{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002373945,0.0004171537,0.0006210634,0.0004557135,0.0002513643,0.0001273893,0.0007492667,0.000256433,0.000003685823],"category_scores_gemma":[0.001305643,0.0002933189,0.0002783633,0.0003223614,0.00008185607,0.00001246582,0.0004728576,0.00198279,0.000002399518],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008185903,"about_ca_system_score_gemma":0.00004681625,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004925862,"about_ca_topic_score_gemma":0.000004049487,"domain_scores_codex":[0.9975719,0.0006123717,0.0004205238,0.0007950447,0.0002468068,0.0003533513],"domain_scores_gemma":[0.9937562,0.005002206,0.0001504636,0.0009303019,0.0000583362,0.0001024551],"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":[0.00002499583,0.00004906003,0.0003978977,0.0003802387,0.000451932,0.000009964553,0.002504673,0.7997466,0.0000788753,0.0002308061,0.0000137098,0.1961112],"study_design_scores_gemma":[0.002262217,0.003560602,0.05987568,0.003333568,0.0009203267,0.000354959,0.0007196028,0.9085407,0.001731319,0.01403246,0.001546931,0.003121616],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3478574,0.0008269525,0.6498109,0.000234034,0.0005978107,0.0001881619,0.00001687282,0.000464379,0.000003459467],"genre_scores_gemma":[0.6526646,0.0001652892,0.3467197,0.0000433666,0.00008474834,0.00003931694,0.000003751612,0.00005048369,0.0002287654],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.3048072,"threshold_uncertainty_score":0.9999519,"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."}}