{"id":"W4312757284","doi":"10.1109/icsme55016.2022.00012","title":"An Empirical Study on Performance Bugs in Deep Learning Frameworks","year":2022,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Software bug; Artificial intelligence; Empirical research; Machine learning; Deep learning; Performance improvement; Quality (philosophy); Software; Software engineering; Programming language","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":[0.01332606,0.0009772303,0.0005972158,0.008215399,0.0009458529,0.001605855,0.001769827,0.001239392,0.001349831],"category_scores_gemma":[0.1595898,0.0007299616,0.0007509617,0.005218267,0.001950905,0.004372063,0.001788081,0.002322217,0.0004771691],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001448964,"about_ca_system_score_gemma":0.001720917,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005480888,"about_ca_topic_score_gemma":0.006651284,"domain_scores_codex":[0.9797641,0.005024857,0.002618822,0.003100502,0.008143401,0.001348288],"domain_scores_gemma":[0.727603,0.1592286,0.06361702,0.01342879,0.03179351,0.004329027],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0004939637,0.0008997202,0.875232,0.0009797128,0.0002199594,0.0009112335,0.004684616,0.003843398,0.002596549,0.001531255,0.008460227,0.1001474],"study_design_scores_gemma":[0.0001123584,0.001409676,0.9113221,0.0009130083,0.0003281017,0.003436216,0.006554473,0.05030934,0.008496424,0.002541192,0.01435938,0.0002177714],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9912683,0.001197565,0.003382035,0.0005497523,0.00003388857,0.0001048609,0.001216021,0.00105528,0.001192358],"genre_scores_gemma":[0.990624,0.0004369454,0.005286202,0.000171477,0.00002699419,0.0001151693,0.00239573,0.0003192739,0.0006241006],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01332606,"threshold_uncertainty_score":0.07047582,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02238543423906986,"score_gpt":0.3255321372703295,"score_spread":0.3031467030312597,"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."}}