.9978087,0.0006496251,0.0000705866,0.0005891408,0.0004846833,0.000397254],"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":[0.00007271017,0.0005053336,0.2070899,0.000433636,0.0003316338,0.0001232843,0.002967967,0.05669847,0.00648824,0.03052345,0.005652633,0.6891128],"study_design_scores_gemma":[0.001385051,0.00127713,0.5226977,0.0007574364,0.00001206477,0.0001522841,0.0001106243,0.4353876,0.003015596,0.0004745026,0.03259996,0.002130002],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2840347,0.00002766745,0.7126169,0.0004407174,0.0005789953,0.0004656715,0.00001060998,0.001764765,0.00005996223],"genre_scores_gemma":[0.7518556,0.000009176241,0.2472903,0.000237695,0.00009913569,0.0002408823,0.00002216542,0.00004058278,0.0002045781],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6869828,"threshold_uncertainty_score":0.9998966,"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."}}