{"id":"W4401908463","doi":"10.1109/icst60714.2024.00039","title":"Are We Testing or Being Tested? Exploring the Practical Applications of Large Language Models in Software Testing","year":2024,"lang":"en","type":"article","venue":"","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Software testing; Software reliability testing; Software performance testing; Software engineering; System integration testing; Test strategy; Software; Programming language; Software construction; Software system","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009463958,0.0001707074,0.0001928523,0.0002291058,0.0001701924,0.0002418982,0.0006486486,0.00005317901,0.000003573154],"category_scores_gemma":[0.004324333,0.0001132202,0.00004203661,0.00230813,0.00004148346,0.0008136247,0.000478829,0.0003911158,0.000007569341],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005397896,"about_ca_system_score_gemma":0.0001586221,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001571322,"about_ca_topic_score_gemma":0.00003644923,"domain_scores_codex":[0.9984089,0.00007535746,0.0003885562,0.0004589054,0.0002956624,0.0003726025],"domain_scores_gemma":[0.9903975,0.00860476,0.0001346844,0.0006602394,0.0001436828,0.00005911374],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00000963005,0.0004820834,0.05810988,0.00123538,0.00005308668,0.000860693,0.01292987,0.003590662,0.0006226971,0.0972526,0.004571524,0.8202819],"study_design_scores_gemma":[0.0001213817,0.00006619739,0.00159354,0.001958475,0.00001744077,0.0002410704,0.0005027242,0.9171414,0.001061822,0.07664268,0.0003082701,0.00034497],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004959596,0.0002702124,0.9811241,0.0009508784,0.00007045831,0.0003135072,0.000003564114,0.01113048,0.001177186],"genre_scores_gemma":[0.4877975,0.000004267228,0.5117238,0.0001199901,0.00005210054,0.0002233891,5.525562e-7,0.0000177366,0.00006068047],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9135508,"threshold_uncertainty_score":0.5176943,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1581902158217574,"score_gpt":0.3575882324472093,"score_spread":0.199398016625452,"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."}}