{"id":"W4400681481","doi":"10.1109/saner60148.2024.00035","title":"Investigating and Detecting Silent Bugs in PyTorch Programs","year":2024,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Software bug; Programming language; Artificial intelligence; Software","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003549089,0.001456357,0.0006994585,0.004434805,0.0005790885,0.001081844,0.001750753,0.001138233,0.001261991],"category_scores_gemma":[0.0234517,0.0005843934,0.0007738773,0.001490485,0.0007666558,0.002490089,0.002022881,0.001304417,0.001022844],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006924031,"about_ca_system_score_gemma":0.001754876,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004131354,"about_ca_topic_score_gemma":0.008934091,"domain_scores_codex":[0.9954283,0.0009160188,0.0004287657,0.001182971,0.001682438,0.0003615426],"domain_scores_gemma":[0.9794526,0.01191774,0.003383893,0.002190639,0.002650236,0.0004048648],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0008849538,0.0007427647,0.213714,0.002131776,0.0002831061,0.002874797,0.003047228,0.02649195,0.05726519,0.002675466,0.04226501,0.6476237],"study_design_scores_gemma":[0.0001427123,0.0005550248,0.08127768,0.0003455139,0.0002079363,0.001750491,0.001024375,0.7737964,0.108964,0.006254346,0.02551687,0.0001645844],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.626317,0.001079753,0.2396008,0.0007880912,0.0001606921,0.0004373929,0.005753851,0.1223697,0.003492714],"genre_scores_gemma":[0.7680531,0.0004086728,0.2138023,0.000464672,0.00005240364,0.000302325,0.01103349,0.002312373,0.00357071],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004434805,"threshold_uncertainty_score":0.01876956,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02949678047109058,"score_gpt":0.2851109023873632,"score_spread":0.2556141219162726,"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."}}