{"id":"W3163202066","doi":"10.1109/tse.2021.3082068","title":"An Empirical Study of Type-Related Defects in Python Projects","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Python (programming language); Computer science; Programming language; Artificial intelligence","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":[0.000269679,0.00020789,0.0002776901,0.0005376117,0.00004765617,0.00005512087,0.0004599985,0.0001245294,0.00001653366],"category_scores_gemma":[0.0002312552,0.0002324658,0.00006655807,0.002407687,0.00001246001,0.0003554059,0.000007587832,0.0005592165,0.00001522179],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001343802,"about_ca_system_score_gemma":0.0001594265,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002816018,"about_ca_topic_score_gemma":0.00002743157,"domain_scores_codex":[0.9982297,0.0000921057,0.0003395611,0.0005140785,0.0004489452,0.0003755729],"domain_scores_gemma":[0.9982844,0.000604029,0.00002972703,0.0007940101,0.0001526821,0.0001351629],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001300587,0.00130813,0.01745469,0.00007424811,0.00005311334,0.0002602431,0.003002418,0.9711639,0.002844607,0.00001402373,0.00001124645,0.003800359],"study_design_scores_gemma":[0.004672013,0.003459265,0.2472527,0.0005214025,0.0000593311,0.0002203007,0.0006423232,0.6090955,0.1323311,0.00003708325,0.0001329974,0.001575963],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5163841,0.00003352632,0.482531,0.000005356263,0.0004407667,0.0001595361,0.000001165692,0.0004423387,0.000002154039],"genre_scores_gemma":[0.9796572,0.000006193326,0.0201893,0.000009287319,0.00001405441,0.00004789592,0.00000116206,0.00004288311,0.00003204382],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.463273,"threshold_uncertainty_score":0.9479681,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02540647067592235,"score_gpt":0.2945407086543776,"score_spread":0.2691342379784553,"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."}}