{"id":"W2360967250","doi":"10.1145/2884781.2884804","title":"Automatically learning semantic features for defect prediction","year":2016,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":692,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Software bug; Focus (optics); ENCODE; Machine learning; Code (set theory); Artificial intelligence; Software; Software engineering; Data mining; Programming language","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.000326925,0.00006303542,0.0000670068,0.00007888087,0.00006345475,0.0000751193,0.0003217389,0.00003965156,0.00001668448],"category_scores_gemma":[0.001859733,0.00003835024,0.00005640797,0.0001344264,0.00001434933,0.0002151073,0.00009204545,0.00006235942,0.00006586353],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003524547,"about_ca_system_score_gemma":0.00002906645,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002421863,"about_ca_topic_score_gemma":9.201623e-7,"domain_scores_codex":[0.9992512,0.00002342905,0.00008487861,0.0002080024,0.0001990085,0.0002334086],"domain_scores_gemma":[0.998128,0.001502732,0.00001275943,0.0002329664,0.00006148891,0.00006203202],"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":[0.00002490814,0.0001074377,0.08008159,0.0002857783,0.0001674244,0.00001771981,0.0006210024,0.001738514,0.03759814,0.1567738,0.03579654,0.6867871],"study_design_scores_gemma":[0.001919432,0.001054149,0.5221991,0.0002849618,0.00001854651,0.00009713774,0.00001274492,0.4279944,0.0222663,0.009588992,0.01399326,0.0005709878],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01675,0.00002253927,0.9806471,0.000760862,0.0001654384,0.0001512095,5.387766e-7,0.001204987,0.0002973021],"genre_scores_gemma":[0.9109014,0.00000308242,0.08544143,0.0000243836,0.00006017871,0.00004311742,4.09138e-7,0.000009468731,0.003516483],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8952057,"threshold_uncertainty_score":0.2226409,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01051924701454742,"score_gpt":0.2535673509846479,"score_spread":0.2430481039701005,"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."}}