{"id":"W4400480621","doi":"10.1145/3678168","title":"Studying the Impact of TensorFlow and PyTorch Bindings on Machine Learning Software Quality","year":2024,"lang":"en","type":"preprint","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Cloud Computing and Resource Management","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Huawei Technologies (Canada); University of Alberta","funders":"University of Alberta","keywords":"Computer science; Artificial intelligence; Quality (philosophy); Deep learning; Software; Machine learning; Programming language; Physics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02739001,0.002105351,0.001027574,0.002035779,0.001583165,0.003377956,0.003562077,0.001975892,0.00414483],"category_scores_gemma":[0.2016453,0.001859527,0.001597861,0.002501327,0.003023967,0.00948123,0.004121746,0.005102948,0.001165938],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002965898,"about_ca_system_score_gemma":0.004231039,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01041714,"about_ca_topic_score_gemma":0.009887476,"domain_scores_codex":[0.9613212,0.01142785,0.003361832,0.004275953,0.01600238,0.003610783],"domain_scores_gemma":[0.7706335,0.1509056,0.0134507,0.04255203,0.01946191,0.002996197],"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":[0.007739414,0.002538888,0.1087692,0.002554904,0.001117727,0.00131078,0.001979474,0.3503194,0.09182252,0.03514729,0.02584421,0.3708563],"study_design_scores_gemma":[0.0005857896,0.002758397,0.03973282,0.0004805293,0.0006996216,0.0009911036,0.001103561,0.7957449,0.1216752,0.01873568,0.01717648,0.0003159456],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8650033,0.003090476,0.0959753,0.00220716,0.000601519,0.0002320905,0.0007850982,0.02349897,0.008606068],"genre_scores_gemma":[0.9115747,0.0004922205,0.07709844,0.0006170954,0.00007053553,0.0001665798,0.001305019,0.00633248,0.002343038],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02739001,"threshold_uncertainty_score":0.144854,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1039954382372841,"score_gpt":0.3530575879943977,"score_spread":0.2490621497571135,"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."}}